mkv-episode-matcher 0.3.3__tar.gz → 0.3.5__tar.gz

mkv_episode_matcher-0.3.5/.github/workflows/tests.yml

@@ -0,0 +1,40 @@
+name: Tests
+
+on:
+  push:
+    branches: [main, master]
+  pull_request:
+    branches: [main, master]
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version:
+          - "3.9"
+          - "3.10"
+          - "3.11"
+          - "3.12"
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Install uv and set the python version
+        uses: astral-sh/setup-uv@v4
+        with:
+          python-version: ${{ matrix.python-version }}
+
+      - name: Install dependencies
+        run: |
+          uv venv
+          uv pip install -e .
+
+      - name: Run tests with pytest and coverage
+        run: |
+          uv run --dev pytest --cov-branch --cov-report=xml
+
+      - name: Upload coverage reports to Codecov
+        uses: codecov/codecov-action@v5
+        with:
+          token: ${{ secrets.CODECOV_TOKEN }}

{mkv_episode_matcher-0.3.3 → mkv_episode_matcher-0.3.5}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.2
 Name: mkv-episode-matcher
-Version: 0.3.3
+Version: 0.3.5
 Summary: The MKV Episode Matcher is a tool for identifying TV series episodes from MKV files and renaming the files accordingly.
 Home-page: https://github.com/Jsakkos/mkv-episode-matcher
 Author: Jonathan Sakkos
@@ -51,6 +51,14 @@ Automatically match and rename your MKV TV episodes using The Movie Database (TM
 - ✨ **Bulk Processing**: Handle entire seasons at once
 - 🧪 **Dry Run Mode**: Test changes before applying
 
+## Prerequisites
+
+- Python 3.9 or higher
+- [FFmpeg](https://ffmpeg.org/download.html) installed and available in system PATH
+- [Tesseract OCR](https://github.com/UB-Mannheim/tesseract/wiki) installed (required for image-based subtitle processing)
+- TMDb API key
+- OpenSubtitles account (optional, for subtitle downloads)
+
 ## Quick Start
 
 1. Install the package:
@@ -60,37 +68,13 @@ pip install mkv-episode-matcher
 
 2. Run on your show directory:
 ```bash
-mkv-match --show-dir "path/to/your/show" --season 1
+mkv-match --show-dir "path/to/your/show" --get-subs true
 ```
 
-## Requirements
-
-- Python 3.8 or higher
-- TMDb API key
-- OpenSubtitles account (optional, for subtitle downloads)
-
 ## Documentation
 
 Full documentation is available at [https://jsakkos.github.io/mkv-episode-matcher/](https://jsakkos.github.io/mkv-episode-matcher/)
 
-## Basic Usage
-
-```python
-from mkv_episode_matcher import process_show
-
-# Process all seasons
-process_show()
-
-# Process specific season
-process_show(season=1)
-
-# Test run without making changes
-process_show(season=1, dry_run=True)
-
-# Process and download subtitles
-process_show(get_subs=True)
-```
-
 ## Directory Structure
 
 MKV Episode Matcher expects your TV shows to be organized as follows:
@@ -105,6 +89,23 @@ Show Name/
 │   └── episode2.mkv
 ```
 
+## Reference Subtitle File Structure
+
+Subtitle files that are not automatically downloaded using the `--get-subs` flag should be named as follows:
+
+```
+
+~/.mkv-episode-matcher/cache/data/Show Name/
+├── Show Name - S01E01.srt
+├── Show Name - S01E02.srt
+└── ...
+```
+
+On Windows, the cache directory is located at `C:\Users\{username}\.mkv-episode-matcher\cache\data\`
+
+Reference subtitle files should follow this naming pattern:
+`{show_name} - S{season:02d}E{episode:02d}.srt`
+
 ## Contributing
 
 1. Fork the repository

{mkv_episode_matcher-0.3.3 → mkv_episode_matcher-0.3.5}/README.md

@@ -22,6 +22,14 @@ Automatically match and rename your MKV TV episodes using The Movie Database (TM
 - ✨ **Bulk Processing**: Handle entire seasons at once
 - 🧪 **Dry Run Mode**: Test changes before applying
 
+## Prerequisites
+
+- Python 3.9 or higher
+- [FFmpeg](https://ffmpeg.org/download.html) installed and available in system PATH
+- [Tesseract OCR](https://github.com/UB-Mannheim/tesseract/wiki) installed (required for image-based subtitle processing)
+- TMDb API key
+- OpenSubtitles account (optional, for subtitle downloads)
+
 ## Quick Start
 
 1. Install the package:
@@ -31,37 +39,13 @@ pip install mkv-episode-matcher
 
 2. Run on your show directory:
 ```bash
-mkv-match --show-dir "path/to/your/show" --season 1
+mkv-match --show-dir "path/to/your/show" --get-subs true
 ```
 
-## Requirements
-
-- Python 3.8 or higher
-- TMDb API key
-- OpenSubtitles account (optional, for subtitle downloads)
-
 ## Documentation
 
 Full documentation is available at [https://jsakkos.github.io/mkv-episode-matcher/](https://jsakkos.github.io/mkv-episode-matcher/)
 
-## Basic Usage
-
-```python
-from mkv_episode_matcher import process_show
-
-# Process all seasons
-process_show()
-
-# Process specific season
-process_show(season=1)
-
-# Test run without making changes
-process_show(season=1, dry_run=True)
-
-# Process and download subtitles
-process_show(get_subs=True)
-```
-
 ## Directory Structure
 
 MKV Episode Matcher expects your TV shows to be organized as follows:
@@ -76,6 +60,23 @@ Show Name/
 │   └── episode2.mkv
 ```
 
+## Reference Subtitle File Structure
+
+Subtitle files that are not automatically downloaded using the `--get-subs` flag should be named as follows:
+
+```
+
+~/.mkv-episode-matcher/cache/data/Show Name/
+├── Show Name - S01E01.srt
+├── Show Name - S01E02.srt
+└── ...
+```
+
+On Windows, the cache directory is located at `C:\Users\{username}\.mkv-episode-matcher\cache\data\`
+
+Reference subtitle files should follow this naming pattern:
+`{show_name} - S{season:02d}E{episode:02d}.srt`
+
 ## Contributing
 
 1. Fork the repository

{mkv_episode_matcher-0.3.3 → mkv_episode_matcher-0.3.5}/docs/quickstart.md

@@ -41,28 +41,22 @@ Show Name/
 │   ├── episode1.mkv
 │   └── episode2.mkv
 ```
+<!-- Add a note about the .srt reference files -->
 
-## Python API Usage
+## Reference Subtitle File Structure
 
-```python
-from mkv_episode_matcher import process_show
+Subtitle files that are not automatically downloaded using the `--get-subs` flag should be named as follows:
 
-# Process all seasons
-process_show()
-
-# Process specific season
-process_show(season=1)
-
-# Test run
-process_show(season=1, dry_run=True)
-
-# With subtitles
-process_show(season=1, get_subs=True)
+```plaintext
+~/.mkv-episode-matcher/cache/data/Show Name/
+├── Show Name - S01E01.srt
+├── Show Name - S01E02.srt
+└── ...
 ```
 
 ## Configuration
 
-Create a configuration file at `~/.mkv-episode-matcher/config.ini`:
+The configuration file is automatically generated at `~/.mkv-episode-matcher/config.ini`:
 
 ```ini
 [Config]

{mkv_episode_matcher-0.3.3 → mkv_episode_matcher-0.3.5}/mkv_episode_matcher/episode_identification.py

@@ -9,6 +9,10 @@ from loguru import logger
 import whisper
 import numpy as np
 import re
+from pathlib import Path
+import chardet
+from loguru import logger
+
 class EpisodeMatcher:
     def __init__(self, cache_dir, show_name, min_confidence=0.6):
         self.cache_dir = Path(cache_dir)
@@ -50,34 +54,32 @@ class EpisodeMatcher:
         return str(chunk_path)
 
     def load_reference_chunk(self, srt_file, chunk_idx):
-        """Load reference subtitles for a specific time chunk."""
+        """
+        Load reference subtitles for a specific time chunk with robust encoding handling.
+        
+        Args:
+            srt_file (str or Path): Path to the SRT file
+            chunk_idx (int): Index of the chunk to load
+            
+        Returns:
+            str: Combined text from the subtitle chunk
+        """
         chunk_start = chunk_idx * self.chunk_duration
         chunk_end = chunk_start + self.chunk_duration
-        text_lines = []
         
-        with open(srt_file, 'r', encoding='utf-8') as f:
-            content = f.read().strip()
+        try:
+            # Read the file content using our robust reader
+            reader = SubtitleReader()
+            content = reader.read_srt_file(srt_file)
             
-        for block in content.split('\n\n'):
-            lines = block.split('\n')
-            if len(lines) < 3 or '-->' not in lines[1]:  # Skip malformed blocks
-                continue
-                
-            try:
-                timestamp = lines[1]
-                text = ' '.join(lines[2:])
-                
-                end_time = timestamp.split(' --> ')[1].strip()
-                hours, minutes, seconds = map(float, end_time.replace(',','.').split(':'))
-                total_seconds = hours * 3600 + minutes * 60 + seconds
-                
-                if chunk_start <= total_seconds <= chunk_end:
-                    text_lines.append(text)
-                    
-            except (IndexError, ValueError):
-                continue
-                
-        return ' '.join(text_lines)
+            # Extract subtitles for the time chunk
+            text_lines = reader.extract_subtitle_chunk(content, chunk_start, chunk_end)
+            
+            return ' '.join(text_lines)
+            
+        except Exception as e:
+            logger.error(f"Error loading reference chunk from {srt_file}: {e}")
+            return ''
 
     def identify_episode(self, video_file, temp_dir, season_number):
         try:
@@ -147,4 +149,121 @@ class EpisodeMatcher:
         finally:
             # Cleanup temp files
             for file in self.temp_dir.glob("chunk_*.wav"):
-                file.unlink()
+                file.unlink()
+
+def detect_file_encoding(file_path):
+    """
+    Detect the encoding of a file using chardet.
+    
+    Args:
+        file_path (str or Path): Path to the file
+        
+    Returns:
+        str: Detected encoding, defaults to 'utf-8' if detection fails
+    """
+    try:
+        with open(file_path, 'rb') as f:
+            raw_data = f.read()
+        result = chardet.detect(raw_data)
+        encoding = result['encoding']
+        confidence = result['confidence']
+        
+        logger.debug(f"Detected encoding {encoding} with {confidence:.2%} confidence for {file_path}")
+        return encoding if encoding else 'utf-8'
+    except Exception as e:
+        logger.warning(f"Error detecting encoding for {file_path}: {e}")
+        return 'utf-8'
+
+def read_file_with_fallback(file_path, encodings=None):
+    """
+    Read a file trying multiple encodings in order of preference.
+    
+    Args:
+        file_path (str or Path): Path to the file
+        encodings (list): List of encodings to try, defaults to common subtitle encodings
+        
+    Returns:
+        str: File contents
+        
+    Raises:
+        ValueError: If file cannot be read with any encoding
+    """
+    if encodings is None:
+        # First try detected encoding, then fallback to common subtitle encodings
+        detected = detect_file_encoding(file_path)
+        encodings = [detected, 'utf-8', 'latin-1', 'cp1252', 'iso-8859-1']
+    
+    file_path = Path(file_path)
+    errors = []
+    
+    for encoding in encodings:
+        try:
+            with open(file_path, 'r', encoding=encoding) as f:
+                content = f.read()
+            logger.debug(f"Successfully read {file_path} using {encoding} encoding")
+            return content
+        except UnicodeDecodeError as e:
+            errors.append(f"{encoding}: {str(e)}")
+            continue
+            
+    error_msg = f"Failed to read {file_path} with any encoding. Errors:\n" + "\n".join(errors)
+    logger.error(error_msg)
+    raise ValueError(error_msg)
+
+class SubtitleReader:
+    """Helper class for reading and parsing subtitle files."""
+    
+    @staticmethod
+    def parse_timestamp(timestamp):
+        """Parse SRT timestamp into seconds."""
+        hours, minutes, seconds = timestamp.replace(',', '.').split(':')
+        return float(hours) * 3600 + float(minutes) * 60 + float(seconds)
+    
+    @staticmethod
+    def read_srt_file(file_path):
+        """
+        Read an SRT file and return its contents with robust encoding handling.
+        
+        Args:
+            file_path (str or Path): Path to the SRT file
+            
+        Returns:
+            str: Contents of the SRT file
+        """
+        return read_file_with_fallback(file_path)
+    
+    @staticmethod
+    def extract_subtitle_chunk(content, start_time, end_time):
+        """
+        Extract subtitle text for a specific time window.
+        
+        Args:
+            content (str): Full SRT file content
+            start_time (float): Chunk start time in seconds
+            end_time (float): Chunk end time in seconds
+            
+        Returns:
+            list: List of subtitle texts within the time window
+        """
+        text_lines = []
+        
+        for block in content.strip().split('\n\n'):
+            lines = block.split('\n')
+            if len(lines) < 3 or '-->' not in lines[1]:
+                continue
+                
+            try:
+                timestamp = lines[1]
+                text = ' '.join(lines[2:])
+                
+                end_stamp = timestamp.split(' --> ')[1].strip()
+                total_seconds = SubtitleReader.parse_timestamp(end_stamp)
+                
+                if start_time <= total_seconds <= end_time:
+                    text_lines.append(text)
+                    
+            except (IndexError, ValueError) as e:
+                logger.warning(f"Error parsing subtitle block: {e}")
+                continue
+                
+        return text_lines

mkv_episode_matcher-0.3.5/mkv_episode_matcher/subtitle_utils.py

@@ -0,0 +1,82 @@
+from typing import List, Optional, Union
+import os
+import re
+
+def generate_subtitle_patterns(series_name: str, season: int, episode: int) -> List[str]:
+    """
+    Generate various common subtitle filename patterns.
+    
+    Args:
+        series_name (str): Name of the series
+        season (int): Season number
+        episode (int): Episode number
+        
+    Returns:
+        List[str]: List of possible subtitle filenames
+    """
+    patterns = [
+        # Standard format: "Show Name - S01E02.srt"
+        f"{series_name} - S{season:02d}E{episode:02d}.srt",
+        
+        # Season x Episode format: "Show Name - 1x02.srt"
+        f"{series_name} - {season}x{episode:02d}.srt",
+        
+        # Separate season/episode: "Show Name - Season 1 Episode 02.srt"
+        f"{series_name} - Season {season} Episode {episode:02d}.srt",
+        
+        # Compact format: "ShowName.S01E02.srt"
+        f"{series_name.replace(' ', '')}.S{season:02d}E{episode:02d}.srt",
+        
+        # Numbered format: "Show Name 102.srt"
+        f"{series_name} {season:01d}{episode:02d}.srt",
+        
+        # Dot format: "Show.Name.1x02.srt"
+        f"{series_name.replace(' ', '.')}.{season}x{episode:02d}.srt",
+        
+        # Underscore format: "Show_Name_S01E02.srt"
+        f"{series_name.replace(' ', '_')}_S{season:02d}E{episode:02d}.srt",
+    ]
+    
+    return patterns
+
+def find_existing_subtitle(series_cache_dir: str, series_name: str, season: int, episode: int) -> Optional[str]:
+    """
+    Check for existing subtitle files in various naming formats.
+    
+    Args:
+        series_cache_dir (str): Directory containing subtitle files
+        series_name (str): Name of the series
+        season (int): Season number
+        episode (int): Episode number
+        
+    Returns:
+        Optional[str]: Path to existing subtitle file if found, None otherwise
+    """
+    patterns = generate_subtitle_patterns(series_name, season, episode)
+    
+    for pattern in patterns:
+        filepath = os.path.join(series_cache_dir, pattern)
+        if os.path.exists(filepath):
+            return filepath
+            
+    return None
+
+def sanitize_filename(filename: str) -> str:
+    """
+    Sanitize filename by removing/replacing invalid characters.
+    
+    Args:
+        filename (str): Original filename
+        
+    Returns:
+        str: Sanitized filename
+    """
+    # Replace problematic characters
+    filename = filename.replace(':', ' -')
+    filename = filename.replace('/', '-')
+    filename = filename.replace('\\', '-')
+    
+    # Remove any other invalid characters
+    filename = re.sub(r'[<>:"/\\|?*]', '', filename)
+    
+    return filename.strip()

{mkv_episode_matcher-0.3.3 → mkv_episode_matcher-0.3.5}/mkv_episode_matcher/utils.py

@@ -10,7 +10,7 @@ from opensubtitlescom import OpenSubtitles
 from mkv_episode_matcher.__main__ import CACHE_DIR, CONFIG_FILE
 from mkv_episode_matcher.config import get_config
 from mkv_episode_matcher.tmdb_client import fetch_season_details
-
+from mkv_episode_matcher.subtitle_utils import find_existing_subtitle,sanitize_filename
 def get_valid_seasons(show_dir):
     """
     Get all season directories that contain MKV files.
@@ -128,20 +128,17 @@ def get_subtitles(show_id, seasons: set[int]):
     Args:
         show_id (int): The ID of the TV show.
         seasons (Set[int]): A set of season numbers for which subtitles should be retrieved.
-
-    Returns:
-        None
     """
-
     logger.info(f"Getting subtitles for show ID {show_id}")
     config = get_config(CONFIG_FILE)
     show_dir = config.get("show_dir")
-    series_name = os.path.basename(show_dir)
+    series_name = sanitize_filename(os.path.basename(show_dir))
     tmdb_api_key = config.get("tmdb_api_key")
     open_subtitles_api_key = config.get("open_subtitles_api_key")
     open_subtitles_user_agent = config.get("open_subtitles_user_agent")
     open_subtitles_username = config.get("open_subtitles_username")
     open_subtitles_password = config.get("open_subtitles_password")
+
     if not all([
         show_dir,
         tmdb_api_key,
@@ -151,63 +148,66 @@ def get_subtitles(show_id, seasons: set[int]):
         open_subtitles_password,
     ]):
         logger.error("Missing configuration settings. Please run the setup script.")
+        return
+
     try:
-        # Initialize the OpenSubtitles client
         subtitles = OpenSubtitles(open_subtitles_user_agent, open_subtitles_api_key)
-
-        # Log in (retrieve auth token)
         subtitles.login(open_subtitles_username, open_subtitles_password)
     except Exception as e:
         logger.error(f"Failed to log in to OpenSubtitles: {e}")
         return
+
     for season in seasons:
         episodes = fetch_season_details(show_id, season)
         logger.info(f"Found {episodes} episodes in Season {season}")
 
         for episode in range(1, episodes + 1):
             logger.info(f"Processing Season {season}, Episode {episode}...")
+            
             series_cache_dir = os.path.join(CACHE_DIR, "data", series_name)
             os.makedirs(series_cache_dir, exist_ok=True)
+            
+            # Check for existing subtitle in any supported format
+            existing_subtitle = find_existing_subtitle(
+                series_cache_dir, series_name, season, episode
+            )
+            
+            if existing_subtitle:
+                logger.info(f"Subtitle already exists: {os.path.basename(existing_subtitle)}")
+                continue
+                
+            # Default to standard format for new downloads
             srt_filepath = os.path.join(
                 series_cache_dir,
                 f"{series_name} - S{season:02d}E{episode:02d}.srt",
             )
-            if not os.path.exists(srt_filepath):
-                # get the episode info from TMDB
-                url = f"https://api.themoviedb.org/3/tv/{show_id}/season/{season}/episode/{episode}?api_key={tmdb_api_key}"
-                response = requests.get(url)
-                response.raise_for_status()
-                episode_data = response.json()
-                episode_data["name"]
-                episode_id = episode_data["id"]
-                # search for the subtitle
-                response = subtitles.search(tmdb_id=episode_id, languages="en")
-                if len(response.data) == 0:
-                    logger.warning(
-                        f"No subtitles found for {series_name} - S{season:02d}E{episode:02d}"
-                    )
-
-                for subtitle in response.data:
-                    subtitle_dict = subtitle.to_dict()
-                    # Remove special characters and convert to uppercase
-                    filename_clean = re.sub(
-                        r"\W+", " ", subtitle_dict["file_name"]
-                    ).upper()
-                    if f"E{episode:02d}" in filename_clean:
-                        logger.info(f"Original filename: {subtitle_dict['file_name']}")
-                        srt_file = subtitles.download_and_save(subtitle)
-                        series_name = series_name.replace(":", " -")
-                        shutil.move(srt_file, srt_filepath)
-                        logger.info(f"Subtitle saved to {srt_filepath}")
-                        break
-                    else:
-                        continue
-            else:
-                logger.info(
-                    f"Subtitle already exists for {series_name} - S{season:02d}E{episode:02d}"
+
+            # get the episode info from TMDB
+            url = f"https://api.themoviedb.org/3/tv/{show_id}/season/{season}/episode/{episode}?api_key={tmdb_api_key}"
+            response = requests.get(url)
+            response.raise_for_status()
+            episode_data = response.json()
+            episode_id = episode_data["id"]
+            
+            # search for the subtitle
+            response = subtitles.search(tmdb_id=episode_id, languages="en")
+            if len(response.data) == 0:
+                logger.warning(
+                    f"No subtitles found for {series_name} - S{season:02d}E{episode:02d}"
                 )
                 continue
 
+            for subtitle in response.data:
+                subtitle_dict = subtitle.to_dict()
+                # Remove special characters and convert to uppercase
+                filename_clean = re.sub(r"\W+", " ", subtitle_dict["file_name"]).upper()
+                if f"E{episode:02d}" in filename_clean:
+                    logger.info(f"Original filename: {subtitle_dict['file_name']}")
+                    srt_file = subtitles.download_and_save(subtitle)
+                    shutil.move(srt_file, srt_filepath)
+                    logger.info(f"Subtitle saved to {srt_filepath}")
+                    break
+
 
 def cleanup_ocr_files(show_dir):
     """
@@ -236,7 +236,7 @@ def clean_text(text):
     # Strip leading/trailing whitespace
     return cleaned_text.strip()
 
-
+@logger.catch
 def process_reference_srt_files(series_name):
     """
     Process reference SRT files for a given series.

{mkv_episode_matcher-0.3.3 → mkv_episode_matcher-0.3.5}/mkv_episode_matcher.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.2
 Name: mkv-episode-matcher
-Version: 0.3.3
+Version: 0.3.5
 Summary: The MKV Episode Matcher is a tool for identifying TV series episodes from MKV files and renaming the files accordingly.
 Home-page: https://github.com/Jsakkos/mkv-episode-matcher
 Author: Jonathan Sakkos
@@ -51,6 +51,14 @@ Automatically match and rename your MKV TV episodes using The Movie Database (TM
 - ✨ **Bulk Processing**: Handle entire seasons at once
 - 🧪 **Dry Run Mode**: Test changes before applying
 
+## Prerequisites
+
+- Python 3.9 or higher
+- [FFmpeg](https://ffmpeg.org/download.html) installed and available in system PATH
+- [Tesseract OCR](https://github.com/UB-Mannheim/tesseract/wiki) installed (required for image-based subtitle processing)
+- TMDb API key
+- OpenSubtitles account (optional, for subtitle downloads)
+
 ## Quick Start
 
 1. Install the package:
@@ -60,37 +68,13 @@ pip install mkv-episode-matcher
 
 2. Run on your show directory:
 ```bash
-mkv-match --show-dir "path/to/your/show" --season 1
+mkv-match --show-dir "path/to/your/show" --get-subs true
 ```
 
-## Requirements
-
-- Python 3.8 or higher
-- TMDb API key
-- OpenSubtitles account (optional, for subtitle downloads)
-
 ## Documentation
 
 Full documentation is available at [https://jsakkos.github.io/mkv-episode-matcher/](https://jsakkos.github.io/mkv-episode-matcher/)
 
-## Basic Usage
-
-```python
-from mkv_episode_matcher import process_show
-
-# Process all seasons
-process_show()
-
-# Process specific season
-process_show(season=1)
-
-# Test run without making changes
-process_show(season=1, dry_run=True)
-
-# Process and download subtitles
-process_show(get_subs=True)
-```
-
 ## Directory Structure
 
 MKV Episode Matcher expects your TV shows to be organized as follows:
@@ -105,6 +89,23 @@ Show Name/
 │   └── episode2.mkv
 ```
 
+## Reference Subtitle File Structure
+
+Subtitle files that are not automatically downloaded using the `--get-subs` flag should be named as follows:
+
+```
+
+~/.mkv-episode-matcher/cache/data/Show Name/
+├── Show Name - S01E01.srt
+├── Show Name - S01E02.srt
+└── ...
+```
+
+On Windows, the cache directory is located at `C:\Users\{username}\.mkv-episode-matcher\cache\data\`
+
+Reference subtitle files should follow this naming pattern:
+`{show_name} - S{season:02d}E{episode:02d}.srt`
+
 ## Contributing
 
 1. Fork the repository

{mkv_episode_matcher-0.3.3 → mkv_episode_matcher-0.3.5}/mkv_episode_matcher.egg-info/SOURCES.txt

@@ -12,6 +12,7 @@ uv.lock
 .github/funding.yml
 .github/workflows/documentation.yml
 .github/workflows/python-publish.yml
+.github/workflows/tests.yml
 .vscode/settings.json
 docs/cli.md
 docs/configuration.md
@@ -27,6 +28,7 @@ mkv_episode_matcher/episode_identification.py
 mkv_episode_matcher/episode_matcher.py
 mkv_episode_matcher/mkv_to_srt.py
 mkv_episode_matcher/speech_to_text.py
+mkv_episode_matcher/subtitle_utils.py
 mkv_episode_matcher/tmdb_client.py
 mkv_episode_matcher/utils.py
 mkv_episode_matcher.egg-info/PKG-INFO
@@ -46,5 +48,4 @@ mkv_episode_matcher/libraries/pgs2srt/Libraries/SubZero/SubZero.py
 mkv_episode_matcher/libraries/pgs2srt/Libraries/SubZero/post_processing.py
 mkv_episode_matcher/libraries/pgs2srt/Libraries/SubZero/dictionaries/data.py
 tests/__init__.py
-tests/test_improvements.py
 tests/test_main.py

{mkv_episode_matcher-0.3.3 → mkv_episode_matcher-0.3.5}/pyproject.toml

@@ -47,6 +47,7 @@ dev = [
     "pytest-cov>=6.0.0",
     "pytest>=8.3.3",
     "ruff>=0.8.0",
+    "chardet>=5.2.0",
 ]
 
 

{mkv_episode_matcher-0.3.3 → mkv_episode_matcher-0.3.5}/setup.cfg

@@ -1,6 +1,6 @@
 [metadata]
 name = mkv_episode_matcher
-version = 0.3.3
+version = 0.3.5
 author = Jonathan Sakkos
 author_email = jonathansakkos@gmail.com
 description = The MKV Episode Matcher is a tool for identifying TV series episodes from MKV files and renaming the files accordingly.

{mkv_episode_matcher-0.3.3 → mkv_episode_matcher-0.3.5}/tests/test_main.py

@@ -13,6 +13,31 @@ from mkv_episode_matcher.utils import (
 )
 from mkv_episode_matcher.episode_identification import EpisodeMatcher
 from mkv_episode_matcher.config import get_config, set_config
+from unittest.mock import Mock, patch
+
+
+# @pytest.fixture
+# def mock_config():
+#     return {
+#         "tmdb_api_key": "test_key",
+#         "show_dir": "/test/path",
+#         "max_threads": 4,
+#         "tesseract_path": "/usr/bin/tesseract",
+#     }
+
+
+@pytest.fixture
+def mock_episode_data():
+    return {
+        "name": "Test Episode",
+        "season_number": 1,
+        "episode_number": 1,
+        "overview": "Test overview",
+    }
+
+@pytest.fixture
+def mock_seasons():
+    return ["/test/path/Season 1"]
 
 @pytest.fixture
 def temp_show_dir(tmp_path):
@@ -101,8 +126,8 @@ class TestEpisodeMatcher:
         return EpisodeMatcher(tmp_path, "Test Show")
 
     def test_clean_text(self, matcher):
-        text = "Test [action] <tag> T-t-test"
-        assert matcher.clean_text(text) == "test action tag test"
+        text = "Test [action] T-t-test"
+        assert matcher.clean_text(text) == "test action test"
 
     def test_chunk_score(self, matcher):
         score = matcher.chunk_score("Test dialogue", "test dialog")
@@ -116,22 +141,27 @@ class TestEpisodeMatcher:
         assert isinstance(chunk, str)
         assert mock_run.called
 
-class TestProcessShow:
-    @patch('mkv_episode_matcher.episode_matcher.get_valid_seasons')
-    @patch('mkv_episode_matcher.episode_matcher.get_config')
-    def test_process_show_no_seasons(self, mock_config, mock_seasons, mock_config_data):
-        mock_seasons.return_value = []
-        mock_config.return_value = mock_config_data
-        process_show()
-        mock_seasons.assert_called_once()
-
-    @patch('mkv_episode_matcher.episode_matcher.get_valid_seasons')
-    @patch('mkv_episode_matcher.episode_matcher.get_config')
-    def test_process_show_with_season(self, mock_config, mock_seasons, temp_show_dir, mock_config_data):
-        mock_seasons.return_value = [str(temp_show_dir / "Season 1")]
-        mock_config.return_value = mock_config_data
-        process_show(season=1)
-        mock_seasons.assert_called_once()
+class TestEpisodeMatcher:
+    def test_extract_season_episode(self):
+        from mkv_episode_matcher.utils import extract_season_episode
+
+        # Test valid filename
+        assert extract_season_episode("Show - S01E02.mkv") == (1, 2)
+
+        # Test invalid filename
+        assert extract_season_episode("invalid.mkv") == (None, None)
+
+    @patch("mkv_episode_matcher.tmdb_client.requests.get")
+    def test_fetch_show_id(self, mock_get):
+        from mkv_episode_matcher.tmdb_client import fetch_show_id
+
+        mock_response = Mock()
+        mock_response.status_code = 200
+        mock_response.json.return_value = {"results": [{"id": 12345}]}
+        mock_get.return_value = mock_response
+
+        assert fetch_show_id("Test Show") == "12345"
+
 
 if __name__ == '__main__':
     pytest.main(['-v'])

{mkv_episode_matcher-0.3.3 → mkv_episode_matcher-0.3.5}/uv.lock

@@ -24,6 +24,15 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/12/90/3c9ff0512038035f59d279fddeb79f5f1eccd8859f06d6163c58798b9487/certifi-2024.8.30-py3-none-any.whl", hash = "sha256:922820b53db7a7257ffbda3f597266d435245903d80737e34f8a45ff3e3230d8", size = 167321 },
 ]
 
+[[package]]
+name = "chardet"
+version = "5.2.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/f3/0d/f7b6ab21ec75897ed80c17d79b15951a719226b9fababf1e40ea74d69079/chardet-5.2.0.tar.gz", hash = "sha256:1b3b6ff479a8c414bc3fa2c0852995695c4a026dcd6d0633b2dd092ca39c1cf7", size = 2069618 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/38/6f/f5fbc992a329ee4e0f288c1fe0e2ad9485ed064cac731ed2fe47dcc38cbf/chardet-5.2.0-py3-none-any.whl", hash = "sha256:e1cf59446890a00105fe7b7912492ea04b6e6f06d4b742b2c788469e34c82970", size = 199385 },
+]
+
 [[package]]
 name = "charset-normalizer"
 version = "3.4.0"
@@ -374,7 +383,7 @@ wheels = [
 
 [[package]]
 name = "mkv-episode-matcher"
-version = "0.3.2.post1.dev0+g2c513fa.d20241126"
+version = "0.3.4.post1.dev3+g95f005b.d20250112"
 source = { editable = "." }
 dependencies = [
     { name = "configparser" },
@@ -391,6 +400,7 @@ dependencies = [
 
 [package.dev-dependencies]
 dev = [
+    { name = "chardet" },
     { name = "pytest" },
     { name = "pytest-cov" },
     { name = "ruff" },
@@ -412,6 +422,7 @@ requires-dist = [
 
 [package.metadata.requires-dev]
 dev = [
+    { name = "chardet", specifier = ">=5.2.0" },
     { name = "pytest", specifier = ">=8.3.3" },
     { name = "pytest-cov", specifier = ">=6.0.0" },
     { name = "ruff", specifier = ">=0.8.0" },

mkv_episode_matcher-0.3.3/tests/test_improvements.py

@@ -1,59 +0,0 @@
-from unittest.mock import Mock, patch
-
-import pytest
-
-
-@pytest.fixture
-def mock_config():
-    return {
-        "tmdb_api_key": "test_key",
-        "show_dir": "/test/path",
-        "max_threads": 4,
-        "tesseract_path": "/usr/bin/tesseract",
-    }
-
-
-@pytest.fixture
-def mock_episode_data():
-    return {
-        "name": "Test Episode",
-        "season_number": 1,
-        "episode_number": 1,
-        "overview": "Test overview",
-    }
-
-
-class TestEpisodeMatcher:
-    def test_extract_season_episode(self):
-        from mkv_episode_matcher.episode_matcher import extract_season_episode
-
-        # Test valid filename
-        assert extract_season_episode("Show - S01E02.mkv") == (1, 2)
-
-        # Test invalid filename
-        assert extract_season_episode("invalid.mkv") == (None, None)
-
-    @patch("mkv_episode_matcher.tmdb_client.requests.get")
-    def test_fetch_show_id(self, mock_get):
-        from mkv_episode_matcher.tmdb_client import fetch_show_id
-
-        mock_response = Mock()
-        mock_response.status_code = 200
-        mock_response.json.return_value = {"results": [{"id": 12345}]}
-        mock_get.return_value = mock_response
-
-        assert fetch_show_id("Test Show") == "12345"
-
-    @patch("mkv_episode_matcher.utils.OpenSubtitles")
-    def test_get_subtitles(self, mock_subtitles):
-        from mkv_episode_matcher.utils import get_subtitles
-
-        # Test subtitle download
-        mock_subtitles.return_value.search.return_value.data = [
-            {"file_name": "Test.Show.S01E01.srt"}
-        ]
-
-        with patch("pathlib.Path.exists", return_value=False):
-            get_subtitles(12345, {1})
-
-            mock_subtitles.return_value.download_and_save.assert_called_once()