mkv-episode-matcher 0.3.4__tar.gz → 0.3.5__tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Potentially problematic release.


This version of mkv-episode-matcher might be problematic. Click here for more details.

Files changed (53) hide show
  1. mkv_episode_matcher-0.3.5/.coverage +0 -0
  2. mkv_episode_matcher-0.3.5/.github/workflows/tests.yml +40 -0
  3. {mkv_episode_matcher-0.3.4 → mkv_episode_matcher-0.3.5}/PKG-INFO +28 -27
  4. {mkv_episode_matcher-0.3.4 → mkv_episode_matcher-0.3.5}/README.md +26 -25
  5. {mkv_episode_matcher-0.3.4 → mkv_episode_matcher-0.3.5}/docs/quickstart.md +9 -15
  6. {mkv_episode_matcher-0.3.4 → mkv_episode_matcher-0.3.5}/mkv_episode_matcher/episode_identification.py +144 -25
  7. {mkv_episode_matcher-0.3.4 → mkv_episode_matcher-0.3.5}/mkv_episode_matcher.egg-info/PKG-INFO +28 -27
  8. {mkv_episode_matcher-0.3.4 → mkv_episode_matcher-0.3.5}/mkv_episode_matcher.egg-info/SOURCES.txt +2 -1
  9. {mkv_episode_matcher-0.3.4 → mkv_episode_matcher-0.3.5}/pyproject.toml +1 -0
  10. {mkv_episode_matcher-0.3.4 → mkv_episode_matcher-0.3.5}/setup.cfg +1 -1
  11. {mkv_episode_matcher-0.3.4 → mkv_episode_matcher-0.3.5}/tests/test_main.py +48 -18
  12. {mkv_episode_matcher-0.3.4 → mkv_episode_matcher-0.3.5}/uv.lock +12 -1
  13. mkv_episode_matcher-0.3.4/tests/test_improvements.py +0 -59
  14. {mkv_episode_matcher-0.3.4 → mkv_episode_matcher-0.3.5}/.gitattributes +0 -0
  15. {mkv_episode_matcher-0.3.4 → mkv_episode_matcher-0.3.5}/.github/funding.yml +0 -0
  16. {mkv_episode_matcher-0.3.4 → mkv_episode_matcher-0.3.5}/.github/workflows/documentation.yml +0 -0
  17. {mkv_episode_matcher-0.3.4 → mkv_episode_matcher-0.3.5}/.github/workflows/python-publish.yml +0 -0
  18. {mkv_episode_matcher-0.3.4 → mkv_episode_matcher-0.3.5}/.gitignore +0 -0
  19. {mkv_episode_matcher-0.3.4 → mkv_episode_matcher-0.3.5}/.gitmodules +0 -0
  20. {mkv_episode_matcher-0.3.4 → mkv_episode_matcher-0.3.5}/.python-version +0 -0
  21. {mkv_episode_matcher-0.3.4 → mkv_episode_matcher-0.3.5}/.vscode/settings.json +0 -0
  22. {mkv_episode_matcher-0.3.4 → mkv_episode_matcher-0.3.5}/docs/api/index.md +0 -0
  23. {mkv_episode_matcher-0.3.4 → mkv_episode_matcher-0.3.5}/docs/cli.md +0 -0
  24. {mkv_episode_matcher-0.3.4 → mkv_episode_matcher-0.3.5}/docs/configuration.md +0 -0
  25. {mkv_episode_matcher-0.3.4 → mkv_episode_matcher-0.3.5}/docs/installation.md +0 -0
  26. {mkv_episode_matcher-0.3.4 → mkv_episode_matcher-0.3.5}/docs/tips.md +0 -0
  27. {mkv_episode_matcher-0.3.4 → mkv_episode_matcher-0.3.5}/mkdocs.yml +0 -0
  28. {mkv_episode_matcher-0.3.4 → mkv_episode_matcher-0.3.5}/mkv_episode_matcher/.gitattributes +0 -0
  29. {mkv_episode_matcher-0.3.4 → mkv_episode_matcher-0.3.5}/mkv_episode_matcher/__init__.py +0 -0
  30. {mkv_episode_matcher-0.3.4 → mkv_episode_matcher-0.3.5}/mkv_episode_matcher/__main__.py +0 -0
  31. {mkv_episode_matcher-0.3.4 → mkv_episode_matcher-0.3.5}/mkv_episode_matcher/config.py +0 -0
  32. {mkv_episode_matcher-0.3.4 → mkv_episode_matcher-0.3.5}/mkv_episode_matcher/episode_matcher.py +0 -0
  33. {mkv_episode_matcher-0.3.4 → mkv_episode_matcher-0.3.5}/mkv_episode_matcher/libraries/pgs2srt/.gitignore +0 -0
  34. {mkv_episode_matcher-0.3.4 → mkv_episode_matcher-0.3.5}/mkv_episode_matcher/libraries/pgs2srt/Libraries/SubZero/SubZero.py +0 -0
  35. {mkv_episode_matcher-0.3.4 → mkv_episode_matcher-0.3.5}/mkv_episode_matcher/libraries/pgs2srt/Libraries/SubZero/dictionaries/data.py +0 -0
  36. {mkv_episode_matcher-0.3.4 → mkv_episode_matcher-0.3.5}/mkv_episode_matcher/libraries/pgs2srt/Libraries/SubZero/post_processing.py +0 -0
  37. {mkv_episode_matcher-0.3.4 → mkv_episode_matcher-0.3.5}/mkv_episode_matcher/libraries/pgs2srt/README.md +0 -0
  38. {mkv_episode_matcher-0.3.4 → mkv_episode_matcher-0.3.5}/mkv_episode_matcher/libraries/pgs2srt/__init__.py +0 -0
  39. {mkv_episode_matcher-0.3.4 → mkv_episode_matcher-0.3.5}/mkv_episode_matcher/libraries/pgs2srt/imagemaker.py +0 -0
  40. {mkv_episode_matcher-0.3.4 → mkv_episode_matcher-0.3.5}/mkv_episode_matcher/libraries/pgs2srt/pgs2srt.py +0 -0
  41. {mkv_episode_matcher-0.3.4 → mkv_episode_matcher-0.3.5}/mkv_episode_matcher/libraries/pgs2srt/pgsreader.py +0 -0
  42. {mkv_episode_matcher-0.3.4 → mkv_episode_matcher-0.3.5}/mkv_episode_matcher/libraries/pgs2srt/requirements.txt +0 -0
  43. {mkv_episode_matcher-0.3.4 → mkv_episode_matcher-0.3.5}/mkv_episode_matcher/mkv_to_srt.py +0 -0
  44. {mkv_episode_matcher-0.3.4 → mkv_episode_matcher-0.3.5}/mkv_episode_matcher/speech_to_text.py +0 -0
  45. {mkv_episode_matcher-0.3.4 → mkv_episode_matcher-0.3.5}/mkv_episode_matcher/subtitle_utils.py +0 -0
  46. {mkv_episode_matcher-0.3.4 → mkv_episode_matcher-0.3.5}/mkv_episode_matcher/tmdb_client.py +0 -0
  47. {mkv_episode_matcher-0.3.4 → mkv_episode_matcher-0.3.5}/mkv_episode_matcher/utils.py +0 -0
  48. {mkv_episode_matcher-0.3.4 → mkv_episode_matcher-0.3.5}/mkv_episode_matcher.egg-info/dependency_links.txt +0 -0
  49. {mkv_episode_matcher-0.3.4 → mkv_episode_matcher-0.3.5}/mkv_episode_matcher.egg-info/entry_points.txt +0 -0
  50. {mkv_episode_matcher-0.3.4 → mkv_episode_matcher-0.3.5}/mkv_episode_matcher.egg-info/requires.txt +0 -0
  51. {mkv_episode_matcher-0.3.4 → mkv_episode_matcher-0.3.5}/mkv_episode_matcher.egg-info/top_level.txt +0 -0
  52. {mkv_episode_matcher-0.3.4 → mkv_episode_matcher-0.3.5}/setup.py +0 -0
  53. {mkv_episode_matcher-0.3.4 → mkv_episode_matcher-0.3.5}/tests/__init__.py +0 -0
Binary file
@@ -0,0 +1,40 @@
1
+ name: Tests
2
+
3
+ on:
4
+ push:
5
+ branches: [main, master]
6
+ pull_request:
7
+ branches: [main, master]
8
+
9
+ jobs:
10
+ test:
11
+ runs-on: ubuntu-latest
12
+ strategy:
13
+ matrix:
14
+ python-version:
15
+ - "3.9"
16
+ - "3.10"
17
+ - "3.11"
18
+ - "3.12"
19
+
20
+ steps:
21
+ - uses: actions/checkout@v4
22
+
23
+ - name: Install uv and set the python version
24
+ uses: astral-sh/setup-uv@v4
25
+ with:
26
+ python-version: ${{ matrix.python-version }}
27
+
28
+ - name: Install dependencies
29
+ run: |
30
+ uv venv
31
+ uv pip install -e .
32
+
33
+ - name: Run tests with pytest and coverage
34
+ run: |
35
+ uv run --dev pytest --cov-branch --cov-report=xml
36
+
37
+ - name: Upload coverage reports to Codecov
38
+ uses: codecov/codecov-action@v5
39
+ with:
40
+ token: ${{ secrets.CODECOV_TOKEN }}
@@ -1,6 +1,6 @@
1
- Metadata-Version: 2.1
1
+ Metadata-Version: 2.2
2
2
  Name: mkv-episode-matcher
3
- Version: 0.3.4
3
+ Version: 0.3.5
4
4
  Summary: The MKV Episode Matcher is a tool for identifying TV series episodes from MKV files and renaming the files accordingly.
5
5
  Home-page: https://github.com/Jsakkos/mkv-episode-matcher
6
6
  Author: Jonathan Sakkos
@@ -51,6 +51,14 @@ Automatically match and rename your MKV TV episodes using The Movie Database (TM
51
51
  - ✨ **Bulk Processing**: Handle entire seasons at once
52
52
  - 🧪 **Dry Run Mode**: Test changes before applying
53
53
 
54
+ ## Prerequisites
55
+
56
+ - Python 3.9 or higher
57
+ - [FFmpeg](https://ffmpeg.org/download.html) installed and available in system PATH
58
+ - [Tesseract OCR](https://github.com/UB-Mannheim/tesseract/wiki) installed (required for image-based subtitle processing)
59
+ - TMDb API key
60
+ - OpenSubtitles account (optional, for subtitle downloads)
61
+
54
62
  ## Quick Start
55
63
 
56
64
  1. Install the package:
@@ -60,37 +68,13 @@ pip install mkv-episode-matcher
60
68
 
61
69
  2. Run on your show directory:
62
70
  ```bash
63
- mkv-match --show-dir "path/to/your/show" --season 1
71
+ mkv-match --show-dir "path/to/your/show" --get-subs true
64
72
  ```
65
73
 
66
- ## Requirements
67
-
68
- - Python 3.8 or higher
69
- - TMDb API key
70
- - OpenSubtitles account (optional, for subtitle downloads)
71
-
72
74
  ## Documentation
73
75
 
74
76
  Full documentation is available at [https://jsakkos.github.io/mkv-episode-matcher/](https://jsakkos.github.io/mkv-episode-matcher/)
75
77
 
76
- ## Basic Usage
77
-
78
- ```python
79
- from mkv_episode_matcher import process_show
80
-
81
- # Process all seasons
82
- process_show()
83
-
84
- # Process specific season
85
- process_show(season=1)
86
-
87
- # Test run without making changes
88
- process_show(season=1, dry_run=True)
89
-
90
- # Process and download subtitles
91
- process_show(get_subs=True)
92
- ```
93
-
94
78
  ## Directory Structure
95
79
 
96
80
  MKV Episode Matcher expects your TV shows to be organized as follows:
@@ -105,6 +89,23 @@ Show Name/
105
89
  │ └── episode2.mkv
106
90
  ```
107
91
 
92
+ ## Reference Subtitle File Structure
93
+
94
+ Subtitle files that are not automatically downloaded using the `--get-subs` flag should be named as follows:
95
+
96
+ ```
97
+
98
+ ~/.mkv-episode-matcher/cache/data/Show Name/
99
+ ├── Show Name - S01E01.srt
100
+ ├── Show Name - S01E02.srt
101
+ └── ...
102
+ ```
103
+
104
+ On Windows, the cache directory is located at `C:\Users\{username}\.mkv-episode-matcher\cache\data\`
105
+
106
+ Reference subtitle files should follow this naming pattern:
107
+ `{show_name} - S{season:02d}E{episode:02d}.srt`
108
+
108
109
  ## Contributing
109
110
 
110
111
  1. Fork the repository
@@ -22,6 +22,14 @@ Automatically match and rename your MKV TV episodes using The Movie Database (TM
22
22
  - ✨ **Bulk Processing**: Handle entire seasons at once
23
23
  - 🧪 **Dry Run Mode**: Test changes before applying
24
24
 
25
+ ## Prerequisites
26
+
27
+ - Python 3.9 or higher
28
+ - [FFmpeg](https://ffmpeg.org/download.html) installed and available in system PATH
29
+ - [Tesseract OCR](https://github.com/UB-Mannheim/tesseract/wiki) installed (required for image-based subtitle processing)
30
+ - TMDb API key
31
+ - OpenSubtitles account (optional, for subtitle downloads)
32
+
25
33
  ## Quick Start
26
34
 
27
35
  1. Install the package:
@@ -31,37 +39,13 @@ pip install mkv-episode-matcher
31
39
 
32
40
  2. Run on your show directory:
33
41
  ```bash
34
- mkv-match --show-dir "path/to/your/show" --season 1
42
+ mkv-match --show-dir "path/to/your/show" --get-subs true
35
43
  ```
36
44
 
37
- ## Requirements
38
-
39
- - Python 3.8 or higher
40
- - TMDb API key
41
- - OpenSubtitles account (optional, for subtitle downloads)
42
-
43
45
  ## Documentation
44
46
 
45
47
  Full documentation is available at [https://jsakkos.github.io/mkv-episode-matcher/](https://jsakkos.github.io/mkv-episode-matcher/)
46
48
 
47
- ## Basic Usage
48
-
49
- ```python
50
- from mkv_episode_matcher import process_show
51
-
52
- # Process all seasons
53
- process_show()
54
-
55
- # Process specific season
56
- process_show(season=1)
57
-
58
- # Test run without making changes
59
- process_show(season=1, dry_run=True)
60
-
61
- # Process and download subtitles
62
- process_show(get_subs=True)
63
- ```
64
-
65
49
  ## Directory Structure
66
50
 
67
51
  MKV Episode Matcher expects your TV shows to be organized as follows:
@@ -76,6 +60,23 @@ Show Name/
76
60
  │ └── episode2.mkv
77
61
  ```
78
62
 
63
+ ## Reference Subtitle File Structure
64
+
65
+ Subtitle files that are not automatically downloaded using the `--get-subs` flag should be named as follows:
66
+
67
+ ```
68
+
69
+ ~/.mkv-episode-matcher/cache/data/Show Name/
70
+ ├── Show Name - S01E01.srt
71
+ ├── Show Name - S01E02.srt
72
+ └── ...
73
+ ```
74
+
75
+ On Windows, the cache directory is located at `C:\Users\{username}\.mkv-episode-matcher\cache\data\`
76
+
77
+ Reference subtitle files should follow this naming pattern:
78
+ `{show_name} - S{season:02d}E{episode:02d}.srt`
79
+
79
80
  ## Contributing
80
81
 
81
82
  1. Fork the repository
@@ -41,28 +41,22 @@ Show Name/
41
41
  │ ├── episode1.mkv
42
42
  │ └── episode2.mkv
43
43
  ```
44
+ <!-- Add a note about the .srt reference files -->
44
45
 
45
- ## Python API Usage
46
+ ## Reference Subtitle File Structure
46
47
 
47
- ```python
48
- from mkv_episode_matcher import process_show
48
+ Subtitle files that are not automatically downloaded using the `--get-subs` flag should be named as follows:
49
49
 
50
- # Process all seasons
51
- process_show()
52
-
53
- # Process specific season
54
- process_show(season=1)
55
-
56
- # Test run
57
- process_show(season=1, dry_run=True)
58
-
59
- # With subtitles
60
- process_show(season=1, get_subs=True)
50
+ ```plaintext
51
+ ~/.mkv-episode-matcher/cache/data/Show Name/
52
+ ├── Show Name - S01E01.srt
53
+ ├── Show Name - S01E02.srt
54
+ └── ...
61
55
  ```
62
56
 
63
57
  ## Configuration
64
58
 
65
- Create a configuration file at `~/.mkv-episode-matcher/config.ini`:
59
+ The configuration file is automatically generated at `~/.mkv-episode-matcher/config.ini`:
66
60
 
67
61
  ```ini
68
62
  [Config]
@@ -9,6 +9,10 @@ from loguru import logger
9
9
  import whisper
10
10
  import numpy as np
11
11
  import re
12
+ from pathlib import Path
13
+ import chardet
14
+ from loguru import logger
15
+
12
16
  class EpisodeMatcher:
13
17
  def __init__(self, cache_dir, show_name, min_confidence=0.6):
14
18
  self.cache_dir = Path(cache_dir)
@@ -50,34 +54,32 @@ class EpisodeMatcher:
50
54
  return str(chunk_path)
51
55
 
52
56
  def load_reference_chunk(self, srt_file, chunk_idx):
53
- """Load reference subtitles for a specific time chunk."""
57
+ """
58
+ Load reference subtitles for a specific time chunk with robust encoding handling.
59
+
60
+ Args:
61
+ srt_file (str or Path): Path to the SRT file
62
+ chunk_idx (int): Index of the chunk to load
63
+
64
+ Returns:
65
+ str: Combined text from the subtitle chunk
66
+ """
54
67
  chunk_start = chunk_idx * self.chunk_duration
55
68
  chunk_end = chunk_start + self.chunk_duration
56
- text_lines = []
57
69
 
58
- with open(srt_file, 'r', encoding='utf-8') as f:
59
- content = f.read().strip()
70
+ try:
71
+ # Read the file content using our robust reader
72
+ reader = SubtitleReader()
73
+ content = reader.read_srt_file(srt_file)
60
74
 
61
- for block in content.split('\n\n'):
62
- lines = block.split('\n')
63
- if len(lines) < 3 or '-->' not in lines[1]: # Skip malformed blocks
64
- continue
65
-
66
- try:
67
- timestamp = lines[1]
68
- text = ' '.join(lines[2:])
69
-
70
- end_time = timestamp.split(' --> ')[1].strip()
71
- hours, minutes, seconds = map(float, end_time.replace(',','.').split(':'))
72
- total_seconds = hours * 3600 + minutes * 60 + seconds
73
-
74
- if chunk_start <= total_seconds <= chunk_end:
75
- text_lines.append(text)
76
-
77
- except (IndexError, ValueError):
78
- continue
79
-
80
- return ' '.join(text_lines)
75
+ # Extract subtitles for the time chunk
76
+ text_lines = reader.extract_subtitle_chunk(content, chunk_start, chunk_end)
77
+
78
+ return ' '.join(text_lines)
79
+
80
+ except Exception as e:
81
+ logger.error(f"Error loading reference chunk from {srt_file}: {e}")
82
+ return ''
81
83
 
82
84
  def identify_episode(self, video_file, temp_dir, season_number):
83
85
  try:
@@ -147,4 +149,121 @@ class EpisodeMatcher:
147
149
  finally:
148
150
  # Cleanup temp files
149
151
  for file in self.temp_dir.glob("chunk_*.wav"):
150
- file.unlink()
152
+ file.unlink()
153
+
154
+ def detect_file_encoding(file_path):
155
+ """
156
+ Detect the encoding of a file using chardet.
157
+
158
+ Args:
159
+ file_path (str or Path): Path to the file
160
+
161
+ Returns:
162
+ str: Detected encoding, defaults to 'utf-8' if detection fails
163
+ """
164
+ try:
165
+ with open(file_path, 'rb') as f:
166
+ raw_data = f.read()
167
+ result = chardet.detect(raw_data)
168
+ encoding = result['encoding']
169
+ confidence = result['confidence']
170
+
171
+ logger.debug(f"Detected encoding {encoding} with {confidence:.2%} confidence for {file_path}")
172
+ return encoding if encoding else 'utf-8'
173
+ except Exception as e:
174
+ logger.warning(f"Error detecting encoding for {file_path}: {e}")
175
+ return 'utf-8'
176
+
177
+ def read_file_with_fallback(file_path, encodings=None):
178
+ """
179
+ Read a file trying multiple encodings in order of preference.
180
+
181
+ Args:
182
+ file_path (str or Path): Path to the file
183
+ encodings (list): List of encodings to try, defaults to common subtitle encodings
184
+
185
+ Returns:
186
+ str: File contents
187
+
188
+ Raises:
189
+ ValueError: If file cannot be read with any encoding
190
+ """
191
+ if encodings is None:
192
+ # First try detected encoding, then fallback to common subtitle encodings
193
+ detected = detect_file_encoding(file_path)
194
+ encodings = [detected, 'utf-8', 'latin-1', 'cp1252', 'iso-8859-1']
195
+
196
+ file_path = Path(file_path)
197
+ errors = []
198
+
199
+ for encoding in encodings:
200
+ try:
201
+ with open(file_path, 'r', encoding=encoding) as f:
202
+ content = f.read()
203
+ logger.debug(f"Successfully read {file_path} using {encoding} encoding")
204
+ return content
205
+ except UnicodeDecodeError as e:
206
+ errors.append(f"{encoding}: {str(e)}")
207
+ continue
208
+
209
+ error_msg = f"Failed to read {file_path} with any encoding. Errors:\n" + "\n".join(errors)
210
+ logger.error(error_msg)
211
+ raise ValueError(error_msg)
212
+
213
+ class SubtitleReader:
214
+ """Helper class for reading and parsing subtitle files."""
215
+
216
+ @staticmethod
217
+ def parse_timestamp(timestamp):
218
+ """Parse SRT timestamp into seconds."""
219
+ hours, minutes, seconds = timestamp.replace(',', '.').split(':')
220
+ return float(hours) * 3600 + float(minutes) * 60 + float(seconds)
221
+
222
+ @staticmethod
223
+ def read_srt_file(file_path):
224
+ """
225
+ Read an SRT file and return its contents with robust encoding handling.
226
+
227
+ Args:
228
+ file_path (str or Path): Path to the SRT file
229
+
230
+ Returns:
231
+ str: Contents of the SRT file
232
+ """
233
+ return read_file_with_fallback(file_path)
234
+
235
+ @staticmethod
236
+ def extract_subtitle_chunk(content, start_time, end_time):
237
+ """
238
+ Extract subtitle text for a specific time window.
239
+
240
+ Args:
241
+ content (str): Full SRT file content
242
+ start_time (float): Chunk start time in seconds
243
+ end_time (float): Chunk end time in seconds
244
+
245
+ Returns:
246
+ list: List of subtitle texts within the time window
247
+ """
248
+ text_lines = []
249
+
250
+ for block in content.strip().split('\n\n'):
251
+ lines = block.split('\n')
252
+ if len(lines) < 3 or '-->' not in lines[1]:
253
+ continue
254
+
255
+ try:
256
+ timestamp = lines[1]
257
+ text = ' '.join(lines[2:])
258
+
259
+ end_stamp = timestamp.split(' --> ')[1].strip()
260
+ total_seconds = SubtitleReader.parse_timestamp(end_stamp)
261
+
262
+ if start_time <= total_seconds <= end_time:
263
+ text_lines.append(text)
264
+
265
+ except (IndexError, ValueError) as e:
266
+ logger.warning(f"Error parsing subtitle block: {e}")
267
+ continue
268
+
269
+ return text_lines
@@ -1,6 +1,6 @@
1
- Metadata-Version: 2.1
1
+ Metadata-Version: 2.2
2
2
  Name: mkv-episode-matcher
3
- Version: 0.3.4
3
+ Version: 0.3.5
4
4
  Summary: The MKV Episode Matcher is a tool for identifying TV series episodes from MKV files and renaming the files accordingly.
5
5
  Home-page: https://github.com/Jsakkos/mkv-episode-matcher
6
6
  Author: Jonathan Sakkos
@@ -51,6 +51,14 @@ Automatically match and rename your MKV TV episodes using The Movie Database (TM
51
51
  - ✨ **Bulk Processing**: Handle entire seasons at once
52
52
  - 🧪 **Dry Run Mode**: Test changes before applying
53
53
 
54
+ ## Prerequisites
55
+
56
+ - Python 3.9 or higher
57
+ - [FFmpeg](https://ffmpeg.org/download.html) installed and available in system PATH
58
+ - [Tesseract OCR](https://github.com/UB-Mannheim/tesseract/wiki) installed (required for image-based subtitle processing)
59
+ - TMDb API key
60
+ - OpenSubtitles account (optional, for subtitle downloads)
61
+
54
62
  ## Quick Start
55
63
 
56
64
  1. Install the package:
@@ -60,37 +68,13 @@ pip install mkv-episode-matcher
60
68
 
61
69
  2. Run on your show directory:
62
70
  ```bash
63
- mkv-match --show-dir "path/to/your/show" --season 1
71
+ mkv-match --show-dir "path/to/your/show" --get-subs true
64
72
  ```
65
73
 
66
- ## Requirements
67
-
68
- - Python 3.8 or higher
69
- - TMDb API key
70
- - OpenSubtitles account (optional, for subtitle downloads)
71
-
72
74
  ## Documentation
73
75
 
74
76
  Full documentation is available at [https://jsakkos.github.io/mkv-episode-matcher/](https://jsakkos.github.io/mkv-episode-matcher/)
75
77
 
76
- ## Basic Usage
77
-
78
- ```python
79
- from mkv_episode_matcher import process_show
80
-
81
- # Process all seasons
82
- process_show()
83
-
84
- # Process specific season
85
- process_show(season=1)
86
-
87
- # Test run without making changes
88
- process_show(season=1, dry_run=True)
89
-
90
- # Process and download subtitles
91
- process_show(get_subs=True)
92
- ```
93
-
94
78
  ## Directory Structure
95
79
 
96
80
  MKV Episode Matcher expects your TV shows to be organized as follows:
@@ -105,6 +89,23 @@ Show Name/
105
89
  │ └── episode2.mkv
106
90
  ```
107
91
 
92
+ ## Reference Subtitle File Structure
93
+
94
+ Subtitle files that are not automatically downloaded using the `--get-subs` flag should be named as follows:
95
+
96
+ ```
97
+
98
+ ~/.mkv-episode-matcher/cache/data/Show Name/
99
+ ├── Show Name - S01E01.srt
100
+ ├── Show Name - S01E02.srt
101
+ └── ...
102
+ ```
103
+
104
+ On Windows, the cache directory is located at `C:\Users\{username}\.mkv-episode-matcher\cache\data\`
105
+
106
+ Reference subtitle files should follow this naming pattern:
107
+ `{show_name} - S{season:02d}E{episode:02d}.srt`
108
+
108
109
  ## Contributing
109
110
 
110
111
  1. Fork the repository
@@ -1,3 +1,4 @@
1
+ .coverage
1
2
  .gitattributes
2
3
  .gitignore
3
4
  .gitmodules
@@ -11,6 +12,7 @@ uv.lock
11
12
  .github/funding.yml
12
13
  .github/workflows/documentation.yml
13
14
  .github/workflows/python-publish.yml
15
+ .github/workflows/tests.yml
14
16
  .vscode/settings.json
15
17
  docs/cli.md
16
18
  docs/configuration.md
@@ -46,5 +48,4 @@ mkv_episode_matcher/libraries/pgs2srt/Libraries/SubZero/SubZero.py
46
48
  mkv_episode_matcher/libraries/pgs2srt/Libraries/SubZero/post_processing.py
47
49
  mkv_episode_matcher/libraries/pgs2srt/Libraries/SubZero/dictionaries/data.py
48
50
  tests/__init__.py
49
- tests/test_improvements.py
50
51
  tests/test_main.py
@@ -47,6 +47,7 @@ dev = [
47
47
  "pytest-cov>=6.0.0",
48
48
  "pytest>=8.3.3",
49
49
  "ruff>=0.8.0",
50
+ "chardet>=5.2.0",
50
51
  ]
51
52
 
52
53
 
@@ -1,6 +1,6 @@
1
1
  [metadata]
2
2
  name = mkv_episode_matcher
3
- version = 0.3.4
3
+ version = 0.3.5
4
4
  author = Jonathan Sakkos
5
5
  author_email = jonathansakkos@gmail.com
6
6
  description = The MKV Episode Matcher is a tool for identifying TV series episodes from MKV files and renaming the files accordingly.
@@ -13,6 +13,31 @@ from mkv_episode_matcher.utils import (
13
13
  )
14
14
  from mkv_episode_matcher.episode_identification import EpisodeMatcher
15
15
  from mkv_episode_matcher.config import get_config, set_config
16
+ from unittest.mock import Mock, patch
17
+
18
+
19
+ # @pytest.fixture
20
+ # def mock_config():
21
+ # return {
22
+ # "tmdb_api_key": "test_key",
23
+ # "show_dir": "/test/path",
24
+ # "max_threads": 4,
25
+ # "tesseract_path": "/usr/bin/tesseract",
26
+ # }
27
+
28
+
29
+ @pytest.fixture
30
+ def mock_episode_data():
31
+ return {
32
+ "name": "Test Episode",
33
+ "season_number": 1,
34
+ "episode_number": 1,
35
+ "overview": "Test overview",
36
+ }
37
+
38
+ @pytest.fixture
39
+ def mock_seasons():
40
+ return ["/test/path/Season 1"]
16
41
 
17
42
  @pytest.fixture
18
43
  def temp_show_dir(tmp_path):
@@ -101,8 +126,8 @@ class TestEpisodeMatcher:
101
126
  return EpisodeMatcher(tmp_path, "Test Show")
102
127
 
103
128
  def test_clean_text(self, matcher):
104
- text = "Test [action] <tag> T-t-test"
105
- assert matcher.clean_text(text) == "test action tag test"
129
+ text = "Test [action] T-t-test"
130
+ assert matcher.clean_text(text) == "test action test"
106
131
 
107
132
  def test_chunk_score(self, matcher):
108
133
  score = matcher.chunk_score("Test dialogue", "test dialog")
@@ -116,22 +141,27 @@ class TestEpisodeMatcher:
116
141
  assert isinstance(chunk, str)
117
142
  assert mock_run.called
118
143
 
119
- class TestProcessShow:
120
- @patch('mkv_episode_matcher.episode_matcher.get_valid_seasons')
121
- @patch('mkv_episode_matcher.episode_matcher.get_config')
122
- def test_process_show_no_seasons(self, mock_config, mock_seasons, mock_config_data):
123
- mock_seasons.return_value = []
124
- mock_config.return_value = mock_config_data
125
- process_show()
126
- mock_seasons.assert_called_once()
127
-
128
- @patch('mkv_episode_matcher.episode_matcher.get_valid_seasons')
129
- @patch('mkv_episode_matcher.episode_matcher.get_config')
130
- def test_process_show_with_season(self, mock_config, mock_seasons, temp_show_dir, mock_config_data):
131
- mock_seasons.return_value = [str(temp_show_dir / "Season 1")]
132
- mock_config.return_value = mock_config_data
133
- process_show(season=1)
134
- mock_seasons.assert_called_once()
144
+ class TestEpisodeMatcher:
145
+ def test_extract_season_episode(self):
146
+ from mkv_episode_matcher.utils import extract_season_episode
147
+
148
+ # Test valid filename
149
+ assert extract_season_episode("Show - S01E02.mkv") == (1, 2)
150
+
151
+ # Test invalid filename
152
+ assert extract_season_episode("invalid.mkv") == (None, None)
153
+
154
+ @patch("mkv_episode_matcher.tmdb_client.requests.get")
155
+ def test_fetch_show_id(self, mock_get):
156
+ from mkv_episode_matcher.tmdb_client import fetch_show_id
157
+
158
+ mock_response = Mock()
159
+ mock_response.status_code = 200
160
+ mock_response.json.return_value = {"results": [{"id": 12345}]}
161
+ mock_get.return_value = mock_response
162
+
163
+ assert fetch_show_id("Test Show") == "12345"
164
+
135
165
 
136
166
  if __name__ == '__main__':
137
167
  pytest.main(['-v'])
@@ -24,6 +24,15 @@ wheels = [
24
24
  { url = "https://files.pythonhosted.org/packages/12/90/3c9ff0512038035f59d279fddeb79f5f1eccd8859f06d6163c58798b9487/certifi-2024.8.30-py3-none-any.whl", hash = "sha256:922820b53db7a7257ffbda3f597266d435245903d80737e34f8a45ff3e3230d8", size = 167321 },
25
25
  ]
26
26
 
27
+ [[package]]
28
+ name = "chardet"
29
+ version = "5.2.0"
30
+ source = { registry = "https://pypi.org/simple" }
31
+ sdist = { url = "https://files.pythonhosted.org/packages/f3/0d/f7b6ab21ec75897ed80c17d79b15951a719226b9fababf1e40ea74d69079/chardet-5.2.0.tar.gz", hash = "sha256:1b3b6ff479a8c414bc3fa2c0852995695c4a026dcd6d0633b2dd092ca39c1cf7", size = 2069618 }
32
+ wheels = [
33
+ { url = "https://files.pythonhosted.org/packages/38/6f/f5fbc992a329ee4e0f288c1fe0e2ad9485ed064cac731ed2fe47dcc38cbf/chardet-5.2.0-py3-none-any.whl", hash = "sha256:e1cf59446890a00105fe7b7912492ea04b6e6f06d4b742b2c788469e34c82970", size = 199385 },
34
+ ]
35
+
27
36
  [[package]]
28
37
  name = "charset-normalizer"
29
38
  version = "3.4.0"
@@ -374,7 +383,7 @@ wheels = [
374
383
 
375
384
  [[package]]
376
385
  name = "mkv-episode-matcher"
377
- version = "0.3.3.post1.dev0+g40bb202.d20241207"
386
+ version = "0.3.4.post1.dev3+g95f005b.d20250112"
378
387
  source = { editable = "." }
379
388
  dependencies = [
380
389
  { name = "configparser" },
@@ -391,6 +400,7 @@ dependencies = [
391
400
 
392
401
  [package.dev-dependencies]
393
402
  dev = [
403
+ { name = "chardet" },
394
404
  { name = "pytest" },
395
405
  { name = "pytest-cov" },
396
406
  { name = "ruff" },
@@ -412,6 +422,7 @@ requires-dist = [
412
422
 
413
423
  [package.metadata.requires-dev]
414
424
  dev = [
425
+ { name = "chardet", specifier = ">=5.2.0" },
415
426
  { name = "pytest", specifier = ">=8.3.3" },
416
427
  { name = "pytest-cov", specifier = ">=6.0.0" },
417
428
  { name = "ruff", specifier = ">=0.8.0" },
@@ -1,59 +0,0 @@
1
- from unittest.mock import Mock, patch
2
-
3
- import pytest
4
-
5
-
6
- @pytest.fixture
7
- def mock_config():
8
- return {
9
- "tmdb_api_key": "test_key",
10
- "show_dir": "/test/path",
11
- "max_threads": 4,
12
- "tesseract_path": "/usr/bin/tesseract",
13
- }
14
-
15
-
16
- @pytest.fixture
17
- def mock_episode_data():
18
- return {
19
- "name": "Test Episode",
20
- "season_number": 1,
21
- "episode_number": 1,
22
- "overview": "Test overview",
23
- }
24
-
25
-
26
- class TestEpisodeMatcher:
27
- def test_extract_season_episode(self):
28
- from mkv_episode_matcher.episode_matcher import extract_season_episode
29
-
30
- # Test valid filename
31
- assert extract_season_episode("Show - S01E02.mkv") == (1, 2)
32
-
33
- # Test invalid filename
34
- assert extract_season_episode("invalid.mkv") == (None, None)
35
-
36
- @patch("mkv_episode_matcher.tmdb_client.requests.get")
37
- def test_fetch_show_id(self, mock_get):
38
- from mkv_episode_matcher.tmdb_client import fetch_show_id
39
-
40
- mock_response = Mock()
41
- mock_response.status_code = 200
42
- mock_response.json.return_value = {"results": [{"id": 12345}]}
43
- mock_get.return_value = mock_response
44
-
45
- assert fetch_show_id("Test Show") == "12345"
46
-
47
- @patch("mkv_episode_matcher.utils.OpenSubtitles")
48
- def test_get_subtitles(self, mock_subtitles):
49
- from mkv_episode_matcher.utils import get_subtitles
50
-
51
- # Test subtitle download
52
- mock_subtitles.return_value.search.return_value.data = [
53
- {"file_name": "Test.Show.S01E01.srt"}
54
- ]
55
-
56
- with patch("pathlib.Path.exists", return_value=False):
57
- get_subtitles(12345, {1})
58
-
59
- mock_subtitles.return_value.download_and_save.assert_called_once()