Add Ice Age: Continental Drift (2012) BDRip file to test filenames

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "renamer"
-version = "0.5.9"
+version = "0.5.10"
 description = "Terminal-based media file renamer and metadata viewer"
 readme = "README.md"
 requires-python = ">=3.11"

renamer/app.py

@@ -17,7 +17,6 @@ from .formatters.proposed_name_formatter import ProposedNameFormatter
 from .formatters.text_formatter import TextFormatter
 from .formatters.catalog_formatter import CatalogFormatter
 from .settings import Settings
-from .cache import Cache
 
 
 # Set up logging conditionally
@@ -57,7 +56,6 @@ class RenamerApp(App):
         self.scan_dir = Path(scan_dir) if scan_dir else None
         self.tree_expanded = False
         self.settings = Settings()
-        self.cache = Cache()
 
     def compose(self) -> ComposeResult:
         with Horizontal():
@@ -148,10 +146,9 @@ class RenamerApp(App):
                 ).start()
 
     def _extract_and_show_details(self, file_path: Path):
-        time.sleep(1)  # Minimum delay to show loading
         try:
             # Initialize extractors and formatters
-            extractor = MediaExtractor.create(file_path, self.cache, self.settings.get("cache_ttl_extractors"))
+            extractor = MediaExtractor(file_path)
             
             mode = self.settings.get("mode")
             if mode == "technical":
@@ -205,11 +202,6 @@ class RenamerApp(App):
         tree = self.query_one("#file_tree", Tree)
         node = tree.cursor_node
         if node and node.data and isinstance(node.data, Path) and node.data.is_file():
-            # Clear cache for this file
-            cache_key_base = str(node.data)
-            # Invalidate all keys for this file (we can improve this later)
-            for key in ["title", "year", "source", "extension", "video_tracks", "audio_tracks", "subtitle_tracks"]:
-                self.cache.invalidate(f"{cache_key_base}_{key}")
             self._start_loading_animation()
             threading.Thread(
                 target=self._extract_and_show_details, args=(node.data,)
@@ -240,7 +232,7 @@ class RenamerApp(App):
         node = tree.cursor_node
         if node and node.data and isinstance(node.data, Path) and node.data.is_file():
             # Get the proposed name from the extractor
-            extractor = MediaExtractor.create(node.data, self.cache, self.settings.get("cache_ttl_extractors"))
+            extractor = MediaExtractor(node.data)
             proposed_formatter = ProposedNameFormatter(extractor)
             new_name = str(proposed_formatter)
             logging.info(f"Proposed new name: {new_name!r} for file: {node.data}")
@@ -273,11 +265,6 @@ class RenamerApp(App):
         """Update the tree node for a renamed file."""
         logging.info(f"update_renamed_file called with old_path={old_path}, new_path={new_path}")
         
-        # Clear cache for old file
-        cache_key_base = str(old_path)
-        for key in ["title", "year", "source", "extension", "video_tracks", "audio_tracks", "subtitle_tracks"]:
-            self.cache.invalidate(f"{cache_key_base}_{key}")
-        
         tree = self.query_one("#file_tree", Tree)
         logging.info(f"Before update: cursor_node.data = {tree.cursor_node.data if tree.cursor_node else None}")
         

renamer/cache.py

@@ -11,13 +11,16 @@ class Cache:
     """File-based cache with TTL support."""
 
     def __init__(self, cache_dir: Optional[Path] = None):
-        if cache_dir is None:
+        # Always use the default cache dir to avoid creating cache in scan dir
         cache_dir = Path.home() / ".cache" / "renamer"
         self.cache_dir = cache_dir
         self.cache_dir.mkdir(parents=True, exist_ok=True)
+        self._memory_cache = {}  # In-memory cache for faster access
 
     def _get_cache_file(self, key: str) -> Path:
         """Get cache file path with hashed filename and subdirs."""
+        import logging
+        logging.info(f"Cache _get_cache_file called with key: {key!r}")
         # Parse key format: ClassName.method_name.param_hash
         if '.' in key:
             parts = key.split('.')
@@ -26,12 +29,27 @@ class Cache:
                 method_name = parts[1]
                 param_hash = parts[2]
                 
+                # Use class name as subdir, but if it contains '/', use general to avoid creating nested dirs
+                if '/' in class_name or '\\' in class_name:
+                    subdir = "general"
+                    subkey = key
+                    file_ext = "json"
+                else:
+                    subdir = class_name
+                    file_ext = "pkl"
+                
                 # Use class name as subdir
-                cache_subdir = self.cache_dir / class_name
+                cache_subdir = self.cache_dir / subdir
+                logging.info(f"Cache parsed key, class_name: {class_name!r}, cache_subdir: {cache_subdir!r}")
                 cache_subdir.mkdir(parents=True, exist_ok=True)
                 
+                if file_ext == "pkl":
                     # Use method_name.param_hash as filename
                     return cache_subdir / f"{method_name}.{param_hash}.pkl"
+                else:
+                    # Hash the subkey for filename
+                    key_hash = hashlib.md5(subkey.encode('utf-8')).hexdigest()
+                    return cache_subdir / f"{key_hash}.json"
         
         # Fallback for old keys (tmdb_, poster_, etc.)
         if key.startswith("tmdb_"):
@@ -40,12 +58,16 @@ class Cache:
         elif key.startswith("poster_"):
             subdir = "posters"
             subkey = key[7:]  # Remove "poster_" prefix
+        elif key.startswith("extractor_"):
+            subdir = "extractors"
+            subkey = key[10:]  # Remove "extractor_" prefix
         else:
             subdir = "general"
             subkey = key
         
         # Create subdir
         cache_subdir = self.cache_dir / subdir
+        logging.info(f"Cache fallback, subdir: {subdir!r}, cache_subdir: {cache_subdir!r}")
         cache_subdir.mkdir(parents=True, exist_ok=True)
         
         # Hash the subkey for filename
@@ -54,6 +76,14 @@ class Cache:
 
     def get(self, key: str) -> Optional[Any]:
         """Get cached value if not expired."""
+        # Check memory cache first
+        if key in self._memory_cache:
+            data = self._memory_cache[key]
+            if time.time() > data.get('expires', 0):
+                del self._memory_cache[key]
+                return None
+            return data.get('value')
+        
         cache_file = self._get_cache_file(key)
         if not cache_file.exists():
             return None
@@ -67,6 +97,8 @@ class Cache:
                 cache_file.unlink(missing_ok=True)
                 return None
             
+            # Store in memory cache
+            self._memory_cache[key] = data
             return data.get('value')
         except (json.JSONDecodeError, IOError):
             # Corrupted, remove
@@ -75,11 +107,14 @@ class Cache:
 
     def set(self, key: str, value: Any, ttl_seconds: int) -> None:
         """Set cached value with TTL."""
-        cache_file = self._get_cache_file(key)
         data = {
             'value': value,
             'expires': time.time() + ttl_seconds
         }
+        # Store in memory cache
+        self._memory_cache[key] = data
+        
+        cache_file = self._get_cache_file(key)
         try:
             with open(cache_file, 'w') as f:
                 json.dump(data, f)
@@ -154,6 +189,14 @@ class Cache:
 
     def get_object(self, key: str) -> Optional[Any]:
         """Get pickled object from cache if not expired."""
+        # Check memory cache first
+        if key in self._memory_cache:
+            data = self._memory_cache[key]
+            if time.time() > data.get('expires', 0):
+                del self._memory_cache[key]
+                return None
+            return data.get('value')
+        
         cache_file = self._get_cache_file(key)
         if not cache_file.exists():
             return None
@@ -167,6 +210,8 @@ class Cache:
                 cache_file.unlink(missing_ok=True)
                 return None
             
+            # Store in memory cache
+            self._memory_cache[key] = data
             return data.get('value')
         except (pickle.PickleError, IOError):
             # Corrupted, remove
@@ -175,11 +220,14 @@ class Cache:
 
     def set_object(self, key: str, obj: Any, ttl_seconds: int) -> None:
         """Pickle and cache object with TTL."""
-        cache_file = self._get_cache_file(key)
         data = {
             'value': obj,
             'expires': time.time() + ttl_seconds
         }
+        # Store in memory cache
+        self._memory_cache[key] = data
+        
+        cache_file = self._get_cache_file(key)
         try:
             with open(cache_file, 'wb') as f:
                 pickle.dump(data, f)

renamer/decorators/caching.py

@@ -31,12 +31,17 @@ def cached_method(ttl_seconds: int = 3600) -> Callable:
             
             # Use instance identifier (file_path for extractors)
             instance_id = getattr(self, 'file_path', str(id(self)))
+            # If instance_id contains path separators, hash it to avoid creating subdirs
+            if '/' in str(instance_id) or '\\' in str(instance_id):
+                instance_id = hashlib.md5(str(instance_id).encode('utf-8')).hexdigest()
             
-            # Create hash from args and kwargs (excluding self)
+            # Create hash from args and kwargs only if they exist (excluding self)
+            if args or kwargs:
                 param_str = json.dumps((args, kwargs), sort_keys=True, default=str)
                 param_hash = hashlib.md5(param_str.encode('utf-8')).hexdigest()
-            
                 cache_key = f"{class_name}.{method_name}.{instance_id}.{param_hash}"
+            else:
+                cache_key = f"{class_name}.{method_name}.{instance_id}"
             
             # Try to get from cache
             cached_result = _cache.get_object(cache_key)

renamer/extractors/extractor.py

@@ -10,38 +10,14 @@ from .default_extractor import DefaultExtractor
 class MediaExtractor:
     """Class to extract various metadata from media files using specialized extractors"""
 
-    @classmethod
+    def __init__(self, file_path: Path):
-    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, cache, ttl_seconds)
+        self.tmdb_extractor = TMDBExtractor(file_path)
         self.default_extractor = DefaultExtractor()
         
         # Extractor mapping
@@ -191,15 +167,8 @@ 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():

renamer/extractors/tmdb_extractor.py

@@ -3,30 +3,34 @@ import os
 import time
 import hashlib
 import requests
+import logging
 from pathlib import Path
 from typing import Dict, Optional, Tuple, Any
 from ..secrets import TMDB_API_KEY, TMDB_ACCESS_TOKEN
-
+from ..cache import Cache
+from ..settings import Settings
 
 class TMDBExtractor:
     """Class to extract TMDB movie information"""
 
-    def __init__(self, file_path: Path, cache=None, ttl_seconds: int = 21600):
+    def __init__(self, file_path: Path):
         self.file_path = file_path
-        self.cache = cache
+        self.cache = Cache()
-        self.ttl_seconds = ttl_seconds
+        self.ttl_seconds = Settings().get("cache_ttl_extractors", 21600)
         self._movie_db_info = None
 
     def _get_cached_data(self, cache_key: str) -> Optional[Dict[str, Any]]:
         """Get data from cache if valid"""
         if self.cache:
-            return self.cache.get(f"tmdb_{cache_key}")
+            return self.cache.get_object(f"tmdb_{cache_key}")
         return None
 
     def _set_cached_data(self, cache_key: str, data: Dict[str, Any]):
         """Store data in cache"""
         if self.cache:
-            self.cache.set(f"tmdb_{cache_key}", data, self.ttl_seconds)
+            self.cache.set_object(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"""
@@ -56,8 +60,10 @@ class TMDBExtractor:
         # Check cache first
         cached = self._get_cached_data(cache_key)
         if cached is not None:
+            logging.info(f"TMDB cache hit for search: {title} ({year})")
             return cached
 
+        logging.info(f"TMDB cache miss for search: {title} ({year}), making request")
         params = {'query': title}
         if year:
             params['year'] = year
@@ -95,8 +101,10 @@ class TMDBExtractor:
         # Check cache first
         cached = self._get_cached_data(cache_key)
         if cached is not None:
+            logging.info(f"TMDB cache hit for movie details: {movie_id}")
             return cached
 
+        logging.info(f"TMDB cache miss for movie details: {movie_id}, making request")
         result = self._make_tmdb_request(f'/movie/{movie_id}')
         if result:
             # Cache the result

renamer/formatters/formatter.py

@@ -74,18 +74,6 @@ class FormatterApplier:
         # Sort formatters according to the global order
         ordered_formatters = sorted(formatters, key=lambda f: FormatterApplier.FORMATTER_ORDER.index(f) if f in FormatterApplier.FORMATTER_ORDER else len(FormatterApplier.FORMATTER_ORDER))
         
-        # Get caller info
-        frame = inspect.currentframe()
-        if frame and frame.f_back:
-            caller = f"{frame.f_back.f_code.co_filename}:{frame.f_back.f_lineno} in {frame.f_back.f_code.co_name}"
-        else:
-            caller = "Unknown"
-        
-        logging.info(f"Caller: {caller}")
-        logging.info(f"Original formatters: {[f.__name__ if hasattr(f, '__name__') else str(f) for f in formatters]}")
-        logging.info(f"Ordered formatters: {[f.__name__ if hasattr(f, '__name__') else str(f) for f in ordered_formatters]}")
-        logging.info(f"Input value: {repr(value)}")
-        
         # Apply in the ordered sequence
         for formatter in ordered_formatters:
             try:
@@ -96,7 +84,6 @@ class FormatterApplier:
                 logging.error(f"Error applying {formatter.__name__ if hasattr(formatter, '__name__') else str(formatter)}: {e}")
                 value = "Unknown"
         
-        logging.info(f"Final value: {repr(value)}")
         return value
         
     @staticmethod

renamer/settings.py

@@ -51,9 +51,9 @@ class Settings:
         except IOError as e:
             print(f"Error: Could not save settings: {e}")
 
-    def get(self, key: str) -> Any:
+    def get(self, key: str, default: Any = None) -> Any:
         """Get a setting value."""
-        return self._settings.get(key, self.DEFAULTS.get(key))
+        return self._settings.get(key, self.DEFAULTS.get(key, default))
 
     def set(self, key: str, value: Any) -> None:
         """Set a setting value and save."""

uv.lock

@@ -342,7 +342,7 @@ wheels = [
 
 [[package]]
 name = "renamer"
-version = "0.5.9"
+version = "0.5.10"
 source = { editable = "." }
 dependencies = [
     { name = "langcodes" },