mkv-episode-matcher 0.3.5__tar.gz → 0.4.0__tar.gz

{mkv_episode_matcher-0.3.5 → mkv_episode_matcher-0.4.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: mkv-episode-matcher
-Version: 0.3.5
+Version: 0.4.0
 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
@@ -25,7 +25,18 @@ Requires-Dist: pytesseract>=0.3.13
 Requires-Dist: rapidfuzz>=3.10.1
 Requires-Dist: requests>=2.32.3
 Requires-Dist: tmdb-client>=0.0.1
+Requires-Dist: torch>=2.5.1
+Requires-Dist: torchaudio>=2.5.1
+Requires-Dist: torchvision>=0.20.1
 Requires-Dist: wave>=0.0.2
+Provides-Extra: cpu
+Requires-Dist: torch>=2.5.1; extra == "cpu"
+Requires-Dist: torchvision>=0.20.1; extra == "cpu"
+Requires-Dist: torchaudio>=2.5.1; extra == "cpu"
+Provides-Extra: cu124
+Requires-Dist: torch>=2.5.1; extra == "cu124"
+Requires-Dist: torchvision>=0.20.1; extra == "cu124"
+Requires-Dist: torchaudio>=2.5.1; extra == "cu124"
 
 # MKV Episode Matcher
 
@@ -65,10 +76,11 @@ Automatically match and rename your MKV TV episodes using The Movie Database (TM
 ```bash
 pip install mkv-episode-matcher
 ```
+2. Download .srt subtitles files to ~/.mkv-episode-matcher/cache/data/Show Name/
 
-2. Run on your show directory:
+3. Run on your show directory:
 ```bash
-mkv-match --show-dir "path/to/your/show" --get-subs true
+mkv-match --show-dir "path/to/your/show"
 ```
 
 ## Documentation

{mkv_episode_matcher-0.3.5 → mkv_episode_matcher-0.4.0}/README.md

@@ -36,10 +36,11 @@ Automatically match and rename your MKV TV episodes using The Movie Database (TM
 ```bash
 pip install mkv-episode-matcher
 ```
+2. Download .srt subtitles files to ~/.mkv-episode-matcher/cache/data/Show Name/
 
-2. Run on your show directory:
+3. Run on your show directory:
 ```bash
-mkv-match --show-dir "path/to/your/show" --get-subs true
+mkv-match --show-dir "path/to/your/show"
 ```
 
 ## Documentation

{mkv_episode_matcher-0.3.5 → mkv_episode_matcher-0.4.0}/docs/cli.md

@@ -16,14 +16,14 @@ mkv-match --show-dir "/path/to/show" --season 1
 
 ## Command Options
 
-| Option | Description | Default |
-|--------|-------------|---------|
-| `--show-dir` | Show directory path | None |
-| `--season` | Season number to process | None (all) |
-| `--dry-run` | Test without making changes | False |
-| `--get-subs` | Download subtitles | False |
-| `--tmdb-api-key` | TMDb API key | None |
-| `--tesseract-path` | Path to Tesseract | None |
+| Option             | Description                 | Default    |
+| ------------------ | --------------------------- | ---------- |
+| `--show-dir`       | Show directory path         | None       |
+| `--season`         | Season number to process    | None (all) |
+| `--dry-run`        | Test without making changes | False      |
+| `--get-subs`       | Download subtitles          | False      |
+| `--tmdb-api-key`   | TMDb API key                | None       |
+| `--tesseract-path` | Path to Tesseract           | None       |
 
 ## Examples
 
@@ -55,25 +55,6 @@ mkv-match \
   --dry-run true
 ```
 
-## Environment Variables
-
-Alternative to command line options:
-
-```bash
-export TMDB_API_KEY="your_key"
-export SHOW_DIR="/path/to/shows"
-mkv-match
-```
-
-## Exit Codes
-
-| Code | Meaning |
-|------|---------|
-| 0 | Success |
-| 1 | General error |
-| 2 | Configuration error |
-| 3 | API error |
-
 ## Logging
 
 Logs are stored in:
@@ -89,3 +70,4 @@ Logs are stored in:
 2. Use dry-run first to test
 3. Check logs for details
 4. Use full paths for reliability
+5. Avoid using a trailing slash in paths

{mkv_episode_matcher-0.3.5 → mkv_episode_matcher-0.4.0}/docs/configuration.md

@@ -102,4 +102,8 @@ Adjust based on your system's capabilities:
 tesseract_path = /path/to/tesseract
 ```
 
-Required only if processing image-based subtitles.
+Required for processing image-based subtitles. Common paths:
+- Windows: `C:\Program Files\Tesseract-OCR\tesseract.exe`
+- Linux/macOS: `/usr/bin/tesseract`
+
+Make sure Tesseract OCR is properly installed before using this feature.

{mkv_episode_matcher-0.3.5 → mkv_episode_matcher-0.4.0}/docs/installation.md

@@ -1,5 +1,23 @@
 # Installation Guide
 
+## Prerequisites
+
+### Required System Dependencies
+
+1. **FFmpeg**
+   - Windows: Download from [FFmpeg website](https://ffmpeg.org/download.html)
+   - Linux: `sudo apt install ffmpeg` or equivalent
+   - macOS: `brew install ffmpeg`
+   - Verify installation: `ffmpeg -version`
+
+2. **Tesseract OCR**
+   - Windows: Install from [UB-Mannheim](https://github.com/UB-Mannheim/tesseract/wiki)
+   - Linux: `sudo apt install tesseract-ocr` or equivalent
+   - macOS: `brew install tesseract`
+   - Verify installation: `tesseract --version`
+
+Make sure both FFmpeg and Tesseract are added to your system PATH.
+
 ## Basic Installation
 
 Install MKV Episode Matcher using pip:

{mkv_episode_matcher-0.3.5 → mkv_episode_matcher-0.4.0}/docs/quickstart.md

@@ -41,7 +41,6 @@ Show Name/
 │   ├── episode1.mkv
 │   └── episode2.mkv
 ```
-<!-- Add a note about the .srt reference files -->
 
 ## Reference Subtitle File Structure
 
@@ -60,10 +59,14 @@ The configuration file is automatically generated at `~/.mkv-episode-matcher/con
 
 ```ini
 [Config]
-tmdb_api_key = your_api_key
-open_subtitles_api_key = your_opensubs_key
-show_dir = /path/to/shows
+tmdb_api_key = your_tmdb_api_key
+show_dir = /path/to/show
 max_threads = 4
+open_subtitles_api_key = your_opensubs_key
+open_subtitles_user_agent = your_user_agent
+open_subtitles_username = your_username
+open_subtitles_password = your_password
+tesseract_path = C:\Program Files\Tesseract-OCR\tesseract.exe
 ```
 
 ## Next Steps

{mkv_episode_matcher-0.3.5 → mkv_episode_matcher-0.4.0}/mkv_episode_matcher/__main__.py

@@ -92,7 +92,18 @@ def main():
         nargs="?",
         help="Path to the tesseract executable (default: None)",
     )
+    parser.add_argument(
+        "--check-gpu",
+        type=bool,
+        default=False,
+        nargs="?",
+        help="Check if GPU is available (default: False)",
+    )
     args = parser.parse_args()
+    if args.check_gpu:
+        from mkv_episode_matcher.speech_to_text import check_gpu_support
+        check_gpu_support()
+        return
     logger.debug(f"Command-line arguments: {args}")
     open_subtitles_api_key = ""
     open_subtitles_user_agent = ""

{mkv_episode_matcher-0.3.5 → mkv_episode_matcher-0.4.0}/mkv_episode_matcher/episode_identification.py

@@ -96,14 +96,27 @@ class EpisodeMatcher:
             # Load Whisper model
             model = whisper.load_model("base", device=self.device)
             
-            # Get season-specific reference files
+            # Get season-specific reference files using multiple patterns
             reference_dir = self.cache_dir / "data" / self.show_name
-            season_pattern = f"S{season_number:02d}E"
-            reference_files = [
-                f for f in reference_dir.glob("*.srt")
-                if season_pattern in f.name
+            
+            # Create season patterns for different formats
+            patterns = [
+                f"S{season_number:02d}E",  # S01E01
+                f"S{season_number}E",      # S1E01
+                f"{season_number:02d}x",   # 01x01
+                f"{season_number}x",       # 1x01
             ]
             
+            reference_files = []
+            for pattern in patterns:
+                files = [f for f in reference_dir.glob("*.srt") 
+                        if any(re.search(f"{p}\\d+", f.name, re.IGNORECASE) 
+                        for p in patterns)]
+                reference_files.extend(files)
+            
+            # Remove duplicates while preserving order
+            reference_files = list(dict.fromkeys(reference_files))
+            
             if not reference_files:
                 logger.error(f"No reference files found for season {season_number}")
                 return None

{mkv_episode_matcher-0.3.5 → mkv_episode_matcher-0.4.0}/mkv_episode_matcher/episode_matcher.py

@@ -29,6 +29,14 @@ def process_show(season=None, dry_run=False, get_subs=False):
     show_name = clean_text(os.path.basename(show_dir))
     matcher = EpisodeMatcher(CACHE_DIR, show_name)
     
+    # Early check for reference files
+    reference_dir = Path(CACHE_DIR) / "data" / show_name
+    reference_files = list(reference_dir.glob("*.srt"))
+    if not reference_files:
+        logger.error(f"No reference subtitle files found in {reference_dir}")
+        logger.info("Please download reference subtitles first")
+        return
+        
     season_paths = get_valid_seasons(show_dir)
     if not season_paths:
         logger.warning(f"No seasons with .mkv files found")

{mkv_episode_matcher-0.3.5 → mkv_episode_matcher-0.4.0}/mkv_episode_matcher/speech_to_text.py

@@ -87,4 +87,10 @@ def extract_audio(mkv_file, output_dir):
     else:
         logger.info(f"Audio file {wav_file} already exists, skipping extraction")
     
-    return wav_file
+    return wav_file
+def check_gpu_support():
+    logger.info('Checking GPU support...')
+    if torch.cuda.is_available():
+        logger.info(f"CUDA is available. Using GPU: {torch.cuda.get_device_name(0)}")
+    else:
+        logger.warning("CUDA not available. Using CPU. Refer to https://pytorch.org/get-started/locally/ for GPU support.")

{mkv_episode_matcher-0.3.5 → mkv_episode_matcher-0.4.0}/mkv_episode_matcher/utils.py

@@ -300,7 +300,7 @@ def extract_srt_text(filepath):
 
 def extract_season_episode(filename):
     """
-    Extract season and episode numbers from filename.
+    Extract season and episode numbers from filename with support for multiple formats.
     
     Args:
         filename (str): Filename to parse
@@ -308,10 +308,20 @@ def extract_season_episode(filename):
     Returns:
         tuple: (season_number, episode_number)
     """
-    match = re.search(r'S(\d+)E(\d+)', filename)
-    if match:
-        return int(match.group(1)), int(match.group(2))
+    # List of patterns to try
+    patterns = [
+        r'S(\d+)E(\d+)',          # S01E01
+        r'(\d+)x(\d+)',           # 1x01 or 01x01
+        r'Season\s*(\d+).*?(\d+)' # Season 1 - 01
+    ]
+    
+    for pattern in patterns:
+        match = re.search(pattern, filename, re.IGNORECASE)
+        if match:
+            return int(match.group(1)), int(match.group(2))
+            
     return None, None
+
 def process_srt_files(show_dir):
     """
     Process all SRT files in the given directory and its subdirectories.

{mkv_episode_matcher-0.3.5 → mkv_episode_matcher-0.4.0}/mkv_episode_matcher.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: mkv-episode-matcher
-Version: 0.3.5
+Version: 0.4.0
 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
@@ -25,7 +25,18 @@ Requires-Dist: pytesseract>=0.3.13
 Requires-Dist: rapidfuzz>=3.10.1
 Requires-Dist: requests>=2.32.3
 Requires-Dist: tmdb-client>=0.0.1
+Requires-Dist: torch>=2.5.1
+Requires-Dist: torchaudio>=2.5.1
+Requires-Dist: torchvision>=0.20.1
 Requires-Dist: wave>=0.0.2
+Provides-Extra: cpu
+Requires-Dist: torch>=2.5.1; extra == "cpu"
+Requires-Dist: torchvision>=0.20.1; extra == "cpu"
+Requires-Dist: torchaudio>=2.5.1; extra == "cpu"
+Provides-Extra: cu124
+Requires-Dist: torch>=2.5.1; extra == "cu124"
+Requires-Dist: torchvision>=0.20.1; extra == "cu124"
+Requires-Dist: torchaudio>=2.5.1; extra == "cu124"
 
 # MKV Episode Matcher
 
@@ -65,10 +76,11 @@ Automatically match and rename your MKV TV episodes using The Movie Database (TM
 ```bash
 pip install mkv-episode-matcher
 ```
+2. Download .srt subtitles files to ~/.mkv-episode-matcher/cache/data/Show Name/
 
-2. Run on your show directory:
+3. Run on your show directory:
 ```bash
-mkv-match --show-dir "path/to/your/show" --get-subs true
+mkv-match --show-dir "path/to/your/show"
 ```
 
 ## Documentation

{mkv_episode_matcher-0.3.5 → mkv_episode_matcher-0.4.0}/mkv_episode_matcher.egg-info/requires.txt

@@ -7,4 +7,17 @@ pytesseract>=0.3.13
 rapidfuzz>=3.10.1
 requests>=2.32.3
 tmdb-client>=0.0.1
+torch>=2.5.1
+torchaudio>=2.5.1
+torchvision>=0.20.1
 wave>=0.0.2
+
+[cpu]
+torch>=2.5.1
+torchvision>=0.20.1
+torchaudio>=2.5.1
+
+[cu124]
+torch>=2.5.1
+torchvision>=0.20.1
+torchaudio>=2.5.1

{mkv_episode_matcher-0.3.5 → mkv_episode_matcher-0.4.0}/pyproject.toml

@@ -32,6 +32,9 @@ dependencies = [
     "rapidfuzz>=3.10.1",
     "requests>=2.32.3",
     "tmdb-client>=0.0.1",
+    "torch>=2.5.1",
+    "torchaudio>=2.5.1",
+    "torchvision>=0.20.1",
     "wave>=0.0.2",
 ]
 [project.urls]
@@ -50,6 +53,49 @@ dev = [
     "chardet>=5.2.0",
 ]
 
+[project.optional-dependencies]
+cpu = [
+  "torch>=2.5.1",
+  "torchvision>=0.20.1",
+  "torchaudio>=2.5.1",
+]
+cu124 = [
+  "torch>=2.5.1",
+  "torchvision>=0.20.1",
+    "torchaudio>=2.5.1",
+]
+
+[tool.uv]
+conflicts = [
+  [
+    { extra = "cpu" },
+    { extra = "cu124" },
+  ],
+]
+
+[tool.uv.sources]
+torch = [
+  { index = "pytorch-cpu", extra = "cpu" },
+  { index = "pytorch-cu124", extra = "cu124" },
+]
+torchvision = [
+  { index = "pytorch-cpu", extra = "cpu" },
+  { index = "pytorch-cu124", extra = "cu124" },
+]
+torchaudio = [
+  { index = "pytorch-cpu", extra = "cpu" },
+  { index = "pytorch-cu124", extra = "cu124" },
+]
+
+[[tool.uv.index]]
+name = "pytorch-cpu"
+url = "https://download.pytorch.org/whl/cpu"
+explicit = true
+
+[[tool.uv.index]]
+name = "pytorch-cu124"
+url = "https://download.pytorch.org/whl/cu124"
+explicit = true
 
 [tool.ruff.format]
 preview = true

{mkv_episode_matcher-0.3.5 → mkv_episode_matcher-0.4.0}/setup.cfg

@@ -1,6 +1,6 @@
 [metadata]
 name = mkv_episode_matcher
-version = 0.3.5
+version = 0.4.0
 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.