Refactor code structure and remove redundant code blocks for improved readability and maintainability

renamer/extractors/default_extractor.py

@@ -1,71 +1,117 @@
-class DefaultExtractor:
-    """Extractor that provides default fallback values"""
+"""Default extractor providing fallback values.
 
-    def extract_title(self):
+This module provides a minimal implementation of the DataExtractor protocol
+that returns default/empty values for all extraction methods. Used as a
+fallback when no specific extractor is available.
+"""
+
+from typing import Optional
+
+
+class DefaultExtractor:
+    """Extractor that provides default fallback values for all extraction methods.
+
+    This class implements the DataExtractor protocol by returning sensible
+    defaults (None, empty strings, empty lists) for all extraction operations.
+    It's used as a final fallback in the extractor chain when no other
+    extractor can provide data.
+
+    All methods return None or empty values, making it safe to use when
+    no actual data extraction is possible.
+    """
+
+    def extract_title(self) -> Optional[str]:
+        """Return default title.
+
+        Returns:
+            Default title string "Unknown Title"
+        """
         return "Unknown Title"
 
-    def extract_year(self):
+    def extract_year(self) -> Optional[str]:
+        """Return year. Returns None as no year information is available."""
         return None
 
-    def extract_source(self):
+    def extract_source(self) -> Optional[str]:
+        """Return video source. Returns None as no source information is available."""
         return None
 
-    def extract_order(self):
+    def extract_order(self) -> Optional[str]:
+        """Return sequence order. Returns None as no order information is available."""
         return None
 
-    def extract_resolution(self):
+    def extract_resolution(self) -> Optional[str]:
+        """Return resolution. Returns None as no resolution information is available."""
         return None
 
-    def extract_hdr(self):
+    def extract_hdr(self) -> Optional[str]:
+        """Return HDR information. Returns None as no HDR information is available."""
         return None
 
-    def extract_movie_db(self):
+    def extract_movie_db(self) -> list[str] | None:
+        """Return movie database ID. Returns None as no database information is available."""
         return None
 
-    def extract_special_info(self):
+    def extract_special_info(self) -> Optional[str]:
+        """Return special edition info. Returns None as no special info is available."""
         return None
 
-    def extract_audio_langs(self):
+    def extract_audio_langs(self) -> Optional[str]:
+        """Return audio languages. Returns None as no language information is available."""
         return None
 
-    def extract_meta_type(self):
+    def extract_meta_type(self) -> Optional[str]:
+        """Return metadata type. Returns None as no type information is available."""
         return None
 
-    def extract_size(self):
+    def extract_size(self) -> Optional[int]:
+        """Return file size. Returns None as no size information is available."""
         return None
 
-    def extract_modification_time(self):
+    def extract_modification_time(self) -> Optional[float]:
+        """Return modification time. Returns None as no timestamp is available."""
         return None
 
-    def extract_file_name(self):
+    def extract_file_name(self) -> Optional[str]:
+        """Return file name. Returns None as no filename is available."""
         return None
 
-    def extract_file_path(self):
+    def extract_file_path(self) -> Optional[str]:
+        """Return file path. Returns None as no file path is available."""
         return None
 
-    def extract_frame_class(self):
+    def extract_frame_class(self) -> Optional[str]:
+        """Return frame class. Returns None as no frame class information is available."""
         return None
 
-    def extract_video_tracks(self):
+    def extract_video_tracks(self) -> list[dict]:
+        """Return video tracks. Returns empty list as no video tracks are available."""
         return []
 
-    def extract_audio_tracks(self):
+    def extract_audio_tracks(self) -> list[dict]:
+        """Return audio tracks. Returns empty list as no audio tracks are available."""
         return []
 
-    def extract_subtitle_tracks(self):
+    def extract_subtitle_tracks(self) -> list[dict]:
+        """Return subtitle tracks. Returns empty list as no subtitle tracks are available."""
         return []
 
-    def extract_anamorphic(self):
+    def extract_anamorphic(self) -> Optional[str]:
+        """Return anamorphic info. Returns None as no anamorphic information is available."""
         return None
 
-    def extract_extension(self):
+    def extract_extension(self) -> Optional[str]:
+        """Return file extension. Returns None as no extension is available."""
         return None
 
-    def extract_tmdb_url(self):
+    def extract_tmdb_url(self) -> Optional[str]:
+        """Return TMDB URL. Returns None as no TMDB URL is available."""
         return None
 
-    def extract_tmdb_id(self):
+    def extract_tmdb_id(self) -> Optional[str]:
+        """Return TMDB ID. Returns None as no TMDB ID is available."""
         return None
 
-    def extract_original_title(self):
+    def extract_original_title(self) -> Optional[str]:
+        """Return original title. Returns None as no original title is available."""
         return None

renamer/extractors/extractor.py

@@ -1,3 +1,11 @@
+"""Media metadata extraction coordinator.
+
+This module provides the MediaExtractor class which coordinates multiple
+specialized extractors to gather comprehensive metadata about media files.
+It implements a priority-based extraction system where data is retrieved
+from the most appropriate source.
+"""
+
 from pathlib import Path
 from .filename_extractor import FilenameExtractor
 from .metadata_extractor import MetadataExtractor
@@ -8,7 +16,34 @@ from .default_extractor import DefaultExtractor
 
 
 class MediaExtractor:
-    """Class to extract various metadata from media files using specialized extractors"""
+    """Coordinator for extracting metadata from media files using multiple specialized extractors.
+
+    This class manages a collection of specialized extractors and provides a unified
+    interface for retrieving metadata. It implements a priority-based system where
+    each type of data is retrieved from the most appropriate source.
+
+    The extraction priority order varies by data type:
+    - Title: TMDB → Metadata → Filename → Default
+    - Year: Filename → Default
+    - Technical info: MediaInfo → Default
+    - File info: FileInfo → Default
+
+    Attributes:
+        file_path: Path to the media file
+        filename_extractor: Extracts metadata from filename patterns
+        metadata_extractor: Extracts embedded metadata tags
+        mediainfo_extractor: Extracts technical media information
+        fileinfo_extractor: Extracts basic file system information
+        tmdb_extractor: Fetches metadata from The Movie Database API
+        default_extractor: Provides fallback default values
+
+    Example:
+        >>> from pathlib import Path
+        >>> extractor = MediaExtractor(Path("Movie (2020) [1080p].mkv"))
+        >>> title = extractor.get("title")
+        >>> year = extractor.get("year")
+        >>> tracks = extractor.get("video_tracks")
+    """
 
     def __init__(self, file_path: Path):
         self.file_path = file_path
@@ -168,7 +203,24 @@ class MediaExtractor:
         }
 
     def get(self, key: str, source: str | None = None):
-        """Get extracted data by key, optionally from specific source"""
+        """Get metadata value by key, optionally from a specific source.
+
+        Retrieves metadata using a priority-based system. If a source is specified,
+        only that extractor is used. Otherwise, extractors are tried in priority
+        order until a non-None value is found.
+
+        Args:
+            key: The metadata key to retrieve (e.g., "title", "year", "resolution")
+            source: Optional specific extractor to use ("TMDB", "MediaInfo", "Filename", etc.)
+
+        Returns:
+            The extracted metadata value, or None if not found
+
+        Example:
+            >>> extractor = MediaExtractor(Path("movie.mkv"))
+            >>> title = extractor.get("title")  # Try all sources in priority order
+            >>> year = extractor.get("year", source="Filename")  # Use only filename
+        """
         if source:
             # Specific source requested - find the extractor and call the method directly
             for extractor_name, extractor in self._extractors.items():

renamer/extractors/fileinfo_extractor.py

@@ -1,3 +1,9 @@
+"""File system information extractor.
+
+This module provides the FileInfoExtractor class for extracting basic
+file system metadata such as size, timestamps, paths, and extensions.
+"""
+
 from pathlib import Path
 import logging
 import os
@@ -5,45 +11,89 @@ from ..decorators import cached_method
 
 # Set up logging conditionally
 if os.getenv('FORMATTER_LOG', '0') == '1':
-    logging.basicConfig(filename='formatter.log', level=logging.INFO, 
+    logging.basicConfig(filename='formatter.log', level=logging.INFO,
                         format='%(asctime)s - %(levelname)s - %(message)s')
 else:
     logging.basicConfig(level=logging.CRITICAL)  # Disable logging
 
 
 class FileInfoExtractor:
-    """Class to extract file information"""
+    """Extractor for basic file system information.
+
+    This class extracts file system metadata including size, modification time,
+    file name, path, and extension. All extraction methods are cached for
+    performance.
+
+    Attributes:
+        file_path: Path object pointing to the file
+        _size: Cached file size in bytes
+        _modification_time: Cached modification timestamp
+        _file_name: Cached file name
+        _file_path: Cached full file path as string
+        _cache: Internal cache for method results
+
+    Example:
+        >>> from pathlib import Path
+        >>> extractor = FileInfoExtractor(Path("movie.mkv"))
+        >>> size = extractor.extract_size()  # Returns size in bytes
+        >>> name = extractor.extract_file_name()  # Returns "movie.mkv"
+    """
 
     def __init__(self, file_path: Path):
+        """Initialize the FileInfoExtractor.
+
+        Args:
+            file_path: Path object pointing to the file to extract info from
+        """
         self.file_path = file_path
         self._size = file_path.stat().st_size
         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
+        self._cache: dict[str, any] = {}  # 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"""
+        """Extract file size in bytes.
+
+        Returns:
+            File size in bytes as an integer
+        """
         return self._size
 
     @cached_method()
     def extract_modification_time(self) -> float:
-        """Extract file modification time"""
+        """Extract file modification time.
+
+        Returns:
+            Unix timestamp (seconds since epoch) as a float
+        """
         return self._modification_time
 
     @cached_method()
     def extract_file_name(self) -> str:
-        """Extract file name"""
+        """Extract file name (basename).
+
+        Returns:
+            File name including extension (e.g., "movie.mkv")
+        """
         return self._file_name
 
     @cached_method()
     def extract_file_path(self) -> str:
-        """Extract full file path as string"""
+        """Extract full file path as string.
+
+        Returns:
+            Absolute file path as a string
+        """
         return self._file_path
 
     @cached_method()
     def extract_extension(self) -> str:
-        """Extract file extension without the dot"""
+        """Extract file extension without the dot.
+
+        Returns:
+            File extension in lowercase without leading dot (e.g., "mkv", "mp4")
+        """
         return self.file_path.suffix.lower().lstrip('.')

renamer/extractors/filename_extractor.py

@@ -9,6 +9,7 @@ from ..constants import (
     CYRILLIC_TO_ENGLISH
 )
 from ..decorators import cached_method
+from ..utils.pattern_utils import PatternExtractor
 import langcodes
 
 logger = logging.getLogger(__name__)
@@ -25,6 +26,9 @@ class FilenameExtractor:
             self.file_path = file_path
             self.file_name = file_path.name
 
+        # Initialize utility helper
+        self._pattern_extractor = PatternExtractor()
+
     def _normalize_cyrillic(self, text: str) -> str:
         """Normalize Cyrillic characters to English equivalents for parsing"""
         for cyr, eng in CYRILLIC_TO_ENGLISH.items():
@@ -222,23 +226,10 @@ class FilenameExtractor:
     @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
-        # Patterns: [tmdbid-123] {imdb-tt123} [imdbid-tt123] etc.
-        
-        # Match patterns like [tmdbid-123456] or {imdb-tt1234567}
-        pattern = r'[\[\{]([a-zA-Z]+(?:id)?)[-\s]*([a-zA-Z0-9]+)[\]\}]'
-        matches = re.findall(pattern, self.file_name)
-        
-        if matches:
-            # Take the last match (closest to end of filename)
-            db_type, db_id = matches[-1]
-            
-            # Normalize database type
-            db_type_lower = db_type.lower()
-            for db_key, db_info in MOVIE_DB_DICT.items():
-                if any(db_type_lower.startswith(pattern.rstrip('-')) for pattern in db_info['patterns']):
-                    return [db_key, db_id]
-        
+        # Use PatternExtractor utility to avoid code duplication
+        db_info = self._pattern_extractor.extract_movie_db_ids(self.file_name)
+        if db_info:
+            return [db_info['type'], db_info['id']]
         return None
 
     @cached_method()

renamer/extractors/metadata_extractor.py

@@ -1,3 +1,9 @@
+"""Embedded metadata extractor using Mutagen.
+
+This module provides the MetadataExtractor class for reading embedded
+metadata tags from media files using the Mutagen library.
+"""
+
 import mutagen
 import logging
 from pathlib import Path
@@ -8,11 +14,32 @@ logger = logging.getLogger(__name__)
 
 
 class MetadataExtractor:
-    """Class to extract information from file metadata"""
+    """Extractor for embedded metadata tags from media files.
+
+    This class uses the Mutagen library to read embedded metadata tags
+    such as title, artist, and duration. Falls back to MIME type detection
+    when Mutagen cannot read the file.
+
+    Attributes:
+        file_path: Path object pointing to the file
+        info: Mutagen file info object, or None if file cannot be read
+        _cache: Internal cache for method results
+
+    Example:
+        >>> from pathlib import Path
+        >>> extractor = MetadataExtractor(Path("movie.mkv"))
+        >>> title = extractor.extract_title()
+        >>> duration = extractor.extract_duration()
+    """
 
     def __init__(self, file_path: Path):
+        """Initialize the MetadataExtractor.
+
+        Args:
+            file_path: Path object pointing to the media file
+        """
         self.file_path = file_path
-        self._cache = {}  # Internal cache for method results
+        self._cache: dict[str, any] = {}  # Internal cache for method results
         try:
             self.info = mutagen.File(file_path) # type: ignore
         except Exception as e:
@@ -21,34 +48,60 @@ class MetadataExtractor:
 
     @cached_method()
     def extract_title(self) -> str | None:
-        """Extract title from metadata"""
+        """Extract title from embedded metadata tags.
+
+        Returns:
+            Title string if found in metadata, None otherwise
+        """
         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"""
+        """Extract duration from metadata.
+
+        Returns:
+            Duration in seconds as a float, or None if not available
+        """
         if self.info:
             return getattr(self.info, 'length', None)
         return None
 
     @cached_method()
     def extract_artist(self) -> str | None:
-        """Extract artist from metadata"""
+        """Extract artist from embedded metadata tags.
+
+        Returns:
+            Artist string if found in metadata, None otherwise
+        """
         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"""
+        """Extract metadata container type.
+
+        Returns the Mutagen class name (e.g., "FLAC", "MP4") if available,
+        otherwise falls back to MIME type detection.
+
+        Returns:
+            Container type name, or "Unknown" if cannot be determined
+        """
         if self.info:
             return type(self.info).__name__
         return self._detect_by_mime()
 
     def _detect_by_mime(self) -> str:
-        """Detect meta type by MIME"""
+        """Detect metadata type by MIME type.
+
+        Uses python-magic library to detect file MIME type and maps it
+        to a metadata container type.
+
+        Returns:
+            Container type name based on MIME type, or "Unknown" if detection fails
+        """
         try:
             import magic
             mime = magic.from_file(str(self.file_path), mime=True)