mkv-episode-matcher 0.5.0__py3-none-any.whl → 0.6.0__py3-none-any.whl

mkv_episode_matcher/episode_matcher.py

@@ -1,33 +1,33 @@
 # mkv_episode_matcher/episode_matcher.py
 
-from pathlib import Path
-import shutil
 import glob
 import os
-from loguru import logger
 import re
-from mkv_episode_matcher.__main__ import CONFIG_FILE, CACHE_DIR
+import shutil
+from pathlib import Path
+
+from loguru import logger
+
+from mkv_episode_matcher.__main__ import CACHE_DIR, CONFIG_FILE
 from mkv_episode_matcher.config import get_config
-from mkv_episode_matcher.mkv_to_srt import convert_mkv_to_srt
+from mkv_episode_matcher.episode_identification import EpisodeMatcher
 from mkv_episode_matcher.tmdb_client import fetch_show_id
 from mkv_episode_matcher.utils import (
     check_filename,
     clean_text,
-    cleanup_ocr_files,
     get_subtitles,
-    process_reference_srt_files,
-    process_srt_files,
-    compare_and_rename_files,get_valid_seasons,rename_episode_file
+    get_valid_seasons,
+    rename_episode_file,
 )
-from mkv_episode_matcher.episode_identification import EpisodeMatcher
+
 
 def process_show(season=None, dry_run=False, get_subs=False):
-    """Process the show using streaming speech recognition with OCR fallback."""
+    """Process the show using streaming speech recognition."""
     config = get_config(CONFIG_FILE)
     show_dir = config.get("show_dir")
     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"))
@@ -35,10 +35,10 @@ def process_show(season=None, dry_run=False, get_subs=False):
         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")
+        logger.warning("No seasons with .mkv files found")
         return
 
     if season is not None:
@@ -51,55 +51,35 @@ def process_show(season=None, dry_run=False, get_subs=False):
     for season_path in season_paths:
         mkv_files = [f for f in glob.glob(os.path.join(season_path, "*.mkv"))
                     if not check_filename(f)]
-        
+
         if not mkv_files:
             logger.info(f"No new files to process in {season_path}")
             continue
 
         season_num = int(re.search(r'Season (\d+)', season_path).group(1))
         temp_dir = Path(season_path) / "temp"
-        ocr_dir = Path(season_path) / "ocr"
         temp_dir.mkdir(exist_ok=True)
-        ocr_dir.mkdir(exist_ok=True)
 
         try:
             if get_subs:
                 show_id = fetch_show_id(matcher.show_name)
                 if show_id:
                     get_subtitles(show_id, seasons={season_num}, config=config)
-                    
-            unmatched_files = []
+
             for mkv_file in mkv_files:
                 logger.info(f"Attempting speech recognition match for {mkv_file}")
                 match = matcher.identify_episode(mkv_file, temp_dir, season_num)
-                
+
                 if match:
                     new_name = f"{matcher.show_name} - S{match['season']:02d}E{match['episode']:02d}.mkv"
                     logger.info(f"Speech matched {os.path.basename(mkv_file)} to {new_name} "
                               f"(confidence: {match['confidence']:.2f})")
-                    
+
                     if not dry_run:
                         logger.info(f"Renaming {mkv_file} to {new_name}")
                         rename_episode_file(mkv_file, new_name)
                 else:
-                    logger.info(f"Speech recognition match failed for {mkv_file}, trying OCR")
-                    unmatched_files.append(mkv_file)
-
-            # OCR fallback for unmatched files
-            if unmatched_files:
-                logger.info(f"Attempting OCR matching for {len(unmatched_files)} unmatched files")
-                convert_mkv_to_srt(season_path, unmatched_files)
-                
-                reference_text_dict = process_reference_srt_files(matcher.show_name)
-                srt_text_dict = process_srt_files(str(ocr_dir))
-                
-                compare_and_rename_files(
-                    srt_text_dict, 
-                    reference_text_dict, 
-                    dry_run=dry_run,
-                )
-
+                    logger.info(f"Speech recognition match failed for {mkv_file}")
         finally:
             if not dry_run:
                 shutil.rmtree(temp_dir)
-                cleanup_ocr_files(show_dir)

mkv_episode_matcher/subtitle_utils.py

@@ -1,82 +1,83 @@
-from typing import List, Optional, Union
 import os
 import re
+from typing import Optional
 
-def generate_subtitle_patterns(series_name: str, season: int, episode: int) -> List[str]:
+
+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]:
+
+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('\\', '-')
-    
+    filename = filename.replace(":", " -")
+    filename = filename.replace("/", "-")
+    filename = filename.replace("\\", "-")
+
     # Remove any other invalid characters
-    filename = re.sub(r'[<>:"/\\|?*]', '', filename)
-    
-    return filename.strip()
+    filename = re.sub(r'[<>:"/\\|?*]', "", filename)
+
+    return filename.strip()

mkv_episode_matcher/utils.py

@@ -2,15 +2,18 @@
 import os
 import re
 import shutil
-import torch
+
 import requests
+import torch
 from loguru import logger
 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.subtitle_utils import find_existing_subtitle, sanitize_filename
 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.
@@ -36,13 +39,17 @@ def get_valid_seasons(show_dir):
             valid_season_paths.append(season_path)
 
     if not valid_season_paths:
-        logger.warning(f"No seasons with .mkv files found in show '{os.path.basename(show_dir)}'")
+        logger.warning(
+            f"No seasons with .mkv files found in show '{os.path.basename(show_dir)}'"
+        )
     else:
         logger.info(
             f"Found {len(valid_season_paths)} seasons with .mkv files in '{os.path.basename(show_dir)}'"
         )
 
     return valid_season_paths
+
+
 def check_filename(filename):
     """
     Check if the filename is in the correct format (S01E02).
@@ -54,7 +61,7 @@ def check_filename(filename):
         bool: True if the filename matches the expected pattern.
     """
     # Check if the filename matches the expected format
-    match = re.search(r'.*S\d+E\d+', filename)
+    match = re.search(r".*S\d+E\d+", filename)
     return bool(match)
 
 
@@ -95,11 +102,11 @@ def rename_episode_file(original_file_path, new_filename):
     """
     original_dir = os.path.dirname(original_file_path)
     new_file_path = os.path.join(original_dir, new_filename)
-    
+
     # Check if new filepath already exists
     if os.path.exists(new_file_path):
         logger.warning(f"File already exists: {new_filename}")
-        
+
         # Add numeric suffix if file exists
         base, ext = os.path.splitext(new_filename)
         suffix = 2
@@ -109,7 +116,7 @@ def rename_episode_file(original_file_path, new_filename):
             if not os.path.exists(new_file_path):
                 break
             suffix += 1
-    
+
     try:
         os.rename(original_file_path, new_file_path)
         logger.info(f"Renamed {os.path.basename(original_file_path)} -> {new_filename}")
@@ -120,7 +127,8 @@ def rename_episode_file(original_file_path, new_filename):
     except FileExistsError as e:
         logger.error(f"Failed to rename file: {e}")
         return None
-        
+
+
 def get_subtitles(show_id, seasons: set[int], config=None):
     """
     Retrieves and saves subtitles for a given TV show and seasons.
@@ -164,19 +172,21 @@ def get_subtitles(show_id, seasons: set[int], config=None):
 
         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)}")
+                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,
@@ -189,7 +199,7 @@ def get_subtitles(show_id, seasons: set[int], config=None):
             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:
@@ -210,33 +220,13 @@ def get_subtitles(show_id, seasons: set[int], config=None):
                     break
 
 
-def cleanup_ocr_files(show_dir):
-    """
-    Clean up OCR files generated during the episode matching process.
-
-    Args:
-        show_dir (str): The directory containing the show files.
-
-    Returns:
-        None
-
-    This function cleans up the OCR files generated during the episode matching process.
-    It deletes the 'ocr' directory and all its contents in each season directory of the show.
-    """
-    for season_dir in os.listdir(show_dir):
-        season_dir_path = os.path.join(show_dir, season_dir)
-        ocr_dir_path = os.path.join(season_dir_path, "ocr")
-        if os.path.exists(ocr_dir_path):
-            logger.info(f"Cleaning up OCR files in {ocr_dir_path}")
-            shutil.rmtree(ocr_dir_path)
-
-
 def clean_text(text):
     # Remove brackets, parentheses, and their content
     cleaned_text = re.sub(r"\[.*?\]|\(.*?\)|\{.*?\}", "", text)
     # Strip leading/trailing whitespace
     return cleaned_text.strip()
 
+
 @logger.catch
 def process_reference_srt_files(series_name):
     """
@@ -249,12 +239,13 @@ def process_reference_srt_files(series_name):
         dict: A dictionary containing the reference files where the keys are the MKV filenames
               and the values are the corresponding SRT texts.
     """
-    from mkv_episode_matcher.__main__ import CACHE_DIR
     import os
-    
+
+    from mkv_episode_matcher.__main__ import CACHE_DIR
+
     reference_files = {}
     reference_dir = os.path.join(CACHE_DIR, "data", series_name)
-    
+
     for dirpath, _, filenames in os.walk(reference_dir):
         for filename in filenames:
             if filename.lower().endswith(".srt"):
@@ -264,9 +255,10 @@ def process_reference_srt_files(series_name):
                 season, episode = extract_season_episode(filename)
                 mkv_filename = f"{series_name} - S{season:02}E{episode:02}.mkv"
                 reference_files[mkv_filename] = srt_text
-                
+
     return reference_files
 
+
 def extract_srt_text(filepath):
     """
     Extracts text content from an SRT file.
@@ -280,49 +272,51 @@ def extract_srt_text(filepath):
     # Read the file content
     with open(filepath) as f:
         content = f.read()
-        
+
     # Split into subtitle blocks
-    blocks = content.strip().split('\n\n')
-    
+    blocks = content.strip().split("\n\n")
+
     text_lines = []
     for block in blocks:
-        lines = block.split('\n')
+        lines = block.split("\n")
         if len(lines) < 3:
             continue
-            
+
         # Skip index and timestamp, get all remaining lines as text
-        text = ' '.join(lines[2:])
+        text = " ".join(lines[2:])
         # Remove stage directions and tags
-        text = re.sub(r'\[.*?\]|\<.*?\>', '', text)
+        text = re.sub(r"\[.*?\]|\<.*?\>", "", text)
         if text:
             text_lines.append(text)
-            
+
     return text_lines
 
+
 def extract_season_episode(filename):
     """
     Extract season and episode numbers from filename with support for multiple formats.
-    
+
     Args:
         filename (str): Filename to parse
-        
+
     Returns:
         tuple: (season_number, episode_number)
     """
     # 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
+        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.
@@ -342,6 +336,8 @@ def process_srt_files(show_dir):
                 srt_text = extract_srt_text(srt_file)
                 srt_files[srt_file] = srt_text
     return srt_files
+
+
 def compare_and_rename_files(srt_files, reference_files, dry_run=False):
     """
     Compare the srt files with the reference files and rename the matching mkv files.
@@ -372,6 +368,7 @@ def compare_and_rename_files(srt_files, reference_files, dry_run=False):
                     logger.info(f"Renaming {mkv_file} to {new_filename}")
                     rename_episode_file(mkv_file, new_filename)
 
+
 def compare_text(text1, text2):
     """
     Compare two lists of text lines and return the number of matching lines.
@@ -391,9 +388,12 @@ def compare_text(text1, text2):
     matching_lines = set(flat_text1).intersection(flat_text2)
     return len(matching_lines)
 
+
 def check_gpu_support():
-    logger.info('Checking 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.")
+        logger.warning(
+            "CUDA not available. Using CPU. Refer to https://pytorch.org/get-started/locally/ for GPU support."
+        )

{mkv_episode_matcher-0.5.0.dist-info → mkv_episode_matcher-0.6.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: mkv-episode-matcher
-Version: 0.5.0
+Version: 0.6.0
 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
@@ -21,7 +21,6 @@ Requires-Dist: ffmpeg>=1.4
 Requires-Dist: loguru>=0.7.2
 Requires-Dist: openai-whisper>=20240930
 Requires-Dist: opensubtitlescom>=0.1.5
-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
@@ -29,14 +28,6 @@ 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
 
@@ -48,7 +39,7 @@ Requires-Dist: torchaudio>=2.5.1; extra == "cu124"
 [![GitHub last commit](https://img.shields.io/github/last-commit/Jsakkos/mkv-episode-matcher)](https://github.com/Jsakkos/mkv-episode-matcher/commits/main)
 [![GitHub issues](https://img.shields.io/github/issues/Jsakkos/mkv-episode-matcher)](https://github.com/Jsakkos/mkv-episode-matcher/issues)
 [![Tests](https://github.com/Jsakkos/mkv-episode-matcher/actions/workflows/tests.yml/badge.svg)](https://github.com/Jsakkos/mkv-episode-matcher/actions/workflows/tests.yml)
-[![codecov](https://codecov.io/gh/Jsakkos/mkv-episode-matcher/branch/main/graph/badge.svg)](https://codecov.io/gh/Jsakkos/mkv-episode-matcher)
+[![codecov](https://codecov.io/gh/Jsakkos/mkv-episode-matcher/branch/main/graph/badge.svg)](https://codecov.io/gh/Jsakkos/mkv-episode-matcher/)
 
 Automatically match and rename your MKV TV episodes using The Movie Database (TMDb).
 
@@ -56,7 +47,7 @@ Automatically match and rename your MKV TV episodes using The Movie Database (TM
 
 - 🎯 **Automatic Episode Matching**: Uses TMDb to accurately identify episodes
 - 📝 **Subtitle Extraction**: Extracts subtitles from MKV files
-- 🔍 **OCR Support**: Handles image-based subtitles
+- 🔊 **Speech Recognition**: Uses Whisper for accurate episode identification
 - 🚀 **Multi-threaded**: Fast processing of multiple files
 - ⬇️ **Subtitle Downloads**: Integration with OpenSubtitles
 - ✨ **Bulk Processing**: Handle entire seasons at once
@@ -66,7 +57,6 @@ Automatically match and rename your MKV TV episodes using The Movie Database (TM
 
 - 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 (optional, for subtitle downloads)
 - OpenSubtitles account (optional, for subtitle downloads)
 
@@ -135,3 +125,7 @@ Distributed under the MIT License. See `LICENSE` for more information.
 ## Documentation
 
 Full documentation is available at [https://jsakkos.github.io/mkv-episode-matcher/](https://jsakkos.github.io/mkv-episode-matcher/)
+
+## Changelog
+
+See [CHANGELOG.md](CHANGELOG.md) for a detailed list of changes.

mkv_episode_matcher-0.6.0.dist-info/RECORD

@@ -0,0 +1,14 @@
+mkv_episode_matcher/.gitattributes,sha256=Gh2-F2vCM7SZ01pX23UT8pQcmauXWfF3gwyRSb6ZAFs,66
+mkv_episode_matcher/__init__.py,sha256=u3yZcpuK0ICeUjxYKePvW-zS61E5ss5q2AvqnSHuz9E,240
+mkv_episode_matcher/__main__.py,sha256=-iRYoAfut3eDfV29UvobJvCKmYTpsOn8qM49QBFnMUM,5735
+mkv_episode_matcher/config.py,sha256=EcJJjkekQ7oWtarUkufCYON_QWbQvq55-zMqCTOqSa4,2265
+mkv_episode_matcher/episode_identification.py,sha256=rWhUzeNE5_uqsLcRuw_B6g7k3ud9Oa1oKgvXrBA-Jsc,12457
+mkv_episode_matcher/episode_matcher.py,sha256=Yqos1hImF_QIZ8cV0IlemUxhpHwvwBn-mg89N9NDq9U,3126
+mkv_episode_matcher/subtitle_utils.py,sha256=Hz9b4CKPV07YKTY4dcN3WbvdbvH-S3J4zcb9CiyvPlE,2551
+mkv_episode_matcher/tmdb_client.py,sha256=LbMCgjmp7sCbrQo_CDlpcnryKPz5S7inE24YY9Pyjk4,4172
+mkv_episode_matcher/utils.py,sha256=1-RwYn1w_YQFp4KxTmYbCSQEieK-mnToVIS34EVAZLw,13837
+mkv_episode_matcher-0.6.0.dist-info/METADATA,sha256=LBtoWNzGS5Exd0H5q6fP5MdBSsMPOieYMOQ5uQoBZ64,5193
+mkv_episode_matcher-0.6.0.dist-info/WHEEL,sha256=jB7zZ3N9hIM9adW7qlTAyycLYW9npaWKLRzaoVcLKcM,91
+mkv_episode_matcher-0.6.0.dist-info/entry_points.txt,sha256=IglJ43SuCZq2eQ3shMFILCkmQASJHnDCI3ogohW2Hn4,64
+mkv_episode_matcher-0.6.0.dist-info/top_level.txt,sha256=XRLbd93HUaedeWLtkyTvQjFcE5QcBRYa3V-CfHrq-OI,20
+mkv_episode_matcher-0.6.0.dist-info/RECORD,,

{mkv_episode_matcher-0.5.0.dist-info → mkv_episode_matcher-0.6.0.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (75.8.0)
+Generator: setuptools (75.8.2)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

mkv_episode_matcher/libraries/pgs2srt/.gitignore

@@ -1,2 +0,0 @@
-__pycache__/
-.DS_Store