mkv-episode-matcher 0.9.7__tar.gz → 0.9.8__tar.gz

{mkv_episode_matcher-0.9.7 → mkv_episode_matcher-0.9.8}/.claude/settings.local.json

@@ -13,7 +13,9 @@
       "Bash(git add:*)",
       "Bash(git commit:*)",
       "Bash(git push:*)",
-      "Bash(rm:*)"
+      "Bash(rm:*)",
+      "Bash(uv sync:*)",
+      "Bash(grep:*)"
     ],
     "deny": []
   }

mkv_episode_matcher-0.9.8/CLAUDE.md

@@ -0,0 +1,148 @@
+# CLAUDE.md
+
+This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
+
+## Development Commands
+
+### Testing
+```bash
+# Run all tests with coverage
+uv run pytest --cov=mkv_episode_matcher --cov-report=term-missing
+
+# Run specific test file
+uv run pytest tests/test_main.py -v
+
+# Run tests in verbose mode
+uv run pytest -v
+```
+
+### Linting and Formatting
+```bash
+# Run ruff linting
+uv run ruff check .
+
+# Run ruff formatting
+uv run ruff format .
+
+# Fix auto-fixable issues
+uv run ruff check --fix .
+```
+
+### Dependency Management and Installation
+```bash
+# Install dependencies
+uv sync
+
+# Install with dev dependencies (default behavior)
+uv sync --group dev
+
+# Add new dependency
+uv add package-name
+
+# Add dev dependency
+uv add --group dev package-name
+
+# Install in editable mode for development
+uv sync --editable
+
+# Build distribution packages
+uv build
+```
+
+### Running the Application
+```bash
+# Run onboarding (first time setup)
+mkv-match --onboard
+
+# Process a show directory
+mkv-match --show-dir "/path/to/show"
+
+# Dry run mode (test without making changes)
+mkv-match --show-dir "/path/to/show" --dry-run
+
+# Process specific season
+mkv-match --show-dir "/path/to/show" --season 1
+
+# Download subtitles and process
+mkv-match --show-dir "/path/to/show" --get-subs
+```
+
+## Architecture Overview
+
+### Core Components
+
+**Main Entry Point** (`__main__.py`):
+- CLI argument parsing and rich console interface
+- Configuration management and onboarding flow
+- Coordinates the overall process execution
+
+**Episode Matcher** (`episode_matcher.py`):
+- High-level orchestration of the matching process
+- Progress tracking and user feedback
+- Handles season/episode file processing workflow
+
+**Episode Identification** (`episode_identification.py`):
+- Core speech recognition using OpenAI Whisper
+- Subtitle comparison and matching algorithms
+- Audio extraction and processing with FFmpeg
+- Caching systems for performance optimization
+
+**Configuration System** (`config.py`):
+- INI-based configuration management
+- API key and credential storage
+- Show directory and user preferences
+
+**Utilities** (`utils.py`):
+- File operations (renaming, validation)
+- Text processing and cleaning
+- Season/episode extraction from filenames
+
+### Dependencies
+
+**Required External Tools**:
+- FFmpeg (for audio extraction from MKV files)
+- Python 3.9-3.12
+
+**Key Python Dependencies**:
+- OpenAI Whisper (speech recognition)
+- TMDb Client (show metadata)
+- OpenSubtitles API (subtitle downloads)
+- Rich (CLI interface)
+- RapidFuzz (text matching)
+- PyTorch (Whisper backend)
+
+### Data Flow
+
+1. **Configuration**: Load user settings, API keys, and show directory
+2. **File Discovery**: Find MKV files in season directories
+3. **Audio Extraction**: Extract audio chunks from MKV files using FFmpeg
+4. **Speech Recognition**: Use Whisper to transcribe audio chunks
+5. **Subtitle Matching**: Compare transcriptions with reference subtitles
+6. **File Renaming**: Rename files based on identified episodes
+
+### Caching Strategy
+
+- **Whisper Models**: Cached globally to avoid reloading
+- **Audio Chunks**: Temporary files cached during processing
+- **Reference Subtitles**: Parsed subtitle content cached per session
+- **Video Duration**: FFprobe results cached with LRU cache
+
+### Configuration Files
+
+- **Config Location**: `~/.mkv-episode-matcher/config.ini`
+- **Cache Directory**: `~/.mkv-episode-matcher/cache/`
+- **Logs Directory**: `~/.mkv-episode-matcher/logs/`
+
+### Testing Strategy
+
+- Uses pytest with fixtures for mock data
+- Coverage reporting configured via pytest-cov
+- Test files follow `test_*.py` naming convention
+- Mocks external dependencies (TMDb API, file operations)
+
+### Code Quality
+
+- Ruff for linting and formatting
+- Type hints where applicable
+- Comprehensive error handling and logging
+- Rich console output for user experience

{mkv_episode_matcher-0.9.7 → mkv_episode_matcher-0.9.8}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mkv-episode-matcher
-Version: 0.9.7
+Version: 0.9.8
 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

{mkv_episode_matcher-0.9.7 → mkv_episode_matcher-0.9.8}/mkv_episode_matcher/__main__.py

@@ -122,6 +122,7 @@ def select_season(seasons):
     selected_season = seasons[int(choice) - 1]
     return int(Path(selected_season).name.replace("Season ", ""))
 
+
 def onboarding(config_path):
     """Prompt user for all required config values, showing existing as defaults."""
     config = get_config(config_path) if config_path.exists() else {}
@@ -153,6 +154,7 @@ def onboarding(config_path):
     )
     console.print("[bold green]Onboarding complete! Configuration saved.[/bold green]")
 
+
 @logger.catch
 def main():
     """

{mkv_episode_matcher-0.9.7 → mkv_episode_matcher-0.9.8}/mkv_episode_matcher/utils.py

@@ -304,8 +304,20 @@ def get_subtitles(show_id, seasons: set[int], config=None, max_retries=3):
 
 
 def clean_text(text):
-    # Remove brackets, parentheses, and their content
-    cleaned_text = re.sub(r"\[.*?\]|\(.*?\)|\{.*?\}", "", text)
+    # Remove brackets and curly braces with their content
+    cleaned_text = re.sub(r"\[.*?\]|\{.*?\}", "", text)
+    # Remove parentheses content EXCEPT for those containing exactly 4 digits (years)
+    # First, temporarily replace year patterns with a placeholder
+    year_pattern = r"\((\d{4})\)"
+    years = re.findall(year_pattern, cleaned_text)
+    cleaned_text = re.sub(year_pattern, "YEAR_PLACEHOLDER", cleaned_text)
+    # Remove all remaining parentheses content
+    cleaned_text = re.sub(r"\([^)]*\)", "", cleaned_text)
+    # Restore the years
+    for year in years:
+        cleaned_text = cleaned_text.replace("YEAR_PLACEHOLDER", f"({year})", 1)
+    # Normalize multiple spaces to single spaces
+    cleaned_text = re.sub(r"\s+", " ", cleaned_text)
     # Strip leading/trailing whitespace
     return cleaned_text.strip()
 

{mkv_episode_matcher-0.9.7 → mkv_episode_matcher-0.9.8}/mkv_episode_matcher.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mkv-episode-matcher
-Version: 0.9.7
+Version: 0.9.8
 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

{mkv_episode_matcher-0.9.7 → mkv_episode_matcher-0.9.8}/mkv_episode_matcher.egg-info/SOURCES.txt

@@ -4,6 +4,7 @@
 .gitmodules
 .python-version
 CHANGELOG.md
+CLAUDE.md
 LICENSE
 README.md
 mkdocs.yml

{mkv_episode_matcher-0.9.7 → mkv_episode_matcher-0.9.8}/setup.cfg

@@ -1,6 +1,6 @@
 [metadata]
 name = mkv_episode_matcher
-version = 0.9.7
+version = 0.9.8
 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-0.9.7 → mkv_episode_matcher-0.9.8}/tests/test_episode_identification.py

@@ -1,8 +1,7 @@
-import unittest
 import tempfile
-import re
+import unittest
 from pathlib import Path
-from unittest.mock import Mock, patch
+from unittest.mock import Mock
 
 from mkv_episode_matcher.episode_identification import EpisodeMatcher
 

{mkv_episode_matcher-0.9.7 → mkv_episode_matcher-0.9.8}/tests/test_main.py

@@ -72,6 +72,48 @@ class TestUtilities:
     def test_clean_text(self):
         text = "Test [action] (note) {tag}"
         assert clean_text(text) == "Test"
+        
+        # Test that years are preserved
+        text_with_year = "Bluey (2018)"
+        assert clean_text(text_with_year) == "Bluey (2018)"
+        
+        # Test mixed content with year
+        text_mixed = "Show Name [HD] (2020) {release}"
+        assert clean_text(text_mixed) == "Show Name (2020)"
+
+    def test_clean_text_edge_cases(self):
+        """Test edge cases for clean_text function reported by users."""
+        # Test exact user reported case
+        bluey_case = "Bluey (2018)"
+        assert clean_text(bluey_case) == "Bluey (2018)"
+        
+        # Test with extra whitespace and tags
+        bluey_with_junk = "Bluey [1080p] (2018) {AMZN}"
+        assert clean_text(bluey_with_junk) == "Bluey (2018)"
+        
+        # Test show name with multiple years (should preserve all)
+        multiple_years = "Show (1999) vs Show (2020)"
+        assert clean_text(multiple_years) == "Show (1999) vs Show (2020)"
+        
+        # Test year at beginning
+        year_first = "(2018) Bluey [HD]"
+        assert clean_text(year_first) == "(2018) Bluey"
+        
+        # Test year with other content in same parentheses (should remove)
+        year_with_text = "Show (2018 Remaster)"
+        assert clean_text(year_with_text) == "Show"
+        
+        # Test 4-digit numbers (preserves any 4-digit number in parentheses)
+        four_digit = "Show (1234)"
+        assert clean_text(four_digit) == "Show (1234)"
+        
+        # Test edge case years
+        assert clean_text("Show (1900)") == "Show (1900)"  # Very old year
+        assert clean_text("Show (2099)") == "Show (2099)"  # Future year
+        
+        # Test multiple spaces and normalization
+        messy_spacing = "Bluey    [HD]     (2018)    {RELEASE}"
+        assert clean_text(messy_spacing) == "Bluey (2018)"
 
     def test_extract_season_episode(self):
         filename = "Show - S01E02.mkv"