first commit

app.py

@@ -0,0 +1,108 @@
+from flask import Flask, render_template, request, jsonify
+import requests
+import json
+import speech_recognition as sr
+import io
+import base64
+import os
+
+app = Flask(__name__)
+
+SUPPORTED_LANGUAGES = {
+    "arabic": "Arabic",
+    "armenian": "Armenian",
+    "azerbaijani": "Azerbaijani",
+    "english": "English",
+    "french": "French",
+    "georgian": "Georgian",
+    "kazakh": "Kazakh",
+    "mandarin": "Mandarin Chinese",
+    "persian": "Persian (Farsi)",
+    "portuguese": "Portuguese",
+    "russian": "Russian",
+    "turkish": "Turkish",
+    "uzbek": "Uzbek"
+}
+
+OLLAMA_API_URL = "http://100.64.0.4:11434/api/generate"
+
+@app.route('/')
+def index():
+    return render_template('index.html', languages=SUPPORTED_LANGUAGES)
+
+@app.route('/translate', methods=['POST'])
+def translate():
+    data = request.json
+    source_language = data.get('sourceLanguage')
+    target_language = data.get('targetLanguage')
+    text = data.get('text')
+
+    if not all([source_language, target_language, text]):
+        return jsonify({"error": "Missing required parameters"}), 400
+
+    # Create prompt for Gemma 3
+    prompt = f"""Translate the following text from {source_language} to {target_language}.
+Text to translate: {text}
+
+Provide ONLY the translated text with no additional commentary, explanations, or formatting.
+"""
+
+    # Call Ollama API with the Gemma 3 model
+    payload = {
+        "model": "gemma3:12b",
+        "prompt": prompt,
+        "stream": False
+    }
+    
+    try:
+        response = requests.post(OLLAMA_API_URL, json=payload)
+        response.raise_for_status()
+        result = response.json()
+        
+        # Extract the generated translation
+        translation = result.get("response", "").strip()
+        
+        return jsonify({"translation": translation})
+    except Exception as e:
+        return jsonify({"error": f"Translation failed: {str(e)}"}), 500
+
+@app.route('/speech-to-text', methods=['POST'])
+def speech_to_text():
+    try:
+        audio_data = request.json.get('audio')
+        language_code = request.json.get('language')
+        
+        # Convert base64 audio to file
+        audio_bytes = base64.b64decode(audio_data.split(',')[1])
+        
+        # Use speech recognition
+        recognizer = sr.Recognizer()
+        with sr.AudioFile(io.BytesIO(audio_bytes)) as source:
+            audio = recognizer.record(source)
+            
+        # Convert speech to text
+        language_code_map = {
+            "arabic": "ar-AR",
+            "armenian": "hy-AM",
+            "azerbaijani": "az-AZ",
+            "english": "en-US",
+            "french": "fr-FR",
+            "georgian": "ka-GE",
+            "kazakh": "kk-KZ",
+            "mandarin": "zh-CN",
+            "persian": "fa-IR",
+            "portuguese": "pt-PT",
+            "russian": "ru-RU", 
+            "turkish": "tr-TR",
+            "uzbek": "uz-UZ"
+        }
+        
+        lang_code = language_code_map.get(language_code, "en-US")
+        text = recognizer.recognize_google(audio, language=lang_code)
+        
+        return jsonify({"text": text})
+    except Exception as e:
+        return jsonify({"error": f"Speech recognition failed: {str(e)}"}), 500
+
+if __name__ == '__main__':
+    app.run(host='0.0.0.0', port=5005, debug=True)

static/css/style.css

@@ -0,0 +1,236 @@
+* {
+    box-sizing: border-box;
+    margin: 0;
+    padding: 0;
+}
+
+body {
+    font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', Roboto, Oxygen, Ubuntu, Cantarell, 'Open Sans', 'Helvetica Neue', sans-serif;
+    background-color: #f5f7fa;
+    color: #333;
+    line-height: 1.6;
+}
+
+.container {
+    max-width: 800px;
+    margin: 0 auto;
+    padding: 20px;
+}
+
+h1 {
+    text-align: center;
+    margin-bottom: 5px;
+    color: #2c3e50;
+}
+
+.subtitle {
+    text-align: center;
+    color: #7f8c8d;
+    margin-bottom: 30px;
+    font-size: 0.9rem;
+}
+
+.translation-panel {
+    background-color: white;
+    border-radius: 12px;
+    box-shadow: 0 4px 12px rgba(0, 0, 0, 0.1);
+    padding: 20px;
+    margin-bottom: 20px;
+}
+
+.language-selector {
+    display: flex;
+    justify-content: space-between;
+    align-items: center;
+    margin-bottom: 20px;
+    flex-wrap: wrap;
+}
+
+.select-container {
+    flex: 1;
+    min-width: 120px;
+    margin: 5px;
+}
+
+.select-container label {
+    display: block;
+    margin-bottom: 5px;
+    font-size: 0.9rem;
+    color: #7f8c8d;
+}
+
+select {
+    width: 100%;
+    padding: 10px;
+    border: 1px solid #ddd;
+    border-radius: 6px;
+    background-color: #f9f9f9;
+    font-size: 1rem;
+}
+
+#swapLanguages {
+    background-color: #e8f4fc;
+    border: none;
+    width: 40px;
+    height: 40px;
+    border-radius: 50%;
+    display: flex;
+    align-items: center;
+    justify-content: center;
+    font-size: 1.2rem;
+    cursor: pointer;
+    transition: background-color 0.3s;
+    margin: 0 10px;
+}
+
+#swapLanguages:hover {
+    background-color: #d1e9f9;
+}
+
+.text-panels {
+    display: flex;
+    flex-direction: column;
+    gap: 20px;
+    margin-bottom: 20px;
+}
+
+.text-panel {
+    flex: 1;
+}
+
+textarea {
+    width: 100%;
+    height: 120px;
+    padding: 15px;
+    border: 1px solid #ddd;
+    border-radius: 8px;
+    font-size: 1rem;
+    resize: none;
+    margin-bottom: 10px;
+}
+
+.controls {
+    display: flex;
+    gap: 10px;
+}
+
+button {
+    padding: 10px 15px;
+    border-radius: 6px;
+    border: none;
+    cursor: pointer;
+    font-size: 0.9rem;
+    transition: background-color 0.3s, transform 0.1s;
+}
+
+button:active {
+    transform: translateY(1px);
+}
+
+.record-button, .speak-button {
+    background-color: #e8f4fc;
+    color: #3498db;
+    display: flex;
+    align-items: center;
+    gap: 5px;
+}
+
+.record-button:hover, .speak-button:hover {
+    background-color: #d1e9f9;
+}
+
+.record-button.recording {
+    background-color: #ffe9e9;
+    color: #e74c3c;
+    animation: pulse 1.5s infinite;
+}
+
+.clear-button, .copy-button {
+    background-color: #f5f5f5;
+    color: #7f8c8d;
+}
+
+.clear-button:hover, .copy-button:hover {
+    background-color: #e9e9e9;
+}
+
+.primary-button {
+    width: 100%;
+    padding: 15px;
+    background-color: #3498db;
+    color: white;
+    font-size: 1rem;
+    font-weight: 500;
+    border-radius: 8px;
+}
+
+.primary-button:hover {
+    background-color: #2980b9;
+}
+
+.status-message {
+    text-align: center;
+    min-height: 24px;
+    color: #7f8c8d;
+    font-size: 0.9rem;
+}
+
+.status-message.error {
+    color: #e74c3c;
+}
+
+.status-message.success {
+    color: #2ecc71;
+}
+
+/* Animation for recording */
+@keyframes pulse {
+    0% {
+        opacity: 1;
+    }
+    50% {
+        opacity: 0.7;
+    }
+    100% {
+        opacity: 1;
+    }
+}
+
+/* Media queries for responsiveness */
+@media (min-width: 768px) {
+    .text-panels {
+        flex-direction: row;
+    }
+    
+    textarea {
+        height: 150px;
+    }
+}
+
+@media (max-width: 480px) {
+    .container {
+        padding: 10px;
+    }
+    
+    h1 {
+        font-size: 1.5rem;
+    }
+    
+    .translation-panel {
+        padding: 15px;
+    }
+    
+    textarea {
+        height: 100px;
+    }
+    
+    .button-text {
+        display: none;
+    }
+    
+    .record-button, .speak-button, .clear-button, .copy-button {
+        padding: 10px;
+        flex: 1;
+        justify-content: center;
+    }
+}

static/js/main.js

@@ -0,0 +1,255 @@
+document.addEventListener('DOMContentLoaded', function() {
+    // DOM elements
+    const sourceLanguage = document.getElementById('sourceLanguage');
+    const targetLanguage = document.getElementById('targetLanguage');
+    const swapButton = document.getElementById('swapLanguages');
+    const sourceText = document.getElementById('sourceText');
+    const translatedText = document.getElementById('translatedText');
+    const recordSourceButton = document.getElementById('recordSource');
+    const speakButton = document.getElementById('speak');
+    const clearSourceButton = document.getElementById('clearSource');
+    const copyTranslationButton = document.getElementById('copyTranslation');
+    const translateButton = document.getElementById('translateButton');
+    const statusMessage = document.getElementById('status');
+
+    // Audio recording variables
+    let mediaRecorder;
+    let audioChunks = [];
+    let isRecording = false;
+
+    // Speech recognition setup
+    const SpeechRecognition = window.SpeechRecognition || window.webkitSpeechRecognition;
+    const recognition = SpeechRecognition ? new SpeechRecognition() : null;
+    
+    if (recognition) {
+        recognition.continuous = false;
+        recognition.interimResults = false;
+    }
+
+    // Event listeners
+    swapButton.addEventListener('click', swapLanguages);
+    translateButton.addEventListener('click', translateText);
+    clearSourceButton.addEventListener('click', clearSource);
+    copyTranslationButton.addEventListener('click', copyTranslation);
+    
+    if (recognition) {
+        recordSourceButton.addEventListener('click', toggleRecording);
+    } else {
+        recordSourceButton.textContent = "Speech API not supported";
+        recordSourceButton.disabled = true;
+    }
+    
+    speakButton.addEventListener('click', speakTranslation);
+
+    // Functions (continued)
+    function swapLanguages() {
+        const tempLang = sourceLanguage.value;
+        sourceLanguage.value = targetLanguage.value;
+        targetLanguage.value = tempLang;
+        
+        // Also swap the text if both fields have content
+        if (sourceText.value && translatedText.value) {
+            const tempText = sourceText.value;
+            sourceText.value = translatedText.value;
+            translatedText.value = tempText;
+        }
+    }
+    
+    function clearSource() {
+        sourceText.value = '';
+        updateStatus('');
+    }
+    
+    function copyTranslation() {
+        if (!translatedText.value) {
+            updateStatus('Nothing to copy', 'error');
+            return;
+        }
+        
+        navigator.clipboard.writeText(translatedText.value)
+            .then(() => {
+                updateStatus('Copied to clipboard!', 'success');
+                setTimeout(() => updateStatus(''), 2000);
+            })
+            .catch(err => {
+                updateStatus('Failed to copy: ' + err, 'error');
+            });
+    }
+    
+    async function translateText() {
+        const source = sourceText.value.trim();
+        if (!source) {
+            updateStatus('Please enter or speak some text to translate', 'error');
+            return;
+        }
+        
+        updateStatus('Translating...');
+        translatedText.value = '';
+        
+        try {
+            const response = await fetch('/translate', {
+                method: 'POST',
+                headers: {
+                    'Content-Type': 'application/json',
+                },
+                body: JSON.stringify({
+                    sourceLanguage: sourceLanguage.value,
+                    targetLanguage: targetLanguage.value,
+                    text: source
+                })
+            });
+            
+            const data = await response.json();
+            
+            if (response.ok) {
+                translatedText.value = data.translation;
+                updateStatus('Translation complete', 'success');
+                setTimeout(() => updateStatus(''), 2000);
+            } else {
+                updateStatus(data.error || 'Translation failed', 'error');
+            }
+        } catch (error) {
+            updateStatus('Network error: ' + error.message, 'error');
+        }
+    }
+    
+    function toggleRecording() {
+        if (!recognition) {
+            updateStatus('Speech recognition not supported in this browser', 'error');
+            return;
+        }
+        
+        if (isRecording) {
+            stopRecording();
+        } else {
+            startRecording();
+        }
+    }
+    
+    function startRecording() {
+        sourceText.value = '';
+        updateStatus('Listening...');
+        
+        recognition.lang = getLanguageCode(sourceLanguage.value);
+        recognition.onresult = function(event) {
+            const transcript = event.results[0][0].transcript;
+            sourceText.value = transcript;
+            updateStatus('Recording completed', 'success');
+            setTimeout(() => updateStatus(''), 2000);
+        };
+        
+        recognition.onerror = function(event) {
+            updateStatus('Error in speech recognition: ' + event.error, 'error');
+            stopRecording();
+        };
+        
+        recognition.onend = function() {
+            stopRecording();
+        };
+        
+        try {
+            recognition.start();
+            isRecording = true;
+            recordSourceButton.classList.add('recording');
+            recordSourceButton.querySelector('.button-text').textContent = 'Stop';
+        } catch (error) {
+            updateStatus('Failed to start recording: ' + error.message, 'error');
+        }
+    }
+    
+    function stopRecording() {
+        if (isRecording) {
+            try {
+                recognition.stop();
+            } catch (error) {
+                console.error('Error stopping recognition:', error);
+            }
+            
+            isRecording = false;
+            recordSourceButton.classList.remove('recording');
+            recordSourceButton.querySelector('.button-text').textContent = 'Record';
+        }
+    }
+    
+    function speakTranslation() {
+        const text = translatedText.value.trim();
+        if (!text) {
+            updateStatus('No translation to speak', 'error');
+            return;
+        }
+        
+        // Use the browser's speech synthesis API
+        const speech = new SpeechSynthesisUtterance(text);
+        speech.lang = getLanguageCode(targetLanguage.value);
+        speech.volume = 1;
+        speech.rate = 1;
+        speech.pitch = 1;
+        
+        speech.onstart = function() {
+            updateStatus('Speaking...');
+            speakButton.disabled = true;
+        };
+        
+        speech.onend = function() {
+            updateStatus('');
+            speakButton.disabled = false;
+        };
+        
+        speech.onerror = function(event) {
+            updateStatus('Speech synthesis error: ' + event.error, 'error');
+            speakButton.disabled = false;
+        };
+        
+        window.speechSynthesis.speak(speech);
+    }
+    
+    function getLanguageCode(language) {
+        // Map language names to BCP 47 language tags for speech recognition/synthesis
+        const languageMap = {
+            "arabic": "ar-SA",
+            "armenian": "hy-AM",
+            "azerbaijani": "az-AZ",
+            "english": "en-US",
+            "french": "fr-FR",
+            "georgian": "ka-GE",
+            "kazakh": "kk-KZ",
+            "mandarin": "zh-CN",
+            "persian": "fa-IR",
+            "portuguese": "pt-PT",
+            "russian": "ru-RU",
+            "turkish": "tr-TR",
+            "uzbek": "uz-UZ"
+        };
+        
+        return languageMap[language] || 'en-US';
+    }
+    
+    function updateStatus(message, type = '') {
+        statusMessage.textContent = message;
+        statusMessage.className = 'status-message';
+        
+        if (type) {
+            statusMessage.classList.add(type);
+        }
+    }
+    
+    // Check for microphone and speech support when page loads
+    function checkSupportedFeatures() {
+        if (!navigator.mediaDevices || !navigator.mediaDevices.getUserMedia) {
+            updateStatus('Microphone access is not supported in this browser', 'error');
+            recordSourceButton.disabled = true;
+        }
+        
+        if (!window.SpeechRecognition && !window.webkitSpeechRecognition) {
+            updateStatus('Speech recognition is not supported in this browser', 'error');
+            recordSourceButton.disabled = true;
+        }
+        
+        if (!window.speechSynthesis) {
+            updateStatus('Speech synthesis is not supported in this browser', 'error');
+            speakButton.disabled = true;
+        }
+    }
+    
+    checkSupportedFeatures();
+});

templates/index.html

@@ -0,0 +1,71 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+    <meta charset="UTF-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    <title>Multilingual Voice Translator</title>
+    <link rel="stylesheet" href="{{ url_for('static', filename='css/style.css') }}">
+</head>
+<body>
+    <div class="container">
+        <h1>Voice Translator</h1>
+        <p class="subtitle">Powered by Gemma 3</p>
+        
+        <div class="translation-panel">
+            <div class="language-selector">
+                <div class="select-container">
+                    <label for="sourceLanguage">From:</label>
+                    <select id="sourceLanguage">
+                        {% for code, name in languages.items() %}
+                        <option value="{{ code }}" {% if code == "english" %}selected{% endif %}>{{ name }}</option>
+                        {% endfor %}
+                    </select>
+                </div>
+                
+                <button id="swapLanguages" aria-label="Swap languages">
+                    <span>⇄</span>
+                </button>
+                
+                <div class="select-container">
+                    <label for="targetLanguage">To:</label>
+                    <select id="targetLanguage">
+                        {% for code, name in languages.items() %}
+                        <option value="{{ code }}" {% if code == "french" %}selected{% endif %}>{{ name }}</option>
+                        {% endfor %}
+                    </select>
+                </div>
+            </div>
+            
+            <div class="text-panels">
+                <div class="text-panel">
+                    <textarea id="sourceText" placeholder="Speak or type text to translate"></textarea>
+                    <div class="controls">
+                        <button id="recordSource" class="record-button">
+                            <span class="mic-icon">🎤</span>
+                            <span class="button-text">Record</span>
+                        </button>
+                        <button id="clearSource" class="clear-button">Clear</button>
+                    </div>
+                </div>
+                
+                <div class="text-panel">
+                    <textarea id="translatedText" placeholder="Translation will appear here" readonly></textarea>
+                    <div class="controls">
+                        <button id="speak" class="speak-button">
+                            <span class="speaker-icon">🔊</span>
+                            <span class="button-text">Speak</span>
+                        </button>
+                        <button id="copyTranslation" class="copy-button">Copy</button>
+                    </div>
+                </div>
+            </div>
+            
+            <button id="translateButton" class="primary-button">Translate</button>
+        </div>
+        
+        <div id="status" class="status-message"></div>
+    </div>
+    
+    <script src="{{ url_for('static', filename='js/main.js') }}"></script>
+</body>
+</html>

venv/bin/Activate.ps1

@@ -0,0 +1,247 @@
+<#
+.Synopsis
+Activate a Python virtual environment for the current PowerShell session.
+
+.Description
+Pushes the python executable for a virtual environment to the front of the
+$Env:PATH environment variable and sets the prompt to signify that you are
+in a Python virtual environment. Makes use of the command line switches as
+well as the `pyvenv.cfg` file values present in the virtual environment.
+
+.Parameter VenvDir
+Path to the directory that contains the virtual environment to activate. The
+default value for this is the parent of the directory that the Activate.ps1
+script is located within.
+
+.Parameter Prompt
+The prompt prefix to display when this virtual environment is activated. By
+default, this prompt is the name of the virtual environment folder (VenvDir)
+surrounded by parentheses and followed by a single space (ie. '(.venv) ').
+
+.Example
+Activate.ps1
+Activates the Python virtual environment that contains the Activate.ps1 script.
+
+.Example
+Activate.ps1 -Verbose
+Activates the Python virtual environment that contains the Activate.ps1 script,
+and shows extra information about the activation as it executes.
+
+.Example
+Activate.ps1 -VenvDir C:\Users\MyUser\Common\.venv
+Activates the Python virtual environment located in the specified location.
+
+.Example
+Activate.ps1 -Prompt "MyPython"
+Activates the Python virtual environment that contains the Activate.ps1 script,
+and prefixes the current prompt with the specified string (surrounded in
+parentheses) while the virtual environment is active.
+
+.Notes
+On Windows, it may be required to enable this Activate.ps1 script by setting the
+execution policy for the user. You can do this by issuing the following PowerShell
+command:
+
+PS C:\> Set-ExecutionPolicy -ExecutionPolicy RemoteSigned -Scope CurrentUser
+
+For more information on Execution Policies: 
+https://go.microsoft.com/fwlink/?LinkID=135170
+
+#>
+Param(
+    [Parameter(Mandatory = $false)]
+    [String]
+    $VenvDir,
+    [Parameter(Mandatory = $false)]
+    [String]
+    $Prompt
+)
+
+<# Function declarations --------------------------------------------------- #>
+
+<#
+.Synopsis
+Remove all shell session elements added by the Activate script, including the
+addition of the virtual environment's Python executable from the beginning of
+the PATH variable.
+
+.Parameter NonDestructive
+If present, do not remove this function from the global namespace for the
+session.
+
+#>
+function global:deactivate ([switch]$NonDestructive) {
+    # Revert to original values
+
+    # The prior prompt:
+    if (Test-Path -Path Function:_OLD_VIRTUAL_PROMPT) {
+        Copy-Item -Path Function:_OLD_VIRTUAL_PROMPT -Destination Function:prompt
+        Remove-Item -Path Function:_OLD_VIRTUAL_PROMPT
+    }
+
+    # The prior PYTHONHOME:
+    if (Test-Path -Path Env:_OLD_VIRTUAL_PYTHONHOME) {
+        Copy-Item -Path Env:_OLD_VIRTUAL_PYTHONHOME -Destination Env:PYTHONHOME
+        Remove-Item -Path Env:_OLD_VIRTUAL_PYTHONHOME
+    }
+
+    # The prior PATH:
+    if (Test-Path -Path Env:_OLD_VIRTUAL_PATH) {
+        Copy-Item -Path Env:_OLD_VIRTUAL_PATH -Destination Env:PATH
+        Remove-Item -Path Env:_OLD_VIRTUAL_PATH
+    }
+
+    # Just remove the VIRTUAL_ENV altogether:
+    if (Test-Path -Path Env:VIRTUAL_ENV) {
+        Remove-Item -Path env:VIRTUAL_ENV
+    }
+
+    # Just remove VIRTUAL_ENV_PROMPT altogether.
+    if (Test-Path -Path Env:VIRTUAL_ENV_PROMPT) {
+        Remove-Item -Path env:VIRTUAL_ENV_PROMPT
+    }
+
+    # Just remove the _PYTHON_VENV_PROMPT_PREFIX altogether:
+    if (Get-Variable -Name "_PYTHON_VENV_PROMPT_PREFIX" -ErrorAction SilentlyContinue) {
+        Remove-Variable -Name _PYTHON_VENV_PROMPT_PREFIX -Scope Global -Force
+    }
+
+    # Leave deactivate function in the global namespace if requested:
+    if (-not $NonDestructive) {
+        Remove-Item -Path function:deactivate
+    }
+}
+
+<#
+.Description
+Get-PyVenvConfig parses the values from the pyvenv.cfg file located in the
+given folder, and returns them in a map.
+
+For each line in the pyvenv.cfg file, if that line can be parsed into exactly
+two strings separated by `=` (with any amount of whitespace surrounding the =)
+then it is considered a `key = value` line. The left hand string is the key,
+the right hand is the value.
+
+If the value starts with a `'` or a `"` then the first and last character is
+stripped from the value before being captured.
+
+.Parameter ConfigDir
+Path to the directory that contains the `pyvenv.cfg` file.
+#>
+function Get-PyVenvConfig(
+    [String]
+    $ConfigDir
+) {
+    Write-Verbose "Given ConfigDir=$ConfigDir, obtain values in pyvenv.cfg"
+
+    # Ensure the file exists, and issue a warning if it doesn't (but still allow the function to continue).
+    $pyvenvConfigPath = Join-Path -Resolve -Path $ConfigDir -ChildPath 'pyvenv.cfg' -ErrorAction Continue
+
+    # An empty map will be returned if no config file is found.
+    $pyvenvConfig = @{ }
+
+    if ($pyvenvConfigPath) {
+
+        Write-Verbose "File exists, parse `key = value` lines"
+        $pyvenvConfigContent = Get-Content -Path $pyvenvConfigPath
+
+        $pyvenvConfigContent | ForEach-Object {
+            $keyval = $PSItem -split "\s*=\s*", 2
+            if ($keyval[0] -and $keyval[1]) {
+                $val = $keyval[1]
+
+                # Remove extraneous quotations around a string value.
+                if ("'""".Contains($val.Substring(0, 1))) {
+                    $val = $val.Substring(1, $val.Length - 2)
+                }
+
+                $pyvenvConfig[$keyval[0]] = $val
+                Write-Verbose "Adding Key: '$($keyval[0])'='$val'"
+            }
+        }
+    }
+    return $pyvenvConfig
+}
+
+
+<# Begin Activate script --------------------------------------------------- #>
+
+# Determine the containing directory of this script
+$VenvExecPath = Split-Path -Parent $MyInvocation.MyCommand.Definition
+$VenvExecDir = Get-Item -Path $VenvExecPath
+
+Write-Verbose "Activation script is located in path: '$VenvExecPath'"
+Write-Verbose "VenvExecDir Fullname: '$($VenvExecDir.FullName)"
+Write-Verbose "VenvExecDir Name: '$($VenvExecDir.Name)"
+
+# Set values required in priority: CmdLine, ConfigFile, Default
+# First, get the location of the virtual environment, it might not be
+# VenvExecDir if specified on the command line.
+if ($VenvDir) {
+    Write-Verbose "VenvDir given as parameter, using '$VenvDir' to determine values"
+}
+else {
+    Write-Verbose "VenvDir not given as a parameter, using parent directory name as VenvDir."
+    $VenvDir = $VenvExecDir.Parent.FullName.TrimEnd("\\/")
+    Write-Verbose "VenvDir=$VenvDir"
+}
+
+# Next, read the `pyvenv.cfg` file to determine any required value such
+# as `prompt`.
+$pyvenvCfg = Get-PyVenvConfig -ConfigDir $VenvDir
+
+# Next, set the prompt from the command line, or the config file, or
+# just use the name of the virtual environment folder.
+if ($Prompt) {
+    Write-Verbose "Prompt specified as argument, using '$Prompt'"
+}
+else {
+    Write-Verbose "Prompt not specified as argument to script, checking pyvenv.cfg value"
+    if ($pyvenvCfg -and $pyvenvCfg['prompt']) {
+        Write-Verbose "  Setting based on value in pyvenv.cfg='$($pyvenvCfg['prompt'])'"
+        $Prompt = $pyvenvCfg['prompt'];
+    }
+    else {
+        Write-Verbose "  Setting prompt based on parent's directory's name. (Is the directory name passed to venv module when creating the virtual environment)"
+        Write-Verbose "  Got leaf-name of $VenvDir='$(Split-Path -Path $venvDir -Leaf)'"
+        $Prompt = Split-Path -Path $venvDir -Leaf
+    }
+}
+
+Write-Verbose "Prompt = '$Prompt'"
+Write-Verbose "VenvDir='$VenvDir'"
+
+# Deactivate any currently active virtual environment, but leave the
+# deactivate function in place.
+deactivate -nondestructive
+
+# Now set the environment variable VIRTUAL_ENV, used by many tools to determine
+# that there is an activated venv.
+$env:VIRTUAL_ENV = $VenvDir
+
+if (-not $Env:VIRTUAL_ENV_DISABLE_PROMPT) {
+
+    Write-Verbose "Setting prompt to '$Prompt'"
+
+    # Set the prompt to include the env name
+    # Make sure _OLD_VIRTUAL_PROMPT is global
+    function global:_OLD_VIRTUAL_PROMPT { "" }
+    Copy-Item -Path function:prompt -Destination function:_OLD_VIRTUAL_PROMPT
+    New-Variable -Name _PYTHON_VENV_PROMPT_PREFIX -Description "Python virtual environment prompt prefix" -Scope Global -Option ReadOnly -Visibility Public -Value $Prompt
+
+    function global:prompt {
+        Write-Host -NoNewline -ForegroundColor Green "($_PYTHON_VENV_PROMPT_PREFIX) "
+        _OLD_VIRTUAL_PROMPT
+    }
+    $env:VIRTUAL_ENV_PROMPT = $Prompt
+}
+
+# Clear PYTHONHOME
+if (Test-Path -Path Env:PYTHONHOME) {
+    Copy-Item -Path Env:PYTHONHOME -Destination Env:_OLD_VIRTUAL_PYTHONHOME
+    Remove-Item -Path Env:PYTHONHOME
+}
+
+# Add the venv to the PATH
+Copy-Item -Path Env:PATH -Destination Env:_OLD_VIRTUAL_PATH
+$Env:PATH = "$VenvExecDir$([System.IO.Path]::PathSeparator)$Env:PATH"

venv/bin/activate

@@ -0,0 +1,69 @@
+# This file must be used with "source bin/activate" *from bash*
+# you cannot run it directly
+
+deactivate () {
+    # reset old environment variables
+    if [ -n "${_OLD_VIRTUAL_PATH:-}" ] ; then
+        PATH="${_OLD_VIRTUAL_PATH:-}"
+        export PATH
+        unset _OLD_VIRTUAL_PATH
+    fi
+    if [ -n "${_OLD_VIRTUAL_PYTHONHOME:-}" ] ; then
+        PYTHONHOME="${_OLD_VIRTUAL_PYTHONHOME:-}"
+        export PYTHONHOME
+        unset _OLD_VIRTUAL_PYTHONHOME
+    fi
+
+    # This should detect bash and zsh, which have a hash command that must
+    # be called to get it to forget past commands.  Without forgetting
+    # past commands the $PATH changes we made may not be respected
+    if [ -n "${BASH:-}" -o -n "${ZSH_VERSION:-}" ] ; then
+        hash -r 2> /dev/null
+    fi
+
+    if [ -n "${_OLD_VIRTUAL_PS1:-}" ] ; then
+        PS1="${_OLD_VIRTUAL_PS1:-}"
+        export PS1
+        unset _OLD_VIRTUAL_PS1
+    fi
+
+    unset VIRTUAL_ENV
+    unset VIRTUAL_ENV_PROMPT
+    if [ ! "${1:-}" = "nondestructive" ] ; then
+    # Self destruct!
+        unset -f deactivate
+    fi
+}
+
+# unset irrelevant variables
+deactivate nondestructive
+
+VIRTUAL_ENV=/home/adelorenzo/repos/talk2me/venv
+export VIRTUAL_ENV
+
+_OLD_VIRTUAL_PATH="$PATH"
+PATH="$VIRTUAL_ENV/"bin":$PATH"
+export PATH
+
+# unset PYTHONHOME if set
+# this will fail if PYTHONHOME is set to the empty string (which is bad anyway)
+# could use `if (set -u; : $PYTHONHOME) ;` in bash
+if [ -n "${PYTHONHOME:-}" ] ; then
+    _OLD_VIRTUAL_PYTHONHOME="${PYTHONHOME:-}"
+    unset PYTHONHOME
+fi
+
+if [ -z "${VIRTUAL_ENV_DISABLE_PROMPT:-}" ] ; then
+    _OLD_VIRTUAL_PS1="${PS1:-}"
+    PS1='(venv) '"${PS1:-}"
+    export PS1
+    VIRTUAL_ENV_PROMPT='(venv) '
+    export VIRTUAL_ENV_PROMPT
+fi
+
+# This should detect bash and zsh, which have a hash command that must
+# be called to get it to forget past commands.  Without forgetting
+# past commands the $PATH changes we made may not be respected
+if [ -n "${BASH:-}" -o -n "${ZSH_VERSION:-}" ] ; then
+    hash -r 2> /dev/null
+fi

venv/bin/activate.csh

@@ -0,0 +1,26 @@
+# This file must be used with "source bin/activate.csh" *from csh*.
+# You cannot run it directly.
+# Created by Davide Di Blasi <davidedb@gmail.com>.
+# Ported to Python 3.3 venv by Andrew Svetlov <andrew.svetlov@gmail.com>
+
+alias deactivate 'test $?_OLD_VIRTUAL_PATH != 0 && setenv PATH "$_OLD_VIRTUAL_PATH" && unset _OLD_VIRTUAL_PATH; rehash; test $?_OLD_VIRTUAL_PROMPT != 0 && set prompt="$_OLD_VIRTUAL_PROMPT" && unset _OLD_VIRTUAL_PROMPT; unsetenv VIRTUAL_ENV; unsetenv VIRTUAL_ENV_PROMPT; test "\!:*" != "nondestructive" && unalias deactivate'
+
+# Unset irrelevant variables.
+deactivate nondestructive
+
+setenv VIRTUAL_ENV /home/adelorenzo/repos/talk2me/venv
+
+set _OLD_VIRTUAL_PATH="$PATH"
+setenv PATH "$VIRTUAL_ENV/"bin":$PATH"
+
+
+set _OLD_VIRTUAL_PROMPT="$prompt"
+
+if (! "$?VIRTUAL_ENV_DISABLE_PROMPT") then
+    set prompt = '(venv) '"$prompt"
+    setenv VIRTUAL_ENV_PROMPT '(venv) '
+endif
+
+alias pydoc python -m pydoc
+
+rehash

venv/bin/activate.fish

@@ -0,0 +1,69 @@
+# This file must be used with "source <venv>/bin/activate.fish" *from fish*
+# (https://fishshell.com/); you cannot run it directly.
+
+function deactivate  -d "Exit virtual environment and return to normal shell environment"
+    # reset old environment variables
+    if test -n "$_OLD_VIRTUAL_PATH"
+        set -gx PATH $_OLD_VIRTUAL_PATH
+        set -e _OLD_VIRTUAL_PATH
+    end
+    if test -n "$_OLD_VIRTUAL_PYTHONHOME"
+        set -gx PYTHONHOME $_OLD_VIRTUAL_PYTHONHOME
+        set -e _OLD_VIRTUAL_PYTHONHOME
+    end
+
+    if test -n "$_OLD_FISH_PROMPT_OVERRIDE"
+        set -e _OLD_FISH_PROMPT_OVERRIDE
+        # prevents error when using nested fish instances (Issue #93858)
+        if functions -q _old_fish_prompt
+            functions -e fish_prompt
+            functions -c _old_fish_prompt fish_prompt
+            functions -e _old_fish_prompt
+        end
+    end
+
+    set -e VIRTUAL_ENV
+    set -e VIRTUAL_ENV_PROMPT
+    if test "$argv[1]" != "nondestructive"
+        # Self-destruct!
+        functions -e deactivate
+    end
+end
+
+# Unset irrelevant variables.
+deactivate nondestructive
+
+set -gx VIRTUAL_ENV /home/adelorenzo/repos/talk2me/venv
+
+set -gx _OLD_VIRTUAL_PATH $PATH
+set -gx PATH "$VIRTUAL_ENV/"bin $PATH
+
+# Unset PYTHONHOME if set.
+if set -q PYTHONHOME
+    set -gx _OLD_VIRTUAL_PYTHONHOME $PYTHONHOME
+    set -e PYTHONHOME
+end
+
+if test -z "$VIRTUAL_ENV_DISABLE_PROMPT"
+    # fish uses a function instead of an env var to generate the prompt.
+
+    # Save the current fish_prompt function as the function _old_fish_prompt.
+    functions -c fish_prompt _old_fish_prompt
+
+    # With the original prompt function renamed, we can override with our own.
+    function fish_prompt
+        # Save the return status of the last command.
+        set -l old_status $status
+
+        # Output the venv prompt; color taken from the blue of the Python logo.
+        printf "%s%s%s" (set_color 4B8BBE) '(venv) ' (set_color normal)
+
+        # Restore the return status of the previous command.
+        echo "exit $old_status" | .
+        # Output the original/"old" prompt.
+        _old_fish_prompt
+    end
+
+    set -gx _OLD_FISH_PROMPT_OVERRIDE "$VIRTUAL_ENV"
+    set -gx VIRTUAL_ENV_PROMPT '(venv) '
+end

venv/bin/flask

@@ -0,0 +1,8 @@
+#!/home/adelorenzo/repos/talk2me/venv/bin/python3
+# -*- coding: utf-8 -*-
+import re
+import sys
+from flask.cli import main
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
+    sys.exit(main())

venv/bin/normalizer

@@ -0,0 +1,8 @@
+#!/home/adelorenzo/repos/talk2me/venv/bin/python3
+# -*- coding: utf-8 -*-
+import re
+import sys
+from charset_normalizer import cli
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
+    sys.exit(cli.cli_detect())

venv/bin/pip

@@ -0,0 +1,8 @@
+#!/home/adelorenzo/repos/talk2me/venv/bin/python3
+# -*- coding: utf-8 -*-
+import re
+import sys
+from pip._internal.cli.main import main
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
+    sys.exit(main())

venv/bin/pip3

@@ -0,0 +1,8 @@
+#!/home/adelorenzo/repos/talk2me/venv/bin/python3
+# -*- coding: utf-8 -*-
+import re
+import sys
+from pip._internal.cli.main import main
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
+    sys.exit(main())

venv/bin/pip3.11

@@ -0,0 +1,8 @@
+#!/home/adelorenzo/repos/talk2me/venv/bin/python3
+# -*- coding: utf-8 -*-
+import re
+import sys
+from pip._internal.cli.main import main
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
+    sys.exit(main())

venv/bin/python

@@ -0,0 +1 @@
+python3

venv/bin/python3

@@ -0,0 +1 @@
+/usr/bin/python3

venv/bin/python3.11

@@ -0,0 +1 @@
+python3

venv/lib/python3.11/site-packages/MarkupSafe-3.0.2.dist-info/INSTALLER

@@ -0,0 +1 @@
+pip

venv/lib/python3.11/site-packages/MarkupSafe-3.0.2.dist-info/LICENSE.txt

@@ -0,0 +1,28 @@
+Copyright 2010 Pallets
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are
+met:
+
+1.  Redistributions of source code must retain the above copyright
+    notice, this list of conditions and the following disclaimer.
+
+2.  Redistributions in binary form must reproduce the above copyright
+    notice, this list of conditions and the following disclaimer in the
+    documentation and/or other materials provided with the distribution.
+
+3.  Neither the name of the copyright holder nor the names of its
+    contributors may be used to endorse or promote products derived from
+    this software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
+PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED
+TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
+PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
+LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
+NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

venv/lib/python3.11/site-packages/MarkupSafe-3.0.2.dist-info/METADATA

@@ -0,0 +1,92 @@
+Metadata-Version: 2.1
+Name: MarkupSafe
+Version: 3.0.2
+Summary: Safely add untrusted strings to HTML/XML markup.
+Maintainer-email: Pallets <contact@palletsprojects.com>
+License: Copyright 2010 Pallets
+        
+        Redistribution and use in source and binary forms, with or without
+        modification, are permitted provided that the following conditions are
+        met:
+        
+        1.  Redistributions of source code must retain the above copyright
+            notice, this list of conditions and the following disclaimer.
+        
+        2.  Redistributions in binary form must reproduce the above copyright
+            notice, this list of conditions and the following disclaimer in the
+            documentation and/or other materials provided with the distribution.
+        
+        3.  Neither the name of the copyright holder nor the names of its
+            contributors may be used to endorse or promote products derived from
+            this software without specific prior written permission.
+        
+        THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+        "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+        LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
+        PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+        HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+        SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED
+        TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
+        PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
+        LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
+        NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+        SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+        
+Project-URL: Donate, https://palletsprojects.com/donate
+Project-URL: Documentation, https://markupsafe.palletsprojects.com/
+Project-URL: Changes, https://markupsafe.palletsprojects.com/changes/
+Project-URL: Source, https://github.com/pallets/markupsafe/
+Project-URL: Chat, https://discord.gg/pallets
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: Environment :: Web Environment
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: BSD License
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python
+Classifier: Topic :: Internet :: WWW/HTTP :: Dynamic Content
+Classifier: Topic :: Text Processing :: Markup :: HTML
+Classifier: Typing :: Typed
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+License-File: LICENSE.txt
+
+# MarkupSafe
+
+MarkupSafe implements a text object that escapes characters so it is
+safe to use in HTML and XML. Characters that have special meanings are
+replaced so that they display as the actual characters. This mitigates
+injection attacks, meaning untrusted user input can safely be displayed
+on a page.
+
+
+## Examples
+
+```pycon
+>>> from markupsafe import Markup, escape
+
+>>> # escape replaces special characters and wraps in Markup
+>>> escape("<script>alert(document.cookie);</script>")
+Markup('&lt;script&gt;alert(document.cookie);&lt;/script&gt;')
+
+>>> # wrap in Markup to mark text "safe" and prevent escaping
+>>> Markup("<strong>Hello</strong>")
+Markup('<strong>hello</strong>')
+
+>>> escape(Markup("<strong>Hello</strong>"))
+Markup('<strong>hello</strong>')
+
+>>> # Markup is a str subclass
+>>> # methods and operators escape their arguments
+>>> template = Markup("Hello <em>{name}</em>")
+>>> template.format(name='"World"')
+Markup('Hello <em>&#34;World&#34;</em>')
+```
+
+## Donate
+
+The Pallets organization develops and supports MarkupSafe and other
+popular packages. In order to grow the community of contributors and
+users, and allow the maintainers to devote more time to the projects,
+[please donate today][].
+
+[please donate today]: https://palletsprojects.com/donate

venv/lib/python3.11/site-packages/MarkupSafe-3.0.2.dist-info/RECORD

@@ -0,0 +1,14 @@
+MarkupSafe-3.0.2.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4
+MarkupSafe-3.0.2.dist-info/LICENSE.txt,sha256=SJqOEQhQntmKN7uYPhHg9-HTHwvY-Zp5yESOf_N9B-o,1475
+MarkupSafe-3.0.2.dist-info/METADATA,sha256=aAwbZhSmXdfFuMM-rEHpeiHRkBOGESyVLJIuwzHP-nw,3975
+MarkupSafe-3.0.2.dist-info/RECORD,,
+MarkupSafe-3.0.2.dist-info/WHEEL,sha256=Op2RVjKCU4Yd3uty1Wlljkjcwas4cTvIrdqkKFZWK28,153
+MarkupSafe-3.0.2.dist-info/top_level.txt,sha256=qy0Plje5IJuvsCBjejJyhDCjEAdcDLK_2agVcex8Z6U,11
+markupsafe/__init__.py,sha256=sr-U6_27DfaSrj5jnHYxWN-pvhM27sjlDplMDPZKm7k,13214
+markupsafe/__pycache__/__init__.cpython-311.pyc,,
+markupsafe/__pycache__/_native.cpython-311.pyc,,
+markupsafe/_native.py,sha256=hSLs8Jmz5aqayuengJJ3kdT5PwNpBWpKrmQSdipndC8,210
+markupsafe/_speedups.c,sha256=O7XulmTo-epI6n2FtMVOrJXl8EAaIwD2iNYmBI5SEoQ,4149
+markupsafe/_speedups.cpython-311-aarch64-linux-gnu.so,sha256=ERBcuz-gl_TnODv5KWmFWXAr45_JjnsouJnevCcUXlc,98536
+markupsafe/_speedups.pyi,sha256=ENd1bYe7gbBUf2ywyYWOGUpnXOHNJ-cgTNqetlW8h5k,41
+markupsafe/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0

venv/lib/python3.11/site-packages/MarkupSafe-3.0.2.dist-info/WHEEL

@@ -0,0 +1,6 @@
+Wheel-Version: 1.0
+Generator: setuptools (75.2.0)
+Root-Is-Purelib: false
+Tag: cp311-cp311-manylinux_2_17_aarch64
+Tag: cp311-cp311-manylinux2014_aarch64
+

venv/lib/python3.11/site-packages/MarkupSafe-3.0.2.dist-info/top_level.txt

@@ -0,0 +1 @@
+markupsafe

venv/lib/python3.11/site-packages/SpeechRecognition-3.14.2.dist-info/INSTALLER

@@ -0,0 +1 @@
+pip

venv/lib/python3.11/site-packages/SpeechRecognition-3.14.2.dist-info/LICENSE-FLAC.txt

@@ -0,0 +1,339 @@
+                    GNU GENERAL PUBLIC LICENSE
+                       Version 2, June 1991
+
+ Copyright (C) 1989, 1991 Free Software Foundation, Inc.,
+ 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
+ Everyone is permitted to copy and distribute verbatim copies
+ of this license document, but changing it is not allowed.
+
+                            Preamble
+
+  The licenses for most software are designed to take away your
+freedom to share and change it.  By contrast, the GNU General Public
+License is intended to guarantee your freedom to share and change free
+software--to make sure the software is free for all its users.  This
+General Public License applies to most of the Free Software
+Foundation's software and to any other program whose authors commit to
+using it.  (Some other Free Software Foundation software is covered by
+the GNU Lesser General Public License instead.)  You can apply it to
+your programs, too.
+
+  When we speak of free software, we are referring to freedom, not
+price.  Our General Public Licenses are designed to make sure that you
+have the freedom to distribute copies of free software (and charge for
+this service if you wish), that you receive source code or can get it
+if you want it, that you can change the software or use pieces of it
+in new free programs; and that you know you can do these things.
+
+  To protect your rights, we need to make restrictions that forbid
+anyone to deny you these rights or to ask you to surrender the rights.
+These restrictions translate to certain responsibilities for you if you
+distribute copies of the software, or if you modify it.
+
+  For example, if you distribute copies of such a program, whether
+gratis or for a fee, you must give the recipients all the rights that
+you have.  You must make sure that they, too, receive or can get the
+source code.  And you must show them these terms so they know their
+rights.
+
+  We protect your rights with two steps: (1) copyright the software, and
+(2) offer you this license which gives you legal permission to copy,
+distribute and/or modify the software.
+
+  Also, for each author's protection and ours, we want to make certain
+that everyone understands that there is no warranty for this free
+software.  If the software is modified by someone else and passed on, we
+want its recipients to know that what they have is not the original, so
+that any problems introduced by others will not reflect on the original
+authors' reputations.
+
+  Finally, any free program is threatened constantly by software
+patents.  We wish to avoid the danger that redistributors of a free
+program will individually obtain patent licenses, in effect making the
+program proprietary.  To prevent this, we have made it clear that any
+patent must be licensed for everyone's free use or not licensed at all.
+
+  The precise terms and conditions for copying, distribution and
+modification follow.
+
+                    GNU GENERAL PUBLIC LICENSE
+   TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION
+
+  0. This License applies to any program or other work which contains
+a notice placed by the copyright holder saying it may be distributed
+under the terms of this General Public License.  The "Program", below,
+refers to any such program or work, and a "work based on the Program"
+means either the Program or any derivative work under copyright law:
+that is to say, a work containing the Program or a portion of it,
+either verbatim or with modifications and/or translated into another
+language.  (Hereinafter, translation is included without limitation in
+the term "modification".)  Each licensee is addressed as "you".
+
+Activities other than copying, distribution and modification are not
+covered by this License; they are outside its scope.  The act of
+running the Program is not restricted, and the output from the Program
+is covered only if its contents constitute a work based on the
+Program (independent of having been made by running the Program).
+Whether that is true depends on what the Program does.
+
+  1. You may copy and distribute verbatim copies of the Program's
+source code as you receive it, in any medium, provided that you
+conspicuously and appropriately publish on each copy an appropriate
+copyright notice and disclaimer of warranty; keep intact all the
+notices that refer to this License and to the absence of any warranty;
+and give any other recipients of the Program a copy of this License
+along with the Program.
+
+You may charge a fee for the physical act of transferring a copy, and
+you may at your option offer warranty protection in exchange for a fee.
+
+  2. You may modify your copy or copies of the Program or any portion
+of it, thus forming a work based on the Program, and copy and
+distribute such modifications or work under the terms of Section 1
+above, provided that you also meet all of these conditions:
+
+    a) You must cause the modified files to carry prominent notices
+    stating that you changed the files and the date of any change.
+
+    b) You must cause any work that you distribute or publish, that in
+    whole or in part contains or is derived from the Program or any
+    part thereof, to be licensed as a whole at no charge to all third
+    parties under the terms of this License.
+
+    c) If the modified program normally reads commands interactively
+    when run, you must cause it, when started running for such
+    interactive use in the most ordinary way, to print or display an
+    announcement including an appropriate copyright notice and a
+    notice that there is no warranty (or else, saying that you provide
+    a warranty) and that users may redistribute the program under
+    these conditions, and telling the user how to view a copy of this
+    License.  (Exception: if the Program itself is interactive but
+    does not normally print such an announcement, your work based on
+    the Program is not required to print an announcement.)
+
+These requirements apply to the modified work as a whole.  If
+identifiable sections of that work are not derived from the Program,
+and can be reasonably considered independent and separate works in
+themselves, then this License, and its terms, do not apply to those
+sections when you distribute them as separate works.  But when you
+distribute the same sections as part of a whole which is a work based
+on the Program, the distribution of the whole must be on the terms of
+this License, whose permissions for other licensees extend to the
+entire whole, and thus to each and every part regardless of who wrote it.
+
+Thus, it is not the intent of this section to claim rights or contest
+your rights to work written entirely by you; rather, the intent is to
+exercise the right to control the distribution of derivative or
+collective works based on the Program.
+
+In addition, mere aggregation of another work not based on the Program
+with the Program (or with a work based on the Program) on a volume of
+a storage or distribution medium does not bring the other work under
+the scope of this License.
+
+  3. You may copy and distribute the Program (or a work based on it,
+under Section 2) in object code or executable form under the terms of
+Sections 1 and 2 above provided that you also do one of the following:
+
+    a) Accompany it with the complete corresponding machine-readable
+    source code, which must be distributed under the terms of Sections
+    1 and 2 above on a medium customarily used for software interchange; or,
+
+    b) Accompany it with a written offer, valid for at least three
+    years, to give any third party, for a charge no more than your
+    cost of physically performing source distribution, a complete
+    machine-readable copy of the corresponding source code, to be
+    distributed under the terms of Sections 1 and 2 above on a medium
+    customarily used for software interchange; or,
+
+    c) Accompany it with the information you received as to the offer
+    to distribute corresponding source code.  (This alternative is
+    allowed only for noncommercial distribution and only if you
+    received the program in object code or executable form with such
+    an offer, in accord with Subsection b above.)
+
+The source code for a work means the preferred form of the work for
+making modifications to it.  For an executable work, complete source
+code means all the source code for all modules it contains, plus any
+associated interface definition files, plus the scripts used to
+control compilation and installation of the executable.  However, as a
+special exception, the source code distributed need not include
+anything that is normally distributed (in either source or binary
+form) with the major components (compiler, kernel, and so on) of the
+operating system on which the executable runs, unless that component
+itself accompanies the executable.
+
+If distribution of executable or object code is made by offering
+access to copy from a designated place, then offering equivalent
+access to copy the source code from the same place counts as
+distribution of the source code, even though third parties are not
+compelled to copy the source along with the object code.
+
+  4. You may not copy, modify, sublicense, or distribute the Program
+except as expressly provided under this License.  Any attempt
+otherwise to copy, modify, sublicense or distribute the Program is
+void, and will automatically terminate your rights under this License.
+However, parties who have received copies, or rights, from you under
+this License will not have their licenses terminated so long as such
+parties remain in full compliance.
+
+  5. You are not required to accept this License, since you have not
+signed it.  However, nothing else grants you permission to modify or
+distribute the Program or its derivative works.  These actions are
+prohibited by law if you do not accept this License.  Therefore, by
+modifying or distributing the Program (or any work based on the
+Program), you indicate your acceptance of this License to do so, and
+all its terms and conditions for copying, distributing or modifying
+the Program or works based on it.
+
+  6. Each time you redistribute the Program (or any work based on the
+Program), the recipient automatically receives a license from the
+original licensor to copy, distribute or modify the Program subject to
+these terms and conditions.  You may not impose any further
+restrictions on the recipients' exercise of the rights granted herein.
+You are not responsible for enforcing compliance by third parties to
+this License.
+
+  7. If, as a consequence of a court judgment or allegation of patent
+infringement or for any other reason (not limited to patent issues),
+conditions are imposed on you (whether by court order, agreement or
+otherwise) that contradict the conditions of this License, they do not
+excuse you from the conditions of this License.  If you cannot
+distribute so as to satisfy simultaneously your obligations under this
+License and any other pertinent obligations, then as a consequence you
+may not distribute the Program at all.  For example, if a patent
+license would not permit royalty-free redistribution of the Program by
+all those who receive copies directly or indirectly through you, then
+the only way you could satisfy both it and this License would be to
+refrain entirely from distribution of the Program.
+
+If any portion of this section is held invalid or unenforceable under
+any particular circumstance, the balance of the section is intended to
+apply and the section as a whole is intended to apply in other
+circumstances.
+
+It is not the purpose of this section to induce you to infringe any
+patents or other property right claims or to contest validity of any
+such claims; this section has the sole purpose of protecting the
+integrity of the free software distribution system, which is
+implemented by public license practices.  Many people have made
+generous contributions to the wide range of software distributed
+through that system in reliance on consistent application of that
+system; it is up to the author/donor to decide if he or she is willing
+to distribute software through any other system and a licensee cannot
+impose that choice.
+
+This section is intended to make thoroughly clear what is believed to
+be a consequence of the rest of this License.
+
+  8. If the distribution and/or use of the Program is restricted in
+certain countries either by patents or by copyrighted interfaces, the
+original copyright holder who places the Program under this License
+may add an explicit geographical distribution limitation excluding
+those countries, so that distribution is permitted only in or among
+countries not thus excluded.  In such case, this License incorporates
+the limitation as if written in the body of this License.
+
+  9. The Free Software Foundation may publish revised and/or new versions
+of the General Public License from time to time.  Such new versions will
+be similar in spirit to the present version, but may differ in detail to
+address new problems or concerns.
+
+Each version is given a distinguishing version number.  If the Program
+specifies a version number of this License which applies to it and "any
+later version", you have the option of following the terms and conditions
+either of that version or of any later version published by the Free
+Software Foundation.  If the Program does not specify a version number of
+this License, you may choose any version ever published by the Free Software
+Foundation.
+
+  10. If you wish to incorporate parts of the Program into other free
+programs whose distribution conditions are different, write to the author
+to ask for permission.  For software which is copyrighted by the Free
+Software Foundation, write to the Free Software Foundation; we sometimes
+make exceptions for this.  Our decision will be guided by the two goals
+of preserving the free status of all derivatives of our free software and
+of promoting the sharing and reuse of software generally.
+
+                            NO WARRANTY
+
+  11. BECAUSE THE PROGRAM IS LICENSED FREE OF CHARGE, THERE IS NO WARRANTY
+FOR THE PROGRAM, TO THE EXTENT PERMITTED BY APPLICABLE LAW.  EXCEPT WHEN
+OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES
+PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED
+OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
+MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE.  THE ENTIRE RISK AS
+TO THE QUALITY AND PERFORMANCE OF THE PROGRAM IS WITH YOU.  SHOULD THE
+PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF ALL NECESSARY SERVICING,
+REPAIR OR CORRECTION.
+
+  12. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
+WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY AND/OR
+REDISTRIBUTE THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES,
+INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING
+OUT OF THE USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED
+TO LOSS OF DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY
+YOU OR THIRD PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER
+PROGRAMS), EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE
+POSSIBILITY OF SUCH DAMAGES.
+
+                     END OF TERMS AND CONDITIONS
+
+            How to Apply These Terms to Your New Programs
+
+  If you develop a new program, and you want it to be of the greatest
+possible use to the public, the best way to achieve this is to make it
+free software which everyone can redistribute and change under these terms.
+
+  To do so, attach the following notices to the program.  It is safest
+to attach them to the start of each source file to most effectively
+convey the exclusion of warranty; and each file should have at least
+the "copyright" line and a pointer to where the full notice is found.
+
+    <one line to give the program's name and a brief idea of what it does.>
+    Copyright (C) <year>  <name of author>
+
+    This program is free software; you can redistribute it and/or modify
+    it under the terms of the GNU General Public License as published by
+    the Free Software Foundation; either version 2 of the License, or
+    (at your option) any later version.
+
+    This program is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU General Public License for more details.
+
+    You should have received a copy of the GNU General Public License along
+    with this program; if not, write to the Free Software Foundation, Inc.,
+    51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
+
+Also add information on how to contact you by electronic and paper mail.
+
+If the program is interactive, make it output a short notice like this
+when it starts in an interactive mode:
+
+    Gnomovision version 69, Copyright (C) year name of author
+    Gnomovision comes with ABSOLUTELY NO WARRANTY; for details type `show w'.
+    This is free software, and you are welcome to redistribute it
+    under certain conditions; type `show c' for details.
+
+The hypothetical commands `show w' and `show c' should show the appropriate
+parts of the General Public License.  Of course, the commands you use may
+be called something other than `show w' and `show c'; they could even be
+mouse-clicks or menu items--whatever suits your program.
+
+You should also get your employer (if you work as a programmer) or your
+school, if any, to sign a "copyright disclaimer" for the program, if
+necessary.  Here is a sample; alter the names:
+
+  Yoyodyne, Inc., hereby disclaims all copyright interest in the program
+  `Gnomovision' (which makes passes at compilers) written by James Hacker.
+
+  <signature of Ty Coon>, 1 April 1989
+  Ty Coon, President of Vice
+
+This General Public License does not permit incorporating your program into
+proprietary programs.  If your program is a subroutine library, you may
+consider it more useful to permit linking proprietary applications with the
+library.  If this is what you want to do, use the GNU Lesser General
+Public License instead of this License.

venv/lib/python3.11/site-packages/SpeechRecognition-3.14.2.dist-info/LICENSE.txt

@@ -0,0 +1,12 @@
+Copyright (c) 2014-, Anthony Zhang <azhang9@gmail.com>
+All rights reserved.
+
+Redistribution and use in source and binary forms, with or without modification, are permitted provided that the following conditions are met:
+
+1. Redistributions of source code must retain the above copyright notice, this list of conditions and the following disclaimer.
+
+2. Redistributions in binary form must reproduce the above copyright notice, this list of conditions and the following disclaimer in the documentation and/or other materials provided with the distribution.
+
+3. Neither the name of the copyright holder nor the names of its contributors may be used to endorse or promote products derived from this software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

venv/lib/python3.11/site-packages/SpeechRecognition-3.14.2.dist-info/METADATA

@@ -0,0 +1,464 @@
+Metadata-Version: 2.1
+Name: SpeechRecognition
+Version: 3.14.2
+Summary: Library for performing speech recognition, with support for several engines and APIs, online and offline.
+Home-page: https://github.com/Uberi/speech_recognition#readme
+Author: Anthony Zhang (Uberi)
+Author-email: azhang9@gmail.com
+License: BSD
+Keywords: speech recognition voice sphinx google wit bing api houndify ibm snowboy
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: Intended Audience :: Developers
+Classifier: Natural Language :: English
+Classifier: License :: OSI Approved :: BSD License
+Classifier: Operating System :: Microsoft :: Windows
+Classifier: Operating System :: POSIX :: Linux
+Classifier: Operating System :: MacOS :: MacOS X
+Classifier: Operating System :: Other OS
+Classifier: Programming Language :: Python
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Classifier: Topic :: Multimedia :: Sound/Audio :: Speech
+Requires-Python: >=3.9
+Description-Content-Type: text/x-rst
+License-File: LICENSE-FLAC.txt
+License-File: LICENSE.txt
+Requires-Dist: typing-extensions
+Requires-Dist: standard-aifc ; python_version >= "3.13"
+Requires-Dist: audioop-lts ; python_version >= "3.13"
+Provides-Extra: assemblyai
+Requires-Dist: requests ; extra == 'assemblyai'
+Provides-Extra: audio
+Requires-Dist: PyAudio (>=0.2.11) ; extra == 'audio'
+Provides-Extra: dev
+Requires-Dist: pytest ; extra == 'dev'
+Requires-Dist: pytest-randomly ; extra == 'dev'
+Requires-Dist: respx ; extra == 'dev'
+Requires-Dist: numpy ; extra == 'dev'
+Provides-Extra: faster-whisper
+Requires-Dist: faster-whisper ; extra == 'faster-whisper'
+Provides-Extra: google-cloud
+Requires-Dist: google-cloud-speech ; extra == 'google-cloud'
+Provides-Extra: groq
+Requires-Dist: groq ; extra == 'groq'
+Requires-Dist: httpx (<0.28) ; extra == 'groq'
+Provides-Extra: openai
+Requires-Dist: openai ; extra == 'openai'
+Requires-Dist: httpx (<0.28) ; extra == 'openai'
+Provides-Extra: pocketsphinx
+Requires-Dist: pocketsphinx ; extra == 'pocketsphinx'
+Provides-Extra: whisper-local
+Requires-Dist: openai-whisper ; extra == 'whisper-local'
+Requires-Dist: soundfile ; extra == 'whisper-local'
+
+SpeechRecognition
+=================
+
+.. image:: https://img.shields.io/pypi/v/SpeechRecognition.svg
+    :target: https://pypi.python.org/pypi/SpeechRecognition/
+    :alt: Latest Version
+
+.. image:: https://img.shields.io/pypi/status/SpeechRecognition.svg
+    :target: https://pypi.python.org/pypi/SpeechRecognition/
+    :alt: Development Status
+
+.. image:: https://img.shields.io/pypi/pyversions/SpeechRecognition.svg
+    :target: https://pypi.python.org/pypi/SpeechRecognition/
+    :alt: Supported Python Versions
+
+.. image:: https://img.shields.io/pypi/l/SpeechRecognition.svg
+    :target: https://pypi.python.org/pypi/SpeechRecognition/
+    :alt: License
+
+.. image:: https://api.travis-ci.org/Uberi/speech_recognition.svg?branch=master
+    :target: https://travis-ci.org/Uberi/speech_recognition
+    :alt: Continuous Integration Test Results
+
+Library for performing speech recognition, with support for several engines and APIs, online and offline.
+
+**UPDATE 2022-02-09**: Hey everyone! This project started as a tech demo, but these days it needs more time than I have to keep up with all the PRs and issues. Therefore, I'd like to put out an **open invite for collaborators** - just reach out at me@anthonyz.ca if you're interested!
+
+Speech recognition engine/API support:
+
+* `CMU Sphinx <http://cmusphinx.sourceforge.net/wiki/>`__ (works offline)
+* Google Speech Recognition
+* `Google Cloud Speech API <https://cloud.google.com/speech/>`__
+* `Wit.ai <https://wit.ai/>`__
+* `Microsoft Azure Speech <https://azure.microsoft.com/en-us/services/cognitive-services/speech/>`__
+* `Microsoft Bing Voice Recognition (Deprecated) <https://www.microsoft.com/cognitive-services/en-us/speech-api>`__
+* `Houndify API <https://houndify.com/>`__
+* `IBM Speech to Text <http://www.ibm.com/smarterplanet/us/en/ibmwatson/developercloud/speech-to-text.html>`__
+* `Snowboy Hotword Detection <https://snowboy.kitt.ai/>`__ (works offline)
+* `Tensorflow <https://www.tensorflow.org/>`__
+* `Vosk API <https://github.com/alphacep/vosk-api/>`__ (works offline)
+* `OpenAI whisper <https://github.com/openai/whisper>`__ (works offline)
+* `OpenAI Whisper API <https://platform.openai.com/docs/guides/speech-to-text>`__
+* `Groq Whisper API <https://console.groq.com/docs/speech-text>`__
+
+**Quickstart:** ``pip install SpeechRecognition``. See the "Installing" section for more details.
+
+To quickly try it out, run ``python -m speech_recognition`` after installing.
+
+Project links:
+
+-  `PyPI <https://pypi.python.org/pypi/SpeechRecognition/>`__
+-  `Source code <https://github.com/Uberi/speech_recognition>`__
+-  `Issue tracker <https://github.com/Uberi/speech_recognition/issues>`__
+
+Library Reference
+-----------------
+
+The `library reference <https://github.com/Uberi/speech_recognition/blob/master/reference/library-reference.rst>`__ documents every publicly accessible object in the library. This document is also included under ``reference/library-reference.rst``.
+
+See `Notes on using PocketSphinx <https://github.com/Uberi/speech_recognition/blob/master/reference/pocketsphinx.rst>`__ for information about installing languages, compiling PocketSphinx, and building language packs from online resources. This document is also included under ``reference/pocketsphinx.rst``.
+
+You have to install Vosk models for using Vosk. `Here <https://alphacephei.com/vosk/models>`__ are models avaiable. You have to place them in models folder of your project, like "your-project-folder/models/your-vosk-model"
+
+Examples
+--------
+
+See the ``examples/`` `directory <https://github.com/Uberi/speech_recognition/tree/master/examples>`__ in the repository root for usage examples:
+
+-  `Recognize speech input from the microphone <https://github.com/Uberi/speech_recognition/blob/master/examples/microphone_recognition.py>`__
+-  `Transcribe an audio file <https://github.com/Uberi/speech_recognition/blob/master/examples/audio_transcribe.py>`__
+-  `Save audio data to an audio file <https://github.com/Uberi/speech_recognition/blob/master/examples/write_audio.py>`__
+-  `Show extended recognition results <https://github.com/Uberi/speech_recognition/blob/master/examples/extended_results.py>`__
+-  `Calibrate the recognizer energy threshold for ambient noise levels <https://github.com/Uberi/speech_recognition/blob/master/examples/calibrate_energy_threshold.py>`__ (see ``recognizer_instance.energy_threshold`` for details)
+-  `Listening to a microphone in the background <https://github.com/Uberi/speech_recognition/blob/master/examples/background_listening.py>`__
+-  `Various other useful recognizer features <https://github.com/Uberi/speech_recognition/blob/master/examples/special_recognizer_features.py>`__
+
+Installing
+----------
+
+First, make sure you have all the requirements listed in the "Requirements" section. 
+
+The easiest way to install this is using ``pip install SpeechRecognition``.
+
+Otherwise, download the source distribution from `PyPI <https://pypi.python.org/pypi/SpeechRecognition/>`__, and extract the archive.
+
+In the folder, run ``python setup.py install``.
+
+Requirements
+------------
+
+To use all of the functionality of the library, you should have:
+
+* **Python** 3.9+ (required)
+* **PyAudio** 0.2.11+ (required only if you need to use microphone input, ``Microphone``)
+* **PocketSphinx** (required only if you need to use the Sphinx recognizer, ``recognizer_instance.recognize_sphinx``)
+* **Google API Client Library for Python** (required only if you need to use the Google Cloud Speech API, ``recognizer_instance.recognize_google_cloud``)
+* **FLAC encoder** (required only if the system is not x86-based Windows/Linux/OS X)
+* **Vosk** (required only if you need to use Vosk API speech recognition ``recognizer_instance.recognize_vosk``)
+* **Whisper** (required only if you need to use Whisper ``recognizer_instance.recognize_whisper``)
+* **Faster Whisper** (required only if you need to use Faster Whisper ``recognizer_instance.recognize_faster_whisper``)
+* **openai** (required only if you need to use OpenAI Whisper API speech recognition ``recognizer_instance.recognize_openai``)
+* **groq** (required only if you need to use Groq Whisper API speech recognition ``recognizer_instance.recognize_groq``)
+
+The following requirements are optional, but can improve or extend functionality in some situations:
+
+* If using CMU Sphinx, you may want to `install additional language packs <https://github.com/Uberi/speech_recognition/blob/master/reference/pocketsphinx.rst#installing-other-languages>`__ to support languages like International French or Mandarin Chinese.
+
+The following sections go over the details of each requirement.
+
+Python
+~~~~~~
+
+The first software requirement is `Python 3.9+ <https://www.python.org/downloads/>`__. This is required to use the library.
+
+PyAudio (for microphone users)
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+`PyAudio <http://people.csail.mit.edu/hubert/pyaudio/#downloads>`__ is required if and only if you want to use microphone input (``Microphone``). PyAudio version 0.2.11+ is required, as earlier versions have known memory management bugs when recording from microphones in certain situations.
+
+If not installed, everything in the library will still work, except attempting to instantiate a ``Microphone`` object will raise an ``AttributeError``.
+
+The installation instructions on the PyAudio website are quite good - for convenience, they are summarized below:
+
+* On Windows, install with PyAudio using `Pip <https://pip.readthedocs.org/>`__: execute ``pip install SpeechRecognition[audio]`` in a terminal.
+* On Debian-derived Linux distributions (like Ubuntu and Mint), install PyAudio using `APT <https://wiki.debian.org/Apt>`__: execute ``sudo apt-get install python-pyaudio python3-pyaudio`` in a terminal.
+    * If the version in the repositories is too old, install the latest release using Pip: execute ``sudo apt-get install portaudio19-dev python-all-dev python3-all-dev && sudo pip install SpeechRecognition[audio]`` (replace ``pip`` with ``pip3`` if using Python 3).
+* On OS X, install PortAudio using `Homebrew <http://brew.sh/>`__: ``brew install portaudio``. Then, install with PyAudio using `Pip <https://pip.readthedocs.org/>`__: ``pip install SpeechRecognition[audio]``.
+* On other POSIX-based systems, install the ``portaudio19-dev`` and ``python-all-dev`` (or ``python3-all-dev`` if using Python 3) packages (or their closest equivalents) using a package manager of your choice, and then install with PyAudio using `Pip <https://pip.readthedocs.org/>`__: ``pip install SpeechRecognition[audio]`` (replace ``pip`` with ``pip3`` if using Python 3).
+
+PocketSphinx (for Sphinx users)
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+`PocketSphinx <https://github.com/cmusphinx/pocketsphinx>`__ is **required if and only if you want to use the Sphinx recognizer** (``recognizer_instance.recognize_sphinx``).
+
+On Linux and other POSIX systems (such as OS X), run ``pip install SpeechRecognition[pocketsphinx]``. Follow the instructions under "Building PocketSphinx-Python from source" in `Notes on using PocketSphinx <https://github.com/Uberi/speech_recognition/blob/master/reference/pocketsphinx.rst>`__ for installation instructions.
+
+Note that the versions available in most package repositories are outdated and will not work with the bundled language data. Using the bundled wheel packages or building from source is recommended.
+
+See `Notes on using PocketSphinx <https://github.com/Uberi/speech_recognition/blob/master/reference/pocketsphinx.rst>`__ for information about installing languages, compiling PocketSphinx, and building language packs from online resources. This document is also included under ``reference/pocketsphinx.rst``.
+
+Vosk (for Vosk users)
+~~~~~~~~~~~~~~~~~~~~~
+Vosk API is **required if and only if you want to use Vosk recognizer** (``recognizer_instance.recognize_vosk``).
+
+You can install it with ``python3 -m pip install vosk``.
+
+You also have to install Vosk Models:
+
+`Here <https://alphacephei.com/vosk/models>`__ are models avaiable for download. You have to place them in models folder of your project, like "your-project-folder/models/your-vosk-model"
+
+Google Cloud Speech Library for Python (for Google Cloud Speech-to-Text API users)
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+The library `google-cloud-speech <https://pypi.org/project/google-cloud-speech/>`__ is **required if and only if you want to use Google Cloud Speech-to-Text API** (``recognizer_instance.recognize_google_cloud``).
+You can install it with ``python3 -m pip install SpeechRecognition[google-cloud]``.
+(ref: `official installation instructions <https://cloud.google.com/speech-to-text/docs/transcribe-client-libraries#client-libraries-install-python>`__)
+
+**Prerequisite**: Create local authentication credentials for your Google account
+
+* Digest: `Before you begin (Transcribe speech to text by using client libraries) <https://cloud.google.com/speech-to-text/docs/transcribe-client-libraries#before-you-begin>`__
+* `Set up Speech-to-Text <https://cloud.google.com/speech-to-text/docs/before-you-begin>`__
+* `User credentials (Set up ADC for a local development environment) <https://cloud.google.com/docs/authentication/set-up-adc-local-dev-environment#local-user-cred>`__
+
+Currently only `V1 <https://cloud.google.com/speech-to-text/docs/quickstart>`__ is supported. (`V2 <https://cloud.google.com/speech-to-text/v2/docs/quickstart>`__ is not supported)
+
+FLAC (for some systems)
+~~~~~~~~~~~~~~~~~~~~~~~
+
+A `FLAC encoder <https://xiph.org/flac/>`__ is required to encode the audio data to send to the API. If using Windows (x86 or x86-64), OS X (Intel Macs only, OS X 10.6 or higher), or Linux (x86 or x86-64), this is **already bundled with this library - you do not need to install anything**.
+
+Otherwise, ensure that you have the ``flac`` command line tool, which is often available through the system package manager. For example, this would usually be ``sudo apt-get install flac`` on Debian-derivatives, or ``brew install flac`` on OS X with Homebrew.
+
+Whisper (for Whisper users)
+~~~~~~~~~~~~~~~~~~~~~~~~~~~
+Whisper is **required if and only if you want to use whisper** (``recognizer_instance.recognize_whisper``).
+
+You can install it with ``python3 -m pip install SpeechRecognition[whisper-local]``.
+
+Faster Whisper (for Faster Whisper users)
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+The library `faster-whisper <https://pypi.org/project/faster-whisper/>`__ is **required if and only if you want to use Faster Whisper** (``recognizer_instance.recognize_faster_whisper``).
+
+You can install it with ``python3 -m pip install SpeechRecognition[faster-whisper]``.
+
+OpenAI Whisper API (for OpenAI Whisper API users) 
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+The library `openai <https://pypi.org/project/openai/>`__ is **required if and only if you want to use OpenAI Whisper API** (``recognizer_instance.recognize_openai``).
+
+You can install it with ``python3 -m pip install SpeechRecognition[openai]``.
+
+Please set the environment variable ``OPENAI_API_KEY`` before calling ``recognizer_instance.recognize_openai``.
+
+Groq Whisper API (for Groq Whisper API users)
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+The library `groq <https://pypi.org/project/groq/>`__ is **required if and only if you want to use Groq Whisper API** (``recognizer_instance.recognize_groq``).
+
+You can install it with ``python3 -m pip install SpeechRecognition[groq]``.
+
+Please set the environment variable ``GROQ_API_KEY`` before calling ``recognizer_instance.recognize_groq``.
+
+Troubleshooting
+---------------
+
+The recognizer tries to recognize speech even when I'm not speaking, or after I'm done speaking.
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Try increasing the ``recognizer_instance.energy_threshold`` property. This is basically how sensitive the recognizer is to when recognition should start. Higher values mean that it will be less sensitive, which is useful if you are in a loud room.
+
+This value depends entirely on your microphone or audio data. There is no one-size-fits-all value, but good values typically range from 50 to 4000.
+
+Also, check on your microphone volume settings. If it is too sensitive, the microphone may be picking up a lot of ambient noise. If it is too insensitive, the microphone may be rejecting speech as just noise.
+
+The recognizer can't recognize speech right after it starts listening for the first time.
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+The ``recognizer_instance.energy_threshold`` property is probably set to a value that is too high to start off with, and then being adjusted lower automatically by dynamic energy threshold adjustment. Before it is at a good level, the energy threshold is so high that speech is just considered ambient noise.
+
+The solution is to decrease this threshold, or call ``recognizer_instance.adjust_for_ambient_noise`` beforehand, which will set the threshold to a good value automatically.
+
+The recognizer doesn't understand my particular language/dialect.
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Try setting the recognition language to your language/dialect. To do this, see the documentation for ``recognizer_instance.recognize_sphinx``, ``recognizer_instance.recognize_google``, ``recognizer_instance.recognize_wit``, ``recognizer_instance.recognize_bing``, ``recognizer_instance.recognize_api``, ``recognizer_instance.recognize_houndify``, and ``recognizer_instance.recognize_ibm``.
+
+For example, if your language/dialect is British English, it is better to use ``"en-GB"`` as the language rather than ``"en-US"``.
+
+The recognizer hangs on ``recognizer_instance.listen``; specifically, when it's calling ``Microphone.MicrophoneStream.read``.
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+This usually happens when you're using a Raspberry Pi board, which doesn't have audio input capabilities by itself. This causes the default microphone used by PyAudio to simply block when we try to read it. If you happen to be using a Raspberry Pi, you'll need a USB sound card (or USB microphone).
+
+Once you do this, change all instances of ``Microphone()`` to ``Microphone(device_index=MICROPHONE_INDEX)``, where ``MICROPHONE_INDEX`` is the hardware-specific index of the microphone.
+
+To figure out what the value of ``MICROPHONE_INDEX`` should be, run the following code:
+
+.. code:: python
+
+    import speech_recognition as sr
+    for index, name in enumerate(sr.Microphone.list_microphone_names()):
+        print("Microphone with name \"{1}\" found for `Microphone(device_index={0})`".format(index, name))
+
+This will print out something like the following:
+
+::
+
+    Microphone with name "HDA Intel HDMI: 0 (hw:0,3)" found for `Microphone(device_index=0)`
+    Microphone with name "HDA Intel HDMI: 1 (hw:0,7)" found for `Microphone(device_index=1)`
+    Microphone with name "HDA Intel HDMI: 2 (hw:0,8)" found for `Microphone(device_index=2)`
+    Microphone with name "Blue Snowball: USB Audio (hw:1,0)" found for `Microphone(device_index=3)`
+    Microphone with name "hdmi" found for `Microphone(device_index=4)`
+    Microphone with name "pulse" found for `Microphone(device_index=5)`
+    Microphone with name "default" found for `Microphone(device_index=6)`
+
+Now, to use the Snowball microphone, you would change ``Microphone()`` to ``Microphone(device_index=3)``.
+
+Calling ``Microphone()`` gives the error ``IOError: No Default Input Device Available``.
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+As the error says, the program doesn't know which microphone to use.
+
+To proceed, either use ``Microphone(device_index=MICROPHONE_INDEX, ...)`` instead of ``Microphone(...)``, or set a default microphone in your OS. You can obtain possible values of ``MICROPHONE_INDEX`` using the code in the troubleshooting entry right above this one.
+
+The program doesn't run when compiled with `PyInstaller <https://github.com/pyinstaller/pyinstaller/wiki>`__.
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+As of PyInstaller version 3.0, SpeechRecognition is supported out of the box. If you're getting weird issues when compiling your program using PyInstaller, simply update PyInstaller.
+
+You can easily do this by running ``pip install --upgrade pyinstaller``.
+
+On Ubuntu/Debian, I get annoying output in the terminal saying things like "bt_audio_service_open: [...] Connection refused" and various others.
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+The "bt_audio_service_open" error means that you have a Bluetooth audio device, but as a physical device is not currently connected, we can't actually use it - if you're not using a Bluetooth microphone, then this can be safely ignored. If you are, and audio isn't working, then double check to make sure your microphone is actually connected. There does not seem to be a simple way to disable these messages.
+
+For errors of the form "ALSA lib [...] Unknown PCM", see `this StackOverflow answer <http://stackoverflow.com/questions/7088672/pyaudio-working-but-spits-out-error-messages-each-time>`__. Basically, to get rid of an error of the form "Unknown PCM cards.pcm.rear", simply comment out ``pcm.rear cards.pcm.rear`` in ``/usr/share/alsa/alsa.conf``, ``~/.asoundrc``, and ``/etc/asound.conf``.
+
+For "jack server is not running or cannot be started" or "connect(2) call to /dev/shm/jack-1000/default/jack_0 failed (err=No such file or directory)" or "attempt to connect to server failed", these are caused by ALSA trying to connect to JACK, and can be safely ignored. I'm not aware of any simple way to turn those messages off at this time, besides `entirely disabling printing while starting the microphone <https://github.com/Uberi/speech_recognition/issues/182#issuecomment-266256337>`__.
+
+On OS X, I get a ``ChildProcessError`` saying that it couldn't find the system FLAC converter, even though it's installed.
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Installing `FLAC for OS X <https://xiph.org/flac/download.html>`__ directly from the source code will not work, since it doesn't correctly add the executables to the search path.
+
+Installing FLAC using `Homebrew <http://brew.sh/>`__ ensures that the search path is correctly updated. First, ensure you have Homebrew, then run ``brew install flac`` to install the necessary files.
+
+Developing
+----------
+
+To hack on this library, first make sure you have all the requirements listed in the "Requirements" section.
+
+-  Most of the library code lives in ``speech_recognition/__init__.py``.
+-  Examples live under the ``examples/`` `directory <https://github.com/Uberi/speech_recognition/tree/master/examples>`__, and the demo script lives in ``speech_recognition/__main__.py``.
+-  The FLAC encoder binaries are in the ``speech_recognition/`` `directory <https://github.com/Uberi/speech_recognition/tree/master/speech_recognition>`__.
+-  Documentation can be found in the ``reference/`` `directory <https://github.com/Uberi/speech_recognition/tree/master/reference>`__.
+-  Third-party libraries, utilities, and reference material are in the ``third-party/`` `directory <https://github.com/Uberi/speech_recognition/tree/master/third-party>`__.
+
+To install/reinstall the library locally, run ``python -m pip install -e .[dev]`` in the project `root directory <https://github.com/Uberi/speech_recognition>`__.
+
+Before a release, the version number is bumped in ``README.rst`` and ``speech_recognition/__init__.py``. Version tags are then created using ``git config gpg.program gpg2 && git config user.signingkey DB45F6C431DE7C2DCD99FF7904882258A4063489 && git tag -s VERSION_GOES_HERE -m "Version VERSION_GOES_HERE"``.
+
+Releases are done by running ``make-release.sh VERSION_GOES_HERE`` to build the Python source packages, sign them, and upload them to PyPI.
+
+Testing
+~~~~~~~
+
+Prerequisite: `Install pipx <https://pipx.pypa.io/stable/installation/>`__.
+
+To run all the tests:
+
+.. code:: bash
+
+    python -m unittest discover --verbose
+
+To run static analysis:
+
+.. code:: bash
+
+    make lint
+
+To ensure RST is well-formed:
+
+.. code:: bash
+
+    make rstcheck
+
+Testing is also done automatically by GitHub Actions, upon every push.
+
+FLAC Executables
+~~~~~~~~~~~~~~~~
+
+The included ``flac-win32`` executable is the `official FLAC 1.3.2 32-bit Windows binary <http://downloads.xiph.org/releases/flac/flac-1.3.2-win.zip>`__.
+
+The included ``flac-linux-x86`` and ``flac-linux-x86_64`` executables are built from the `FLAC 1.3.2 source code <http://downloads.xiph.org/releases/flac/flac-1.3.2.tar.xz>`__ with `Manylinux <https://github.com/pypa/manylinux>`__ to ensure that it's compatible with a wide variety of distributions.
+
+The built FLAC executables should be bit-for-bit reproducible. To rebuild them, run the following inside the project directory on a Debian-like system:
+
+.. code:: bash
+
+    # download and extract the FLAC source code
+    cd third-party
+    sudo apt-get install --yes docker.io
+
+    # build FLAC inside the Manylinux i686 Docker image
+    tar xf flac-1.3.2.tar.xz
+    sudo docker run --tty --interactive --rm --volume "$(pwd):/root" quay.io/pypa/manylinux1_i686:latest bash
+        cd /root/flac-1.3.2
+        ./configure LDFLAGS=-static # compiler flags to make a static build
+        make
+    exit
+    cp flac-1.3.2/src/flac/flac ../speech_recognition/flac-linux-x86 && sudo rm -rf flac-1.3.2/
+
+    # build FLAC inside the Manylinux x86_64 Docker image
+    tar xf flac-1.3.2.tar.xz
+    sudo docker run --tty --interactive --rm --volume "$(pwd):/root" quay.io/pypa/manylinux1_x86_64:latest bash
+        cd /root/flac-1.3.2
+        ./configure LDFLAGS=-static # compiler flags to make a static build
+        make
+    exit
+    cp flac-1.3.2/src/flac/flac ../speech_recognition/flac-linux-x86_64 && sudo rm -r flac-1.3.2/
+
+The included ``flac-mac`` executable is extracted from `xACT 2.39 <http://xact.scottcbrown.org/>`__, which is a frontend for FLAC 1.3.2 that conveniently includes binaries for all of its encoders. Specifically, it is a copy of ``xACT 2.39/xACT.app/Contents/Resources/flac`` in ``xACT2.39.zip``.
+
+Authors
+-------
+
+::
+
+    Uberi <me@anthonyz.ca> (Anthony Zhang)
+    bobsayshilol
+    arvindch <achembarpu@gmail.com> (Arvind Chembarpu)
+    kevinismith <kevin_i_smith@yahoo.com> (Kevin Smith)
+    haas85
+    DelightRun <changxu.mail@gmail.com>
+    maverickagm
+    kamushadenes <kamushadenes@hyadesinc.com> (Kamus Hadenes)
+    sbraden <braden.sarah@gmail.com> (Sarah Braden)
+    tb0hdan (Bohdan Turkynewych)
+    Thynix <steve@asksteved.com> (Steve Dougherty)
+    beeedy <broderick.carlin@gmail.com> (Broderick Carlin)
+
+Please report bugs and suggestions at the `issue tracker <https://github.com/Uberi/speech_recognition/issues>`__!
+
+How to cite this library (APA style):
+
+    Zhang, A. (2017). Speech Recognition (Version 3.11) [Software]. Available from https://github.com/Uberi/speech_recognition#readme.
+
+How to cite this library (Chicago style):
+
+    Zhang, Anthony. 2017. *Speech Recognition* (version 3.11).
+
+Also check out the `Python Baidu Yuyin API <https://github.com/DelightRun/PyBaiduYuyin>`__, which is based on an older version of this project, and adds support for `Baidu Yuyin <http://yuyin.baidu.com/>`__. Note that Baidu Yuyin is only available inside China.
+
+License
+-------
+
+Copyright 2014- `Anthony Zhang (Uberi) <http://anthonyz.ca/>`__. The source code for this library is available online at `GitHub <https://github.com/Uberi/speech_recognition>`__.
+
+SpeechRecognition is made available under the 3-clause BSD license. See ``LICENSE.txt`` in the project's `root directory <https://github.com/Uberi/speech_recognition>`__ for more information.
+
+For convenience, all the official distributions of SpeechRecognition already include a copy of the necessary copyright notices and licenses. In your project, you can simply **say that licensing information for SpeechRecognition can be found within the SpeechRecognition README, and make sure SpeechRecognition is visible to users if they wish to see it**.
+
+SpeechRecognition distributes language files from `CMU Sphinx <http://cmusphinx.sourceforge.net/>`__. These files are BSD-licensed and redistributable as long as copyright notices are correctly retained. See ``speech_recognition/pocketsphinx-data/*/LICENSE*.txt`` for license details for individual parts.
+
+SpeechRecognition distributes binaries from `FLAC <https://xiph.org/flac/>`__ - ``speech_recognition/flac-win32.exe``, ``speech_recognition/flac-linux-x86``, and ``speech_recognition/flac-mac``. These files are GPLv2-licensed and redistributable, as long as the terms of the GPL are satisfied. The FLAC binaries are an `aggregate <https://www.gnu.org/licenses/gpl-faq.html#MereAggregation>`__ of `separate programs <https://www.gnu.org/licenses/gpl-faq.html#NFUseGPLPlugins>`__, so these GPL restrictions do not apply to the library or your programs that use the library, only to FLAC itself. See ``LICENSE-FLAC.txt`` for license details.

venv/lib/python3.11/site-packages/SpeechRecognition-3.14.2.dist-info/RECORD

@@ -0,0 +1,63 @@
+SpeechRecognition-3.14.2.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4
+SpeechRecognition-3.14.2.dist-info/LICENSE-FLAC.txt,sha256=gXf5dRMhNSbfLPYYTY_5hsZ1r7UU1OaKQEAQUhuIBkM,18092
+SpeechRecognition-3.14.2.dist-info/LICENSE.txt,sha256=SqBKTm-NBIGjRpyJw3tWUIptM0QqL5MGRDN9k_JSmmU,1515
+SpeechRecognition-3.14.2.dist-info/METADATA,sha256=VQmSG3yuZ4V-cbIp_dA3Jjh9VNwV9D_eKpA9l6Fh5lI,29782
+SpeechRecognition-3.14.2.dist-info/RECORD,,
+SpeechRecognition-3.14.2.dist-info/REQUESTED,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+SpeechRecognition-3.14.2.dist-info/WHEEL,sha256=P9jw-gEje8ByB7_hXoICnHtVCrEwMQh-630tKvQWehc,91
+SpeechRecognition-3.14.2.dist-info/top_level.txt,sha256=QKWAxpoWgbZk34beXvH8PdQwuAWYGijYCmC3owLhul0,25
+speech_recognition/__init__.py,sha256=7Zqcwx6H1mZQDrwlaDPswMGLfi7iTjZ7quy-Rc8RO30,77351
+speech_recognition/__main__.py,sha256=Afbp3l1yq2AW2Bsm7YBz-O0wm6gHNudgPZh69Ijjubc,833
+speech_recognition/__pycache__/__init__.cpython-311.pyc,,
+speech_recognition/__pycache__/__main__.cpython-311.pyc,,
+speech_recognition/__pycache__/audio.cpython-311.pyc,,
+speech_recognition/__pycache__/exceptions.cpython-311.pyc,,
+speech_recognition/audio.py,sha256=THoN6uaHcbbwcvhW6vzkBpAZkpP8s-ouClba48KbOkw,14824
+speech_recognition/exceptions.py,sha256=LnKmutOVQ6RSMcSO1Ji5Af-UZN-Aqrq4petMgBFXkKs,273
+speech_recognition/flac-linux-x86,sha256=FOUk-MAmqO11z7GmT4TyHIJnRZaDXZaBVsh5yfP1k8g,1899154
+speech_recognition/flac-linux-x86_64,sha256=0k6-i9XM2vxk9SKmKuL-0_t0ARrf7ts9Peqmu0YR34Q,2396644
+speech_recognition/flac-mac,sha256=2LyQYpHz0QJGWm_dnNfJoIOYsDsPI8b-JwZAVns4o6E,451168
+speech_recognition/flac-win32.exe,sha256=D8yWtMDceZCrDDnb-8gvrtNmxYiPD0oz9GTqO3m38IU,738816
+speech_recognition/pocketsphinx-data/en-US/LICENSE.txt,sha256=_PXE5BroH3BO1w8VERRicu8PDKe5cIjRHXKJa1ahifU,1537
+speech_recognition/pocketsphinx-data/en-US/acoustic-model/README,sha256=i4jemAVoUJxkbQUnuEFL7vE2lkORkDtAmW0y9ze_dS4,1617
+speech_recognition/pocketsphinx-data/en-US/acoustic-model/feat.params,sha256=ioWtKGlsfyNDRE52M84w8WX-2HQPghlUVExvvUb0lR8,165
+speech_recognition/pocketsphinx-data/en-US/acoustic-model/mdef,sha256=I2D5qGiJwc_ui9YYoCaTh5EeX7KSCllPUGsYuMeWg7A,2959176
+speech_recognition/pocketsphinx-data/en-US/acoustic-model/means,sha256=gyAZ4yysEusxiWT5b0aQNKyxLQNI7t3DgxgxoQDLTdQ,838732
+speech_recognition/pocketsphinx-data/en-US/acoustic-model/noisedict,sha256=cpWwffLCBMT4fGeCtr4aOFnXAG1OOGQYHJVdbasQWjM,56
+speech_recognition/pocketsphinx-data/en-US/acoustic-model/sendump,sha256=jJVkwNW-9pyp2b8QFKvhYvBxZEzwLPH6ikg8PcFlp6g,1969024
+speech_recognition/pocketsphinx-data/en-US/acoustic-model/transition_matrices,sha256=wffyjqQxd75zS-H4i9fxuahT0OZg-FmcZ8bq7Ki7U5o,2080
+speech_recognition/pocketsphinx-data/en-US/acoustic-model/variances,sha256=sA1pb4XpaDT8EPjl8GQo2MTba__b5YRbb2m_bvvEj6U,838732
+speech_recognition/pocketsphinx-data/en-US/language-model.lm.bin,sha256=Ttj1LtBBMEXw6cZaRwmVOJa2_5qZ68EPfvkm9mLF5QY,29208442
+speech_recognition/pocketsphinx-data/en-US/pronounciation-dictionary.dict,sha256=zjv6Nk45C35Ip0g9NQpI2fFhEn9oQoucb5ZygR_BE08,3240807
+speech_recognition/recognizers/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+speech_recognition/recognizers/__pycache__/__init__.cpython-311.pyc,,
+speech_recognition/recognizers/__pycache__/google.cpython-311.pyc,,
+speech_recognition/recognizers/__pycache__/google_cloud.cpython-311.pyc,,
+speech_recognition/recognizers/__pycache__/pocketsphinx.cpython-311.pyc,,
+speech_recognition/recognizers/google.py,sha256=bSgF7Vxmjt8nOsDt3QMsJ_ecPYM22irTXlFjtEavp8Y,10149
+speech_recognition/recognizers/google_cloud.py,sha256=-07GBAfp---EJ6RIjlbcQoDUIxDmDHNOJhJFgt3-z1Q,6101
+speech_recognition/recognizers/pocketsphinx.py,sha256=Y8fw4mPJusFk_Xhrlzh82xLFNGLlfJzhWCWPTGy4yvE,7349
+speech_recognition/recognizers/whisper_api/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+speech_recognition/recognizers/whisper_api/__pycache__/__init__.cpython-311.pyc,,
+speech_recognition/recognizers/whisper_api/__pycache__/base.cpython-311.pyc,,
+speech_recognition/recognizers/whisper_api/__pycache__/groq.cpython-311.pyc,,
+speech_recognition/recognizers/whisper_api/__pycache__/openai.cpython-311.pyc,,
+speech_recognition/recognizers/whisper_api/base.py,sha256=lkONeDe3ec6Z5qt0gRxOijyB-UUu7n_uwJ64GVdtJ5s,679
+speech_recognition/recognizers/whisper_api/groq.py,sha256=UmzcfNhMLrVd0QyvsypcpZk1GtWDzvdt9h2Y-m1Oe1o,1638
+speech_recognition/recognizers/whisper_api/openai.py,sha256=vcGF3qkbU0ABrL6jl8mqCaycwd2Fx2dFfIA8DbQ1VqA,2566
+speech_recognition/recognizers/whisper_local/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+speech_recognition/recognizers/whisper_local/__pycache__/__init__.cpython-311.pyc,,
+speech_recognition/recognizers/whisper_local/__pycache__/base.cpython-311.pyc,,
+speech_recognition/recognizers/whisper_local/__pycache__/faster_whisper.cpython-311.pyc,,
+speech_recognition/recognizers/whisper_local/__pycache__/whisper.cpython-311.pyc,,
+speech_recognition/recognizers/whisper_local/base.py,sha256=W0Q14-VpzS6yGu_vkg1EPN2SQ-RnbykdEKJiW-2_Lis,1265
+speech_recognition/recognizers/whisper_local/faster_whisper.py,sha256=LRWJj0yrHncMcYhAjHQjJyIuhsPTFVP-JrtXdkRzdrg,3252
+speech_recognition/recognizers/whisper_local/whisper.py,sha256=tGVrErg8jnC7m7QvACZDB3lanhOeyUjX-XPxPvaTozk,3340
+tests/__init__.py,sha256=nWC1VOR8uKeCB0MkEfbl0uCsUZKDoqTHhSNyYyVSzUo,133
+tests/__pycache__/__init__.cpython-311.pyc,,
+tests/__pycache__/test_audio.cpython-311.pyc,,
+tests/__pycache__/test_recognition.cpython-311.pyc,,
+tests/__pycache__/test_special_features.cpython-311.pyc,,
+tests/test_audio.py,sha256=eN86PHiVbD_0n85vxcQBwsFvsEemaEWdLXDtMgp93BM,9591
+tests/test_recognition.py,sha256=Kg4sN1UZ-Y4b8H1M5_nVwe7D9DoOHC0hiQlEKkV9MR0,5139
+tests/test_special_features.py,sha256=yC3NUu6VPZ6TCf40QxvxceJgbQ1lJpxjQyoSzGhUa_0,1525

venv/lib/python3.11/site-packages/SpeechRecognition-3.14.2.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: setuptools (75.3.0)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

venv/lib/python3.11/site-packages/SpeechRecognition-3.14.2.dist-info/top_level.txt

@@ -0,0 +1,2 @@
+speech_recognition
+tests

venv/lib/python3.11/site-packages/_distutils_hack/__init__.py

@@ -0,0 +1,222 @@
+# don't import any costly modules
+import sys
+import os
+
+
+is_pypy = '__pypy__' in sys.builtin_module_names
+
+
+def warn_distutils_present():
+    if 'distutils' not in sys.modules:
+        return
+    if is_pypy and sys.version_info < (3, 7):
+        # PyPy for 3.6 unconditionally imports distutils, so bypass the warning
+        # https://foss.heptapod.net/pypy/pypy/-/blob/be829135bc0d758997b3566062999ee8b23872b4/lib-python/3/site.py#L250
+        return
+    import warnings
+
+    warnings.warn(
+        "Distutils was imported before Setuptools, but importing Setuptools "
+        "also replaces the `distutils` module in `sys.modules`. This may lead "
+        "to undesirable behaviors or errors. To avoid these issues, avoid "
+        "using distutils directly, ensure that setuptools is installed in the "
+        "traditional way (e.g. not an editable install), and/or make sure "
+        "that setuptools is always imported before distutils."
+    )
+
+
+def clear_distutils():
+    if 'distutils' not in sys.modules:
+        return
+    import warnings
+
+    warnings.warn("Setuptools is replacing distutils.")
+    mods = [
+        name
+        for name in sys.modules
+        if name == "distutils" or name.startswith("distutils.")
+    ]
+    for name in mods:
+        del sys.modules[name]
+
+
+def enabled():
+    """
+    Allow selection of distutils by environment variable.
+    """
+    which = os.environ.get('SETUPTOOLS_USE_DISTUTILS', 'local')
+    return which == 'local'
+
+
+def ensure_local_distutils():
+    import importlib
+
+    clear_distutils()
+
+    # With the DistutilsMetaFinder in place,
+    # perform an import to cause distutils to be
+    # loaded from setuptools._distutils. Ref #2906.
+    with shim():
+        importlib.import_module('distutils')
+
+    # check that submodules load as expected
+    core = importlib.import_module('distutils.core')
+    assert '_distutils' in core.__file__, core.__file__
+    assert 'setuptools._distutils.log' not in sys.modules
+
+
+def do_override():
+    """
+    Ensure that the local copy of distutils is preferred over stdlib.
+
+    See https://github.com/pypa/setuptools/issues/417#issuecomment-392298401
+    for more motivation.
+    """
+    if enabled():
+        warn_distutils_present()
+        ensure_local_distutils()
+
+
+class _TrivialRe:
+    def __init__(self, *patterns):
+        self._patterns = patterns
+
+    def match(self, string):
+        return all(pat in string for pat in self._patterns)
+
+
+class DistutilsMetaFinder:
+    def find_spec(self, fullname, path, target=None):
+        # optimization: only consider top level modules and those
+        # found in the CPython test suite.
+        if path is not None and not fullname.startswith('test.'):
+            return
+
+        method_name = 'spec_for_{fullname}'.format(**locals())
+        method = getattr(self, method_name, lambda: None)
+        return method()
+
+    def spec_for_distutils(self):
+        if self.is_cpython():
+            return
+
+        import importlib
+        import importlib.abc
+        import importlib.util
+
+        try:
+            mod = importlib.import_module('setuptools._distutils')
+        except Exception:
+            # There are a couple of cases where setuptools._distutils
+            # may not be present:
+            # - An older Setuptools without a local distutils is
+            #   taking precedence. Ref #2957.
+            # - Path manipulation during sitecustomize removes
+            #   setuptools from the path but only after the hook
+            #   has been loaded. Ref #2980.
+            # In either case, fall back to stdlib behavior.
+            return
+
+        class DistutilsLoader(importlib.abc.Loader):
+            def create_module(self, spec):
+                mod.__name__ = 'distutils'
+                return mod
+
+            def exec_module(self, module):
+                pass
+
+        return importlib.util.spec_from_loader(
+            'distutils', DistutilsLoader(), origin=mod.__file__
+        )
+
+    @staticmethod
+    def is_cpython():
+        """
+        Suppress supplying distutils for CPython (build and tests).
+        Ref #2965 and #3007.
+        """
+        return os.path.isfile('pybuilddir.txt')
+
+    def spec_for_pip(self):
+        """
+        Ensure stdlib distutils when running under pip.
+        See pypa/pip#8761 for rationale.
+        """
+        if self.pip_imported_during_build():
+            return
+        clear_distutils()
+        self.spec_for_distutils = lambda: None
+
+    @classmethod
+    def pip_imported_during_build(cls):
+        """
+        Detect if pip is being imported in a build script. Ref #2355.
+        """
+        import traceback
+
+        return any(
+            cls.frame_file_is_setup(frame) for frame, line in traceback.walk_stack(None)
+        )
+
+    @staticmethod
+    def frame_file_is_setup(frame):
+        """
+        Return True if the indicated frame suggests a setup.py file.
+        """
+        # some frames may not have __file__ (#2940)
+        return frame.f_globals.get('__file__', '').endswith('setup.py')
+
+    def spec_for_sensitive_tests(self):
+        """
+        Ensure stdlib distutils when running select tests under CPython.
+
+        python/cpython#91169
+        """
+        clear_distutils()
+        self.spec_for_distutils = lambda: None
+
+    sensitive_tests = (
+        [
+            'test.test_distutils',
+            'test.test_peg_generator',
+            'test.test_importlib',
+        ]
+        if sys.version_info < (3, 10)
+        else [
+            'test.test_distutils',
+        ]
+    )
+
+
+for name in DistutilsMetaFinder.sensitive_tests:
+    setattr(
+        DistutilsMetaFinder,
+        f'spec_for_{name}',
+        DistutilsMetaFinder.spec_for_sensitive_tests,
+    )
+
+
+DISTUTILS_FINDER = DistutilsMetaFinder()
+
+
+def add_shim():
+    DISTUTILS_FINDER in sys.meta_path or insert_shim()
+
+
+class shim:
+    def __enter__(self):
+        insert_shim()
+
+    def __exit__(self, exc, value, tb):
+        remove_shim()
+
+
+def insert_shim():
+    sys.meta_path.insert(0, DISTUTILS_FINDER)
+
+
+def remove_shim():
+    try:
+        sys.meta_path.remove(DISTUTILS_FINDER)
+    except ValueError:
+        pass

venv/lib/python3.11/site-packages/_distutils_hack/override.py

@@ -0,0 +1 @@
+__import__('_distutils_hack').do_override()

venv/lib/python3.11/site-packages/blinker-1.9.0.dist-info/INSTALLER

@@ -0,0 +1 @@
+pip

venv/lib/python3.11/site-packages/blinker-1.9.0.dist-info/LICENSE.txt

@@ -0,0 +1,20 @@
+Copyright 2010 Jason Kirtland
+
+Permission is hereby granted, free of charge, to any person obtaining a
+copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be included
+in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
+OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
+IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY
+CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
+TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
+SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

venv/lib/python3.11/site-packages/blinker-1.9.0.dist-info/METADATA

@@ -0,0 +1,60 @@
+Metadata-Version: 2.3
+Name: blinker
+Version: 1.9.0
+Summary: Fast, simple object-to-object and broadcast signaling
+Author: Jason Kirtland
+Maintainer-email: Pallets Ecosystem <contact@palletsprojects.com>
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python
+Classifier: Typing :: Typed
+Project-URL: Chat, https://discord.gg/pallets
+Project-URL: Documentation, https://blinker.readthedocs.io
+Project-URL: Source, https://github.com/pallets-eco/blinker/
+
+# Blinker
+
+Blinker provides a fast dispatching system that allows any number of
+interested parties to subscribe to events, or "signals".
+
+
+## Pallets Community Ecosystem
+
+> [!IMPORTANT]\
+> This project is part of the Pallets Community Ecosystem. Pallets is the open
+> source organization that maintains Flask; Pallets-Eco enables community
+> maintenance of related projects. If you are interested in helping maintain
+> this project, please reach out on [the Pallets Discord server][discord].
+>
+> [discord]: https://discord.gg/pallets
+
+
+## Example
+
+Signal receivers can subscribe to specific senders or receive signals
+sent by any sender.
+
+```pycon
+>>> from blinker import signal
+>>> started = signal('round-started')
+>>> def each(round):
+...     print(f"Round {round}")
+...
+>>> started.connect(each)
+
+>>> def round_two(round):
+...     print("This is round two.")
+...
+>>> started.connect(round_two, sender=2)
+
+>>> for round in range(1, 4):
+...     started.send(round)
+...
+Round 1!
+Round 2!
+This is round two.
+Round 3!
+```
+

venv/lib/python3.11/site-packages/blinker-1.9.0.dist-info/RECORD

@@ -0,0 +1,12 @@
+blinker-1.9.0.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4
+blinker-1.9.0.dist-info/LICENSE.txt,sha256=nrc6HzhZekqhcCXSrhvjg5Ykx5XphdTw6Xac4p-spGc,1054
+blinker-1.9.0.dist-info/METADATA,sha256=uIRiM8wjjbHkCtbCyTvctU37IAZk0kEe5kxAld1dvzA,1633
+blinker-1.9.0.dist-info/RECORD,,
+blinker-1.9.0.dist-info/WHEEL,sha256=CpUCUxeHQbRN5UGRQHYRJorO5Af-Qy_fHMctcQ8DSGI,82
+blinker/__init__.py,sha256=I2EdZqpy4LyjX17Hn1yzJGWCjeLaVaPzsMgHkLfj_cQ,317
+blinker/__pycache__/__init__.cpython-311.pyc,,
+blinker/__pycache__/_utilities.cpython-311.pyc,,
+blinker/__pycache__/base.cpython-311.pyc,,
+blinker/_utilities.py,sha256=0J7eeXXTUx0Ivf8asfpx0ycVkp0Eqfqnj117x2mYX9E,1675
+blinker/base.py,sha256=QpDuvXXcwJF49lUBcH5BiST46Rz9wSG7VW_p7N_027M,19132
+blinker/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0

venv/lib/python3.11/site-packages/blinker-1.9.0.dist-info/WHEEL

@@ -0,0 +1,4 @@
+Wheel-Version: 1.0
+Generator: flit 3.10.1
+Root-Is-Purelib: true
+Tag: py3-none-any

venv/lib/python3.11/site-packages/blinker/__init__.py

@@ -0,0 +1,17 @@
+from __future__ import annotations
+
+from .base import ANY
+from .base import default_namespace
+from .base import NamedSignal
+from .base import Namespace
+from .base import Signal
+from .base import signal
+
+__all__ = [
+    "ANY",
+    "default_namespace",
+    "NamedSignal",
+    "Namespace",
+    "Signal",
+    "signal",
+]

venv/lib/python3.11/site-packages/blinker/_utilities.py

@@ -0,0 +1,64 @@
+from __future__ import annotations
+
+import collections.abc as c
+import inspect
+import typing as t
+from weakref import ref
+from weakref import WeakMethod
+
+T = t.TypeVar("T")
+
+
+class Symbol:
+    """A constant symbol, nicer than ``object()``. Repeated calls return the
+    same instance.
+
+    >>> Symbol('foo') is Symbol('foo')
+    True
+    >>> Symbol('foo')
+    foo
+    """
+
+    symbols: t.ClassVar[dict[str, Symbol]] = {}
+
+    def __new__(cls, name: str) -> Symbol:
+        if name in cls.symbols:
+            return cls.symbols[name]
+
+        obj = super().__new__(cls)
+        cls.symbols[name] = obj
+        return obj
+
+    def __init__(self, name: str) -> None:
+        self.name = name
+
+    def __repr__(self) -> str:
+        return self.name
+
+    def __getnewargs__(self) -> tuple[t.Any, ...]:
+        return (self.name,)
+
+
+def make_id(obj: object) -> c.Hashable:
+    """Get a stable identifier for a receiver or sender, to be used as a dict
+    key or in a set.
+    """
+    if inspect.ismethod(obj):
+        # The id of a bound method is not stable, but the id of the unbound
+        # function and instance are.
+        return id(obj.__func__), id(obj.__self__)
+
+    if isinstance(obj, (str, int)):
+        # Instances with the same value always compare equal and have the same
+        # hash, even if the id may change.
+        return obj
+
+    # Assume other types are not hashable but will always be the same instance.
+    return id(obj)
+
+
+def make_ref(obj: T, callback: c.Callable[[ref[T]], None] | None = None) -> ref[T]:
+    if inspect.ismethod(obj):
+        return WeakMethod(obj, callback)  # type: ignore[arg-type, return-value]
+
+    return ref(obj, callback)

venv/lib/python3.11/site-packages/blinker/base.py

@@ -0,0 +1,512 @@
+from __future__ import annotations
+
+import collections.abc as c
+import sys
+import typing as t
+import weakref
+from collections import defaultdict
+from contextlib import contextmanager
+from functools import cached_property
+from inspect import iscoroutinefunction
+
+from ._utilities import make_id
+from ._utilities import make_ref
+from ._utilities import Symbol
+
+F = t.TypeVar("F", bound=c.Callable[..., t.Any])
+
+ANY = Symbol("ANY")
+"""Symbol for "any sender"."""
+
+ANY_ID = 0
+
+
+class Signal:
+    """A notification emitter.
+
+    :param doc: The docstring for the signal.
+    """
+
+    ANY = ANY
+    """An alias for the :data:`~blinker.ANY` sender symbol."""
+
+    set_class: type[set[t.Any]] = set
+    """The set class to use for tracking connected receivers and senders.
+    Python's ``set`` is unordered. If receivers must be dispatched in the order
+    they were connected, an ordered set implementation can be used.
+
+    .. versionadded:: 1.7
+    """
+
+    @cached_property
+    def receiver_connected(self) -> Signal:
+        """Emitted at the end of each :meth:`connect` call.
+
+        The signal sender is the signal instance, and the :meth:`connect`
+        arguments are passed through: ``receiver``, ``sender``, and ``weak``.
+
+        .. versionadded:: 1.2
+        """
+        return Signal(doc="Emitted after a receiver connects.")
+
+    @cached_property
+    def receiver_disconnected(self) -> Signal:
+        """Emitted at the end of each :meth:`disconnect` call.
+
+        The sender is the signal instance, and the :meth:`disconnect` arguments
+        are passed through: ``receiver`` and ``sender``.
+
+        This signal is emitted **only** when :meth:`disconnect` is called
+        explicitly. This signal cannot be emitted by an automatic disconnect
+        when a weakly referenced receiver or sender goes out of scope, as the
+        instance is no longer be available to be used as the sender for this
+        signal.
+
+        An alternative approach is available by subscribing to
+        :attr:`receiver_connected` and setting up a custom weakref cleanup
+        callback on weak receivers and senders.
+
+        .. versionadded:: 1.2
+        """
+        return Signal(doc="Emitted after a receiver disconnects.")
+
+    def __init__(self, doc: str | None = None) -> None:
+        if doc:
+            self.__doc__ = doc
+
+        self.receivers: dict[
+            t.Any, weakref.ref[c.Callable[..., t.Any]] | c.Callable[..., t.Any]
+        ] = {}
+        """The map of connected receivers. Useful to quickly check if any
+        receivers are connected to the signal: ``if s.receivers:``. The
+        structure and data is not part of the public API, but checking its
+        boolean value is.
+        """
+
+        self.is_muted: bool = False
+        self._by_receiver: dict[t.Any, set[t.Any]] = defaultdict(self.set_class)
+        self._by_sender: dict[t.Any, set[t.Any]] = defaultdict(self.set_class)
+        self._weak_senders: dict[t.Any, weakref.ref[t.Any]] = {}
+
+    def connect(self, receiver: F, sender: t.Any = ANY, weak: bool = True) -> F:
+        """Connect ``receiver`` to be called when the signal is sent by
+        ``sender``.
+
+        :param receiver: The callable to call when :meth:`send` is called with
+            the given ``sender``, passing ``sender`` as a positional argument
+            along with any extra keyword arguments.
+        :param sender: Any object or :data:`ANY`. ``receiver`` will only be
+            called when :meth:`send` is called with this sender. If ``ANY``, the
+            receiver will be called for any sender. A receiver may be connected
+            to multiple senders by calling :meth:`connect` multiple times.
+        :param weak: Track the receiver with a :mod:`weakref`. The receiver will
+            be automatically disconnected when it is garbage collected. When
+            connecting a receiver defined within a function, set to ``False``,
+            otherwise it will be disconnected when the function scope ends.
+        """
+        receiver_id = make_id(receiver)
+        sender_id = ANY_ID if sender is ANY else make_id(sender)
+
+        if weak:
+            self.receivers[receiver_id] = make_ref(
+                receiver, self._make_cleanup_receiver(receiver_id)
+            )
+        else:
+            self.receivers[receiver_id] = receiver
+
+        self._by_sender[sender_id].add(receiver_id)
+        self._by_receiver[receiver_id].add(sender_id)
+
+        if sender is not ANY and sender_id not in self._weak_senders:
+            # store a cleanup for weakref-able senders
+            try:
+                self._weak_senders[sender_id] = make_ref(
+                    sender, self._make_cleanup_sender(sender_id)
+                )
+            except TypeError:
+                pass
+
+        if "receiver_connected" in self.__dict__ and self.receiver_connected.receivers:
+            try:
+                self.receiver_connected.send(
+                    self, receiver=receiver, sender=sender, weak=weak
+                )
+            except TypeError:
+                # TODO no explanation or test for this
+                self.disconnect(receiver, sender)
+                raise
+
+        return receiver
+
+    def connect_via(self, sender: t.Any, weak: bool = False) -> c.Callable[[F], F]:
+        """Connect the decorated function to be called when the signal is sent
+        by ``sender``.
+
+        The decorated function will be called when :meth:`send` is called with
+        the given ``sender``, passing ``sender`` as a positional argument along
+        with any extra keyword arguments.
+
+        :param sender: Any object or :data:`ANY`. ``receiver`` will only be
+            called when :meth:`send` is called with this sender. If ``ANY``, the
+            receiver will be called for any sender. A receiver may be connected
+            to multiple senders by calling :meth:`connect` multiple times.
+        :param weak: Track the receiver with a :mod:`weakref`. The receiver will
+            be automatically disconnected when it is garbage collected. When
+            connecting a receiver defined within a function, set to ``False``,
+            otherwise it will be disconnected when the function scope ends.=
+
+        .. versionadded:: 1.1
+        """
+
+        def decorator(fn: F) -> F:
+            self.connect(fn, sender, weak)
+            return fn
+
+        return decorator
+
+    @contextmanager
+    def connected_to(
+        self, receiver: c.Callable[..., t.Any], sender: t.Any = ANY
+    ) -> c.Generator[None, None, None]:
+        """A context manager that temporarily connects ``receiver`` to the
+        signal while a ``with`` block executes. When the block exits, the
+        receiver is disconnected. Useful for tests.
+
+        :param receiver: The callable to call when :meth:`send` is called with
+            the given ``sender``, passing ``sender`` as a positional argument
+            along with any extra keyword arguments.
+        :param sender: Any object or :data:`ANY`. ``receiver`` will only be
+            called when :meth:`send` is called with this sender. If ``ANY``, the
+            receiver will be called for any sender.
+
+        .. versionadded:: 1.1
+        """
+        self.connect(receiver, sender=sender, weak=False)
+
+        try:
+            yield None
+        finally:
+            self.disconnect(receiver)
+
+    @contextmanager
+    def muted(self) -> c.Generator[None, None, None]:
+        """A context manager that temporarily disables the signal. No receivers
+        will be called if the signal is sent, until the ``with`` block exits.
+        Useful for tests.
+        """
+        self.is_muted = True
+
+        try:
+            yield None
+        finally:
+            self.is_muted = False
+
+    def send(
+        self,
+        sender: t.Any | None = None,
+        /,
+        *,
+        _async_wrapper: c.Callable[
+            [c.Callable[..., c.Coroutine[t.Any, t.Any, t.Any]]], c.Callable[..., t.Any]
+        ]
+        | None = None,
+        **kwargs: t.Any,
+    ) -> list[tuple[c.Callable[..., t.Any], t.Any]]:
+        """Call all receivers that are connected to the given ``sender``
+        or :data:`ANY`. Each receiver is called with ``sender`` as a positional
+        argument along with any extra keyword arguments. Return a list of
+        ``(receiver, return value)`` tuples.
+
+        The order receivers are called is undefined, but can be influenced by
+        setting :attr:`set_class`.
+
+        If a receiver raises an exception, that exception will propagate up.
+        This makes debugging straightforward, with an assumption that correctly
+        implemented receivers will not raise.
+
+        :param sender: Call receivers connected to this sender, in addition to
+            those connected to :data:`ANY`.
+        :param _async_wrapper: Will be called on any receivers that are async
+            coroutines to turn them into sync callables. For example, could run
+            the receiver with an event loop.
+        :param kwargs: Extra keyword arguments to pass to each receiver.
+
+        .. versionchanged:: 1.7
+            Added the ``_async_wrapper`` argument.
+        """
+        if self.is_muted:
+            return []
+
+        results = []
+
+        for receiver in self.receivers_for(sender):
+            if iscoroutinefunction(receiver):
+                if _async_wrapper is None:
+                    raise RuntimeError("Cannot send to a coroutine function.")
+
+                result = _async_wrapper(receiver)(sender, **kwargs)
+            else:
+                result = receiver(sender, **kwargs)
+
+            results.append((receiver, result))
+
+        return results
+
+    async def send_async(
+        self,
+        sender: t.Any | None = None,
+        /,
+        *,
+        _sync_wrapper: c.Callable[
+            [c.Callable[..., t.Any]], c.Callable[..., c.Coroutine[t.Any, t.Any, t.Any]]
+        ]
+        | None = None,
+        **kwargs: t.Any,
+    ) -> list[tuple[c.Callable[..., t.Any], t.Any]]:
+        """Await all receivers that are connected to the given ``sender``
+        or :data:`ANY`. Each receiver is called with ``sender`` as a positional
+        argument along with any extra keyword arguments. Return a list of
+        ``(receiver, return value)`` tuples.
+
+        The order receivers are called is undefined, but can be influenced by
+        setting :attr:`set_class`.
+
+        If a receiver raises an exception, that exception will propagate up.
+        This makes debugging straightforward, with an assumption that correctly
+        implemented receivers will not raise.
+
+        :param sender: Call receivers connected to this sender, in addition to
+            those connected to :data:`ANY`.
+        :param _sync_wrapper: Will be called on any receivers that are sync
+            callables to turn them into async coroutines. For example,
+            could call the receiver in a thread.
+        :param kwargs: Extra keyword arguments to pass to each receiver.
+
+        .. versionadded:: 1.7
+        """
+        if self.is_muted:
+            return []
+
+        results = []
+
+        for receiver in self.receivers_for(sender):
+            if not iscoroutinefunction(receiver):
+                if _sync_wrapper is None:
+                    raise RuntimeError("Cannot send to a non-coroutine function.")
+
+                result = await _sync_wrapper(receiver)(sender, **kwargs)
+            else:
+                result = await receiver(sender, **kwargs)
+
+            results.append((receiver, result))
+
+        return results
+
+    def has_receivers_for(self, sender: t.Any) -> bool:
+        """Check if there is at least one receiver that will be called with the
+        given ``sender``. A receiver connected to :data:`ANY` will always be
+        called, regardless of sender. Does not check if weakly referenced
+        receivers are still live. See :meth:`receivers_for` for a stronger
+        search.
+
+        :param sender: Check for receivers connected to this sender, in addition
+            to those connected to :data:`ANY`.
+        """
+        if not self.receivers:
+            return False
+
+        if self._by_sender[ANY_ID]:
+            return True
+
+        if sender is ANY:
+            return False
+
+        return make_id(sender) in self._by_sender
+
+    def receivers_for(
+        self, sender: t.Any
+    ) -> c.Generator[c.Callable[..., t.Any], None, None]:
+        """Yield each receiver to be called for ``sender``, in addition to those
+        to be called for :data:`ANY`. Weakly referenced receivers that are not
+        live will be disconnected and skipped.
+
+        :param sender: Yield receivers connected to this sender, in addition
+            to those connected to :data:`ANY`.
+        """
+        # TODO: test receivers_for(ANY)
+        if not self.receivers:
+            return
+
+        sender_id = make_id(sender)
+
+        if sender_id in self._by_sender:
+            ids = self._by_sender[ANY_ID] | self._by_sender[sender_id]
+        else:
+            ids = self._by_sender[ANY_ID].copy()
+
+        for receiver_id in ids:
+            receiver = self.receivers.get(receiver_id)
+
+            if receiver is None:
+                continue
+
+            if isinstance(receiver, weakref.ref):
+                strong = receiver()
+
+                if strong is None:
+                    self._disconnect(receiver_id, ANY_ID)
+                    continue
+
+                yield strong
+            else:
+                yield receiver
+
+    def disconnect(self, receiver: c.Callable[..., t.Any], sender: t.Any = ANY) -> None:
+        """Disconnect ``receiver`` from being called when the signal is sent by
+        ``sender``.
+
+        :param receiver: A connected receiver callable.
+        :param sender: Disconnect from only this sender. By default, disconnect
+            from all senders.
+        """
+        sender_id: c.Hashable
+
+        if sender is ANY:
+            sender_id = ANY_ID
+        else:
+            sender_id = make_id(sender)
+
+        receiver_id = make_id(receiver)
+        self._disconnect(receiver_id, sender_id)
+
+        if (
+            "receiver_disconnected" in self.__dict__
+            and self.receiver_disconnected.receivers
+        ):
+            self.receiver_disconnected.send(self, receiver=receiver, sender=sender)
+
+    def _disconnect(self, receiver_id: c.Hashable, sender_id: c.Hashable) -> None:
+        if sender_id == ANY_ID:
+            if self._by_receiver.pop(receiver_id, None) is not None:
+                for bucket in self._by_sender.values():
+                    bucket.discard(receiver_id)
+
+            self.receivers.pop(receiver_id, None)
+        else:
+            self._by_sender[sender_id].discard(receiver_id)
+            self._by_receiver[receiver_id].discard(sender_id)
+
+    def _make_cleanup_receiver(
+        self, receiver_id: c.Hashable
+    ) -> c.Callable[[weakref.ref[c.Callable[..., t.Any]]], None]:
+        """Create a callback function to disconnect a weakly referenced
+        receiver when it is garbage collected.
+        """
+
+        def cleanup(ref: weakref.ref[c.Callable[..., t.Any]]) -> None:
+            # If the interpreter is shutting down, disconnecting can result in a
+            # weird ignored exception. Don't call it in that case.
+            if not sys.is_finalizing():
+                self._disconnect(receiver_id, ANY_ID)
+
+        return cleanup
+
+    def _make_cleanup_sender(
+        self, sender_id: c.Hashable
+    ) -> c.Callable[[weakref.ref[t.Any]], None]:
+        """Create a callback function to disconnect all receivers for a weakly
+        referenced sender when it is garbage collected.
+        """
+        assert sender_id != ANY_ID
+
+        def cleanup(ref: weakref.ref[t.Any]) -> None:
+            self._weak_senders.pop(sender_id, None)
+
+            for receiver_id in self._by_sender.pop(sender_id, ()):
+                self._by_receiver[receiver_id].discard(sender_id)
+
+        return cleanup
+
+    def _cleanup_bookkeeping(self) -> None:
+        """Prune unused sender/receiver bookkeeping. Not threadsafe.
+
+        Connecting & disconnecting leaves behind a small amount of bookkeeping
+        data. Typical workloads using Blinker, for example in most web apps,
+        Flask, CLI scripts, etc., are not adversely affected by this
+        bookkeeping.
+
+        With a long-running process performing dynamic signal routing with high
+        volume, e.g. connecting to function closures, senders are all unique
+        object instances. Doing all of this over and over may cause memory usage
+        to grow due to extraneous bookkeeping. (An empty ``set`` for each stale
+        sender/receiver pair.)
+
+        This method will prune that bookkeeping away, with the caveat that such
+        pruning is not threadsafe. The risk is that cleanup of a fully
+        disconnected receiver/sender pair occurs while another thread is
+        connecting that same pair. If you are in the highly dynamic, unique
+        receiver/sender situation that has lead you to this method, that failure
+        mode is perhaps not a big deal for you.
+        """
+        for mapping in (self._by_sender, self._by_receiver):
+            for ident, bucket in list(mapping.items()):
+                if not bucket:
+                    mapping.pop(ident, None)
+
+    def _clear_state(self) -> None:
+        """Disconnect all receivers and senders. Useful for tests."""
+        self._weak_senders.clear()
+        self.receivers.clear()
+        self._by_sender.clear()
+        self._by_receiver.clear()
+
+
+class NamedSignal(Signal):
+    """A named generic notification emitter. The name is not used by the signal
+    itself, but matches the key in the :class:`Namespace` that it belongs to.
+
+    :param name: The name of the signal within the namespace.
+    :param doc: The docstring for the signal.
+    """
+
+    def __init__(self, name: str, doc: str | None = None) -> None:
+        super().__init__(doc)
+
+        #: The name of this signal.
+        self.name: str = name
+
+    def __repr__(self) -> str:
+        base = super().__repr__()
+        return f"{base[:-1]}; {self.name!r}>"  # noqa: E702
+
+
+class Namespace(dict[str, NamedSignal]):
+    """A dict mapping names to signals."""
+
+    def signal(self, name: str, doc: str | None = None) -> NamedSignal:
+        """Return the :class:`NamedSignal` for the given ``name``, creating it
+        if required. Repeated calls with the same name return the same signal.
+
+        :param name: The name of the signal.
+        :param doc: The docstring of the signal.
+        """
+        if name not in self:
+            self[name] = NamedSignal(name, doc)
+
+        return self[name]
+
+
+class _PNamespaceSignal(t.Protocol):
+    def __call__(self, name: str, doc: str | None = None) -> NamedSignal: ...
+
+
+default_namespace: Namespace = Namespace()
+"""A default :class:`Namespace` for creating named signals. :func:`signal`
+creates a :class:`NamedSignal` in this namespace.
+"""
+
+signal: _PNamespaceSignal = default_namespace.signal
+"""Return a :class:`NamedSignal` in :data:`default_namespace` with the given
+``name``, creating it if required. Repeated calls with the same name return the
+same signal.
+"""

venv/lib/python3.11/site-packages/certifi-2025.1.31.dist-info/INSTALLER

@@ -0,0 +1 @@
+pip

venv/lib/python3.11/site-packages/certifi-2025.1.31.dist-info/LICENSE

@@ -0,0 +1,20 @@
+This package contains a modified version of ca-bundle.crt:
+
+ca-bundle.crt -- Bundle of CA Root Certificates
+
+This is a bundle of X.509 certificates of public Certificate Authorities
+(CA). These were automatically extracted from Mozilla's root certificates
+file (certdata.txt).  This file can be found in the mozilla source tree:
+https://hg.mozilla.org/mozilla-central/file/tip/security/nss/lib/ckfw/builtins/certdata.txt
+It contains the certificates in PEM format and therefore
+can be directly used with curl / libcurl / php_curl, or with
+an Apache+mod_ssl webserver for SSL client authentication.
+Just configure this file as the SSLCACertificateFile.#
+
+***** BEGIN LICENSE BLOCK *****
+This Source Code Form is subject to the terms of the Mozilla Public License,
+v. 2.0. If a copy of the MPL was not distributed with this file, You can obtain
+one at http://mozilla.org/MPL/2.0/.
+
+***** END LICENSE BLOCK *****
+@(#) $RCSfile: certdata.txt,v $ $Revision: 1.80 $ $Date: 2011/11/03 15:11:58 $

venv/lib/python3.11/site-packages/certifi-2025.1.31.dist-info/METADATA

@@ -0,0 +1,68 @@
+Metadata-Version: 2.1
+Name: certifi
+Version: 2025.1.31
+Summary: Python package for providing Mozilla's CA Bundle.
+Home-page: https://github.com/certifi/python-certifi
+Author: Kenneth Reitz
+Author-email: me@kennethreitz.com
+License: MPL-2.0
+Project-URL: Source, https://github.com/certifi/python-certifi
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: Mozilla Public License 2.0 (MPL 2.0)
+Classifier: Natural Language :: English
+Classifier: Programming Language :: Python
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3 :: Only
+Classifier: Programming Language :: Python :: 3.6
+Classifier: Programming Language :: Python :: 3.7
+Classifier: Programming Language :: Python :: 3.8
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Requires-Python: >=3.6
+License-File: LICENSE
+
+Certifi: Python SSL Certificates
+================================
+
+Certifi provides Mozilla's carefully curated collection of Root Certificates for
+validating the trustworthiness of SSL certificates while verifying the identity
+of TLS hosts. It has been extracted from the `Requests`_ project.
+
+Installation
+------------
+
+``certifi`` is available on PyPI. Simply install it with ``pip``::
+
+    $ pip install certifi
+
+Usage
+-----
+
+To reference the installed certificate authority (CA) bundle, you can use the
+built-in function::
+
+    >>> import certifi
+
+    >>> certifi.where()
+    '/usr/local/lib/python3.7/site-packages/certifi/cacert.pem'
+
+Or from the command line::
+
+    $ python -m certifi
+    /usr/local/lib/python3.7/site-packages/certifi/cacert.pem
+
+Enjoy!
+
+.. _`Requests`: https://requests.readthedocs.io/en/master/
+
+Addition/Removal of Certificates
+--------------------------------
+
+Certifi does not support any addition/removal or other modification of the
+CA trust store content. This project is intended to provide a reliable and
+highly portable root of trust to python deployments. Look to upstream projects
+for methods to use alternate trust.

venv/lib/python3.11/site-packages/certifi-2025.1.31.dist-info/RECORD

@@ -0,0 +1,14 @@
+certifi-2025.1.31.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4
+certifi-2025.1.31.dist-info/LICENSE,sha256=6TcW2mucDVpKHfYP5pWzcPBpVgPSH2-D8FPkLPwQyvc,989
+certifi-2025.1.31.dist-info/METADATA,sha256=l9pPyH8X-gORo4Wgl72vZd2uifJ_kLcnDwKakddIWPM,2273
+certifi-2025.1.31.dist-info/RECORD,,
+certifi-2025.1.31.dist-info/WHEEL,sha256=P9jw-gEje8ByB7_hXoICnHtVCrEwMQh-630tKvQWehc,91
+certifi-2025.1.31.dist-info/top_level.txt,sha256=KMu4vUCfsjLrkPbSNdgdekS-pVJzBAJFO__nI8NF6-U,8
+certifi/__init__.py,sha256=neIaAf7BM36ygmQCmy-ZsSyjnvjWghFeu13wwEAnjj0,94
+certifi/__main__.py,sha256=xBBoj905TUWBLRGANOcf7oi6e-3dMP4cEoG9OyMs11g,243
+certifi/__pycache__/__init__.cpython-311.pyc,,
+certifi/__pycache__/__main__.cpython-311.pyc,,
+certifi/__pycache__/core.cpython-311.pyc,,
+certifi/cacert.pem,sha256=xVsh-Qf3-G1IrdCTVS-1ZRdJ_1-GBQjMu0I9bB-9gMc,297255
+certifi/core.py,sha256=qRDDFyXVJwTB_EmoGppaXU_R9qCZvhl-EzxPMuV3nTA,4426
+certifi/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0

venv/lib/python3.11/site-packages/certifi-2025.1.31.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: setuptools (75.3.0)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

venv/lib/python3.11/site-packages/certifi-2025.1.31.dist-info/top_level.txt

@@ -0,0 +1 @@
+certifi

venv/lib/python3.11/site-packages/certifi/__init__.py

@@ -0,0 +1,4 @@
+from .core import contents, where
+
+__all__ = ["contents", "where"]
+__version__ = "2025.01.31"

venv/lib/python3.11/site-packages/certifi/__main__.py

@@ -0,0 +1,12 @@
+import argparse
+
+from certifi import contents, where
+
+parser = argparse.ArgumentParser()
+parser.add_argument("-c", "--contents", action="store_true")
+args = parser.parse_args()
+
+if args.contents:
+    print(contents())
+else:
+    print(where())

venv/lib/python3.11/site-packages/certifi/core.py

@@ -0,0 +1,114 @@
+"""
+certifi.py
+~~~~~~~~~~
+
+This module returns the installation location of cacert.pem or its contents.
+"""
+import sys
+import atexit
+
+def exit_cacert_ctx() -> None:
+    _CACERT_CTX.__exit__(None, None, None)  # type: ignore[union-attr]
+
+
+if sys.version_info >= (3, 11):
+
+    from importlib.resources import as_file, files
+
+    _CACERT_CTX = None
+    _CACERT_PATH = None
+
+    def where() -> str:
+        # This is slightly terrible, but we want to delay extracting the file
+        # in cases where we're inside of a zipimport situation until someone
+        # actually calls where(), but we don't want to re-extract the file
+        # on every call of where(), so we'll do it once then store it in a
+        # global variable.
+        global _CACERT_CTX
+        global _CACERT_PATH
+        if _CACERT_PATH is None:
+            # This is slightly janky, the importlib.resources API wants you to
+            # manage the cleanup of this file, so it doesn't actually return a
+            # path, it returns a context manager that will give you the path
+            # when you enter it and will do any cleanup when you leave it. In
+            # the common case of not needing a temporary file, it will just
+            # return the file system location and the __exit__() is a no-op.
+            #
+            # We also have to hold onto the actual context manager, because
+            # it will do the cleanup whenever it gets garbage collected, so
+            # we will also store that at the global level as well.
+            _CACERT_CTX = as_file(files("certifi").joinpath("cacert.pem"))
+            _CACERT_PATH = str(_CACERT_CTX.__enter__())
+            atexit.register(exit_cacert_ctx)
+
+        return _CACERT_PATH
+
+    def contents() -> str:
+        return files("certifi").joinpath("cacert.pem").read_text(encoding="ascii")
+
+elif sys.version_info >= (3, 7):
+
+    from importlib.resources import path as get_path, read_text
+
+    _CACERT_CTX = None
+    _CACERT_PATH = None
+
+    def where() -> str:
+        # This is slightly terrible, but we want to delay extracting the
+        # file in cases where we're inside of a zipimport situation until
+        # someone actually calls where(), but we don't want to re-extract
+        # the file on every call of where(), so we'll do it once then store
+        # it in a global variable.
+        global _CACERT_CTX
+        global _CACERT_PATH
+        if _CACERT_PATH is None:
+            # This is slightly janky, the importlib.resources API wants you
+            # to manage the cleanup of this file, so it doesn't actually
+            # return a path, it returns a context manager that will give
+            # you the path when you enter it and will do any cleanup when
+            # you leave it. In the common case of not needing a temporary
+            # file, it will just return the file system location and the
+            # __exit__() is a no-op.
+            #
+            # We also have to hold onto the actual context manager, because
+            # it will do the cleanup whenever it gets garbage collected, so
+            # we will also store that at the global level as well.
+            _CACERT_CTX = get_path("certifi", "cacert.pem")
+            _CACERT_PATH = str(_CACERT_CTX.__enter__())
+            atexit.register(exit_cacert_ctx)
+
+        return _CACERT_PATH
+
+    def contents() -> str:
+        return read_text("certifi", "cacert.pem", encoding="ascii")
+
+else:
+    import os
+    import types
+    from typing import Union
+
+    Package = Union[types.ModuleType, str]
+    Resource = Union[str, "os.PathLike"]
+
+    # This fallback will work for Python versions prior to 3.7 that lack the
+    # importlib.resources module but relies on the existing `where` function
+    # so won't address issues with environments like PyOxidizer that don't set
+    # __file__ on modules.
+    def read_text(
+        package: Package,
+        resource: Resource,
+        encoding: str = 'utf-8',
+        errors: str = 'strict'
+    ) -> str:
+        with open(where(), encoding=encoding) as data:
+            return data.read()
+
+    # If we don't have importlib.resources, then we will just do the old logic
+    # of assuming we're on the filesystem and munge the path directly.
+    def where() -> str:
+        f = os.path.dirname(__file__)
+
+        return os.path.join(f, "cacert.pem")
+
+    def contents() -> str:
+        return read_text("certifi", "cacert.pem", encoding="ascii")

venv/lib/python3.11/site-packages/charset_normalizer-3.4.1.dist-info/INSTALLER

@@ -0,0 +1 @@
+pip

venv/lib/python3.11/site-packages/charset_normalizer-3.4.1.dist-info/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2025 TAHRI Ahmed R.
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

venv/lib/python3.11/site-packages/charset_normalizer-3.4.1.dist-info/METADATA

@@ -0,0 +1,721 @@
+Metadata-Version: 2.1
+Name: charset-normalizer
+Version: 3.4.1
+Summary: The Real First Universal Charset Detector. Open, modern and actively maintained alternative to Chardet.
+Author-email: "Ahmed R. TAHRI" <tahri.ahmed@proton.me>
+Maintainer-email: "Ahmed R. TAHRI" <tahri.ahmed@proton.me>
+License: MIT
+Project-URL: Changelog, https://github.com/jawah/charset_normalizer/blob/master/CHANGELOG.md
+Project-URL: Documentation, https://charset-normalizer.readthedocs.io/
+Project-URL: Code, https://github.com/jawah/charset_normalizer
+Project-URL: Issue tracker, https://github.com/jawah/charset_normalizer/issues
+Keywords: encoding,charset,charset-detector,detector,normalization,unicode,chardet,detect
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.7
+Classifier: Programming Language :: Python :: 3.8
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3 :: Only
+Classifier: Programming Language :: Python :: Implementation :: CPython
+Classifier: Programming Language :: Python :: Implementation :: PyPy
+Classifier: Topic :: Text Processing :: Linguistic
+Classifier: Topic :: Utilities
+Classifier: Typing :: Typed
+Requires-Python: >=3.7
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Provides-Extra: unicode-backport
+
+<h1 align="center">Charset Detection, for Everyone 👋</h1>
+
+<p align="center">
+  <sup>The Real First Universal Charset Detector</sup><br>
+  <a href="https://pypi.org/project/charset-normalizer">
+    <img src="https://img.shields.io/pypi/pyversions/charset_normalizer.svg?orange=blue" />
+  </a>
+  <a href="https://pepy.tech/project/charset-normalizer/">
+    <img alt="Download Count Total" src="https://static.pepy.tech/badge/charset-normalizer/month" />
+  </a>
+  <a href="https://bestpractices.coreinfrastructure.org/projects/7297">
+    <img src="https://bestpractices.coreinfrastructure.org/projects/7297/badge">
+  </a>
+</p>
+<p align="center">
+  <sup><i>Featured Packages</i></sup><br>
+  <a href="https://github.com/jawah/niquests">
+   <img alt="Static Badge" src="https://img.shields.io/badge/Niquests-Best_HTTP_Client-cyan">
+  </a>
+  <a href="https://github.com/jawah/wassima">
+   <img alt="Static Badge" src="https://img.shields.io/badge/Wassima-Certifi_Killer-cyan">
+  </a>
+</p>
+<p align="center">
+  <sup><i>In other language (unofficial port - by the community)</i></sup><br>
+  <a href="https://github.com/nickspring/charset-normalizer-rs">
+   <img alt="Static Badge" src="https://img.shields.io/badge/Rust-red">
+  </a>
+</p>
+
+> A library that helps you read text from an unknown charset encoding.<br /> Motivated by `chardet`,
+> I'm trying to resolve the issue by taking a new approach.
+> All IANA character set names for which the Python core library provides codecs are supported.
+
+<p align="center">
+  >>>>> <a href="https://charsetnormalizerweb.ousret.now.sh" target="_blank">👉 Try Me Online Now, Then Adopt Me 👈 </a> <<<<<
+</p>
+
+This project offers you an alternative to **Universal Charset Encoding Detector**, also known as **Chardet**.
+
+| Feature                                          | [Chardet](https://github.com/chardet/chardet) |                                         Charset Normalizer                                         | [cChardet](https://github.com/PyYoshi/cChardet) |
+|--------------------------------------------------|:---------------------------------------------:|:--------------------------------------------------------------------------------------------------:|:-----------------------------------------------:|
+| `Fast`                                           |                       ❌                       |                                                 ✅                                                  |                        ✅                        |
+| `Universal**`                                    |                       ❌                       |                                                 ✅                                                  |                        ❌                        |
+| `Reliable` **without** distinguishable standards |                       ❌                       |                                                 ✅                                                  |                        ✅                        |
+| `Reliable` **with** distinguishable standards    |                       ✅                       |                                                 ✅                                                  |                        ✅                        |
+| `License`                                        |           LGPL-2.1<br>_restrictive_           |                                                MIT                                                 |            MPL-1.1<br>_restrictive_             |
+| `Native Python`                                  |                       ✅                       |                                                 ✅                                                  |                        ❌                        |
+| `Detect spoken language`                         |                       ❌                       |                                                 ✅                                                  |                       N/A                       |
+| `UnicodeDecodeError Safety`                      |                       ❌                       |                                                 ✅                                                  |                        ❌                        |
+| `Whl Size (min)`                                 |                   193.6 kB                    |                                               42 kB                                                |                     ~200 kB                     |
+| `Supported Encoding`                             |                      33                       | 🎉 [99](https://charset-normalizer.readthedocs.io/en/latest/user/support.html#supported-encodings) |                       40                        |
+
+<p align="center">
+<img src="https://i.imgflip.com/373iay.gif" alt="Reading Normalized Text" width="226"/><img src="https://media.tenor.com/images/c0180f70732a18b4965448d33adba3d0/tenor.gif" alt="Cat Reading Text" width="200"/>
+</p>
+
+*\*\* : They are clearly using specific code for a specific encoding even if covering most of used one*<br>
+
+## ⚡ Performance
+
+This package offer better performance than its counterpart Chardet. Here are some numbers.
+
+| Package                                       | Accuracy | Mean per file (ms) | File per sec (est) |
+|-----------------------------------------------|:--------:|:------------------:|:------------------:|
+| [chardet](https://github.com/chardet/chardet) |   86 %   |       63 ms        |    16 file/sec     |
+| charset-normalizer                            | **98 %** |     **10 ms**      |    100 file/sec    |
+
+| Package                                       | 99th percentile | 95th percentile | 50th percentile |
+|-----------------------------------------------|:---------------:|:---------------:|:---------------:|
+| [chardet](https://github.com/chardet/chardet) |     265 ms      |      71 ms      |      7 ms       |
+| charset-normalizer                            |     100 ms      |      50 ms      |      5 ms       |
+
+_updated as of december 2024 using CPython 3.12_
+
+Chardet's performance on larger file (1MB+) are very poor. Expect huge difference on large payload.
+
+> Stats are generated using 400+ files using default parameters. More details on used files, see GHA workflows.
+> And yes, these results might change at any time. The dataset can be updated to include more files.
+> The actual delays heavily depends on your CPU capabilities. The factors should remain the same.
+> Keep in mind that the stats are generous and that Chardet accuracy vs our is measured using Chardet initial capability
+> (e.g. Supported Encoding) Challenge-them if you want.
+
+## ✨ Installation
+
+Using pip:
+
+```sh
+pip install charset-normalizer -U
+```
+
+## 🚀 Basic Usage
+
+### CLI
+This package comes with a CLI.
+
+```
+usage: normalizer [-h] [-v] [-a] [-n] [-m] [-r] [-f] [-t THRESHOLD]
+                  file [file ...]
+
+The Real First Universal Charset Detector. Discover originating encoding used
+on text file. Normalize text to unicode.
+
+positional arguments:
+  files                 File(s) to be analysed
+
+optional arguments:
+  -h, --help            show this help message and exit
+  -v, --verbose         Display complementary information about file if any.
+                        Stdout will contain logs about the detection process.
+  -a, --with-alternative
+                        Output complementary possibilities if any. Top-level
+                        JSON WILL be a list.
+  -n, --normalize       Permit to normalize input file. If not set, program
+                        does not write anything.
+  -m, --minimal         Only output the charset detected to STDOUT. Disabling
+                        JSON output.
+  -r, --replace         Replace file when trying to normalize it instead of
+                        creating a new one.
+  -f, --force           Replace file without asking if you are sure, use this
+                        flag with caution.
+  -t THRESHOLD, --threshold THRESHOLD
+                        Define a custom maximum amount of chaos allowed in
+                        decoded content. 0. <= chaos <= 1.
+  --version             Show version information and exit.
+```
+
+```bash
+normalizer ./data/sample.1.fr.srt
+```
+
+or
+
+```bash
+python -m charset_normalizer ./data/sample.1.fr.srt
+```
+
+🎉 Since version 1.4.0 the CLI produce easily usable stdout result in JSON format.
+
+```json
+{
+    "path": "/home/default/projects/charset_normalizer/data/sample.1.fr.srt",
+    "encoding": "cp1252",
+    "encoding_aliases": [
+        "1252",
+        "windows_1252"
+    ],
+    "alternative_encodings": [
+        "cp1254",
+        "cp1256",
+        "cp1258",
+        "iso8859_14",
+        "iso8859_15",
+        "iso8859_16",
+        "iso8859_3",
+        "iso8859_9",
+        "latin_1",
+        "mbcs"
+    ],
+    "language": "French",
+    "alphabets": [
+        "Basic Latin",
+        "Latin-1 Supplement"
+    ],
+    "has_sig_or_bom": false,
+    "chaos": 0.149,
+    "coherence": 97.152,
+    "unicode_path": null,
+    "is_preferred": true
+}
+```
+
+### Python
+*Just print out normalized text*
+```python
+from charset_normalizer import from_path
+
+results = from_path('./my_subtitle.srt')
+
+print(str(results.best()))
+```
+
+*Upgrade your code without effort*
+```python
+from charset_normalizer import detect
+```
+
+The above code will behave the same as **chardet**. We ensure that we offer the best (reasonable) BC result possible.
+
+See the docs for advanced usage : [readthedocs.io](https://charset-normalizer.readthedocs.io/en/latest/)
+
+## 😇 Why
+
+When I started using Chardet, I noticed that it was not suited to my expectations, and I wanted to propose a
+reliable alternative using a completely different method. Also! I never back down on a good challenge!
+
+I **don't care** about the **originating charset** encoding, because **two different tables** can
+produce **two identical rendered string.**
+What I want is to get readable text, the best I can.
+
+In a way, **I'm brute forcing text decoding.** How cool is that ? 😎
+
+Don't confuse package **ftfy** with charset-normalizer or chardet. ftfy goal is to repair Unicode string whereas charset-normalizer to convert raw file in unknown encoding to unicode.
+
+## 🍰 How
+
+  - Discard all charset encoding table that could not fit the binary content.
+  - Measure noise, or the mess once opened (by chunks) with a corresponding charset encoding.
+  - Extract matches with the lowest mess detected.
+  - Additionally, we measure coherence / probe for a language.
+
+**Wait a minute**, what is noise/mess and coherence according to **YOU ?**
+
+*Noise :* I opened hundred of text files, **written by humans**, with the wrong encoding table. **I observed**, then
+**I established** some ground rules about **what is obvious** when **it seems like** a mess (aka. defining noise in rendered text).
+ I know that my interpretation of what is noise is probably incomplete, feel free to contribute in order to
+ improve or rewrite it.
+
+*Coherence :* For each language there is on earth, we have computed ranked letter appearance occurrences (the best we can). So I thought
+that intel is worth something here. So I use those records against decoded text to check if I can detect intelligent design.
+
+## ⚡ Known limitations
+
+  - Language detection is unreliable when text contains two or more languages sharing identical letters. (eg. HTML (english tags) + Turkish content (Sharing Latin characters))
+  - Every charset detector heavily depends on sufficient content. In common cases, do not bother run detection on very tiny content.
+
+## ⚠️ About Python EOLs
+
+**If you are running:**
+
+- Python >=2.7,<3.5: Unsupported
+- Python 3.5: charset-normalizer < 2.1
+- Python 3.6: charset-normalizer < 3.1
+- Python 3.7: charset-normalizer < 4.0
+
+Upgrade your Python interpreter as soon as possible.
+
+## 👤 Contributing
+
+Contributions, issues and feature requests are very much welcome.<br />
+Feel free to check [issues page](https://github.com/ousret/charset_normalizer/issues) if you want to contribute.
+
+## 📝 License
+
+Copyright © [Ahmed TAHRI @Ousret](https://github.com/Ousret).<br />
+This project is [MIT](https://github.com/Ousret/charset_normalizer/blob/master/LICENSE) licensed.
+
+Characters frequencies used in this project © 2012 [Denny Vrandečić](http://simia.net/letters/)
+
+## 💼 For Enterprise
+
+Professional support for charset-normalizer is available as part of the [Tidelift
+Subscription][1]. Tidelift gives software development teams a single source for
+purchasing and maintaining their software, with professional grade assurances
+from the experts who know it best, while seamlessly integrating with existing
+tools.
+
+[1]: https://tidelift.com/subscription/pkg/pypi-charset-normalizer?utm_source=pypi-charset-normalizer&utm_medium=readme
+
+[![OpenSSF Best Practices](https://www.bestpractices.dev/projects/7297/badge)](https://www.bestpractices.dev/projects/7297)
+
+# Changelog
+All notable changes to charset-normalizer will be documented in this file. This project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
+The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/).
+
+## [3.4.1](https://github.com/Ousret/charset_normalizer/compare/3.4.0...3.4.1) (2024-12-24)
+
+### Changed
+- Project metadata are now stored using `pyproject.toml` instead of `setup.cfg` using setuptools as the build backend.
+- Enforce annotation delayed loading for a simpler and consistent types in the project.
+- Optional mypyc compilation upgraded to version 1.14 for Python >= 3.8
+
+### Added
+- pre-commit configuration.
+- noxfile.
+
+### Removed
+- `build-requirements.txt` as per using `pyproject.toml` native build configuration.
+- `bin/integration.py` and `bin/serve.py` in favor of downstream integration test (see noxfile).
+- `setup.cfg` in favor of `pyproject.toml` metadata configuration.
+- Unused `utils.range_scan` function.
+
+### Fixed
+- Converting content to Unicode bytes may insert `utf_8` instead of preferred `utf-8`. (#572)
+- Deprecation warning "'count' is passed as positional argument" when converting to Unicode bytes on Python 3.13+
+
+## [3.4.0](https://github.com/Ousret/charset_normalizer/compare/3.3.2...3.4.0) (2024-10-08)
+
+### Added
+- Argument `--no-preemptive` in the CLI to prevent the detector to search for hints.
+- Support for Python 3.13 (#512)
+
+### Fixed
+- Relax the TypeError exception thrown when trying to compare a CharsetMatch with anything else than a CharsetMatch.
+- Improved the general reliability of the detector based on user feedbacks. (#520) (#509) (#498) (#407) (#537)
+- Declared charset in content (preemptive detection) not changed when converting to utf-8 bytes. (#381)
+
+## [3.3.2](https://github.com/Ousret/charset_normalizer/compare/3.3.1...3.3.2) (2023-10-31)
+
+### Fixed
+- Unintentional memory usage regression when using large payload that match several encoding (#376)
+- Regression on some detection case showcased in the documentation (#371)
+
+### Added
+- Noise (md) probe that identify malformed arabic representation due to the presence of letters in isolated form (credit to my wife)
+
+## [3.3.1](https://github.com/Ousret/charset_normalizer/compare/3.3.0...3.3.1) (2023-10-22)
+
+### Changed
+- Optional mypyc compilation upgraded to version 1.6.1 for Python >= 3.8
+- Improved the general detection reliability based on reports from the community
+
+## [3.3.0](https://github.com/Ousret/charset_normalizer/compare/3.2.0...3.3.0) (2023-09-30)
+
+### Added
+- Allow to execute the CLI (e.g. normalizer) through `python -m charset_normalizer.cli` or `python -m charset_normalizer`
+- Support for 9 forgotten encoding that are supported by Python but unlisted in `encoding.aliases` as they have no alias (#323)
+
+### Removed
+- (internal) Redundant utils.is_ascii function and unused function is_private_use_only
+- (internal) charset_normalizer.assets is moved inside charset_normalizer.constant
+
+### Changed
+- (internal) Unicode code blocks in constants are updated using the latest v15.0.0 definition to improve detection
+- Optional mypyc compilation upgraded to version 1.5.1 for Python >= 3.8
+
+### Fixed
+- Unable to properly sort CharsetMatch when both chaos/noise and coherence were close due to an unreachable condition in \_\_lt\_\_ (#350)
+
+## [3.2.0](https://github.com/Ousret/charset_normalizer/compare/3.1.0...3.2.0) (2023-06-07)
+
+### Changed
+- Typehint for function `from_path` no longer enforce `PathLike` as its first argument
+- Minor improvement over the global detection reliability
+
+### Added
+- Introduce function `is_binary` that relies on main capabilities, and optimized to detect binaries
+- Propagate `enable_fallback` argument throughout `from_bytes`, `from_path`, and `from_fp` that allow a deeper control over the detection (default True)
+- Explicit support for Python 3.12
+
+### Fixed
+- Edge case detection failure where a file would contain 'very-long' camel cased word (Issue #289)
+
+## [3.1.0](https://github.com/Ousret/charset_normalizer/compare/3.0.1...3.1.0) (2023-03-06)
+
+### Added
+- Argument `should_rename_legacy` for legacy function `detect` and disregard any new arguments without errors (PR #262)
+
+### Removed
+- Support for Python 3.6 (PR #260)
+
+### Changed
+- Optional speedup provided by mypy/c 1.0.1
+
+## [3.0.1](https://github.com/Ousret/charset_normalizer/compare/3.0.0...3.0.1) (2022-11-18)
+
+### Fixed
+- Multi-bytes cutter/chunk generator did not always cut correctly (PR #233)
+
+### Changed
+- Speedup provided by mypy/c 0.990 on Python >= 3.7
+
+## [3.0.0](https://github.com/Ousret/charset_normalizer/compare/2.1.1...3.0.0) (2022-10-20)
+
+### Added
+- Extend the capability of explain=True when cp_isolation contains at most two entries (min one), will log in details of the Mess-detector results
+- Support for alternative language frequency set in charset_normalizer.assets.FREQUENCIES
+- Add parameter `language_threshold` in `from_bytes`, `from_path` and `from_fp` to adjust the minimum expected coherence ratio
+- `normalizer --version` now specify if current version provide extra speedup (meaning mypyc compilation whl)
+
+### Changed
+- Build with static metadata using 'build' frontend
+- Make the language detection stricter
+- Optional: Module `md.py` can be compiled using Mypyc to provide an extra speedup up to 4x faster than v2.1
+
+### Fixed
+- CLI with opt --normalize fail when using full path for files
+- TooManyAccentuatedPlugin induce false positive on the mess detection when too few alpha character have been fed to it
+- Sphinx warnings when generating the documentation
+
+### Removed
+- Coherence detector no longer return 'Simple English' instead return 'English'
+- Coherence detector no longer return 'Classical Chinese' instead return 'Chinese'
+- Breaking: Method `first()` and `best()` from CharsetMatch
+- UTF-7 will no longer appear as "detected" without a recognized SIG/mark (is unreliable/conflict with ASCII)
+- Breaking: Class aliases CharsetDetector, CharsetDoctor, CharsetNormalizerMatch and CharsetNormalizerMatches
+- Breaking: Top-level function `normalize`
+- Breaking: Properties `chaos_secondary_pass`, `coherence_non_latin` and `w_counter` from CharsetMatch
+- Support for the backport `unicodedata2`
+
+## [3.0.0rc1](https://github.com/Ousret/charset_normalizer/compare/3.0.0b2...3.0.0rc1) (2022-10-18)
+
+### Added
+- Extend the capability of explain=True when cp_isolation contains at most two entries (min one), will log in details of the Mess-detector results
+- Support for alternative language frequency set in charset_normalizer.assets.FREQUENCIES
+- Add parameter `language_threshold` in `from_bytes`, `from_path` and `from_fp` to adjust the minimum expected coherence ratio
+
+### Changed
+- Build with static metadata using 'build' frontend
+- Make the language detection stricter
+
+### Fixed
+- CLI with opt --normalize fail when using full path for files
+- TooManyAccentuatedPlugin induce false positive on the mess detection when too few alpha character have been fed to it
+
+### Removed
+- Coherence detector no longer return 'Simple English' instead return 'English'
+- Coherence detector no longer return 'Classical Chinese' instead return 'Chinese'
+
+## [3.0.0b2](https://github.com/Ousret/charset_normalizer/compare/3.0.0b1...3.0.0b2) (2022-08-21)
+
+### Added
+- `normalizer --version` now specify if current version provide extra speedup (meaning mypyc compilation whl)
+
+### Removed
+- Breaking: Method `first()` and `best()` from CharsetMatch
+- UTF-7 will no longer appear as "detected" without a recognized SIG/mark (is unreliable/conflict with ASCII)
+
+### Fixed
+- Sphinx warnings when generating the documentation
+
+## [3.0.0b1](https://github.com/Ousret/charset_normalizer/compare/2.1.0...3.0.0b1) (2022-08-15)
+
+### Changed
+- Optional: Module `md.py` can be compiled using Mypyc to provide an extra speedup up to 4x faster than v2.1
+
+### Removed
+- Breaking: Class aliases CharsetDetector, CharsetDoctor, CharsetNormalizerMatch and CharsetNormalizerMatches
+- Breaking: Top-level function `normalize`
+- Breaking: Properties `chaos_secondary_pass`, `coherence_non_latin` and `w_counter` from CharsetMatch
+- Support for the backport `unicodedata2`
+
+## [2.1.1](https://github.com/Ousret/charset_normalizer/compare/2.1.0...2.1.1) (2022-08-19)
+
+### Deprecated
+- Function `normalize` scheduled for removal in 3.0
+
+### Changed
+- Removed useless call to decode in fn is_unprintable (#206)
+
+### Fixed
+- Third-party library (i18n xgettext) crashing not recognizing utf_8 (PEP 263) with underscore from [@aleksandernovikov](https://github.com/aleksandernovikov) (#204)
+
+## [2.1.0](https://github.com/Ousret/charset_normalizer/compare/2.0.12...2.1.0) (2022-06-19)
+
+### Added
+- Output the Unicode table version when running the CLI with `--version` (PR #194)
+
+### Changed
+- Re-use decoded buffer for single byte character sets from [@nijel](https://github.com/nijel) (PR #175)
+- Fixing some performance bottlenecks from [@deedy5](https://github.com/deedy5) (PR #183)
+
+### Fixed
+- Workaround potential bug in cpython with Zero Width No-Break Space located in Arabic Presentation Forms-B, Unicode 1.1 not acknowledged as space (PR #175)
+- CLI default threshold aligned with the API threshold from [@oleksandr-kuzmenko](https://github.com/oleksandr-kuzmenko) (PR #181)
+
+### Removed
+- Support for Python 3.5 (PR #192)
+
+### Deprecated
+- Use of backport unicodedata from `unicodedata2` as Python is quickly catching up, scheduled for removal in 3.0 (PR #194)
+
+## [2.0.12](https://github.com/Ousret/charset_normalizer/compare/2.0.11...2.0.12) (2022-02-12)
+
+### Fixed
+- ASCII miss-detection on rare cases (PR #170)
+
+## [2.0.11](https://github.com/Ousret/charset_normalizer/compare/2.0.10...2.0.11) (2022-01-30)
+
+### Added
+- Explicit support for Python 3.11 (PR #164)
+
+### Changed
+- The logging behavior have been completely reviewed, now using only TRACE and DEBUG levels (PR #163 #165)
+
+## [2.0.10](https://github.com/Ousret/charset_normalizer/compare/2.0.9...2.0.10) (2022-01-04)
+
+### Fixed
+- Fallback match entries might lead to UnicodeDecodeError for large bytes sequence (PR #154)
+
+### Changed
+- Skipping the language-detection (CD) on ASCII (PR #155)
+
+## [2.0.9](https://github.com/Ousret/charset_normalizer/compare/2.0.8...2.0.9) (2021-12-03)
+
+### Changed
+- Moderating the logging impact (since 2.0.8) for specific environments (PR #147)
+
+### Fixed
+- Wrong logging level applied when setting kwarg `explain` to True (PR #146)
+
+## [2.0.8](https://github.com/Ousret/charset_normalizer/compare/2.0.7...2.0.8) (2021-11-24)
+### Changed
+- Improvement over Vietnamese detection (PR #126)
+- MD improvement on trailing data and long foreign (non-pure latin) data (PR #124)
+- Efficiency improvements in cd/alphabet_languages from [@adbar](https://github.com/adbar) (PR #122)
+- call sum() without an intermediary list following PEP 289 recommendations from [@adbar](https://github.com/adbar) (PR #129)
+- Code style as refactored by Sourcery-AI (PR #131)
+- Minor adjustment on the MD around european words (PR #133)
+- Remove and replace SRTs from assets / tests (PR #139)
+- Initialize the library logger with a `NullHandler` by default from [@nmaynes](https://github.com/nmaynes) (PR #135)
+- Setting kwarg `explain` to True will add provisionally (bounded to function lifespan) a specific stream handler (PR #135)
+
+### Fixed
+- Fix large (misleading) sequence giving UnicodeDecodeError (PR #137)
+- Avoid using too insignificant chunk (PR #137)
+
+### Added
+- Add and expose function `set_logging_handler` to configure a specific StreamHandler from [@nmaynes](https://github.com/nmaynes) (PR #135)
+- Add `CHANGELOG.md` entries, format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/) (PR #141)
+
+## [2.0.7](https://github.com/Ousret/charset_normalizer/compare/2.0.6...2.0.7) (2021-10-11)
+### Added
+- Add support for Kazakh (Cyrillic) language detection (PR #109)
+
+### Changed
+- Further, improve inferring the language from a given single-byte code page (PR #112)
+- Vainly trying to leverage PEP263 when PEP3120 is not supported (PR #116)
+- Refactoring for potential performance improvements in loops from [@adbar](https://github.com/adbar) (PR #113)
+- Various detection improvement (MD+CD) (PR #117)
+
+### Removed
+- Remove redundant logging entry about detected language(s) (PR #115)
+
+### Fixed
+- Fix a minor inconsistency between Python 3.5 and other versions regarding language detection (PR #117 #102)
+
+## [2.0.6](https://github.com/Ousret/charset_normalizer/compare/2.0.5...2.0.6) (2021-09-18)
+### Fixed
+- Unforeseen regression with the loss of the backward-compatibility with some older minor of Python 3.5.x (PR #100)
+- Fix CLI crash when using --minimal output in certain cases (PR #103)
+
+### Changed
+- Minor improvement to the detection efficiency (less than 1%) (PR #106 #101)
+
+## [2.0.5](https://github.com/Ousret/charset_normalizer/compare/2.0.4...2.0.5) (2021-09-14)
+### Changed
+- The project now comply with: flake8, mypy, isort and black to ensure a better overall quality (PR #81)
+- The BC-support with v1.x was improved, the old staticmethods are restored (PR #82)
+- The Unicode detection is slightly improved (PR #93)
+- Add syntax sugar \_\_bool\_\_ for results CharsetMatches list-container (PR #91)
+
+### Removed
+- The project no longer raise warning on tiny content given for detection, will be simply logged as warning instead (PR #92)
+
+### Fixed
+- In some rare case, the chunks extractor could cut in the middle of a multi-byte character and could mislead the mess detection (PR #95)
+- Some rare 'space' characters could trip up the UnprintablePlugin/Mess detection (PR #96)
+- The MANIFEST.in was not exhaustive (PR #78)
+
+## [2.0.4](https://github.com/Ousret/charset_normalizer/compare/2.0.3...2.0.4) (2021-07-30)
+### Fixed
+- The CLI no longer raise an unexpected exception when no encoding has been found (PR #70)
+- Fix accessing the 'alphabets' property when the payload contains surrogate characters (PR #68)
+- The logger could mislead (explain=True) on detected languages and the impact of one MBCS match (PR #72)
+- Submatch factoring could be wrong in rare edge cases (PR #72)
+- Multiple files given to the CLI were ignored when publishing results to STDOUT. (After the first path) (PR #72)
+- Fix line endings from CRLF to LF for certain project files (PR #67)
+
+### Changed
+- Adjust the MD to lower the sensitivity, thus improving the global detection reliability (PR #69 #76)
+- Allow fallback on specified encoding if any (PR #71)
+
+## [2.0.3](https://github.com/Ousret/charset_normalizer/compare/2.0.2...2.0.3) (2021-07-16)
+### Changed
+- Part of the detection mechanism has been improved to be less sensitive, resulting in more accurate detection results. Especially ASCII. (PR #63)
+- According to the community wishes, the detection will fall back on ASCII or UTF-8 in a last-resort case. (PR #64)
+
+## [2.0.2](https://github.com/Ousret/charset_normalizer/compare/2.0.1...2.0.2) (2021-07-15)
+### Fixed
+- Empty/Too small JSON payload miss-detection fixed. Report from [@tseaver](https://github.com/tseaver) (PR #59)
+
+### Changed
+- Don't inject unicodedata2 into sys.modules from [@akx](https://github.com/akx) (PR #57)
+
+## [2.0.1](https://github.com/Ousret/charset_normalizer/compare/2.0.0...2.0.1) (2021-07-13)
+### Fixed
+- Make it work where there isn't a filesystem available, dropping assets frequencies.json. Report from [@sethmlarson](https://github.com/sethmlarson). (PR #55)
+- Using explain=False permanently disable the verbose output in the current runtime (PR #47)
+- One log entry (language target preemptive) was not show in logs when using explain=True (PR #47)
+- Fix undesired exception (ValueError) on getitem of instance CharsetMatches (PR #52)
+
+### Changed
+- Public function normalize default args values were not aligned with from_bytes (PR #53)
+
+### Added
+- You may now use charset aliases in cp_isolation and cp_exclusion arguments (PR #47)
+
+## [2.0.0](https://github.com/Ousret/charset_normalizer/compare/1.4.1...2.0.0) (2021-07-02)
+### Changed
+- 4x to 5 times faster than the previous 1.4.0 release. At least 2x faster than Chardet.
+- Accent has been made on UTF-8 detection, should perform rather instantaneous.
+- The backward compatibility with Chardet has been greatly improved. The legacy detect function returns an identical charset name whenever possible.
+- The detection mechanism has been slightly improved, now Turkish content is detected correctly (most of the time)
+- The program has been rewritten to ease the readability and maintainability. (+Using static typing)+
+- utf_7 detection has been reinstated.
+
+### Removed
+- This package no longer require anything when used with Python 3.5 (Dropped cached_property)
+- Removed support for these languages: Catalan, Esperanto, Kazakh, Baque, Volapük, Azeri, Galician, Nynorsk, Macedonian, and Serbocroatian.
+- The exception hook on UnicodeDecodeError has been removed.
+
+### Deprecated
+- Methods coherence_non_latin, w_counter, chaos_secondary_pass of the class CharsetMatch are now deprecated and scheduled for removal in v3.0
+
+### Fixed
+- The CLI output used the relative path of the file(s). Should be absolute.
+
+## [1.4.1](https://github.com/Ousret/charset_normalizer/compare/1.4.0...1.4.1) (2021-05-28)
+### Fixed
+- Logger configuration/usage no longer conflict with others (PR #44)
+
+## [1.4.0](https://github.com/Ousret/charset_normalizer/compare/1.3.9...1.4.0) (2021-05-21)
+### Removed
+- Using standard logging instead of using the package loguru.
+- Dropping nose test framework in favor of the maintained pytest.
+- Choose to not use dragonmapper package to help with gibberish Chinese/CJK text.
+- Require cached_property only for Python 3.5 due to constraint. Dropping for every other interpreter version.
+- Stop support for UTF-7 that does not contain a SIG.
+- Dropping PrettyTable, replaced with pure JSON output in CLI.
+
+### Fixed
+- BOM marker in a CharsetNormalizerMatch instance could be False in rare cases even if obviously present. Due to the sub-match factoring process.
+- Not searching properly for the BOM when trying utf32/16 parent codec.
+
+### Changed
+- Improving the package final size by compressing frequencies.json.
+- Huge improvement over the larges payload.
+
+### Added
+- CLI now produces JSON consumable output.
+- Return ASCII if given sequences fit. Given reasonable confidence.
+
+## [1.3.9](https://github.com/Ousret/charset_normalizer/compare/1.3.8...1.3.9) (2021-05-13)
+
+### Fixed
+- In some very rare cases, you may end up getting encode/decode errors due to a bad bytes payload (PR #40)
+
+## [1.3.8](https://github.com/Ousret/charset_normalizer/compare/1.3.7...1.3.8) (2021-05-12)
+
+### Fixed
+- Empty given payload for detection may cause an exception if trying to access the `alphabets` property. (PR #39)
+
+## [1.3.7](https://github.com/Ousret/charset_normalizer/compare/1.3.6...1.3.7) (2021-05-12)
+
+### Fixed
+- The legacy detect function should return UTF-8-SIG if sig is present in the payload. (PR #38)
+
+## [1.3.6](https://github.com/Ousret/charset_normalizer/compare/1.3.5...1.3.6) (2021-02-09)
+
+### Changed
+- Amend the previous release to allow prettytable 2.0 (PR #35)
+
+## [1.3.5](https://github.com/Ousret/charset_normalizer/compare/1.3.4...1.3.5) (2021-02-08)
+
+### Fixed
+- Fix error while using the package with a python pre-release interpreter (PR #33)
+
+### Changed
+- Dependencies refactoring, constraints revised.
+
+### Added
+- Add python 3.9 and 3.10 to the supported interpreters
+
+MIT License
+
+Copyright (c) 2025 TAHRI Ahmed R.
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

venv/lib/python3.11/site-packages/charset_normalizer-3.4.1.dist-info/RECORD

@@ -0,0 +1,35 @@
+../../../bin/normalizer,sha256=lVuCYZlIlimMhsrs9VuhY42OkZOAg4VZbVVZ8-cP38M,257
+charset_normalizer-3.4.1.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4
+charset_normalizer-3.4.1.dist-info/LICENSE,sha256=bQ1Bv-FwrGx9wkjJpj4lTQ-0WmDVCoJX0K-SxuJJuIc,1071
+charset_normalizer-3.4.1.dist-info/METADATA,sha256=JbyHzhmqZh_ugEn1Y7TY7CDYZA9FoU6BP25hrCNDf50,35313
+charset_normalizer-3.4.1.dist-info/RECORD,,
+charset_normalizer-3.4.1.dist-info/WHEEL,sha256=ZiHiI0fxbnsGhDML32hrhH3YKU2c-6yRirdNq7QKO5A,153
+charset_normalizer-3.4.1.dist-info/entry_points.txt,sha256=8C-Y3iXIfyXQ83Tpir2B8t-XLJYpxF5xbb38d_js-h4,65
+charset_normalizer-3.4.1.dist-info/top_level.txt,sha256=7ASyzePr8_xuZWJsnqJjIBtyV8vhEo0wBCv1MPRRi3Q,19
+charset_normalizer/__init__.py,sha256=OKRxRv2Zhnqk00tqkN0c1BtJjm165fWXLydE52IKuHc,1590
+charset_normalizer/__main__.py,sha256=yzYxMR-IhKRHYwcSlavEv8oGdwxsR89mr2X09qXGdps,109
+charset_normalizer/__pycache__/__init__.cpython-311.pyc,,
+charset_normalizer/__pycache__/__main__.cpython-311.pyc,,
+charset_normalizer/__pycache__/api.cpython-311.pyc,,
+charset_normalizer/__pycache__/cd.cpython-311.pyc,,
+charset_normalizer/__pycache__/constant.cpython-311.pyc,,
+charset_normalizer/__pycache__/legacy.cpython-311.pyc,,
+charset_normalizer/__pycache__/md.cpython-311.pyc,,
+charset_normalizer/__pycache__/models.cpython-311.pyc,,
+charset_normalizer/__pycache__/utils.cpython-311.pyc,,
+charset_normalizer/__pycache__/version.cpython-311.pyc,,
+charset_normalizer/api.py,sha256=qBRz8mJ_R5E713R6TOyqHEdnmyxbEDnCSHvx32ubDGg,22617
+charset_normalizer/cd.py,sha256=WKTo1HDb-H9HfCDc3Bfwq5jzS25Ziy9SE2a74SgTq88,12522
+charset_normalizer/cli/__init__.py,sha256=D8I86lFk2-py45JvqxniTirSj_sFyE6sjaY_0-G1shc,136
+charset_normalizer/cli/__main__.py,sha256=VGC9klOoi6_R2z8rmyrc936kv7u2A1udjjHtlmNPDTM,10410
+charset_normalizer/cli/__pycache__/__init__.cpython-311.pyc,,
+charset_normalizer/cli/__pycache__/__main__.cpython-311.pyc,,
+charset_normalizer/constant.py,sha256=4VuTcZNLew1j_8ixA-Rt_VVqNWD4pwgHOHMCMlr0964,40477
+charset_normalizer/legacy.py,sha256=yhNXsPHkBfqPXKRb-sPXNj3Bscp9-mFGcYOkJ62tg9c,2328
+charset_normalizer/md.cpython-311-aarch64-linux-gnu.so,sha256=5hU4sWeM3XiR2vLRWyKxBqAMGpadzRWcsPw0feJSHM0,69800
+charset_normalizer/md.py,sha256=iyXXQGWl54nnLQLueMWTmUtlivO0-rTBgVkmJxIIAGU,20036
+charset_normalizer/md__mypyc.cpython-311-aarch64-linux-gnu.so,sha256=D65ppZ_SHkizbNWYKkGWFif-mnRWW5qQbIiYgS0MFcU,321840
+charset_normalizer/models.py,sha256=lKXhOnIPtiakbK3i__J9wpOfzx3JDTKj7Dn3Rg0VaRI,12394
+charset_normalizer/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+charset_normalizer/utils.py,sha256=T5UHo8AS7NVMmgruWoZyqEf0WrZVcQpgUNetRoborSk,12002
+charset_normalizer/version.py,sha256=Ambcj3O8FfvdLfDLc8dkaxZx97O1IM_R4_aKGD_TDdE,115

venv/lib/python3.11/site-packages/charset_normalizer-3.4.1.dist-info/WHEEL

@@ -0,0 +1,6 @@
+Wheel-Version: 1.0
+Generator: setuptools (75.6.0)
+Root-Is-Purelib: false
+Tag: cp311-cp311-manylinux_2_17_aarch64
+Tag: cp311-cp311-manylinux2014_aarch64
+

venv/lib/python3.11/site-packages/charset_normalizer-3.4.1.dist-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+normalizer = charset_normalizer:cli.cli_detect

venv/lib/python3.11/site-packages/charset_normalizer-3.4.1.dist-info/top_level.txt

@@ -0,0 +1 @@
+charset_normalizer

venv/lib/python3.11/site-packages/charset_normalizer/__init__.py

@@ -0,0 +1,48 @@
+"""
+Charset-Normalizer
+~~~~~~~~~~~~~~
+The Real First Universal Charset Detector.
+A library that helps you read text from an unknown charset encoding.
+Motivated by chardet, This package is trying to resolve the issue by taking a new approach.
+All IANA character set names for which the Python core library provides codecs are supported.
+
+Basic usage:
+   >>> from charset_normalizer import from_bytes
+   >>> results = from_bytes('Bсеки човек има право на образование. Oбразованието!'.encode('utf_8'))
+   >>> best_guess = results.best()
+   >>> str(best_guess)
+   'Bсеки човек има право на образование. Oбразованието!'
+
+Others methods and usages are available - see the full documentation
+at <https://github.com/Ousret/charset_normalizer>.
+:copyright: (c) 2021 by Ahmed TAHRI
+:license: MIT, see LICENSE for more details.
+"""
+
+from __future__ import annotations
+
+import logging
+
+from .api import from_bytes, from_fp, from_path, is_binary
+from .legacy import detect
+from .models import CharsetMatch, CharsetMatches
+from .utils import set_logging_handler
+from .version import VERSION, __version__
+
+__all__ = (
+    "from_fp",
+    "from_path",
+    "from_bytes",
+    "is_binary",
+    "detect",
+    "CharsetMatch",
+    "CharsetMatches",
+    "__version__",
+    "VERSION",
+    "set_logging_handler",
+)
+
+# Attach a NullHandler to the top level logger by default
+# https://docs.python.org/3.3/howto/logging.html#configuring-logging-for-a-library
+
+logging.getLogger("charset_normalizer").addHandler(logging.NullHandler())

venv/lib/python3.11/site-packages/charset_normalizer/__main__.py

@@ -0,0 +1,6 @@
+from __future__ import annotations
+
+from .cli import cli_detect
+
+if __name__ == "__main__":
+    cli_detect()

venv/lib/python3.11/site-packages/charset_normalizer/api.py

@@ -0,0 +1,668 @@
+from __future__ import annotations
+
+import logging
+from os import PathLike
+from typing import BinaryIO
+
+from .cd import (
+    coherence_ratio,
+    encoding_languages,
+    mb_encoding_languages,
+    merge_coherence_ratios,
+)
+from .constant import IANA_SUPPORTED, TOO_BIG_SEQUENCE, TOO_SMALL_SEQUENCE, TRACE
+from .md import mess_ratio
+from .models import CharsetMatch, CharsetMatches
+from .utils import (
+    any_specified_encoding,
+    cut_sequence_chunks,
+    iana_name,
+    identify_sig_or_bom,
+    is_cp_similar,
+    is_multi_byte_encoding,
+    should_strip_sig_or_bom,
+)
+
+logger = logging.getLogger("charset_normalizer")
+explain_handler = logging.StreamHandler()
+explain_handler.setFormatter(
+    logging.Formatter("%(asctime)s | %(levelname)s | %(message)s")
+)
+
+
+def from_bytes(
+    sequences: bytes | bytearray,
+    steps: int = 5,
+    chunk_size: int = 512,
+    threshold: float = 0.2,
+    cp_isolation: list[str] | None = None,
+    cp_exclusion: list[str] | None = None,
+    preemptive_behaviour: bool = True,
+    explain: bool = False,
+    language_threshold: float = 0.1,
+    enable_fallback: bool = True,
+) -> CharsetMatches:
+    """
+    Given a raw bytes sequence, return the best possibles charset usable to render str objects.
+    If there is no results, it is a strong indicator that the source is binary/not text.
+    By default, the process will extract 5 blocks of 512o each to assess the mess and coherence of a given sequence.
+    And will give up a particular code page after 20% of measured mess. Those criteria are customizable at will.
+
+    The preemptive behavior DOES NOT replace the traditional detection workflow, it prioritize a particular code page
+    but never take it for granted. Can improve the performance.
+
+    You may want to focus your attention to some code page or/and not others, use cp_isolation and cp_exclusion for that
+    purpose.
+
+    This function will strip the SIG in the payload/sequence every time except on UTF-16, UTF-32.
+    By default the library does not setup any handler other than the NullHandler, if you choose to set the 'explain'
+    toggle to True it will alter the logger configuration to add a StreamHandler that is suitable for debugging.
+    Custom logging format and handler can be set manually.
+    """
+
+    if not isinstance(sequences, (bytearray, bytes)):
+        raise TypeError(
+            "Expected object of type bytes or bytearray, got: {}".format(
+                type(sequences)
+            )
+        )
+
+    if explain:
+        previous_logger_level: int = logger.level
+        logger.addHandler(explain_handler)
+        logger.setLevel(TRACE)
+
+    length: int = len(sequences)
+
+    if length == 0:
+        logger.debug("Encoding detection on empty bytes, assuming utf_8 intention.")
+        if explain:  # Defensive: ensure exit path clean handler
+            logger.removeHandler(explain_handler)
+            logger.setLevel(previous_logger_level or logging.WARNING)
+        return CharsetMatches([CharsetMatch(sequences, "utf_8", 0.0, False, [], "")])
+
+    if cp_isolation is not None:
+        logger.log(
+            TRACE,
+            "cp_isolation is set. use this flag for debugging purpose. "
+            "limited list of encoding allowed : %s.",
+            ", ".join(cp_isolation),
+        )
+        cp_isolation = [iana_name(cp, False) for cp in cp_isolation]
+    else:
+        cp_isolation = []
+
+    if cp_exclusion is not None:
+        logger.log(
+            TRACE,
+            "cp_exclusion is set. use this flag for debugging purpose. "
+            "limited list of encoding excluded : %s.",
+            ", ".join(cp_exclusion),
+        )
+        cp_exclusion = [iana_name(cp, False) for cp in cp_exclusion]
+    else:
+        cp_exclusion = []
+
+    if length <= (chunk_size * steps):
+        logger.log(
+            TRACE,
+            "override steps (%i) and chunk_size (%i) as content does not fit (%i byte(s) given) parameters.",
+            steps,
+            chunk_size,
+            length,
+        )
+        steps = 1
+        chunk_size = length
+
+    if steps > 1 and length / steps < chunk_size:
+        chunk_size = int(length / steps)
+
+    is_too_small_sequence: bool = len(sequences) < TOO_SMALL_SEQUENCE
+    is_too_large_sequence: bool = len(sequences) >= TOO_BIG_SEQUENCE
+
+    if is_too_small_sequence:
+        logger.log(
+            TRACE,
+            "Trying to detect encoding from a tiny portion of ({}) byte(s).".format(
+                length
+            ),
+        )
+    elif is_too_large_sequence:
+        logger.log(
+            TRACE,
+            "Using lazy str decoding because the payload is quite large, ({}) byte(s).".format(
+                length
+            ),
+        )
+
+    prioritized_encodings: list[str] = []
+
+    specified_encoding: str | None = (
+        any_specified_encoding(sequences) if preemptive_behaviour else None
+    )
+
+    if specified_encoding is not None:
+        prioritized_encodings.append(specified_encoding)
+        logger.log(
+            TRACE,
+            "Detected declarative mark in sequence. Priority +1 given for %s.",
+            specified_encoding,
+        )
+
+    tested: set[str] = set()
+    tested_but_hard_failure: list[str] = []
+    tested_but_soft_failure: list[str] = []
+
+    fallback_ascii: CharsetMatch | None = None
+    fallback_u8: CharsetMatch | None = None
+    fallback_specified: CharsetMatch | None = None
+
+    results: CharsetMatches = CharsetMatches()
+
+    early_stop_results: CharsetMatches = CharsetMatches()
+
+    sig_encoding, sig_payload = identify_sig_or_bom(sequences)
+
+    if sig_encoding is not None:
+        prioritized_encodings.append(sig_encoding)
+        logger.log(
+            TRACE,
+            "Detected a SIG or BOM mark on first %i byte(s). Priority +1 given for %s.",
+            len(sig_payload),
+            sig_encoding,
+        )
+
+    prioritized_encodings.append("ascii")
+
+    if "utf_8" not in prioritized_encodings:
+        prioritized_encodings.append("utf_8")
+
+    for encoding_iana in prioritized_encodings + IANA_SUPPORTED:
+        if cp_isolation and encoding_iana not in cp_isolation:
+            continue
+
+        if cp_exclusion and encoding_iana in cp_exclusion:
+            continue
+
+        if encoding_iana in tested:
+            continue
+
+        tested.add(encoding_iana)
+
+        decoded_payload: str | None = None
+        bom_or_sig_available: bool = sig_encoding == encoding_iana
+        strip_sig_or_bom: bool = bom_or_sig_available and should_strip_sig_or_bom(
+            encoding_iana
+        )
+
+        if encoding_iana in {"utf_16", "utf_32"} and not bom_or_sig_available:
+            logger.log(
+                TRACE,
+                "Encoding %s won't be tested as-is because it require a BOM. Will try some sub-encoder LE/BE.",
+                encoding_iana,
+            )
+            continue
+        if encoding_iana in {"utf_7"} and not bom_or_sig_available:
+            logger.log(
+                TRACE,
+                "Encoding %s won't be tested as-is because detection is unreliable without BOM/SIG.",
+                encoding_iana,
+            )
+            continue
+
+        try:
+            is_multi_byte_decoder: bool = is_multi_byte_encoding(encoding_iana)
+        except (ModuleNotFoundError, ImportError):
+            logger.log(
+                TRACE,
+                "Encoding %s does not provide an IncrementalDecoder",
+                encoding_iana,
+            )
+            continue
+
+        try:
+            if is_too_large_sequence and is_multi_byte_decoder is False:
+                str(
+                    (
+                        sequences[: int(50e4)]
+                        if strip_sig_or_bom is False
+                        else sequences[len(sig_payload) : int(50e4)]
+                    ),
+                    encoding=encoding_iana,
+                )
+            else:
+                decoded_payload = str(
+                    (
+                        sequences
+                        if strip_sig_or_bom is False
+                        else sequences[len(sig_payload) :]
+                    ),
+                    encoding=encoding_iana,
+                )
+        except (UnicodeDecodeError, LookupError) as e:
+            if not isinstance(e, LookupError):
+                logger.log(
+                    TRACE,
+                    "Code page %s does not fit given bytes sequence at ALL. %s",
+                    encoding_iana,
+                    str(e),
+                )
+            tested_but_hard_failure.append(encoding_iana)
+            continue
+
+        similar_soft_failure_test: bool = False
+
+        for encoding_soft_failed in tested_but_soft_failure:
+            if is_cp_similar(encoding_iana, encoding_soft_failed):
+                similar_soft_failure_test = True
+                break
+
+        if similar_soft_failure_test:
+            logger.log(
+                TRACE,
+                "%s is deemed too similar to code page %s and was consider unsuited already. Continuing!",
+                encoding_iana,
+                encoding_soft_failed,
+            )
+            continue
+
+        r_ = range(
+            0 if not bom_or_sig_available else len(sig_payload),
+            length,
+            int(length / steps),
+        )
+
+        multi_byte_bonus: bool = (
+            is_multi_byte_decoder
+            and decoded_payload is not None
+            and len(decoded_payload) < length
+        )
+
+        if multi_byte_bonus:
+            logger.log(
+                TRACE,
+                "Code page %s is a multi byte encoding table and it appear that at least one character "
+                "was encoded using n-bytes.",
+                encoding_iana,
+            )
+
+        max_chunk_gave_up: int = int(len(r_) / 4)
+
+        max_chunk_gave_up = max(max_chunk_gave_up, 2)
+        early_stop_count: int = 0
+        lazy_str_hard_failure = False
+
+        md_chunks: list[str] = []
+        md_ratios = []
+
+        try:
+            for chunk in cut_sequence_chunks(
+                sequences,
+                encoding_iana,
+                r_,
+                chunk_size,
+                bom_or_sig_available,
+                strip_sig_or_bom,
+                sig_payload,
+                is_multi_byte_decoder,
+                decoded_payload,
+            ):
+                md_chunks.append(chunk)
+
+                md_ratios.append(
+                    mess_ratio(
+                        chunk,
+                        threshold,
+                        explain is True and 1 <= len(cp_isolation) <= 2,
+                    )
+                )
+
+                if md_ratios[-1] >= threshold:
+                    early_stop_count += 1
+
+                if (early_stop_count >= max_chunk_gave_up) or (
+                    bom_or_sig_available and strip_sig_or_bom is False
+                ):
+                    break
+        except (
+            UnicodeDecodeError
+        ) as e:  # Lazy str loading may have missed something there
+            logger.log(
+                TRACE,
+                "LazyStr Loading: After MD chunk decode, code page %s does not fit given bytes sequence at ALL. %s",
+                encoding_iana,
+                str(e),
+            )
+            early_stop_count = max_chunk_gave_up
+            lazy_str_hard_failure = True
+
+        # We might want to check the sequence again with the whole content
+        # Only if initial MD tests passes
+        if (
+            not lazy_str_hard_failure
+            and is_too_large_sequence
+            and not is_multi_byte_decoder
+        ):
+            try:
+                sequences[int(50e3) :].decode(encoding_iana, errors="strict")
+            except UnicodeDecodeError as e:
+                logger.log(
+                    TRACE,
+                    "LazyStr Loading: After final lookup, code page %s does not fit given bytes sequence at ALL. %s",
+                    encoding_iana,
+                    str(e),
+                )
+                tested_but_hard_failure.append(encoding_iana)
+                continue
+
+        mean_mess_ratio: float = sum(md_ratios) / len(md_ratios) if md_ratios else 0.0
+        if mean_mess_ratio >= threshold or early_stop_count >= max_chunk_gave_up:
+            tested_but_soft_failure.append(encoding_iana)
+            logger.log(
+                TRACE,
+                "%s was excluded because of initial chaos probing. Gave up %i time(s). "
+                "Computed mean chaos is %f %%.",
+                encoding_iana,
+                early_stop_count,
+                round(mean_mess_ratio * 100, ndigits=3),
+            )
+            # Preparing those fallbacks in case we got nothing.
+            if (
+                enable_fallback
+                and encoding_iana in ["ascii", "utf_8", specified_encoding]
+                and not lazy_str_hard_failure
+            ):
+                fallback_entry = CharsetMatch(
+                    sequences,
+                    encoding_iana,
+                    threshold,
+                    False,
+                    [],
+                    decoded_payload,
+                    preemptive_declaration=specified_encoding,
+                )
+                if encoding_iana == specified_encoding:
+                    fallback_specified = fallback_entry
+                elif encoding_iana == "ascii":
+                    fallback_ascii = fallback_entry
+                else:
+                    fallback_u8 = fallback_entry
+            continue
+
+        logger.log(
+            TRACE,
+            "%s passed initial chaos probing. Mean measured chaos is %f %%",
+            encoding_iana,
+            round(mean_mess_ratio * 100, ndigits=3),
+        )
+
+        if not is_multi_byte_decoder:
+            target_languages: list[str] = encoding_languages(encoding_iana)
+        else:
+            target_languages = mb_encoding_languages(encoding_iana)
+
+        if target_languages:
+            logger.log(
+                TRACE,
+                "{} should target any language(s) of {}".format(
+                    encoding_iana, str(target_languages)
+                ),
+            )
+
+        cd_ratios = []
+
+        # We shall skip the CD when its about ASCII
+        # Most of the time its not relevant to run "language-detection" on it.
+        if encoding_iana != "ascii":
+            for chunk in md_chunks:
+                chunk_languages = coherence_ratio(
+                    chunk,
+                    language_threshold,
+                    ",".join(target_languages) if target_languages else None,
+                )
+
+                cd_ratios.append(chunk_languages)
+
+        cd_ratios_merged = merge_coherence_ratios(cd_ratios)
+
+        if cd_ratios_merged:
+            logger.log(
+                TRACE,
+                "We detected language {} using {}".format(
+                    cd_ratios_merged, encoding_iana
+                ),
+            )
+
+        current_match = CharsetMatch(
+            sequences,
+            encoding_iana,
+            mean_mess_ratio,
+            bom_or_sig_available,
+            cd_ratios_merged,
+            (
+                decoded_payload
+                if (
+                    is_too_large_sequence is False
+                    or encoding_iana in [specified_encoding, "ascii", "utf_8"]
+                )
+                else None
+            ),
+            preemptive_declaration=specified_encoding,
+        )
+
+        results.append(current_match)
+
+        if (
+            encoding_iana in [specified_encoding, "ascii", "utf_8"]
+            and mean_mess_ratio < 0.1
+        ):
+            # If md says nothing to worry about, then... stop immediately!
+            if mean_mess_ratio == 0.0:
+                logger.debug(
+                    "Encoding detection: %s is most likely the one.",
+                    current_match.encoding,
+                )
+                if explain:  # Defensive: ensure exit path clean handler
+                    logger.removeHandler(explain_handler)
+                    logger.setLevel(previous_logger_level)
+                return CharsetMatches([current_match])
+
+            early_stop_results.append(current_match)
+
+        if (
+            len(early_stop_results)
+            and (specified_encoding is None or specified_encoding in tested)
+            and "ascii" in tested
+            and "utf_8" in tested
+        ):
+            probable_result: CharsetMatch = early_stop_results.best()  # type: ignore[assignment]
+            logger.debug(
+                "Encoding detection: %s is most likely the one.",
+                probable_result.encoding,
+            )
+            if explain:  # Defensive: ensure exit path clean handler
+                logger.removeHandler(explain_handler)
+                logger.setLevel(previous_logger_level)
+
+            return CharsetMatches([probable_result])
+
+        if encoding_iana == sig_encoding:
+            logger.debug(
+                "Encoding detection: %s is most likely the one as we detected a BOM or SIG within "
+                "the beginning of the sequence.",
+                encoding_iana,
+            )
+            if explain:  # Defensive: ensure exit path clean handler
+                logger.removeHandler(explain_handler)
+                logger.setLevel(previous_logger_level)
+            return CharsetMatches([results[encoding_iana]])
+
+    if len(results) == 0:
+        if fallback_u8 or fallback_ascii or fallback_specified:
+            logger.log(
+                TRACE,
+                "Nothing got out of the detection process. Using ASCII/UTF-8/Specified fallback.",
+            )
+
+        if fallback_specified:
+            logger.debug(
+                "Encoding detection: %s will be used as a fallback match",
+                fallback_specified.encoding,
+            )
+            results.append(fallback_specified)
+        elif (
+            (fallback_u8 and fallback_ascii is None)
+            or (
+                fallback_u8
+                and fallback_ascii
+                and fallback_u8.fingerprint != fallback_ascii.fingerprint
+            )
+            or (fallback_u8 is not None)
+        ):
+            logger.debug("Encoding detection: utf_8 will be used as a fallback match")
+            results.append(fallback_u8)
+        elif fallback_ascii:
+            logger.debug("Encoding detection: ascii will be used as a fallback match")
+            results.append(fallback_ascii)
+
+    if results:
+        logger.debug(
+            "Encoding detection: Found %s as plausible (best-candidate) for content. With %i alternatives.",
+            results.best().encoding,  # type: ignore
+            len(results) - 1,
+        )
+    else:
+        logger.debug("Encoding detection: Unable to determine any suitable charset.")
+
+    if explain:
+        logger.removeHandler(explain_handler)
+        logger.setLevel(previous_logger_level)
+
+    return results
+
+
+def from_fp(
+    fp: BinaryIO,
+    steps: int = 5,
+    chunk_size: int = 512,
+    threshold: float = 0.20,
+    cp_isolation: list[str] | None = None,
+    cp_exclusion: list[str] | None = None,
+    preemptive_behaviour: bool = True,
+    explain: bool = False,
+    language_threshold: float = 0.1,
+    enable_fallback: bool = True,
+) -> CharsetMatches:
+    """
+    Same thing than the function from_bytes but using a file pointer that is already ready.
+    Will not close the file pointer.
+    """
+    return from_bytes(
+        fp.read(),
+        steps,
+        chunk_size,
+        threshold,
+        cp_isolation,
+        cp_exclusion,
+        preemptive_behaviour,
+        explain,
+        language_threshold,
+        enable_fallback,
+    )
+
+
+def from_path(
+    path: str | bytes | PathLike,  # type: ignore[type-arg]
+    steps: int = 5,
+    chunk_size: int = 512,
+    threshold: float = 0.20,
+    cp_isolation: list[str] | None = None,
+    cp_exclusion: list[str] | None = None,
+    preemptive_behaviour: bool = True,
+    explain: bool = False,
+    language_threshold: float = 0.1,
+    enable_fallback: bool = True,
+) -> CharsetMatches:
+    """
+    Same thing than the function from_bytes but with one extra step. Opening and reading given file path in binary mode.
+    Can raise IOError.
+    """
+    with open(path, "rb") as fp:
+        return from_fp(
+            fp,
+            steps,
+            chunk_size,
+            threshold,
+            cp_isolation,
+            cp_exclusion,
+            preemptive_behaviour,
+            explain,
+            language_threshold,
+            enable_fallback,
+        )
+
+
+def is_binary(
+    fp_or_path_or_payload: PathLike | str | BinaryIO | bytes,  # type: ignore[type-arg]
+    steps: int = 5,
+    chunk_size: int = 512,
+    threshold: float = 0.20,
+    cp_isolation: list[str] | None = None,
+    cp_exclusion: list[str] | None = None,
+    preemptive_behaviour: bool = True,
+    explain: bool = False,
+    language_threshold: float = 0.1,
+    enable_fallback: bool = False,
+) -> bool:
+    """
+    Detect if the given input (file, bytes, or path) points to a binary file. aka. not a string.
+    Based on the same main heuristic algorithms and default kwargs at the sole exception that fallbacks match
+    are disabled to be stricter around ASCII-compatible but unlikely to be a string.
+    """
+    if isinstance(fp_or_path_or_payload, (str, PathLike)):
+        guesses = from_path(
+            fp_or_path_or_payload,
+            steps=steps,
+            chunk_size=chunk_size,
+            threshold=threshold,
+            cp_isolation=cp_isolation,
+            cp_exclusion=cp_exclusion,
+            preemptive_behaviour=preemptive_behaviour,
+            explain=explain,
+            language_threshold=language_threshold,
+            enable_fallback=enable_fallback,
+        )
+    elif isinstance(
+        fp_or_path_or_payload,
+        (
+            bytes,
+            bytearray,
+        ),
+    ):
+        guesses = from_bytes(
+            fp_or_path_or_payload,
+            steps=steps,
+            chunk_size=chunk_size,
+            threshold=threshold,
+            cp_isolation=cp_isolation,
+            cp_exclusion=cp_exclusion,
+            preemptive_behaviour=preemptive_behaviour,
+            explain=explain,
+            language_threshold=language_threshold,
+            enable_fallback=enable_fallback,
+        )
+    else:
+        guesses = from_fp(
+            fp_or_path_or_payload,
+            steps=steps,
+            chunk_size=chunk_size,
+            threshold=threshold,
+            cp_isolation=cp_isolation,
+            cp_exclusion=cp_exclusion,
+            preemptive_behaviour=preemptive_behaviour,
+            explain=explain,
+            language_threshold=language_threshold,
+            enable_fallback=enable_fallback,
+        )
+
+    return not guesses

venv/lib/python3.11/site-packages/charset_normalizer/cd.py

@@ -0,0 +1,395 @@
+from __future__ import annotations
+
+import importlib
+from codecs import IncrementalDecoder
+from collections import Counter
+from functools import lru_cache
+from typing import Counter as TypeCounter
+
+from .constant import (
+    FREQUENCIES,
+    KO_NAMES,
+    LANGUAGE_SUPPORTED_COUNT,
+    TOO_SMALL_SEQUENCE,
+    ZH_NAMES,
+)
+from .md import is_suspiciously_successive_range
+from .models import CoherenceMatches
+from .utils import (
+    is_accentuated,
+    is_latin,
+    is_multi_byte_encoding,
+    is_unicode_range_secondary,
+    unicode_range,
+)
+
+
+def encoding_unicode_range(iana_name: str) -> list[str]:
+    """
+    Return associated unicode ranges in a single byte code page.
+    """
+    if is_multi_byte_encoding(iana_name):
+        raise OSError("Function not supported on multi-byte code page")
+
+    decoder = importlib.import_module(f"encodings.{iana_name}").IncrementalDecoder
+
+    p: IncrementalDecoder = decoder(errors="ignore")
+    seen_ranges: dict[str, int] = {}
+    character_count: int = 0
+
+    for i in range(0x40, 0xFF):
+        chunk: str = p.decode(bytes([i]))
+
+        if chunk:
+            character_range: str | None = unicode_range(chunk)
+
+            if character_range is None:
+                continue
+
+            if is_unicode_range_secondary(character_range) is False:
+                if character_range not in seen_ranges:
+                    seen_ranges[character_range] = 0
+                seen_ranges[character_range] += 1
+                character_count += 1
+
+    return sorted(
+        [
+            character_range
+            for character_range in seen_ranges
+            if seen_ranges[character_range] / character_count >= 0.15
+        ]
+    )
+
+
+def unicode_range_languages(primary_range: str) -> list[str]:
+    """
+    Return inferred languages used with a unicode range.
+    """
+    languages: list[str] = []
+
+    for language, characters in FREQUENCIES.items():
+        for character in characters:
+            if unicode_range(character) == primary_range:
+                languages.append(language)
+                break
+
+    return languages
+
+
+@lru_cache()
+def encoding_languages(iana_name: str) -> list[str]:
+    """
+    Single-byte encoding language association. Some code page are heavily linked to particular language(s).
+    This function does the correspondence.
+    """
+    unicode_ranges: list[str] = encoding_unicode_range(iana_name)
+    primary_range: str | None = None
+
+    for specified_range in unicode_ranges:
+        if "Latin" not in specified_range:
+            primary_range = specified_range
+            break
+
+    if primary_range is None:
+        return ["Latin Based"]
+
+    return unicode_range_languages(primary_range)
+
+
+@lru_cache()
+def mb_encoding_languages(iana_name: str) -> list[str]:
+    """
+    Multi-byte encoding language association. Some code page are heavily linked to particular language(s).
+    This function does the correspondence.
+    """
+    if (
+        iana_name.startswith("shift_")
+        or iana_name.startswith("iso2022_jp")
+        or iana_name.startswith("euc_j")
+        or iana_name == "cp932"
+    ):
+        return ["Japanese"]
+    if iana_name.startswith("gb") or iana_name in ZH_NAMES:
+        return ["Chinese"]
+    if iana_name.startswith("iso2022_kr") or iana_name in KO_NAMES:
+        return ["Korean"]
+
+    return []
+
+
+@lru_cache(maxsize=LANGUAGE_SUPPORTED_COUNT)
+def get_target_features(language: str) -> tuple[bool, bool]:
+    """
+    Determine main aspects from a supported language if it contains accents and if is pure Latin.
+    """
+    target_have_accents: bool = False
+    target_pure_latin: bool = True
+
+    for character in FREQUENCIES[language]:
+        if not target_have_accents and is_accentuated(character):
+            target_have_accents = True
+        if target_pure_latin and is_latin(character) is False:
+            target_pure_latin = False
+
+    return target_have_accents, target_pure_latin
+
+
+def alphabet_languages(
+    characters: list[str], ignore_non_latin: bool = False
+) -> list[str]:
+    """
+    Return associated languages associated to given characters.
+    """
+    languages: list[tuple[str, float]] = []
+
+    source_have_accents = any(is_accentuated(character) for character in characters)
+
+    for language, language_characters in FREQUENCIES.items():
+        target_have_accents, target_pure_latin = get_target_features(language)
+
+        if ignore_non_latin and target_pure_latin is False:
+            continue
+
+        if target_have_accents is False and source_have_accents:
+            continue
+
+        character_count: int = len(language_characters)
+
+        character_match_count: int = len(
+            [c for c in language_characters if c in characters]
+        )
+
+        ratio: float = character_match_count / character_count
+
+        if ratio >= 0.2:
+            languages.append((language, ratio))
+
+    languages = sorted(languages, key=lambda x: x[1], reverse=True)
+
+    return [compatible_language[0] for compatible_language in languages]
+
+
+def characters_popularity_compare(
+    language: str, ordered_characters: list[str]
+) -> float:
+    """
+    Determine if a ordered characters list (by occurrence from most appearance to rarest) match a particular language.
+    The result is a ratio between 0. (absolutely no correspondence) and 1. (near perfect fit).
+    Beware that is function is not strict on the match in order to ease the detection. (Meaning close match is 1.)
+    """
+    if language not in FREQUENCIES:
+        raise ValueError(f"{language} not available")
+
+    character_approved_count: int = 0
+    FREQUENCIES_language_set = set(FREQUENCIES[language])
+
+    ordered_characters_count: int = len(ordered_characters)
+    target_language_characters_count: int = len(FREQUENCIES[language])
+
+    large_alphabet: bool = target_language_characters_count > 26
+
+    for character, character_rank in zip(
+        ordered_characters, range(0, ordered_characters_count)
+    ):
+        if character not in FREQUENCIES_language_set:
+            continue
+
+        character_rank_in_language: int = FREQUENCIES[language].index(character)
+        expected_projection_ratio: float = (
+            target_language_characters_count / ordered_characters_count
+        )
+        character_rank_projection: int = int(character_rank * expected_projection_ratio)
+
+        if (
+            large_alphabet is False
+            and abs(character_rank_projection - character_rank_in_language) > 4
+        ):
+            continue
+
+        if (
+            large_alphabet is True
+            and abs(character_rank_projection - character_rank_in_language)
+            < target_language_characters_count / 3
+        ):
+            character_approved_count += 1
+            continue
+
+        characters_before_source: list[str] = FREQUENCIES[language][
+            0:character_rank_in_language
+        ]
+        characters_after_source: list[str] = FREQUENCIES[language][
+            character_rank_in_language:
+        ]
+        characters_before: list[str] = ordered_characters[0:character_rank]
+        characters_after: list[str] = ordered_characters[character_rank:]
+
+        before_match_count: int = len(
+            set(characters_before) & set(characters_before_source)
+        )
+
+        after_match_count: int = len(
+            set(characters_after) & set(characters_after_source)
+        )
+
+        if len(characters_before_source) == 0 and before_match_count <= 4:
+            character_approved_count += 1
+            continue
+
+        if len(characters_after_source) == 0 and after_match_count <= 4:
+            character_approved_count += 1
+            continue
+
+        if (
+            before_match_count / len(characters_before_source) >= 0.4
+            or after_match_count / len(characters_after_source) >= 0.4
+        ):
+            character_approved_count += 1
+            continue
+
+    return character_approved_count / len(ordered_characters)
+
+
+def alpha_unicode_split(decoded_sequence: str) -> list[str]:
+    """
+    Given a decoded text sequence, return a list of str. Unicode range / alphabet separation.
+    Ex. a text containing English/Latin with a bit a Hebrew will return two items in the resulting list;
+    One containing the latin letters and the other hebrew.
+    """
+    layers: dict[str, str] = {}
+
+    for character in decoded_sequence:
+        if character.isalpha() is False:
+            continue
+
+        character_range: str | None = unicode_range(character)
+
+        if character_range is None:
+            continue
+
+        layer_target_range: str | None = None
+
+        for discovered_range in layers:
+            if (
+                is_suspiciously_successive_range(discovered_range, character_range)
+                is False
+            ):
+                layer_target_range = discovered_range
+                break
+
+        if layer_target_range is None:
+            layer_target_range = character_range
+
+        if layer_target_range not in layers:
+            layers[layer_target_range] = character.lower()
+            continue
+
+        layers[layer_target_range] += character.lower()
+
+    return list(layers.values())
+
+
+def merge_coherence_ratios(results: list[CoherenceMatches]) -> CoherenceMatches:
+    """
+    This function merge results previously given by the function coherence_ratio.
+    The return type is the same as coherence_ratio.
+    """
+    per_language_ratios: dict[str, list[float]] = {}
+    for result in results:
+        for sub_result in result:
+            language, ratio = sub_result
+            if language not in per_language_ratios:
+                per_language_ratios[language] = [ratio]
+                continue
+            per_language_ratios[language].append(ratio)
+
+    merge = [
+        (
+            language,
+            round(
+                sum(per_language_ratios[language]) / len(per_language_ratios[language]),
+                4,
+            ),
+        )
+        for language in per_language_ratios
+    ]
+
+    return sorted(merge, key=lambda x: x[1], reverse=True)
+
+
+def filter_alt_coherence_matches(results: CoherenceMatches) -> CoherenceMatches:
+    """
+    We shall NOT return "English—" in CoherenceMatches because it is an alternative
+    of "English". This function only keeps the best match and remove the em-dash in it.
+    """
+    index_results: dict[str, list[float]] = dict()
+
+    for result in results:
+        language, ratio = result
+        no_em_name: str = language.replace("—", "")
+
+        if no_em_name not in index_results:
+            index_results[no_em_name] = []
+
+        index_results[no_em_name].append(ratio)
+
+    if any(len(index_results[e]) > 1 for e in index_results):
+        filtered_results: CoherenceMatches = []
+
+        for language in index_results:
+            filtered_results.append((language, max(index_results[language])))
+
+        return filtered_results
+
+    return results
+
+
+@lru_cache(maxsize=2048)
+def coherence_ratio(
+    decoded_sequence: str, threshold: float = 0.1, lg_inclusion: str | None = None
+) -> CoherenceMatches:
+    """
+    Detect ANY language that can be identified in given sequence. The sequence will be analysed by layers.
+    A layer = Character extraction by alphabets/ranges.
+    """
+
+    results: list[tuple[str, float]] = []
+    ignore_non_latin: bool = False
+
+    sufficient_match_count: int = 0
+
+    lg_inclusion_list = lg_inclusion.split(",") if lg_inclusion is not None else []
+    if "Latin Based" in lg_inclusion_list:
+        ignore_non_latin = True
+        lg_inclusion_list.remove("Latin Based")
+
+    for layer in alpha_unicode_split(decoded_sequence):
+        sequence_frequencies: TypeCounter[str] = Counter(layer)
+        most_common = sequence_frequencies.most_common()
+
+        character_count: int = sum(o for c, o in most_common)
+
+        if character_count <= TOO_SMALL_SEQUENCE:
+            continue
+
+        popular_character_ordered: list[str] = [c for c, o in most_common]
+
+        for language in lg_inclusion_list or alphabet_languages(
+            popular_character_ordered, ignore_non_latin
+        ):
+            ratio: float = characters_popularity_compare(
+                language, popular_character_ordered
+            )
+
+            if ratio < threshold:
+                continue
+            elif ratio >= 0.8:
+                sufficient_match_count += 1
+
+            results.append((language, round(ratio, 4)))
+
+            if sufficient_match_count >= 3:
+                break
+
+    return sorted(
+        filter_alt_coherence_matches(results), key=lambda x: x[1], reverse=True
+    )

venv/lib/python3.11/site-packages/charset_normalizer/cli/__init__.py

@@ -0,0 +1,8 @@
+from __future__ import annotations
+
+from .__main__ import cli_detect, query_yes_no
+
+__all__ = (
+    "cli_detect",
+    "query_yes_no",
+)

venv/lib/python3.11/site-packages/charset_normalizer/cli/__main__.py

@@ -0,0 +1,321 @@
+from __future__ import annotations
+
+import argparse
+import sys
+from json import dumps
+from os.path import abspath, basename, dirname, join, realpath
+from platform import python_version
+from unicodedata import unidata_version
+
+import charset_normalizer.md as md_module
+from charset_normalizer import from_fp
+from charset_normalizer.models import CliDetectionResult
+from charset_normalizer.version import __version__
+
+
+def query_yes_no(question: str, default: str = "yes") -> bool:
+    """Ask a yes/no question via input() and return their answer.
+
+    "question" is a string that is presented to the user.
+    "default" is the presumed answer if the user just hits <Enter>.
+        It must be "yes" (the default), "no" or None (meaning
+        an answer is required of the user).
+
+    The "answer" return value is True for "yes" or False for "no".
+
+    Credit goes to (c) https://stackoverflow.com/questions/3041986/apt-command-line-interface-like-yes-no-input
+    """
+    valid = {"yes": True, "y": True, "ye": True, "no": False, "n": False}
+    if default is None:
+        prompt = " [y/n] "
+    elif default == "yes":
+        prompt = " [Y/n] "
+    elif default == "no":
+        prompt = " [y/N] "
+    else:
+        raise ValueError("invalid default answer: '%s'" % default)
+
+    while True:
+        sys.stdout.write(question + prompt)
+        choice = input().lower()
+        if default is not None and choice == "":
+            return valid[default]
+        elif choice in valid:
+            return valid[choice]
+        else:
+            sys.stdout.write("Please respond with 'yes' or 'no' " "(or 'y' or 'n').\n")
+
+
+def cli_detect(argv: list[str] | None = None) -> int:
+    """
+    CLI assistant using ARGV and ArgumentParser
+    :param argv:
+    :return: 0 if everything is fine, anything else equal trouble
+    """
+    parser = argparse.ArgumentParser(
+        description="The Real First Universal Charset Detector. "
+        "Discover originating encoding used on text file. "
+        "Normalize text to unicode."
+    )
+
+    parser.add_argument(
+        "files", type=argparse.FileType("rb"), nargs="+", help="File(s) to be analysed"
+    )
+    parser.add_argument(
+        "-v",
+        "--verbose",
+        action="store_true",
+        default=False,
+        dest="verbose",
+        help="Display complementary information about file if any. "
+        "Stdout will contain logs about the detection process.",
+    )
+    parser.add_argument(
+        "-a",
+        "--with-alternative",
+        action="store_true",
+        default=False,
+        dest="alternatives",
+        help="Output complementary possibilities if any. Top-level JSON WILL be a list.",
+    )
+    parser.add_argument(
+        "-n",
+        "--normalize",
+        action="store_true",
+        default=False,
+        dest="normalize",
+        help="Permit to normalize input file. If not set, program does not write anything.",
+    )
+    parser.add_argument(
+        "-m",
+        "--minimal",
+        action="store_true",
+        default=False,
+        dest="minimal",
+        help="Only output the charset detected to STDOUT. Disabling JSON output.",
+    )
+    parser.add_argument(
+        "-r",
+        "--replace",
+        action="store_true",
+        default=False,
+        dest="replace",
+        help="Replace file when trying to normalize it instead of creating a new one.",
+    )
+    parser.add_argument(
+        "-f",
+        "--force",
+        action="store_true",
+        default=False,
+        dest="force",
+        help="Replace file without asking if you are sure, use this flag with caution.",
+    )
+    parser.add_argument(
+        "-i",
+        "--no-preemptive",
+        action="store_true",
+        default=False,
+        dest="no_preemptive",
+        help="Disable looking at a charset declaration to hint the detector.",
+    )
+    parser.add_argument(
+        "-t",
+        "--threshold",
+        action="store",
+        default=0.2,
+        type=float,
+        dest="threshold",
+        help="Define a custom maximum amount of noise allowed in decoded content. 0. <= noise <= 1.",
+    )
+    parser.add_argument(
+        "--version",
+        action="version",
+        version="Charset-Normalizer {} - Python {} - Unicode {} - SpeedUp {}".format(
+            __version__,
+            python_version(),
+            unidata_version,
+            "OFF" if md_module.__file__.lower().endswith(".py") else "ON",
+        ),
+        help="Show version information and exit.",
+    )
+
+    args = parser.parse_args(argv)
+
+    if args.replace is True and args.normalize is False:
+        if args.files:
+            for my_file in args.files:
+                my_file.close()
+        print("Use --replace in addition of --normalize only.", file=sys.stderr)
+        return 1
+
+    if args.force is True and args.replace is False:
+        if args.files:
+            for my_file in args.files:
+                my_file.close()
+        print("Use --force in addition of --replace only.", file=sys.stderr)
+        return 1
+
+    if args.threshold < 0.0 or args.threshold > 1.0:
+        if args.files:
+            for my_file in args.files:
+                my_file.close()
+        print("--threshold VALUE should be between 0. AND 1.", file=sys.stderr)
+        return 1
+
+    x_ = []
+
+    for my_file in args.files:
+        matches = from_fp(
+            my_file,
+            threshold=args.threshold,
+            explain=args.verbose,
+            preemptive_behaviour=args.no_preemptive is False,
+        )
+
+        best_guess = matches.best()
+
+        if best_guess is None:
+            print(
+                'Unable to identify originating encoding for "{}". {}'.format(
+                    my_file.name,
+                    (
+                        "Maybe try increasing maximum amount of chaos."
+                        if args.threshold < 1.0
+                        else ""
+                    ),
+                ),
+                file=sys.stderr,
+            )
+            x_.append(
+                CliDetectionResult(
+                    abspath(my_file.name),
+                    None,
+                    [],
+                    [],
+                    "Unknown",
+                    [],
+                    False,
+                    1.0,
+                    0.0,
+                    None,
+                    True,
+                )
+            )
+        else:
+            x_.append(
+                CliDetectionResult(
+                    abspath(my_file.name),
+                    best_guess.encoding,
+                    best_guess.encoding_aliases,
+                    [
+                        cp
+                        for cp in best_guess.could_be_from_charset
+                        if cp != best_guess.encoding
+                    ],
+                    best_guess.language,
+                    best_guess.alphabets,
+                    best_guess.bom,
+                    best_guess.percent_chaos,
+                    best_guess.percent_coherence,
+                    None,
+                    True,
+                )
+            )
+
+            if len(matches) > 1 and args.alternatives:
+                for el in matches:
+                    if el != best_guess:
+                        x_.append(
+                            CliDetectionResult(
+                                abspath(my_file.name),
+                                el.encoding,
+                                el.encoding_aliases,
+                                [
+                                    cp
+                                    for cp in el.could_be_from_charset
+                                    if cp != el.encoding
+                                ],
+                                el.language,
+                                el.alphabets,
+                                el.bom,
+                                el.percent_chaos,
+                                el.percent_coherence,
+                                None,
+                                False,
+                            )
+                        )
+
+            if args.normalize is True:
+                if best_guess.encoding.startswith("utf") is True:
+                    print(
+                        '"{}" file does not need to be normalized, as it already came from unicode.'.format(
+                            my_file.name
+                        ),
+                        file=sys.stderr,
+                    )
+                    if my_file.closed is False:
+                        my_file.close()
+                    continue
+
+                dir_path = dirname(realpath(my_file.name))
+                file_name = basename(realpath(my_file.name))
+
+                o_: list[str] = file_name.split(".")
+
+                if args.replace is False:
+                    o_.insert(-1, best_guess.encoding)
+                    if my_file.closed is False:
+                        my_file.close()
+                elif (
+                    args.force is False
+                    and query_yes_no(
+                        'Are you sure to normalize "{}" by replacing it ?'.format(
+                            my_file.name
+                        ),
+                        "no",
+                    )
+                    is False
+                ):
+                    if my_file.closed is False:
+                        my_file.close()
+                    continue
+
+                try:
+                    x_[0].unicode_path = join(dir_path, ".".join(o_))
+
+                    with open(x_[0].unicode_path, "wb") as fp:
+                        fp.write(best_guess.output())
+                except OSError as e:
+                    print(str(e), file=sys.stderr)
+                    if my_file.closed is False:
+                        my_file.close()
+                    return 2
+
+        if my_file.closed is False:
+            my_file.close()
+
+    if args.minimal is False:
+        print(
+            dumps(
+                [el.__dict__ for el in x_] if len(x_) > 1 else x_[0].__dict__,
+                ensure_ascii=True,
+                indent=4,
+            )
+        )
+    else:
+        for my_file in args.files:
+            print(
+                ", ".join(
+                    [
+                        el.encoding or "undefined"
+                        for el in x_
+                        if el.path == abspath(my_file.name)
+                    ]
+                )
+            )
+
+    return 0
+
+
+if __name__ == "__main__":
+    cli_detect()

venv/lib/python3.11/site-packages/charset_normalizer/legacy.py

@@ -0,0 +1,66 @@
+from __future__ import annotations
+
+from typing import TYPE_CHECKING, Any
+from warnings import warn
+
+from .api import from_bytes
+from .constant import CHARDET_CORRESPONDENCE
+
+# TODO: remove this check when dropping Python 3.7 support
+if TYPE_CHECKING:
+    from typing_extensions import TypedDict
+
+    class ResultDict(TypedDict):
+        encoding: str | None
+        language: str
+        confidence: float | None
+
+
+def detect(
+    byte_str: bytes, should_rename_legacy: bool = False, **kwargs: Any
+) -> ResultDict:
+    """
+    chardet legacy method
+    Detect the encoding of the given byte string. It should be mostly backward-compatible.
+    Encoding name will match Chardet own writing whenever possible. (Not on encoding name unsupported by it)
+    This function is deprecated and should be used to migrate your project easily, consult the documentation for
+    further information. Not planned for removal.
+
+    :param byte_str:     The byte sequence to examine.
+    :param should_rename_legacy:  Should we rename legacy encodings
+                                  to their more modern equivalents?
+    """
+    if len(kwargs):
+        warn(
+            f"charset-normalizer disregard arguments '{','.join(list(kwargs.keys()))}' in legacy function detect()"
+        )
+
+    if not isinstance(byte_str, (bytearray, bytes)):
+        raise TypeError(  # pragma: nocover
+            "Expected object of type bytes or bytearray, got: " "{}".format(
+                type(byte_str)
+            )
+        )
+
+    if isinstance(byte_str, bytearray):
+        byte_str = bytes(byte_str)
+
+    r = from_bytes(byte_str).best()
+
+    encoding = r.encoding if r is not None else None
+    language = r.language if r is not None and r.language != "Unknown" else ""
+    confidence = 1.0 - r.chaos if r is not None else None
+
+    # Note: CharsetNormalizer does not return 'UTF-8-SIG' as the sig get stripped in the detection/normalization process
+    # but chardet does return 'utf-8-sig' and it is a valid codec name.
+    if r is not None and encoding == "utf_8" and r.bom:
+        encoding += "_sig"
+
+    if should_rename_legacy is False and encoding in CHARDET_CORRESPONDENCE:
+        encoding = CHARDET_CORRESPONDENCE[encoding]
+
+    return {
+        "encoding": encoding,
+        "language": language,
+        "confidence": confidence,
+    }

venv/lib/python3.11/site-packages/charset_normalizer/md.py

@@ -0,0 +1,630 @@
+from __future__ import annotations
+
+from functools import lru_cache
+from logging import getLogger
+
+from .constant import (
+    COMMON_SAFE_ASCII_CHARACTERS,
+    TRACE,
+    UNICODE_SECONDARY_RANGE_KEYWORD,
+)
+from .utils import (
+    is_accentuated,
+    is_arabic,
+    is_arabic_isolated_form,
+    is_case_variable,
+    is_cjk,
+    is_emoticon,
+    is_hangul,
+    is_hiragana,
+    is_katakana,
+    is_latin,
+    is_punctuation,
+    is_separator,
+    is_symbol,
+    is_thai,
+    is_unprintable,
+    remove_accent,
+    unicode_range,
+)
+
+
+class MessDetectorPlugin:
+    """
+    Base abstract class used for mess detection plugins.
+    All detectors MUST extend and implement given methods.
+    """
+
+    def eligible(self, character: str) -> bool:
+        """
+        Determine if given character should be fed in.
+        """
+        raise NotImplementedError  # pragma: nocover
+
+    def feed(self, character: str) -> None:
+        """
+        The main routine to be executed upon character.
+        Insert the logic in witch the text would be considered chaotic.
+        """
+        raise NotImplementedError  # pragma: nocover
+
+    def reset(self) -> None:  # pragma: no cover
+        """
+        Permit to reset the plugin to the initial state.
+        """
+        raise NotImplementedError
+
+    @property
+    def ratio(self) -> float:
+        """
+        Compute the chaos ratio based on what your feed() has seen.
+        Must NOT be lower than 0.; No restriction gt 0.
+        """
+        raise NotImplementedError  # pragma: nocover
+
+
+class TooManySymbolOrPunctuationPlugin(MessDetectorPlugin):
+    def __init__(self) -> None:
+        self._punctuation_count: int = 0
+        self._symbol_count: int = 0
+        self._character_count: int = 0
+
+        self._last_printable_char: str | None = None
+        self._frenzy_symbol_in_word: bool = False
+
+    def eligible(self, character: str) -> bool:
+        return character.isprintable()
+
+    def feed(self, character: str) -> None:
+        self._character_count += 1
+
+        if (
+            character != self._last_printable_char
+            and character not in COMMON_SAFE_ASCII_CHARACTERS
+        ):
+            if is_punctuation(character):
+                self._punctuation_count += 1
+            elif (
+                character.isdigit() is False
+                and is_symbol(character)
+                and is_emoticon(character) is False
+            ):
+                self._symbol_count += 2
+
+        self._last_printable_char = character
+
+    def reset(self) -> None:  # Abstract
+        self._punctuation_count = 0
+        self._character_count = 0
+        self._symbol_count = 0
+
+    @property
+    def ratio(self) -> float:
+        if self._character_count == 0:
+            return 0.0
+
+        ratio_of_punctuation: float = (
+            self._punctuation_count + self._symbol_count
+        ) / self._character_count
+
+        return ratio_of_punctuation if ratio_of_punctuation >= 0.3 else 0.0
+
+
+class TooManyAccentuatedPlugin(MessDetectorPlugin):
+    def __init__(self) -> None:
+        self._character_count: int = 0
+        self._accentuated_count: int = 0
+
+    def eligible(self, character: str) -> bool:
+        return character.isalpha()
+
+    def feed(self, character: str) -> None:
+        self._character_count += 1
+
+        if is_accentuated(character):
+            self._accentuated_count += 1
+
+    def reset(self) -> None:  # Abstract
+        self._character_count = 0
+        self._accentuated_count = 0
+
+    @property
+    def ratio(self) -> float:
+        if self._character_count < 8:
+            return 0.0
+
+        ratio_of_accentuation: float = self._accentuated_count / self._character_count
+        return ratio_of_accentuation if ratio_of_accentuation >= 0.35 else 0.0
+
+
+class UnprintablePlugin(MessDetectorPlugin):
+    def __init__(self) -> None:
+        self._unprintable_count: int = 0
+        self._character_count: int = 0
+
+    def eligible(self, character: str) -> bool:
+        return True
+
+    def feed(self, character: str) -> None:
+        if is_unprintable(character):
+            self._unprintable_count += 1
+        self._character_count += 1
+
+    def reset(self) -> None:  # Abstract
+        self._unprintable_count = 0
+
+    @property
+    def ratio(self) -> float:
+        if self._character_count == 0:
+            return 0.0
+
+        return (self._unprintable_count * 8) / self._character_count
+
+
+class SuspiciousDuplicateAccentPlugin(MessDetectorPlugin):
+    def __init__(self) -> None:
+        self._successive_count: int = 0
+        self._character_count: int = 0
+
+        self._last_latin_character: str | None = None
+
+    def eligible(self, character: str) -> bool:
+        return character.isalpha() and is_latin(character)
+
+    def feed(self, character: str) -> None:
+        self._character_count += 1
+        if (
+            self._last_latin_character is not None
+            and is_accentuated(character)
+            and is_accentuated(self._last_latin_character)
+        ):
+            if character.isupper() and self._last_latin_character.isupper():
+                self._successive_count += 1
+            # Worse if its the same char duplicated with different accent.
+            if remove_accent(character) == remove_accent(self._last_latin_character):
+                self._successive_count += 1
+        self._last_latin_character = character
+
+    def reset(self) -> None:  # Abstract
+        self._successive_count = 0
+        self._character_count = 0
+        self._last_latin_character = None
+
+    @property
+    def ratio(self) -> float:
+        if self._character_count == 0:
+            return 0.0
+
+        return (self._successive_count * 2) / self._character_count
+
+
+class SuspiciousRange(MessDetectorPlugin):
+    def __init__(self) -> None:
+        self._suspicious_successive_range_count: int = 0
+        self._character_count: int = 0
+        self._last_printable_seen: str | None = None
+
+    def eligible(self, character: str) -> bool:
+        return character.isprintable()
+
+    def feed(self, character: str) -> None:
+        self._character_count += 1
+
+        if (
+            character.isspace()
+            or is_punctuation(character)
+            or character in COMMON_SAFE_ASCII_CHARACTERS
+        ):
+            self._last_printable_seen = None
+            return
+
+        if self._last_printable_seen is None:
+            self._last_printable_seen = character
+            return
+
+        unicode_range_a: str | None = unicode_range(self._last_printable_seen)
+        unicode_range_b: str | None = unicode_range(character)
+
+        if is_suspiciously_successive_range(unicode_range_a, unicode_range_b):
+            self._suspicious_successive_range_count += 1
+
+        self._last_printable_seen = character
+
+    def reset(self) -> None:  # Abstract
+        self._character_count = 0
+        self._suspicious_successive_range_count = 0
+        self._last_printable_seen = None
+
+    @property
+    def ratio(self) -> float:
+        if self._character_count <= 13:
+            return 0.0
+
+        ratio_of_suspicious_range_usage: float = (
+            self._suspicious_successive_range_count * 2
+        ) / self._character_count
+
+        return ratio_of_suspicious_range_usage
+
+
+class SuperWeirdWordPlugin(MessDetectorPlugin):
+    def __init__(self) -> None:
+        self._word_count: int = 0
+        self._bad_word_count: int = 0
+        self._foreign_long_count: int = 0
+
+        self._is_current_word_bad: bool = False
+        self._foreign_long_watch: bool = False
+
+        self._character_count: int = 0
+        self._bad_character_count: int = 0
+
+        self._buffer: str = ""
+        self._buffer_accent_count: int = 0
+        self._buffer_glyph_count: int = 0
+
+    def eligible(self, character: str) -> bool:
+        return True
+
+    def feed(self, character: str) -> None:
+        if character.isalpha():
+            self._buffer += character
+            if is_accentuated(character):
+                self._buffer_accent_count += 1
+            if (
+                self._foreign_long_watch is False
+                and (is_latin(character) is False or is_accentuated(character))
+                and is_cjk(character) is False
+                and is_hangul(character) is False
+                and is_katakana(character) is False
+                and is_hiragana(character) is False
+                and is_thai(character) is False
+            ):
+                self._foreign_long_watch = True
+            if (
+                is_cjk(character)
+                or is_hangul(character)
+                or is_katakana(character)
+                or is_hiragana(character)
+                or is_thai(character)
+            ):
+                self._buffer_glyph_count += 1
+            return
+        if not self._buffer:
+            return
+        if (
+            character.isspace() or is_punctuation(character) or is_separator(character)
+        ) and self._buffer:
+            self._word_count += 1
+            buffer_length: int = len(self._buffer)
+
+            self._character_count += buffer_length
+
+            if buffer_length >= 4:
+                if self._buffer_accent_count / buffer_length >= 0.5:
+                    self._is_current_word_bad = True
+                # Word/Buffer ending with an upper case accentuated letter are so rare,
+                # that we will consider them all as suspicious. Same weight as foreign_long suspicious.
+                elif (
+                    is_accentuated(self._buffer[-1])
+                    and self._buffer[-1].isupper()
+                    and all(_.isupper() for _ in self._buffer) is False
+                ):
+                    self._foreign_long_count += 1
+                    self._is_current_word_bad = True
+                elif self._buffer_glyph_count == 1:
+                    self._is_current_word_bad = True
+                    self._foreign_long_count += 1
+            if buffer_length >= 24 and self._foreign_long_watch:
+                camel_case_dst = [
+                    i
+                    for c, i in zip(self._buffer, range(0, buffer_length))
+                    if c.isupper()
+                ]
+                probable_camel_cased: bool = False
+
+                if camel_case_dst and (len(camel_case_dst) / buffer_length <= 0.3):
+                    probable_camel_cased = True
+
+                if not probable_camel_cased:
+                    self._foreign_long_count += 1
+                    self._is_current_word_bad = True
+
+            if self._is_current_word_bad:
+                self._bad_word_count += 1
+                self._bad_character_count += len(self._buffer)
+                self._is_current_word_bad = False
+
+            self._foreign_long_watch = False
+            self._buffer = ""
+            self._buffer_accent_count = 0
+            self._buffer_glyph_count = 0
+        elif (
+            character not in {"<", ">", "-", "=", "~", "|", "_"}
+            and character.isdigit() is False
+            and is_symbol(character)
+        ):
+            self._is_current_word_bad = True
+            self._buffer += character
+
+    def reset(self) -> None:  # Abstract
+        self._buffer = ""
+        self._is_current_word_bad = False
+        self._foreign_long_watch = False
+        self._bad_word_count = 0
+        self._word_count = 0
+        self._character_count = 0
+        self._bad_character_count = 0
+        self._foreign_long_count = 0
+
+    @property
+    def ratio(self) -> float:
+        if self._word_count <= 10 and self._foreign_long_count == 0:
+            return 0.0
+
+        return self._bad_character_count / self._character_count
+
+
+class CjkInvalidStopPlugin(MessDetectorPlugin):
+    """
+    GB(Chinese) based encoding often render the stop incorrectly when the content does not fit and
+    can be easily detected. Searching for the overuse of '丅' and '丄'.
+    """
+
+    def __init__(self) -> None:
+        self._wrong_stop_count: int = 0
+        self._cjk_character_count: int = 0
+
+    def eligible(self, character: str) -> bool:
+        return True
+
+    def feed(self, character: str) -> None:
+        if character in {"丅", "丄"}:
+            self._wrong_stop_count += 1
+            return
+        if is_cjk(character):
+            self._cjk_character_count += 1
+
+    def reset(self) -> None:  # Abstract
+        self._wrong_stop_count = 0
+        self._cjk_character_count = 0
+
+    @property
+    def ratio(self) -> float:
+        if self._cjk_character_count < 16:
+            return 0.0
+        return self._wrong_stop_count / self._cjk_character_count
+
+
+class ArchaicUpperLowerPlugin(MessDetectorPlugin):
+    def __init__(self) -> None:
+        self._buf: bool = False
+
+        self._character_count_since_last_sep: int = 0
+
+        self._successive_upper_lower_count: int = 0
+        self._successive_upper_lower_count_final: int = 0
+
+        self._character_count: int = 0
+
+        self._last_alpha_seen: str | None = None
+        self._current_ascii_only: bool = True
+
+    def eligible(self, character: str) -> bool:
+        return True
+
+    def feed(self, character: str) -> None:
+        is_concerned = character.isalpha() and is_case_variable(character)
+        chunk_sep = is_concerned is False
+
+        if chunk_sep and self._character_count_since_last_sep > 0:
+            if (
+                self._character_count_since_last_sep <= 64
+                and character.isdigit() is False
+                and self._current_ascii_only is False
+            ):
+                self._successive_upper_lower_count_final += (
+                    self._successive_upper_lower_count
+                )
+
+            self._successive_upper_lower_count = 0
+            self._character_count_since_last_sep = 0
+            self._last_alpha_seen = None
+            self._buf = False
+            self._character_count += 1
+            self._current_ascii_only = True
+
+            return
+
+        if self._current_ascii_only is True and character.isascii() is False:
+            self._current_ascii_only = False
+
+        if self._last_alpha_seen is not None:
+            if (character.isupper() and self._last_alpha_seen.islower()) or (
+                character.islower() and self._last_alpha_seen.isupper()
+            ):
+                if self._buf is True:
+                    self._successive_upper_lower_count += 2
+                    self._buf = False
+                else:
+                    self._buf = True
+            else:
+                self._buf = False
+
+        self._character_count += 1
+        self._character_count_since_last_sep += 1
+        self._last_alpha_seen = character
+
+    def reset(self) -> None:  # Abstract
+        self._character_count = 0
+        self._character_count_since_last_sep = 0
+        self._successive_upper_lower_count = 0
+        self._successive_upper_lower_count_final = 0
+        self._last_alpha_seen = None
+        self._buf = False
+        self._current_ascii_only = True
+
+    @property
+    def ratio(self) -> float:
+        if self._character_count == 0:
+            return 0.0
+
+        return self._successive_upper_lower_count_final / self._character_count
+
+
+class ArabicIsolatedFormPlugin(MessDetectorPlugin):
+    def __init__(self) -> None:
+        self._character_count: int = 0
+        self._isolated_form_count: int = 0
+
+    def reset(self) -> None:  # Abstract
+        self._character_count = 0
+        self._isolated_form_count = 0
+
+    def eligible(self, character: str) -> bool:
+        return is_arabic(character)
+
+    def feed(self, character: str) -> None:
+        self._character_count += 1
+
+        if is_arabic_isolated_form(character):
+            self._isolated_form_count += 1
+
+    @property
+    def ratio(self) -> float:
+        if self._character_count < 8:
+            return 0.0
+
+        isolated_form_usage: float = self._isolated_form_count / self._character_count
+
+        return isolated_form_usage
+
+
+@lru_cache(maxsize=1024)
+def is_suspiciously_successive_range(
+    unicode_range_a: str | None, unicode_range_b: str | None
+) -> bool:
+    """
+    Determine if two Unicode range seen next to each other can be considered as suspicious.
+    """
+    if unicode_range_a is None or unicode_range_b is None:
+        return True
+
+    if unicode_range_a == unicode_range_b:
+        return False
+
+    if "Latin" in unicode_range_a and "Latin" in unicode_range_b:
+        return False
+
+    if "Emoticons" in unicode_range_a or "Emoticons" in unicode_range_b:
+        return False
+
+    # Latin characters can be accompanied with a combining diacritical mark
+    # eg. Vietnamese.
+    if ("Latin" in unicode_range_a or "Latin" in unicode_range_b) and (
+        "Combining" in unicode_range_a or "Combining" in unicode_range_b
+    ):
+        return False
+
+    keywords_range_a, keywords_range_b = (
+        unicode_range_a.split(" "),
+        unicode_range_b.split(" "),
+    )
+
+    for el in keywords_range_a:
+        if el in UNICODE_SECONDARY_RANGE_KEYWORD:
+            continue
+        if el in keywords_range_b:
+            return False
+
+    # Japanese Exception
+    range_a_jp_chars, range_b_jp_chars = (
+        unicode_range_a
+        in (
+            "Hiragana",
+            "Katakana",
+        ),
+        unicode_range_b in ("Hiragana", "Katakana"),
+    )
+    if (range_a_jp_chars or range_b_jp_chars) and (
+        "CJK" in unicode_range_a or "CJK" in unicode_range_b
+    ):
+        return False
+    if range_a_jp_chars and range_b_jp_chars:
+        return False
+
+    if "Hangul" in unicode_range_a or "Hangul" in unicode_range_b:
+        if "CJK" in unicode_range_a or "CJK" in unicode_range_b:
+            return False
+        if unicode_range_a == "Basic Latin" or unicode_range_b == "Basic Latin":
+            return False
+
+    # Chinese/Japanese use dedicated range for punctuation and/or separators.
+    if ("CJK" in unicode_range_a or "CJK" in unicode_range_b) or (
+        unicode_range_a in ["Katakana", "Hiragana"]
+        and unicode_range_b in ["Katakana", "Hiragana"]
+    ):
+        if "Punctuation" in unicode_range_a or "Punctuation" in unicode_range_b:
+            return False
+        if "Forms" in unicode_range_a or "Forms" in unicode_range_b:
+            return False
+        if unicode_range_a == "Basic Latin" or unicode_range_b == "Basic Latin":
+            return False
+
+    return True
+
+
+@lru_cache(maxsize=2048)
+def mess_ratio(
+    decoded_sequence: str, maximum_threshold: float = 0.2, debug: bool = False
+) -> float:
+    """
+    Compute a mess ratio given a decoded bytes sequence. The maximum threshold does stop the computation earlier.
+    """
+
+    detectors: list[MessDetectorPlugin] = [
+        md_class() for md_class in MessDetectorPlugin.__subclasses__()
+    ]
+
+    length: int = len(decoded_sequence) + 1
+
+    mean_mess_ratio: float = 0.0
+
+    if length < 512:
+        intermediary_mean_mess_ratio_calc: int = 32
+    elif length <= 1024:
+        intermediary_mean_mess_ratio_calc = 64
+    else:
+        intermediary_mean_mess_ratio_calc = 128
+
+    for character, index in zip(decoded_sequence + "\n", range(length)):
+        for detector in detectors:
+            if detector.eligible(character):
+                detector.feed(character)
+
+        if (
+            index > 0 and index % intermediary_mean_mess_ratio_calc == 0
+        ) or index == length - 1:
+            mean_mess_ratio = sum(dt.ratio for dt in detectors)
+
+            if mean_mess_ratio >= maximum_threshold:
+                break
+
+    if debug:
+        logger = getLogger("charset_normalizer")
+
+        logger.log(
+            TRACE,
+            "Mess-detector extended-analysis start. "
+            f"intermediary_mean_mess_ratio_calc={intermediary_mean_mess_ratio_calc} mean_mess_ratio={mean_mess_ratio} "
+            f"maximum_threshold={maximum_threshold}",
+        )
+
+        if len(decoded_sequence) > 16:
+            logger.log(TRACE, f"Starting with: {decoded_sequence[:16]}")
+            logger.log(TRACE, f"Ending with: {decoded_sequence[-16::]}")
+
+        for dt in detectors:
+            logger.log(TRACE, f"{dt.__class__}: {dt.ratio}")
+
+    return round(mean_mess_ratio, 3)

venv/lib/python3.11/site-packages/charset_normalizer/models.py

@@ -0,0 +1,360 @@
+from __future__ import annotations
+
+from encodings.aliases import aliases
+from hashlib import sha256
+from json import dumps
+from re import sub
+from typing import Any, Iterator, List, Tuple
+
+from .constant import RE_POSSIBLE_ENCODING_INDICATION, TOO_BIG_SEQUENCE
+from .utils import iana_name, is_multi_byte_encoding, unicode_range
+
+
+class CharsetMatch:
+    def __init__(
+        self,
+        payload: bytes,
+        guessed_encoding: str,
+        mean_mess_ratio: float,
+        has_sig_or_bom: bool,
+        languages: CoherenceMatches,
+        decoded_payload: str | None = None,
+        preemptive_declaration: str | None = None,
+    ):
+        self._payload: bytes = payload
+
+        self._encoding: str = guessed_encoding
+        self._mean_mess_ratio: float = mean_mess_ratio
+        self._languages: CoherenceMatches = languages
+        self._has_sig_or_bom: bool = has_sig_or_bom
+        self._unicode_ranges: list[str] | None = None
+
+        self._leaves: list[CharsetMatch] = []
+        self._mean_coherence_ratio: float = 0.0
+
+        self._output_payload: bytes | None = None
+        self._output_encoding: str | None = None
+
+        self._string: str | None = decoded_payload
+
+        self._preemptive_declaration: str | None = preemptive_declaration
+
+    def __eq__(self, other: object) -> bool:
+        if not isinstance(other, CharsetMatch):
+            if isinstance(other, str):
+                return iana_name(other) == self.encoding
+            return False
+        return self.encoding == other.encoding and self.fingerprint == other.fingerprint
+
+    def __lt__(self, other: object) -> bool:
+        """
+        Implemented to make sorted available upon CharsetMatches items.
+        """
+        if not isinstance(other, CharsetMatch):
+            raise ValueError
+
+        chaos_difference: float = abs(self.chaos - other.chaos)
+        coherence_difference: float = abs(self.coherence - other.coherence)
+
+        # Below 1% difference --> Use Coherence
+        if chaos_difference < 0.01 and coherence_difference > 0.02:
+            return self.coherence > other.coherence
+        elif chaos_difference < 0.01 and coherence_difference <= 0.02:
+            # When having a difficult decision, use the result that decoded as many multi-byte as possible.
+            # preserve RAM usage!
+            if len(self._payload) >= TOO_BIG_SEQUENCE:
+                return self.chaos < other.chaos
+            return self.multi_byte_usage > other.multi_byte_usage
+
+        return self.chaos < other.chaos
+
+    @property
+    def multi_byte_usage(self) -> float:
+        return 1.0 - (len(str(self)) / len(self.raw))
+
+    def __str__(self) -> str:
+        # Lazy Str Loading
+        if self._string is None:
+            self._string = str(self._payload, self._encoding, "strict")
+        return self._string
+
+    def __repr__(self) -> str:
+        return f"<CharsetMatch '{self.encoding}' bytes({self.fingerprint})>"
+
+    def add_submatch(self, other: CharsetMatch) -> None:
+        if not isinstance(other, CharsetMatch) or other == self:
+            raise ValueError(
+                "Unable to add instance <{}> as a submatch of a CharsetMatch".format(
+                    other.__class__
+                )
+            )
+
+        other._string = None  # Unload RAM usage; dirty trick.
+        self._leaves.append(other)
+
+    @property
+    def encoding(self) -> str:
+        return self._encoding
+
+    @property
+    def encoding_aliases(self) -> list[str]:
+        """
+        Encoding name are known by many name, using this could help when searching for IBM855 when it's listed as CP855.
+        """
+        also_known_as: list[str] = []
+        for u, p in aliases.items():
+            if self.encoding == u:
+                also_known_as.append(p)
+            elif self.encoding == p:
+                also_known_as.append(u)
+        return also_known_as
+
+    @property
+    def bom(self) -> bool:
+        return self._has_sig_or_bom
+
+    @property
+    def byte_order_mark(self) -> bool:
+        return self._has_sig_or_bom
+
+    @property
+    def languages(self) -> list[str]:
+        """
+        Return the complete list of possible languages found in decoded sequence.
+        Usually not really useful. Returned list may be empty even if 'language' property return something != 'Unknown'.
+        """
+        return [e[0] for e in self._languages]
+
+    @property
+    def language(self) -> str:
+        """
+        Most probable language found in decoded sequence. If none were detected or inferred, the property will return
+        "Unknown".
+        """
+        if not self._languages:
+            # Trying to infer the language based on the given encoding
+            # Its either English or we should not pronounce ourselves in certain cases.
+            if "ascii" in self.could_be_from_charset:
+                return "English"
+
+            # doing it there to avoid circular import
+            from charset_normalizer.cd import encoding_languages, mb_encoding_languages
+
+            languages = (
+                mb_encoding_languages(self.encoding)
+                if is_multi_byte_encoding(self.encoding)
+                else encoding_languages(self.encoding)
+            )
+
+            if len(languages) == 0 or "Latin Based" in languages:
+                return "Unknown"
+
+            return languages[0]
+
+        return self._languages[0][0]
+
+    @property
+    def chaos(self) -> float:
+        return self._mean_mess_ratio
+
+    @property
+    def coherence(self) -> float:
+        if not self._languages:
+            return 0.0
+        return self._languages[0][1]
+
+    @property
+    def percent_chaos(self) -> float:
+        return round(self.chaos * 100, ndigits=3)
+
+    @property
+    def percent_coherence(self) -> float:
+        return round(self.coherence * 100, ndigits=3)
+
+    @property
+    def raw(self) -> bytes:
+        """
+        Original untouched bytes.
+        """
+        return self._payload
+
+    @property
+    def submatch(self) -> list[CharsetMatch]:
+        return self._leaves
+
+    @property
+    def has_submatch(self) -> bool:
+        return len(self._leaves) > 0
+
+    @property
+    def alphabets(self) -> list[str]:
+        if self._unicode_ranges is not None:
+            return self._unicode_ranges
+        # list detected ranges
+        detected_ranges: list[str | None] = [unicode_range(char) for char in str(self)]
+        # filter and sort
+        self._unicode_ranges = sorted(list({r for r in detected_ranges if r}))
+        return self._unicode_ranges
+
+    @property
+    def could_be_from_charset(self) -> list[str]:
+        """
+        The complete list of encoding that output the exact SAME str result and therefore could be the originating
+        encoding.
+        This list does include the encoding available in property 'encoding'.
+        """
+        return [self._encoding] + [m.encoding for m in self._leaves]
+
+    def output(self, encoding: str = "utf_8") -> bytes:
+        """
+        Method to get re-encoded bytes payload using given target encoding. Default to UTF-8.
+        Any errors will be simply ignored by the encoder NOT replaced.
+        """
+        if self._output_encoding is None or self._output_encoding != encoding:
+            self._output_encoding = encoding
+            decoded_string = str(self)
+            if (
+                self._preemptive_declaration is not None
+                and self._preemptive_declaration.lower()
+                not in ["utf-8", "utf8", "utf_8"]
+            ):
+                patched_header = sub(
+                    RE_POSSIBLE_ENCODING_INDICATION,
+                    lambda m: m.string[m.span()[0] : m.span()[1]].replace(
+                        m.groups()[0],
+                        iana_name(self._output_encoding).replace("_", "-"),  # type: ignore[arg-type]
+                    ),
+                    decoded_string[:8192],
+                    count=1,
+                )
+
+                decoded_string = patched_header + decoded_string[8192:]
+
+            self._output_payload = decoded_string.encode(encoding, "replace")
+
+        return self._output_payload  # type: ignore
+
+    @property
+    def fingerprint(self) -> str:
+        """
+        Retrieve the unique SHA256 computed using the transformed (re-encoded) payload. Not the original one.
+        """
+        return sha256(self.output()).hexdigest()
+
+
+class CharsetMatches:
+    """
+    Container with every CharsetMatch items ordered by default from most probable to the less one.
+    Act like a list(iterable) but does not implements all related methods.
+    """
+
+    def __init__(self, results: list[CharsetMatch] | None = None):
+        self._results: list[CharsetMatch] = sorted(results) if results else []
+
+    def __iter__(self) -> Iterator[CharsetMatch]:
+        yield from self._results
+
+    def __getitem__(self, item: int | str) -> CharsetMatch:
+        """
+        Retrieve a single item either by its position or encoding name (alias may be used here).
+        Raise KeyError upon invalid index or encoding not present in results.
+        """
+        if isinstance(item, int):
+            return self._results[item]
+        if isinstance(item, str):
+            item = iana_name(item, False)
+            for result in self._results:
+                if item in result.could_be_from_charset:
+                    return result
+        raise KeyError
+
+    def __len__(self) -> int:
+        return len(self._results)
+
+    def __bool__(self) -> bool:
+        return len(self._results) > 0
+
+    def append(self, item: CharsetMatch) -> None:
+        """
+        Insert a single match. Will be inserted accordingly to preserve sort.
+        Can be inserted as a submatch.
+        """
+        if not isinstance(item, CharsetMatch):
+            raise ValueError(
+                "Cannot append instance '{}' to CharsetMatches".format(
+                    str(item.__class__)
+                )
+            )
+        # We should disable the submatch factoring when the input file is too heavy (conserve RAM usage)
+        if len(item.raw) < TOO_BIG_SEQUENCE:
+            for match in self._results:
+                if match.fingerprint == item.fingerprint and match.chaos == item.chaos:
+                    match.add_submatch(item)
+                    return
+        self._results.append(item)
+        self._results = sorted(self._results)
+
+    def best(self) -> CharsetMatch | None:
+        """
+        Simply return the first match. Strict equivalent to matches[0].
+        """
+        if not self._results:
+            return None
+        return self._results[0]
+
+    def first(self) -> CharsetMatch | None:
+        """
+        Redundant method, call the method best(). Kept for BC reasons.
+        """
+        return self.best()
+
+
+CoherenceMatch = Tuple[str, float]
+CoherenceMatches = List[CoherenceMatch]
+
+
+class CliDetectionResult:
+    def __init__(
+        self,
+        path: str,
+        encoding: str | None,
+        encoding_aliases: list[str],
+        alternative_encodings: list[str],
+        language: str,
+        alphabets: list[str],
+        has_sig_or_bom: bool,
+        chaos: float,
+        coherence: float,
+        unicode_path: str | None,
+        is_preferred: bool,
+    ):
+        self.path: str = path
+        self.unicode_path: str | None = unicode_path
+        self.encoding: str | None = encoding
+        self.encoding_aliases: list[str] = encoding_aliases
+        self.alternative_encodings: list[str] = alternative_encodings
+        self.language: str = language
+        self.alphabets: list[str] = alphabets
+        self.has_sig_or_bom: bool = has_sig_or_bom
+        self.chaos: float = chaos
+        self.coherence: float = coherence
+        self.is_preferred: bool = is_preferred
+
+    @property
+    def __dict__(self) -> dict[str, Any]:  # type: ignore
+        return {
+            "path": self.path,
+            "encoding": self.encoding,
+            "encoding_aliases": self.encoding_aliases,
+            "alternative_encodings": self.alternative_encodings,
+            "language": self.language,
+            "alphabets": self.alphabets,
+            "has_sig_or_bom": self.has_sig_or_bom,
+            "chaos": self.chaos,
+            "coherence": self.coherence,
+            "unicode_path": self.unicode_path,
+            "is_preferred": self.is_preferred,
+        }
+
+    def to_json(self) -> str:
+        return dumps(self.__dict__, ensure_ascii=True, indent=4)

venv/lib/python3.11/site-packages/charset_normalizer/utils.py

@@ -0,0 +1,408 @@
+from __future__ import annotations
+
+import importlib
+import logging
+import unicodedata
+from codecs import IncrementalDecoder
+from encodings.aliases import aliases
+from functools import lru_cache
+from re import findall
+from typing import Generator
+
+from _multibytecodec import (  # type: ignore[import-not-found,import]
+    MultibyteIncrementalDecoder,
+)
+
+from .constant import (
+    ENCODING_MARKS,
+    IANA_SUPPORTED_SIMILAR,
+    RE_POSSIBLE_ENCODING_INDICATION,
+    UNICODE_RANGES_COMBINED,
+    UNICODE_SECONDARY_RANGE_KEYWORD,
+    UTF8_MAXIMAL_ALLOCATION,
+)
+
+
+@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
+def is_accentuated(character: str) -> bool:
+    try:
+        description: str = unicodedata.name(character)
+    except ValueError:  # Defensive: unicode database outdated?
+        return False
+    return (
+        "WITH GRAVE" in description
+        or "WITH ACUTE" in description
+        or "WITH CEDILLA" in description
+        or "WITH DIAERESIS" in description
+        or "WITH CIRCUMFLEX" in description
+        or "WITH TILDE" in description
+        or "WITH MACRON" in description
+        or "WITH RING ABOVE" in description
+    )
+
+
+@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
+def remove_accent(character: str) -> str:
+    decomposed: str = unicodedata.decomposition(character)
+    if not decomposed:
+        return character
+
+    codes: list[str] = decomposed.split(" ")
+
+    return chr(int(codes[0], 16))
+
+
+@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
+def unicode_range(character: str) -> str | None:
+    """
+    Retrieve the Unicode range official name from a single character.
+    """
+    character_ord: int = ord(character)
+
+    for range_name, ord_range in UNICODE_RANGES_COMBINED.items():
+        if character_ord in ord_range:
+            return range_name
+
+    return None
+
+
+@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
+def is_latin(character: str) -> bool:
+    try:
+        description: str = unicodedata.name(character)
+    except ValueError:  # Defensive: unicode database outdated?
+        return False
+    return "LATIN" in description
+
+
+@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
+def is_punctuation(character: str) -> bool:
+    character_category: str = unicodedata.category(character)
+
+    if "P" in character_category:
+        return True
+
+    character_range: str | None = unicode_range(character)
+
+    if character_range is None:
+        return False
+
+    return "Punctuation" in character_range
+
+
+@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
+def is_symbol(character: str) -> bool:
+    character_category: str = unicodedata.category(character)
+
+    if "S" in character_category or "N" in character_category:
+        return True
+
+    character_range: str | None = unicode_range(character)
+
+    if character_range is None:
+        return False
+
+    return "Forms" in character_range and character_category != "Lo"
+
+
+@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
+def is_emoticon(character: str) -> bool:
+    character_range: str | None = unicode_range(character)
+
+    if character_range is None:
+        return False
+
+    return "Emoticons" in character_range or "Pictographs" in character_range
+
+
+@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
+def is_separator(character: str) -> bool:
+    if character.isspace() or character in {"｜", "+", "<", ">"}:
+        return True
+
+    character_category: str = unicodedata.category(character)
+
+    return "Z" in character_category or character_category in {"Po", "Pd", "Pc"}
+
+
+@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
+def is_case_variable(character: str) -> bool:
+    return character.islower() != character.isupper()
+
+
+@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
+def is_cjk(character: str) -> bool:
+    try:
+        character_name = unicodedata.name(character)
+    except ValueError:  # Defensive: unicode database outdated?
+        return False
+
+    return "CJK" in character_name
+
+
+@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
+def is_hiragana(character: str) -> bool:
+    try:
+        character_name = unicodedata.name(character)
+    except ValueError:  # Defensive: unicode database outdated?
+        return False
+
+    return "HIRAGANA" in character_name
+
+
+@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
+def is_katakana(character: str) -> bool:
+    try:
+        character_name = unicodedata.name(character)
+    except ValueError:  # Defensive: unicode database outdated?
+        return False
+
+    return "KATAKANA" in character_name
+
+
+@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
+def is_hangul(character: str) -> bool:
+    try:
+        character_name = unicodedata.name(character)
+    except ValueError:  # Defensive: unicode database outdated?
+        return False
+
+    return "HANGUL" in character_name
+
+
+@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
+def is_thai(character: str) -> bool:
+    try:
+        character_name = unicodedata.name(character)
+    except ValueError:  # Defensive: unicode database outdated?
+        return False
+
+    return "THAI" in character_name
+
+
+@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
+def is_arabic(character: str) -> bool:
+    try:
+        character_name = unicodedata.name(character)
+    except ValueError:  # Defensive: unicode database outdated?
+        return False
+
+    return "ARABIC" in character_name
+
+
+@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
+def is_arabic_isolated_form(character: str) -> bool:
+    try:
+        character_name = unicodedata.name(character)
+    except ValueError:  # Defensive: unicode database outdated?
+        return False
+
+    return "ARABIC" in character_name and "ISOLATED FORM" in character_name
+
+
+@lru_cache(maxsize=len(UNICODE_RANGES_COMBINED))
+def is_unicode_range_secondary(range_name: str) -> bool:
+    return any(keyword in range_name for keyword in UNICODE_SECONDARY_RANGE_KEYWORD)
+
+
+@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
+def is_unprintable(character: str) -> bool:
+    return (
+        character.isspace() is False  # includes \n \t \r \v
+        and character.isprintable() is False
+        and character != "\x1a"  # Why? Its the ASCII substitute character.
+        and character != "\ufeff"  # bug discovered in Python,
+        # Zero Width No-Break Space located in 	Arabic Presentation Forms-B, Unicode 1.1 not acknowledged as space.
+    )
+
+
+def any_specified_encoding(sequence: bytes, search_zone: int = 8192) -> str | None:
+    """
+    Extract using ASCII-only decoder any specified encoding in the first n-bytes.
+    """
+    if not isinstance(sequence, bytes):
+        raise TypeError
+
+    seq_len: int = len(sequence)
+
+    results: list[str] = findall(
+        RE_POSSIBLE_ENCODING_INDICATION,
+        sequence[: min(seq_len, search_zone)].decode("ascii", errors="ignore"),
+    )
+
+    if len(results) == 0:
+        return None
+
+    for specified_encoding in results:
+        specified_encoding = specified_encoding.lower().replace("-", "_")
+
+        encoding_alias: str
+        encoding_iana: str
+
+        for encoding_alias, encoding_iana in aliases.items():
+            if encoding_alias == specified_encoding:
+                return encoding_iana
+            if encoding_iana == specified_encoding:
+                return encoding_iana
+
+    return None
+
+
+@lru_cache(maxsize=128)
+def is_multi_byte_encoding(name: str) -> bool:
+    """
+    Verify is a specific encoding is a multi byte one based on it IANA name
+    """
+    return name in {
+        "utf_8",
+        "utf_8_sig",
+        "utf_16",
+        "utf_16_be",
+        "utf_16_le",
+        "utf_32",
+        "utf_32_le",
+        "utf_32_be",
+        "utf_7",
+    } or issubclass(
+        importlib.import_module(f"encodings.{name}").IncrementalDecoder,
+        MultibyteIncrementalDecoder,
+    )
+
+
+def identify_sig_or_bom(sequence: bytes) -> tuple[str | None, bytes]:
+    """
+    Identify and extract SIG/BOM in given sequence.
+    """
+
+    for iana_encoding in ENCODING_MARKS:
+        marks: bytes | list[bytes] = ENCODING_MARKS[iana_encoding]
+
+        if isinstance(marks, bytes):
+            marks = [marks]
+
+        for mark in marks:
+            if sequence.startswith(mark):
+                return iana_encoding, mark
+
+    return None, b""
+
+
+def should_strip_sig_or_bom(iana_encoding: str) -> bool:
+    return iana_encoding not in {"utf_16", "utf_32"}
+
+
+def iana_name(cp_name: str, strict: bool = True) -> str:
+    """Returns the Python normalized encoding name (Not the IANA official name)."""
+    cp_name = cp_name.lower().replace("-", "_")
+
+    encoding_alias: str
+    encoding_iana: str
+
+    for encoding_alias, encoding_iana in aliases.items():
+        if cp_name in [encoding_alias, encoding_iana]:
+            return encoding_iana
+
+    if strict:
+        raise ValueError(f"Unable to retrieve IANA for '{cp_name}'")
+
+    return cp_name
+
+
+def cp_similarity(iana_name_a: str, iana_name_b: str) -> float:
+    if is_multi_byte_encoding(iana_name_a) or is_multi_byte_encoding(iana_name_b):
+        return 0.0
+
+    decoder_a = importlib.import_module(f"encodings.{iana_name_a}").IncrementalDecoder
+    decoder_b = importlib.import_module(f"encodings.{iana_name_b}").IncrementalDecoder
+
+    id_a: IncrementalDecoder = decoder_a(errors="ignore")
+    id_b: IncrementalDecoder = decoder_b(errors="ignore")
+
+    character_match_count: int = 0
+
+    for i in range(255):
+        to_be_decoded: bytes = bytes([i])
+        if id_a.decode(to_be_decoded) == id_b.decode(to_be_decoded):
+            character_match_count += 1
+
+    return character_match_count / 254
+
+
+def is_cp_similar(iana_name_a: str, iana_name_b: str) -> bool:
+    """
+    Determine if two code page are at least 80% similar. IANA_SUPPORTED_SIMILAR dict was generated using
+    the function cp_similarity.
+    """
+    return (
+        iana_name_a in IANA_SUPPORTED_SIMILAR
+        and iana_name_b in IANA_SUPPORTED_SIMILAR[iana_name_a]
+    )
+
+
+def set_logging_handler(
+    name: str = "charset_normalizer",
+    level: int = logging.INFO,
+    format_string: str = "%(asctime)s | %(levelname)s | %(message)s",
+) -> None:
+    logger = logging.getLogger(name)
+    logger.setLevel(level)
+
+    handler = logging.StreamHandler()
+    handler.setFormatter(logging.Formatter(format_string))
+    logger.addHandler(handler)
+
+
+def cut_sequence_chunks(
+    sequences: bytes,
+    encoding_iana: str,
+    offsets: range,
+    chunk_size: int,
+    bom_or_sig_available: bool,
+    strip_sig_or_bom: bool,
+    sig_payload: bytes,
+    is_multi_byte_decoder: bool,
+    decoded_payload: str | None = None,
+) -> Generator[str, None, None]:
+    if decoded_payload and is_multi_byte_decoder is False:
+        for i in offsets:
+            chunk = decoded_payload[i : i + chunk_size]
+            if not chunk:
+                break
+            yield chunk
+    else:
+        for i in offsets:
+            chunk_end = i + chunk_size
+            if chunk_end > len(sequences) + 8:
+                continue
+
+            cut_sequence = sequences[i : i + chunk_size]
+
+            if bom_or_sig_available and strip_sig_or_bom is False:
+                cut_sequence = sig_payload + cut_sequence
+
+            chunk = cut_sequence.decode(
+                encoding_iana,
+                errors="ignore" if is_multi_byte_decoder else "strict",
+            )
+
+            # multi-byte bad cutting detector and adjustment
+            # not the cleanest way to perform that fix but clever enough for now.
+            if is_multi_byte_decoder and i > 0:
+                chunk_partial_size_chk: int = min(chunk_size, 16)
+
+                if (
+                    decoded_payload
+                    and chunk[:chunk_partial_size_chk] not in decoded_payload
+                ):
+                    for j in range(i, i - 4, -1):
+                        cut_sequence = sequences[j:chunk_end]
+
+                        if bom_or_sig_available and strip_sig_or_bom is False:
+                            cut_sequence = sig_payload + cut_sequence
+
+                        chunk = cut_sequence.decode(encoding_iana, errors="ignore")
+
+                        if chunk[:chunk_partial_size_chk] in decoded_payload:
+                            break
+
+            yield chunk

venv/lib/python3.11/site-packages/charset_normalizer/version.py

@@ -0,0 +1,8 @@
+"""
+Expose version
+"""
+
+from __future__ import annotations
+
+__version__ = "3.4.1"
+VERSION = __version__.split(".")

venv/lib/python3.11/site-packages/click-8.1.8.dist-info/INSTALLER

@@ -0,0 +1 @@
+pip

venv/lib/python3.11/site-packages/click-8.1.8.dist-info/LICENSE.txt

@@ -0,0 +1,28 @@
+Copyright 2014 Pallets
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are
+met:
+
+1.  Redistributions of source code must retain the above copyright
+    notice, this list of conditions and the following disclaimer.
+
+2.  Redistributions in binary form must reproduce the above copyright
+    notice, this list of conditions and the following disclaimer in the
+    documentation and/or other materials provided with the distribution.
+
+3.  Neither the name of the copyright holder nor the names of its
+    contributors may be used to endorse or promote products derived from
+    this software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
+PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED
+TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
+PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
+LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
+NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

venv/lib/python3.11/site-packages/click-8.1.8.dist-info/METADATA

@@ -0,0 +1,74 @@
+Metadata-Version: 2.3
+Name: click
+Version: 8.1.8
+Summary: Composable command line interface toolkit
+Maintainer-email: Pallets <contact@palletsprojects.com>
+Requires-Python: >=3.7
+Description-Content-Type: text/markdown
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: BSD License
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python
+Classifier: Typing :: Typed
+Requires-Dist: colorama; platform_system == 'Windows'
+Requires-Dist: importlib-metadata; python_version < '3.8'
+Project-URL: Changes, https://click.palletsprojects.com/changes/
+Project-URL: Chat, https://discord.gg/pallets
+Project-URL: Documentation, https://click.palletsprojects.com/
+Project-URL: Donate, https://palletsprojects.com/donate
+Project-URL: Source, https://github.com/pallets/click/
+
+# $ click_
+
+Click is a Python package for creating beautiful command line interfaces
+in a composable way with as little code as necessary. It's the "Command
+Line Interface Creation Kit". It's highly configurable but comes with
+sensible defaults out of the box.
+
+It aims to make the process of writing command line tools quick and fun
+while also preventing any frustration caused by the inability to
+implement an intended CLI API.
+
+Click in three points:
+
+-   Arbitrary nesting of commands
+-   Automatic help page generation
+-   Supports lazy loading of subcommands at runtime
+
+
+## A Simple Example
+
+```python
+import click
+
+@click.command()
+@click.option("--count", default=1, help="Number of greetings.")
+@click.option("--name", prompt="Your name", help="The person to greet.")
+def hello(count, name):
+    """Simple program that greets NAME for a total of COUNT times."""
+    for _ in range(count):
+        click.echo(f"Hello, {name}!")
+
+if __name__ == '__main__':
+    hello()
+```
+
+```
+$ python hello.py --count=3
+Your name: Click
+Hello, Click!
+Hello, Click!
+Hello, Click!
+```
+
+
+## Donate
+
+The Pallets organization develops and supports Click and other popular
+packages. In order to grow the community of contributors and users, and
+allow the maintainers to devote more time to the projects, [please
+donate today][].
+
+[please donate today]: https://palletsprojects.com/donate
+

venv/lib/python3.11/site-packages/click-8.1.8.dist-info/RECORD

@@ -0,0 +1,38 @@
+click-8.1.8.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4
+click-8.1.8.dist-info/LICENSE.txt,sha256=morRBqOU6FO_4h9C9OctWSgZoigF2ZG18ydQKSkrZY0,1475
+click-8.1.8.dist-info/METADATA,sha256=WJtQ6uGS2ybLfvUE4vC0XIhIBr4yFGwjrMBR2fiCQ-Q,2263
+click-8.1.8.dist-info/RECORD,,
+click-8.1.8.dist-info/WHEEL,sha256=CpUCUxeHQbRN5UGRQHYRJorO5Af-Qy_fHMctcQ8DSGI,82
+click/__init__.py,sha256=j1DJeCbga4ribkv5uyvIAzI0oFN13fW9mevDKShFelo,3188
+click/__pycache__/__init__.cpython-311.pyc,,
+click/__pycache__/_compat.cpython-311.pyc,,
+click/__pycache__/_termui_impl.cpython-311.pyc,,
+click/__pycache__/_textwrap.cpython-311.pyc,,
+click/__pycache__/_winconsole.cpython-311.pyc,,
+click/__pycache__/core.cpython-311.pyc,,
+click/__pycache__/decorators.cpython-311.pyc,,
+click/__pycache__/exceptions.cpython-311.pyc,,
+click/__pycache__/formatting.cpython-311.pyc,,
+click/__pycache__/globals.cpython-311.pyc,,
+click/__pycache__/parser.cpython-311.pyc,,
+click/__pycache__/shell_completion.cpython-311.pyc,,
+click/__pycache__/termui.cpython-311.pyc,,
+click/__pycache__/testing.cpython-311.pyc,,
+click/__pycache__/types.cpython-311.pyc,,
+click/__pycache__/utils.cpython-311.pyc,,
+click/_compat.py,sha256=IGKh_J5QdfKELitnRfTGHneejWxoCw_NX9tfMbdcg3w,18730
+click/_termui_impl.py,sha256=a5z7I9gOFeMmu7Gb6_RPyQ8GPuVP1EeblixcWSPSQPk,24783
+click/_textwrap.py,sha256=10fQ64OcBUMuK7mFvh8363_uoOxPlRItZBmKzRJDgoY,1353
+click/_winconsole.py,sha256=5ju3jQkcZD0W27WEMGqmEP4y_crUVzPCqsX_FYb7BO0,7860
+click/core.py,sha256=Q1nEVdctZwvIPOlt4vfHko0TYnHCeE40UEEul8Wpyvs,114748
+click/decorators.py,sha256=7t6F-QWowtLh6F_6l-4YV4Y4yNTcqFQEu9i37zIz68s,18925
+click/exceptions.py,sha256=V7zDT6emqJ8iNl0kF1P5kpFmLMWQ1T1L7aNNKM4YR0w,9600
+click/formatting.py,sha256=Frf0-5W33-loyY_i9qrwXR8-STnW3m5gvyxLVUdyxyk,9706
+click/globals.py,sha256=cuJ6Bbo073lgEEmhjr394PeM-QFmXM-Ci-wmfsd7H5g,1954
+click/parser.py,sha256=h4sndcpF5OHrZQN8vD8IWb5OByvW7ABbhRToxovrqS8,19067
+click/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+click/shell_completion.py,sha256=TR0dXEGcvWb9Eo3aaQEXGhnvNS3FF4H4QcuLnvAvYo4,18636
+click/termui.py,sha256=dLxiS70UOvIYBda_nEEZaPAFOVDVmRs1sEPMuLDowQo,28310
+click/testing.py,sha256=3RA8anCf7TZ8-5RAF5it2Te-aWXBAL5VLasQnMiC2ZQ,16282
+click/types.py,sha256=BD5Qqq4h-8kawBmOIzJlmq4xzThAf4wCvaOLZSBDNx0,36422
+click/utils.py,sha256=ce-IrO9ilII76LGkU354pOdHbepM8UftfNH7SfMU_28,20330