feat: enhance NFO processing and movie detection

* fix: NFO processing overhaul - looking GOOD! Listen up, buddy! Your boy Cat just made this NFO processing smoother than my pompadour on a good hair day! WHAT'S THE DEAL? • Movie NFOs were getting DISSED when dates went missing • Episode NFOs with long names were cluttering up the joint • Nobody wants a messy media library - that's just WRONG! WHAT I FIXED (because I'm THAT good): • Movies: NFO processing now happens FIRST, baby! No more skipping when dates are wonky - we standardize EVERYTHING! • TV Shows: Long episode NFO names? GONE! We migrate that metadata to proper S##E## format and trash the old junk • Dates get moved to the bottom where they belong (it's all about the STYLE!) • NFOGuard signatures added to everything (gotta sign your work!) FILES TOUCHED: • nfoguard.py:1008-1025 - Fixed that early exit nonsense • core/nfo_manager.py - Added find_existing_episode_nfo() function • core/nfo_manager.py - Enhanced create_episode_nfo() with migration RESULTS: ✨ Existing movie.nfo files get the full treatment ✨ Long episode NFO names become sleek S##E## format ✨ All metadata preserved (we're not ANIMALS!) ✨ Dates organized properly at the bottom ✨ NFOGuard branding on everything This code is now looking SO good, it should be in GQ! What's not to like about perfection? * testing: Testing database date adds for old files * database debuging * fixing database calls as well as ID for imdb * fix: dirs with no imdb in title movies with no imdb getting skipped * update: fix core parsing
2025-09-20 20:24:02 -04:00
parent d5937b13be
commit cd22cd3340
4 changed files with 184 additions and 18 deletions
@@ -173,6 +173,7 @@ class NFOGuardDatabase:
    def upsert_movie_dates(self, imdb_id: str, released: Optional[str], 
                          dateadded: Optional[str], source: str, has_video_file: bool = False):
        """Insert or update movie date record"""
+        print(f"🔍 DATABASE UPSERT: imdb_id={imdb_id}, dateadded={dateadded}, source={source}")
        with self.get_connection() as conn:
            cursor = conn.cursor()
            # Use INSERT OR REPLACE to ensure we always update the dates properly
@@ -185,6 +186,11 @@ class NFOGuardDatabase:
                )
            """, (imdb_id, imdb_id, released, dateadded, source, has_video_file, datetime.utcnow().isoformat()))
            
+            # Debug: Check what was actually saved
+            cursor.execute("SELECT dateadded, source FROM movies WHERE imdb_id = ?", (imdb_id,))
+            result = cursor.fetchone()
+            print(f"🔍 DATABASE VERIFY: After upsert, found dateadded={result[0] if result else 'NOT_FOUND'}, source={result[1] if result else 'NOT_FOUND'}")
+    
    def get_series_episodes(self, imdb_id: str, has_video_file_only: bool = False) -> List[Dict]:
        """Get all episodes for a series"""
        with self.get_connection() as conn:
@@ -49,6 +49,93 @@ class NFOManager:
        
        return None
    
+    def parse_imdb_from_nfo(self, nfo_path: Path) -> Optional[str]:
+        """Extract IMDb ID from NFO file content"""
+        if not nfo_path.exists():
+            return None
+            
+        try:
+            tree = ET.parse(nfo_path)
+            root = tree.getroot()
+            
+            # Check for <uniqueid type="imdb">ttXXXXXX</uniqueid>
+            imdb_uniqueid = root.find('.//uniqueid[@type="imdb"]')
+            if imdb_uniqueid is not None and imdb_uniqueid.text:
+                imdb_id = imdb_uniqueid.text.strip()
+                if imdb_id.startswith('tt'):
+                    return imdb_id
+                    
+            # Check for legacy <imdbid>ttXXXXXX</imdbid>
+            imdbid_elem = root.find('.//imdbid')
+            if imdbid_elem is not None and imdbid_elem.text:
+                imdb_id = imdbid_elem.text.strip()
+                if imdb_id.startswith('tt'):
+                    return imdb_id
+                    
+            # Check for legacy <imdb>ttXXXXXX</imdb>
+            imdb_elem = root.find('.//imdb')
+            if imdb_elem is not None and imdb_elem.text:
+                imdb_id = imdb_elem.text.strip()
+                if imdb_id.startswith('tt'):
+                    return imdb_id
+                    
+        except (ET.ParseError, Exception):
+            # Skip corrupted or non-XML files
+            pass
+            
+        return None
+    
+    def find_movie_imdb_id(self, movie_dir: Path) -> Optional[str]:
+        """Find IMDb ID from directory name, filenames, or NFO file"""
+        # First try directory name
+        imdb_id = self.parse_imdb_from_path(movie_dir)
+        if imdb_id:
+            return imdb_id
+            
+        # Try all files in the directory for IMDb ID patterns
+        for file_path in movie_dir.iterdir():
+            if file_path.is_file():
+                imdb_id = self.parse_imdb_from_path(file_path)
+                if imdb_id:
+                    return imdb_id
+                    
+        # Finally, try NFO file content
+        nfo_path = movie_dir / "movie.nfo"
+        imdb_id = self.parse_imdb_from_nfo(nfo_path)
+        if imdb_id:
+            print(f"🔍 Found IMDb ID in NFO file: {imdb_id} from {nfo_path}")
+            return imdb_id
+            
+        return None
+    
+    def _parse_nfo_with_tolerance(self, nfo_path: Path):
+        """Parse NFO file with tolerance for URLs appended after XML"""
+        try:
+            # First try normal parsing
+            tree = ET.parse(nfo_path)
+            return tree.getroot()
+        except ET.ParseError as e:
+            # If parsing fails, try to extract just the XML part
+            try:
+                with open(nfo_path, 'r', encoding='utf-8') as f:
+                    content = f.read()
+                
+                # Find the last </movie> tag and truncate after it
+                last_movie_end = content.rfind('</movie>')
+                if last_movie_end != -1:
+                    xml_content = content[:last_movie_end + 8]  # +8 for </movie>
+                    
+                    # Try parsing the truncated content
+                    root = ET.fromstring(xml_content)
+                    print(f"✅ Successfully parsed NFO after removing trailing content: {nfo_path.name}")
+                    return root
+                else:
+                    # Re-raise original error if we can't find </movie>
+                    raise e
+            except Exception:
+                # Re-raise original error if our fix attempt fails
+                raise e
+    
    def create_movie_nfo(self, movie_dir: Path, imdb_id: str, dateadded: str, 
                        released: Optional[str] = None, source: str = "unknown",
                        lock_metadata: bool = True) -> None:
@@ -59,8 +146,8 @@ class NFOManager:
            # Try to load existing NFO file
            if nfo_path.exists():
                try:
-                    tree = ET.parse(nfo_path)
-                    movie = tree.getroot()
+                    # Try to parse the XML, handling URLs appended after </movie>
+                    movie = self._parse_nfo_with_tolerance(nfo_path)
                    
                    # Ensure root element is <movie>
                    if movie.tag != "movie":
@@ -279,6 +366,48 @@ class NFOManager:
        except Exception as e:
            print(f"❌ Error creating/updating season NFO {nfo_path}: {e}")
    
+    def find_existing_episode_nfo(self, season_dir: Path, season_num: int, episode_num: int) -> Optional[Path]:
+        """Find existing episode NFO file that matches season/episode but isn't standardized name"""
+        if not season_dir.exists():
+            return None
+            
+        # Standard filename pattern we're looking to create
+        standard_pattern = f"S{season_num:02d}E{episode_num:02d}.nfo"
+        
+        # Look for NFO files in the season directory
+        for nfo_file in season_dir.glob("*.nfo"):
+            # Skip if it's already the standard format
+            if nfo_file.name == standard_pattern:
+                continue
+                
+            # Check if this NFO contains the right season/episode
+            try:
+                tree = ET.parse(nfo_file)
+                root = tree.getroot()
+                
+                if root.tag == "episodedetails":
+                    # Check for season/episode elements
+                    season_elem = root.find("season")
+                    episode_elem = root.find("episode")
+                    
+                    if (season_elem is not None and episode_elem is not None and
+                        season_elem.text and episode_elem.text):
+                        try:
+                            file_season = int(season_elem.text)
+                            file_episode = int(episode_elem.text)
+                            
+                            if file_season == season_num and file_episode == episode_num:
+                                print(f"🔍 Found existing episode NFO: {nfo_file.name} -> will migrate to {standard_pattern}")
+                                return nfo_file
+                        except ValueError:
+                            continue
+                            
+            except (ET.ParseError, Exception):
+                # Skip corrupted or non-XML files
+                continue
+                
+        return None
+    
    def create_episode_nfo(self, season_dir: Path, season_num: int, episode_num: int,
                          aired: Optional[str], dateadded: Optional[str], source: str,
                          lock_metadata: bool = True, enhanced_metadata: Optional[Dict[str, Any]] = None) -> None:
@@ -287,17 +416,30 @@ class NFOManager:
        episode_filename = f"S{season_num:02d}E{episode_num:02d}.nfo"
        nfo_path = season_dir / episode_filename
        
+        # Track if we need to delete an old long-named NFO file
+        old_nfo_to_delete = None
+        
        try:
-            # Try to load existing NFO file
-            if nfo_path.exists():
+            # First, check for existing long-named NFO files that need migration
+            existing_long_nfo = self.find_existing_episode_nfo(season_dir, season_num, episode_num)
+            
+            # Try to load existing NFO file (either standard or long-named)
+            source_nfo_path = nfo_path if nfo_path.exists() else existing_long_nfo
+            
+            if source_nfo_path:
                try:
-                    tree = ET.parse(nfo_path)
+                    tree = ET.parse(source_nfo_path)
                    episode = tree.getroot()
                    
                    # Ensure root element is <episodedetails>
                    if episode.tag != "episodedetails":
                        raise ValueError("Root element is not <episodedetails>")
                    
+                    # If we're migrating from a long-named file, mark it for deletion
+                    if existing_long_nfo and source_nfo_path == existing_long_nfo:
+                        old_nfo_to_delete = existing_long_nfo
+                        print(f"📦 Migrating episode NFO: {existing_long_nfo.name} -> {episode_filename}")
+                    
                    # Remove existing NFOGuard-managed elements to avoid duplicates
                    # These will be re-added at the bottom
                    nfoguard_fields = ["aired", "dateadded", "lockdata", "season", "episode"]
@@ -374,6 +516,14 @@ class NFOManager:
            print(f"✅ Successfully created/updated episode NFO: {nfo_path}")
            print(f"   S{season_num:02d}E{episode_num:02d}, Aired: {aired}, Date Added: {dateadded}")
            
+            # Clean up old long-named NFO file if we migrated from it
+            if old_nfo_to_delete and old_nfo_to_delete.exists():
+                try:
+                    old_nfo_to_delete.unlink()
+                    print(f"🗑️  Cleaned up old NFO file: {old_nfo_to_delete.name}")
+                except Exception as cleanup_error:
+                    print(f"⚠️  Warning: Could not delete old NFO file {old_nfo_to_delete.name}: {cleanup_error}")
+            
        except Exception as e:
            print(f"❌ Error creating/updating episode NFO {nfo_path}: {e}")
    
@@ -949,9 +949,9 @@ class MovieProcessor:
    
    def process_movie(self, movie_path: Path, webhook_mode: bool = False) -> None:
        """Process a movie directory"""
-        imdb_id = self.nfo_manager.parse_imdb_from_path(movie_path)
+        imdb_id = self.nfo_manager.find_movie_imdb_id(movie_path)
        if not imdb_id:
-            _log("ERROR", f"No IMDb ID found in movie path: {movie_path}")
+            _log("ERROR", f"No IMDb ID found in movie directory, filenames, or NFO file: {movie_path}")
            return
        
        _log("INFO", f"Processing movie: {movie_path.name} (IMDb: {imdb_id})")
@@ -1005,24 +1005,34 @@ class MovieProcessor:
            # Use existing movie date decision logic
            dateadded, source, released = self._decide_movie_dates(imdb_id, movie_path, should_query, existing)
        
-        # Skip processing if no valid date found and file dates disabled
-        if dateadded is None:
-            _log("WARNING", f"Skipping movie {movie_path.name} - no valid date source available")
-            self.db.upsert_movie_dates(imdb_id, released, None, source, True)
-            return
-        
-        # Create NFO
+        # Create NFO regardless of date availability (preserves existing metadata)
        if config.manage_nfo:
            self.nfo_manager.create_movie_nfo(
                movie_path, imdb_id, dateadded, released, source, config.lock_metadata
            )
        
-        # Update file mtimes
+        # Skip remaining processing if no valid date found and file dates disabled
+        if dateadded is None:
+            _log("WARNING", f"Movie {movie_path.name} - no valid date source available, but NFO was still processed")
+            self.db.upsert_movie_dates(imdb_id, released, None, source, True)
+            return
+        
+        _log("DEBUG", f"Movie {movie_path.name} proceeding to save: dateadded={dateadded}, source={source}")
+        
+        # Update file mtimes (only if we have a valid date)
        if config.fix_dir_mtimes and dateadded and dateadded != "MANUAL_REVIEW_NEEDED":
            self.nfo_manager.update_movie_files_mtime(movie_path, dateadded)
        
+        _log("DEBUG", f"Movie processing reached file mtime section: fix_dir_mtimes={config.fix_dir_mtimes}, dateadded={dateadded}")
+        
        # Save to database
+        _log("DEBUG", f"About to save to database: imdb_id={imdb_id}, dateadded={dateadded}")
+        try:
            self.db.upsert_movie_dates(imdb_id, released, dateadded, source, True)
+            _log("DEBUG", f"Database save completed for {imdb_id}")
+        except Exception as e:
+            _log("ERROR", f"Database save failed for {imdb_id}: {e}")
+            raise
        
        _log("INFO", f"Completed processing movie: {movie_path.name} (source: {source})")
    
@@ -1874,7 +1884,7 @@ async def manual_scan(background_tasks: BackgroundTasks, path: Optional[str] = N
                _log("INFO", f"Scanning movies in: {scan_path}")
                movie_count = 0
                for item in scan_path.iterdir():
-                    if item.is_dir() and nfo_manager.parse_imdb_from_path(item):
+                    if item.is_dir() and nfo_manager.find_movie_imdb_id(item):
                        movie_count += 1
                        _log("INFO", f"Processing movie: {item.name}")
                        try:
@@ -1986,7 +1996,7 @@ async def test_movie_scan():
            
            if path.exists():
                for item in path.iterdir():
-                    if item.is_dir() and nfo_manager.parse_imdb_from_path(item):
+                    if item.is_dir() and nfo_manager.find_movie_imdb_id(item):
                        path_result["movies_found"] += 1
            
            results.append(path_result)