added media catalog mode, impooved cache

renamer/extractors/extractor.py

@@ -10,14 +10,40 @@ from .default_extractor import DefaultExtractor
 class MediaExtractor:
     """Class to extract various metadata from media files using specialized extractors"""
 
-    def __init__(self, file_path: Path):
+    @classmethod
+    def create(cls, file_path: Path, cache=None, ttl_seconds: int = 21600):
+        """Factory method that returns cached object if available, else creates new."""
+        if cache:
+            cache_key = f"extractor_{file_path}"
+            cached_obj = cache.get_object(cache_key)
+            if cached_obj:
+                print(f"Loaded MediaExtractor object from cache for {file_path.name}")
+                return cached_obj
+        
+        # Create new instance
+        instance = cls(file_path, cache, ttl_seconds)
+        
+        # Cache the object
+        if cache:
+            cache_key = f"extractor_{file_path}"
+            cache.set_object(cache_key, instance, ttl_seconds)
+            print(f"Cached MediaExtractor object for {file_path.name}")
+        
+        return instance
+
+    def __init__(self, file_path: Path, cache=None, ttl_seconds: int = 21600):
+        self.file_path = file_path
+        self.cache = cache
+        self.ttl_seconds = ttl_seconds
+        self.cache_key = f"file_data_{file_path}"
+        
         self.filename_extractor = FilenameExtractor(file_path)
         self.metadata_extractor = MetadataExtractor(file_path)
         self.mediainfo_extractor = MediaInfoExtractor(file_path)
         self.fileinfo_extractor = FileInfoExtractor(file_path)
-        self.tmdb_extractor = TMDBExtractor(file_path)
+        self.tmdb_extractor = TMDBExtractor(file_path, cache, ttl_seconds)
         self.default_extractor = DefaultExtractor()
-
+        
         # Extractor mapping
         self._extractors = {
             "Metadata": self.metadata_extractor,
@@ -164,9 +190,16 @@ class MediaExtractor:
                 ],
             },
         }
-
+        
+        # No caching logic here - handled in create() method
+    
     def get(self, key: str, source: str | None = None):
         """Get extracted data by key, optionally from specific source"""
+        print(f"Extracting real data for key '{key}' in {self.file_path.name}")
+        return self._get_uncached(key, source)
+
+    def _get_uncached(self, key: str, source: str | None = None):
+        """Original get logic without caching"""
         if source:
             # Specific source requested - find the extractor and call the method directly
             for extractor_name, extractor in self._extractors.items():
@@ -174,27 +207,20 @@ class MediaExtractor:
                     method = f"extract_{key}"
                     if hasattr(extractor, method):
                         val = getattr(extractor, method)()
-                        # Apply condition if specified
-                        if key in self._data and "condition" in self._data[key]:
-                            condition = self._data[key]["condition"]
-                            return val if condition(val) else None
-                        return val
+                        return val if val is not None else None
             return None
         
         # Fallback mode - try sources in order
         if key in self._data:
-            data = self._data[key]
-            sources = data["sources"]
-            condition = data.get("condition", lambda x: x is not None)
+            sources = self._data[key]["sources"]
         else:
             # Try extractors in order for unconfigured keys
             sources = [(name, f"extract_{key}") for name in ["MediaInfo", "Metadata", "Filename", "FileInfo"]]
-            condition = lambda x: x is not None
         
         # Try each source in order until a valid value is found
         for src, method in sources:
             if src in self._extractors and hasattr(self._extractors[src], method):
                 val = getattr(self._extractors[src], method)()
-                if condition(val):
+                if val is not None:
                     return val
         return None

renamer/extractors/fileinfo_extractor.py

@@ -1,6 +1,7 @@
 from pathlib import Path
 import logging
 import os
+from ..decorators import cached_method
 
 # Set up logging conditionally
 if os.getenv('FORMATTER_LOG', '0') == '1':
@@ -19,24 +20,30 @@ class FileInfoExtractor:
         self._modification_time = file_path.stat().st_mtime
         self._file_name = file_path.name
         self._file_path = str(file_path)
+        self._cache = {}  # Internal cache for method results
         logging.info(f"FileInfoExtractor: file_name={self._file_name!r}, file_path={self._file_path!r}")
 
+    @cached_method()
     def extract_size(self) -> int:
         """Extract file size in bytes"""
         return self._size
 
+    @cached_method()
     def extract_modification_time(self) -> float:
         """Extract file modification time"""
         return self._modification_time
 
+    @cached_method()
     def extract_file_name(self) -> str:
         """Extract file name"""
         return self._file_name
 
+    @cached_method()
     def extract_file_path(self) -> str:
         """Extract full file path as string"""
         return self._file_path
 
+    @cached_method()
     def extract_extension(self) -> str:
         """Extract file extension without the dot"""
         return self.file_path.suffix.lower().lstrip('.')

renamer/extractors/filename_extractor.py

@@ -2,6 +2,7 @@ import re
 from pathlib import Path
 from collections import Counter
 from ..constants import SOURCE_DICT, FRAME_CLASSES, MOVIE_DB_DICT, SPECIAL_EDITIONS
+from ..decorators import cached_method
 import langcodes
 
 
@@ -34,6 +35,7 @@ class FilenameExtractor:
                 return frame_class
         return None
 
+    @cached_method()
     def extract_title(self) -> str | None:
         """Extract movie title from filename"""
         # Find positions of year, source, and quality brackets
@@ -120,6 +122,7 @@ class FilenameExtractor:
         
         return title if title else None
 
+    @cached_method()
     def extract_year(self) -> str | None:
         """Extract year from filename"""
         # First try to find year in parentheses (most common and reliable)
@@ -144,6 +147,7 @@ class FilenameExtractor:
         
         return None
 
+    @cached_method()
     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)
@@ -154,6 +158,7 @@ class FilenameExtractor:
                     return src
         return None
 
+    @cached_method()
     def extract_order(self) -> str | None:
         """Extract collection order number from filename (at the beginning)"""
         # Look for order patterns at the start of filename
@@ -176,6 +181,7 @@ class FilenameExtractor:
         
         return None
 
+    @cached_method()
     def extract_frame_class(self) -> str | None:
         """Extract frame class from filename (480p, 720p, 1080p, 2160p, etc.)"""
         # Normalize Cyrillic characters for resolution parsing
@@ -200,6 +206,7 @@ class FilenameExtractor:
         
         return None
 
+    @cached_method()
     def extract_hdr(self) -> str | None:
         """Extract HDR information from filename"""
         # Check for SDR first - indicates no HDR
@@ -212,6 +219,7 @@ class FilenameExtractor:
         
         return None
 
+    @cached_method()
     def extract_movie_db(self) -> list[str] | None:
         """Extract movie database identifier from filename"""
         # Look for patterns at the end of filename in brackets or braces
@@ -233,6 +241,7 @@ class FilenameExtractor:
         
         return None
 
+    @cached_method()
     def extract_special_info(self) -> list[str] | None:
         """Extract special edition information from filename"""
         # Look for special edition indicators in brackets or as standalone text
@@ -258,6 +267,7 @@ class FilenameExtractor:
         
         return special_info if special_info else None
 
+    @cached_method()
     def extract_audio_langs(self) -> str:
         """Extract audio languages from filename"""
         # Look for language patterns in brackets and outside brackets
@@ -389,6 +399,7 @@ class FilenameExtractor:
         audio_langs = [f"{count}{lang}" if count > 1 else lang for lang, count in lang_counts.items()]
         return ','.join(audio_langs)
 
+    @cached_method()
     def extract_audio_tracks(self) -> list[dict]:
         """Extract audio track data from filename (simplified version with only language)"""
         # Similar to extract_audio_langs but returns list of dicts

renamer/extractors/mediainfo_extractor.py

@@ -2,6 +2,7 @@ from pathlib import Path
 from pymediainfo import MediaInfo
 from collections import Counter
 from ..constants import FRAME_CLASSES, MEDIA_TYPES
+from ..decorators import cached_method
 import langcodes
 
 
@@ -10,6 +11,7 @@ class MediaInfoExtractor:
 
     def __init__(self, file_path: Path):
         self.file_path = file_path
+        self._cache = {}  # Internal cache for method results
         try:
             self.media_info = MediaInfo.parse(file_path)
             self.video_tracks = [t for t in self.media_info.tracks if t.track_type == 'Video']
@@ -54,6 +56,7 @@ class MediaInfoExtractor:
             return closest
         return None
 
+    @cached_method()
     def extract_duration(self) -> float | None:
         """Extract duration from media info in seconds"""
         if self.media_info:
@@ -62,6 +65,7 @@ class MediaInfoExtractor:
                     return getattr(track, 'duration', 0) / 1000 if getattr(track, 'duration', None) else None
         return None
 
+    @cached_method()
     def extract_frame_class(self) -> str | None:
         """Extract frame class from media info (480p, 720p, 1080p, etc.)"""
         if not self.video_tracks:
@@ -106,6 +110,7 @@ class MediaInfoExtractor:
             return f"{closest_height}{scan_type}"
         return None
 
+    @cached_method()
     def extract_resolution(self) -> tuple[int, int] | None:
         """Extract actual video resolution as (width, height) tuple from media info"""
         if not self.video_tracks:
@@ -116,6 +121,7 @@ class MediaInfoExtractor:
             return width, height
         return None
     
+    @cached_method()
     def extract_aspect_ratio(self) -> str | None:
         """Extract video aspect ratio from media info"""
         if not self.video_tracks:
@@ -125,6 +131,7 @@ class MediaInfoExtractor:
             return str(aspect_ratio)
         return None
 
+    @cached_method()
     def extract_hdr(self) -> str | None:
         """Extract HDR info from media info"""
         if not self.video_tracks:
@@ -134,6 +141,7 @@ class MediaInfoExtractor:
             return 'HDR'
         return None
 
+    @cached_method()
     def extract_audio_langs(self) -> str | None:
         """Extract audio languages from media info"""
         if not self.audio_tracks:
@@ -154,6 +162,7 @@ class MediaInfoExtractor:
         audio_langs = [f"{count}{lang}" if count > 1 else lang for lang, count in lang_counts.items()]
         return ','.join(audio_langs)
 
+    @cached_method()
     def extract_video_tracks(self) -> list[dict]:
         """Extract video track data"""
         tracks = []
@@ -169,6 +178,7 @@ class MediaInfoExtractor:
             tracks.append(track_data)
         return tracks
 
+    @cached_method()
     def extract_audio_tracks(self) -> list[dict]:
         """Extract audio track data"""
         tracks = []
@@ -182,6 +192,7 @@ class MediaInfoExtractor:
             tracks.append(track_data)
         return tracks
 
+    @cached_method()
     def extract_subtitle_tracks(self) -> list[dict]:
         """Extract subtitle track data"""
         tracks = []
@@ -193,6 +204,7 @@ class MediaInfoExtractor:
             tracks.append(track_data)
         return tracks
 
+    @cached_method()
     def is_3d(self) -> bool:
         """Check if the video is 3D"""
         if not self.video_tracks:
@@ -205,6 +217,7 @@ class MediaInfoExtractor:
             return True
         return False
 
+    @cached_method()
     def extract_anamorphic(self) -> str | None:
         """Extract anamorphic info for 3D videos"""
         if not self.video_tracks:
@@ -214,6 +227,7 @@ class MediaInfoExtractor:
             return 'Anamorphic:Yes'
         return None
 
+    @cached_method()
     def extract_extension(self) -> str | None:
         """Extract file extension based on container format"""
         if not self.media_info:
@@ -233,6 +247,7 @@ class MediaInfoExtractor:
                 return exts[0] if exts else None
         return None
 
+    @cached_method()
     def extract_3d_layout(self) -> str | None:
         """Extract 3D stereoscopic layout from MediaInfo"""
         if not self.is_3d():

renamer/extractors/metadata_extractor.py

@@ -1,6 +1,7 @@
 import mutagen
 from pathlib import Path
 from ..constants import MEDIA_TYPES
+from ..decorators import cached_method
 
 
 class MetadataExtractor:
@@ -8,36 +9,40 @@ class MetadataExtractor:
 
     def __init__(self, file_path: Path):
         self.file_path = file_path
+        self._cache = {}  # Internal cache for method results
         try:
             self.info = mutagen.File(file_path) # type: ignore
         except Exception:
             self.info = None
 
+    @cached_method()
     def extract_title(self) -> str | None:
         """Extract title from metadata"""
         if self.info:
             return getattr(self.info, 'title', None) or getattr(self.info, 'get', lambda x, default=None: default)('title', [None])[0]  # type: ignore
         return None
 
+    @cached_method()
     def extract_duration(self) -> float | None:
         """Extract duration from metadata"""
         if self.info:
             return getattr(self.info, 'length', None)
         return None
 
+    @cached_method()
     def extract_artist(self) -> str | None:
         """Extract artist from metadata"""
         if self.info:
             return getattr(self.info, 'artist', None) or getattr(self.info, 'get', lambda x, default=None: default)('artist', [None])[0]  # type: ignore
         return None
 
+    @cached_method()
     def extract_meta_type(self) -> str:
         """Extract meta type from metadata"""
         if self.info:
             return type(self.info).__name__
         return self._detect_by_mime()
 
-
     def _detect_by_mime(self) -> str:
         """Detect meta type by MIME"""
         try:

renamer/extractors/tmdb_extractor.py

@@ -11,53 +11,22 @@ from ..secrets import TMDB_API_KEY, TMDB_ACCESS_TOKEN
 class TMDBExtractor:
     """Class to extract TMDB movie information"""
 
-    CACHE_DIR = Path.home() / ".cache" / "renamer" / "tmdb"
-    CACHE_DURATION = 5 * 24 * 60 * 60  # 5 days in seconds
-
-    def __init__(self, file_path: Path):
+    def __init__(self, file_path: Path, cache=None, ttl_seconds: int = 21600):
         self.file_path = file_path
+        self.cache = cache
+        self.ttl_seconds = ttl_seconds
         self._movie_db_info = None
 
-    def _get_cache_file_path(self, cache_key: str) -> Path:
-        """Get the cache file path for a given cache key"""
-        # Create a hash of the cache key for the filename
-        key_hash = hashlib.md5(cache_key.encode('utf-8')).hexdigest()
-        return self.CACHE_DIR / f"{key_hash}.json"
-
-    def _is_cache_valid(self, cache_key: str) -> bool:
-        """Check if cache entry is still valid"""
-        cache_file = self._get_cache_file_path(cache_key)
-        if not cache_file.exists():
-            return False
-        
-        try:
-            # Check file modification time
-            stat = cache_file.stat()
-            return time.time() - stat.st_mtime < self.CACHE_DURATION
-        except OSError:
-            return False
-
     def _get_cached_data(self, cache_key: str) -> Optional[Dict[str, Any]]:
         """Get data from cache if valid"""
-        if not self._is_cache_valid(cache_key):
-            return None
-        
-        cache_file = self._get_cache_file_path(cache_key)
-        try:
-            with open(cache_file, 'r', encoding='utf-8') as f:
-                return json.load(f)
-        except (json.JSONDecodeError, OSError):
-            return None
+        if self.cache:
+            return self.cache.get(f"tmdb_{cache_key}")
+        return None
 
     def _set_cached_data(self, cache_key: str, data: Dict[str, Any]):
         """Store data in cache"""
-        try:
-            self.CACHE_DIR.mkdir(parents=True, exist_ok=True)
-            cache_file = self._get_cache_file_path(cache_key)
-            with open(cache_file, 'w', encoding='utf-8') as f:
-                json.dump(data, f, indent=2, ensure_ascii=False)
-        except OSError:
-            pass  # Silently fail if we can't save cache
+        if self.cache:
+            self.cache.set(f"tmdb_{cache_key}", data, self.ttl_seconds)
 
     def _make_tmdb_request(self, endpoint: str, params: Optional[Dict[str, Any]] = None) -> Optional[Dict[str, Any]]:
         """Make a request to TMDB API"""
@@ -230,9 +199,70 @@ class TMDBExtractor:
             return f"https://www.themoviedb.org/movie/{movie_id}"
         return None
 
-    def extract_movie_db(self) -> Optional[Tuple[str, str]]:
-        """Extract TMDB database info as (name, id) tuple"""
-        movie_id = self.extract_tmdb_id()
-        if movie_id:
-            return ("tmdb", movie_id)
+    def extract_duration(self) -> Optional[str]:
+        """Extract TMDB runtime in minutes"""
+        movie_info = self._get_movie_info()
+        if movie_info and movie_info.get('runtime'):
+            return str(movie_info['runtime'])
         return None
+
+    def extract_popularity(self) -> Optional[str]:
+        """Extract TMDB popularity"""
+        movie_info = self._get_movie_info()
+        if movie_info:
+            return str(movie_info.get('popularity', ''))
+        return None
+
+    def extract_vote_average(self) -> Optional[str]:
+        """Extract TMDB vote average"""
+        movie_info = self._get_movie_info()
+        if movie_info:
+            return str(movie_info.get('vote_average', ''))
+        return None
+
+    def extract_overview(self) -> Optional[str]:
+        """Extract TMDB overview"""
+        movie_info = self._get_movie_info()
+        if movie_info:
+            return movie_info.get('overview')
+        return None
+
+    def extract_genres(self) -> Optional[str]:
+        """Extract TMDB genres as codes"""
+        movie_info = self._get_movie_info()
+        if movie_info and movie_info.get('genres'):
+            return ', '.join(genre['name'] for genre in movie_info['genres'])
+        return None
+
+    def extract_poster_path(self) -> Optional[str]:
+        """Extract TMDB poster path"""
+        movie_info = self._get_movie_info()
+        if movie_info:
+            return movie_info.get('poster_path')
+        return None
+
+    def extract_poster_image_path(self) -> Optional[str]:
+        """Download and cache poster image, return local path"""
+        poster_path = self.extract_poster_path()
+        if not poster_path or not self.cache:
+            return None
+        
+        cache_key = f"poster_{poster_path}"
+        cached_path = self.cache.get_image(cache_key)
+        if cached_path:
+            return str(cached_path)
+        
+        # Download poster
+        base_url = "https://image.tmdb.org/t/p/w500"  # Medium size
+        url = f"{base_url}{poster_path}"
+        
+        try:
+            response = requests.get(url, timeout=10)
+            response.raise_for_status()
+            image_data = response.content
+            
+            # Cache image
+            local_path = self.cache.set_image(cache_key, image_data, self.ttl_seconds)
+            return str(local_path) if local_path else None
+        except requests.RequestException:
+            return None