github-personal/moma
1
0
Fork 0
mirror of https://github.com/shadoll/moma.git synced 2026-08-28 11:33:25 +00:00
Code Issues Packages Projects Releases 4 Wiki Activity

feat: Enhance metadata extraction and formatting, improve extractor architecture, and update documentation

Browse Source
This commit is contained in:
sha
2025-12-26 13:38:17 +00:00
parent 8f68624529
commit 91df347727
13 changed files with 170 additions and 76 deletions
Download Patch File Download Diff File Expand all files Collapse all files
renamer/constants.py
+1 -1
View File
@@ -36,7 +36,7 @@ MEDIA_TYPES = {
}
SOURCE_DICT = {
"WEB-DL": ["WEB-DL", "WEBRip", "WEB-Rip", "WEB"],
"WEB-DL": ["WEB-DL", "WEBRip", "WEB-Rip", "WEB", "WEB-DLRip"],
"BDRip": ["BDRip", "BD-Rip", "BDRIP"],
"BDRemux": ["BDRemux", "BD-Remux", "BDREMUX"],
"DVDRip": ["DVDRip", "DVD-Rip", "DVDRIP"],
renamer/extractor.py
+13 -2
View File
@@ -64,6 +64,15 @@ class MediaExtractor:
'extension': [
('FileInfo', lambda: self.fileinfo_extractor.extract_extension())
],
'video_tracks': [
('MediaInfo', lambda: self.mediainfo_extractor.extract_video_tracks())
],
'audio_tracks': [
('MediaInfo', lambda: self.mediainfo_extractor.extract_audio_tracks())
],
'subtitle_tracks': [
('MediaInfo', lambda: self.mediainfo_extractor.extract_subtitle_tracks())
],
}
# Conditions for when a value is considered valid
@@ -76,8 +85,10 @@ class MediaExtractor:
'aspect_ratio': lambda x: x is not None,
'hdr': lambda x: x is not None,
'audio_langs': lambda x: x is not None,
'metadata': lambda x: x is not None,
'tracks': lambda x: x is not None and any(x.get(k, []) for k in ['video_tracks', 'audio_tracks', 'subtitle_tracks'])
'tracks': lambda x: x is not None and any(x.get(k, []) for k in ['video_tracks', 'audio_tracks', 'subtitle_tracks']),
'video_tracks': lambda x: x is not None and len(x) > 0,
'audio_tracks': lambda x: x is not None and len(x) > 0,
'subtitle_tracks': lambda x: x is not None and len(x) > 0,
}
def get(self, key: str, source: str | None = None):
renamer/extractors/filename_extractor.py
+30 -4
View File
@@ -31,23 +31,49 @@ class FilenameExtractor:
def extract_year(self) -> str | None:
"""Extract year from filename"""
year_match = re.search(r'\((\d{4})\)|(\d{4})', self.file_name)
return (year_match.group(1) or year_match.group(2)) if year_match else None
# First try to find year in parentheses (most common and reliable)
paren_match = re.search(r'\((\d{4})\)', self.file_name)
if paren_match:
return paren_match.group(1)
# Fallback: look for year in dots (like .1971.)
dot_match = re.search(r'\.(\d{4})\.', self.file_name)
if dot_match:
return dot_match.group(1)
# Last resort: any 4-digit number (but this is less reliable)
any_match = re.search(r'\b(\d{4})\b', self.file_name)
if any_match:
year = any_match.group(1)
# Basic sanity check: years should be between 1900 and current year + a few years
current_year = 2025 # Update this as needed
if 1900 <= int(year) <= current_year + 10:
return year
return None
def extract_source(self) -> str | None:
"""Extract video source from filename"""
temp_name = re.sub(r'\s*\(\d{4}\)\s*|\s*\d{4}\s*|\.\d{4}\.', '', self.file_name)
temp_name = re.sub(r'\s*\(\d{4}\)\s*|\s*\d{4}\s*|\.\d{4}\.', ' ', self.file_name)
for src, aliases in SOURCE_DICT.items():
for alias in aliases:
if re.search(r'\b' + re.escape(alias) + r'\b', temp_name, re.IGNORECASE):
if alias.upper() in temp_name.upper():
return src
return None
def extract_frame_class(self) -> str | None:
"""Extract frame class from filename (480p, 720p, 1080p, 2160p, etc.)"""
# First check for specific numeric resolutions
match = re.search(r'(\d{3,4})[pi]', self.file_name, re.IGNORECASE)
if match:
height = int(match.group(1))
return self._get_frame_class_from_height(height)
# If no specific resolution found, check for quality indicators
unclassified_indicators = ['SD', 'LQ', 'HD', 'QHD']
for indicator in unclassified_indicators:
if re.search(r'\b' + re.escape(indicator) + r'\b', self.file_name, re.IGNORECASE):
return 'Unclassified'
return 'Unclassified'
renamer/extractors/metadata_extractor.py
-4
View File
@@ -37,10 +37,6 @@ class MetadataExtractor:
return type(self.info).__name__
return self._detect_by_mime()
def extract_meta_description(self) -> str:
"""Extract meta description"""
meta_type = self.extract_meta_type()
return {info['meta_type']: info['description'] for info in MEDIA_TYPES.values()}.get(meta_type, f'Unknown type {meta_type}')
def _detect_by_mime(self) -> str:
"""Detect meta type by MIME"""
renamer/formatters/media_formatter.py
+12 -14
View File
@@ -132,7 +132,10 @@ class MediaFormatter:
"label_formatters": [TextFormatter.bold, TextFormatter.uppercase],
}
]
for item in self.extractor.get("tracks").get("video_tracks"):
# Get video tracks
video_tracks = self.extractor.get("video_tracks", "MediaInfo") or []
for item in video_tracks:
data.append(
{
"group": "Tracks Info",
@@ -142,9 +145,10 @@ class MediaFormatter:
"display_formatters": [TextFormatter.green],
}
)
for i, item in enumerate(
self.extractor.get("tracks").get("audio_tracks"), start=1
):
# Get audio tracks
audio_tracks = self.extractor.get("audio_tracks", "MediaInfo") or []
for i, item in enumerate(audio_tracks, start=1):
data.append(
{
"group": "Tracks Info",
@@ -154,9 +158,10 @@ class MediaFormatter:
"display_formatters": [TextFormatter.yellow],
}
)
for i, item in enumerate(
self.extractor.get("tracks").get("subtitle_tracks"), start=1
):
# Get subtitle tracks
subtitle_tracks = self.extractor.get("subtitle_tracks", "MediaInfo") or []
for i, item in enumerate(subtitle_tracks, start=1):
data.append(
{
"group": "Tracks Info",
@@ -195,13 +200,6 @@ class MediaFormatter:
"value": self.extractor.get("artist", "Metadata") or "Not extracted",
"display_formatters": [TextFormatter.grey],
},
{
"label": "Description",
"label_formatters": [TextFormatter.bold],
"value": self.extractor.get("meta_description", "Metadata")
or "Not extracted",
"display_formatters": [TextFormatter.grey],
},
]
return [self._format_data_item(item) for item in data]
renamer/test/filenames.txt
+7 -1
View File
@@ -90,7 +90,6 @@ The Invention of Lying (2009) [720p,ukr,eng].mkv
The Island of Dr. Moreau.(1977).[720p,ukr].mp4
The Killing.(1956).[SD,ukr,eng].mkv
The Love Guru.(2008).[SD,ukr].avi
The Love Guru.(2008).[SD,ukr].avi
The Manchurian Candidate.(2004).[720p,ukr,eng].mkv
The Mortal Instruments. City of Bones.(2013).[720p,ukr,eng].mkv
The Mutant Chronicles.(2008).[SD,ukr,eng].mkv
@@ -203,3 +202,10 @@ Upgrade.(2018).[SD,eng].mkv
Человек с бульвара Капуцинов (1987) [1080p,rus] [tmdbid-45227].mkv
Человек-амфибия (1961) [SD,rus] [tmdbid-43685].avi
Чук и Гек (1953) [SD,rus] [tmdbid-148412].avi
The long title.(2008).[SD 720p,ukr].avi
The_long_title.(2008).2K.1440p.ukr.avi
The long title (2008) SD 720p UKR.avi
The long title (2008) UHD 1440p ENG.mp4
The long title (2008) UHD 1440 ENG.mp4
The long title (2008) 8K 4320p ENG.mp4
renamer/test/test_fileinfo_extractor.py
+13 -10
View File
@@ -4,32 +4,35 @@ from renamer.extractors.fileinfo_extractor import FileInfoExtractor
class TestFileInfoExtractor:
@pytest.fixture
def extractor(self, test_file):
return FileInfoExtractor(test_file)
@pytest.fixture
def test_file(self):
"""Use the filenames.txt file for testing"""
return Path(__file__).parent / "filenames.txt"
def test_extract_size(self, test_file):
def test_extract_size(self, extractor):
"""Test extracting file size"""
size = FileInfoExtractor.extract_size(test_file)
size = extractor.extract_size()
assert isinstance(size, int)
assert size > 0
def test_extract_modification_time(self, test_file):
def test_extract_modification_time(self, extractor):
"""Test extracting modification time"""
mtime = FileInfoExtractor.extract_modification_time(test_file)
mtime = extractor.extract_modification_time()
assert isinstance(mtime, float)
assert mtime > 0
def test_extract_file_name(self, test_file):
def test_extract_file_name(self, extractor):
"""Test extracting file name"""
name = FileInfoExtractor.extract_file_name(test_file)
name = extractor.extract_file_name()
assert isinstance(name, str)
assert name == "filenames.txt"
def test_extract_file_path(self, test_file):
def test_extract_file_path(self, extractor):
"""Test extracting file path"""
path = FileInfoExtractor.extract_file_path(test_file)
path = extractor.extract_file_path()
assert isinstance(path, str)
assert "filenames.txt" in path
assert str(test_file) == path
assert "filenames.txt" in path
renamer/test/test_filename_extractor.py
+8 -4
View File
@@ -17,7 +17,8 @@ def load_test_filenames():
def test_extract_title(filename):
"""Test title extraction from filename"""
file_path = Path(filename)
title = FilenameExtractor.extract_title(file_path)
extractor = FilenameExtractor(file_path)
title = extractor.extract_title()
# Print filename and extracted title clearly
print(f"\nFilename: \033[1;36m{filename}\033[0m")
print(f"Extracted title: \033[1;32m{title}\033[0m")
@@ -29,7 +30,8 @@ def test_extract_title(filename):
def test_extract_year(filename):
"""Test year extraction from filename"""
file_path = Path(filename)
year = FilenameExtractor.extract_year(file_path)
extractor = FilenameExtractor(file_path)
year = extractor.extract_year()
# Print filename and extracted year clearly
print(f"\nFilename: \033[1;36m{filename}\033[0m")
print(f"Extracted year: \033[1;32m{year}\033[0m")
@@ -42,7 +44,8 @@ def test_extract_year(filename):
def test_extract_source(filename):
"""Test source extraction from filename"""
file_path = Path(filename)
source = FilenameExtractor.extract_source(file_path)
extractor = FilenameExtractor(file_path)
source = extractor.extract_source()
# Print filename and extracted source clearly
print(f"\nFilename: \033[1;36m{filename}\033[0m")
print(f"Extracted source: \033[1;32m{source}\033[0m")
@@ -54,7 +57,8 @@ def test_extract_source(filename):
def test_extract_frame_class(filename):
"""Test frame class extraction from filename"""
file_path = Path(filename)
frame_class = FilenameExtractor.extract_frame_class(file_path)
extractor = FilenameExtractor(file_path)
frame_class = extractor.extract_frame_class()
# Print filename and extracted frame class clearly
print(f"\nFilename: \033[1;36m{filename}\033[0m")
print(f"Extracted frame_class: \033[1;32m{frame_class}\033[0m")
renamer/test/test_mediainfo_extractor.py
+5 -5
View File
@@ -5,8 +5,8 @@ from renamer.extractors.mediainfo_extractor import MediaInfoExtractor
class TestMediaInfoExtractor:
@pytest.fixture
def extractor(self):
return MediaInfoExtractor()
def extractor(self, test_file):
return MediaInfoExtractor(test_file)
@pytest.fixture
def test_file(self):
@@ -15,18 +15,18 @@ class TestMediaInfoExtractor:
def test_extract_resolution(self, extractor, test_file):
"""Test extracting resolution from media info"""
resolution = extractor.extract_resolution(test_file)
resolution = extractor.extract_resolution()
# Text files don't have video resolution
assert resolution is None
def test_extract_hdr(self, extractor, test_file):
"""Test extracting HDR info"""
hdr = extractor.extract_hdr(test_file)
hdr = extractor.extract_hdr()
# Text files don't have HDR
assert hdr is None
def test_extract_audio_langs(self, extractor, test_file):
"""Test extracting audio languages"""
langs = extractor.extract_audio_langs(test_file)
langs = extractor.extract_audio_langs()
# Text files don't have audio tracks
assert langs == ''
renamer/test/test_metadata_extractor.py
+11 -17
View File
@@ -4,35 +4,29 @@ from renamer.extractors.metadata_extractor import MetadataExtractor
class TestMetadataExtractor:
@pytest.fixture
def extractor(self, test_file):
return MetadataExtractor(test_file)
@pytest.fixture
def test_file(self):
"""Use the filenames.txt file for testing"""
return Path(__file__).parent / "filenames.txt"
def test_extract_title(self, test_file):
def test_extract_title(self, extractor):
"""Test extracting title from metadata"""
title = MetadataExtractor.extract_title(test_file)
title = extractor.extract_title()
# Text files don't have metadata, so should be None
assert title is None
def test_extract_duration(self, test_file):
def test_extract_duration(self, extractor):
"""Test extracting duration from metadata"""
duration = MetadataExtractor.extract_duration(test_file)
duration = extractor.extract_duration()
# Text files don't have duration
assert duration is None
def test_extract_artist(self, test_file):
def test_extract_artist(self, extractor):
"""Test extracting artist from metadata"""
artist = MetadataExtractor.extract_artist(test_file)
artist = extractor.extract_artist()
# Text files don't have artist
assert artist is None
def test_extract_all_metadata(self, test_file):
"""Test extracting all metadata"""
metadata = MetadataExtractor.extract_all_metadata(test_file)
expected = {
'title': None,
'duration': None,
'artist': None
}
assert metadata == expected
assert artist is None