nfo: improvments to processing

api/routes.py

@@ -2317,9 +2317,9 @@ def register_routes(app, dependencies: dict):
             import subprocess
             import re
             
-            # Find all NFO files and check which ones are missing dateadded
+            # Separate tracking for TV and movie missing files
-            # This is much faster than database-driven approach
+            missing_tv_nfo_files = []
-            missing_nfo_files = []
+            missing_movie_nfo_files = []
             
             # Find all NFO files in TV directory
             if os.path.exists(tv_path):
@@ -2342,7 +2342,7 @@ def register_routes(app, dependencies: dict):
                             
                             if i % 1000 == 0 and i > 0:
                                 elapsed = time.time() - scan_start_time
-                                print(f"📊 Progress: {i}/{len(tv_nfo_files)} TV NFO files checked in {elapsed:.1f}s, {len(missing_nfo_files)} missing found")
+                                print(f"📊 Progress: {i}/{len(tv_nfo_files)} TV NFO files checked in {elapsed:.1f}s, {len(missing_tv_nfo_files)} missing found")
                             
                             # Timeout check
                             if time.time() - scan_start_time > 180:  # 3 minutes
@@ -2358,7 +2358,7 @@ def register_routes(app, dependencies: dict):
                                 
                                 # If grep returns non-zero, dateadded is missing
                                 if grep_result.returncode != 0:
-                                    missing_nfo_files.append(nfo_file)
+                                    missing_tv_nfo_files.append(nfo_file)
                                     
                                     # Log specific files we're looking for
                                     if 'Hudson' in nfo_file and 'S08E05' in nfo_file:
@@ -2383,9 +2383,9 @@ def register_routes(app, dependencies: dict):
             else:
                 print(f"❌ TV path does not exist: {tv_path}")
             
-            print(f"📊 Found {len(missing_nfo_files)} NFO files missing dateadded elements")
+            print(f"📊 Found {len(missing_tv_nfo_files)} TV NFO files missing dateadded elements")
             
-            # Convert file paths to episode/movie information with direct NFO parsing
+            # Convert TV file paths to episode information with direct NFO parsing
             def extract_imdb_from_nfo_content(nfo_file, is_episode=True):
                 """Extract IMDb ID directly from NFO file content - we already know the file exists"""
                 imdb_id = "unknown"
@@ -2459,7 +2459,7 @@ def register_routes(app, dependencies: dict):
                 print(f"❌ No IMDb ID found in {os.path.basename(nfo_file)}")
                 return "unknown"
             
-            for nfo_file in missing_nfo_files:
+            for nfo_file in missing_tv_nfo_files:
                 try:
                     # Parse episode info from file path
                     # Example: /media/TV/tv/Hudson & Rex (2019) [imdb-tt9111220]/Season 08/Hudson & Rex (2019)-S08E05-Episode.nfo
@@ -2522,7 +2522,7 @@ def register_routes(app, dependencies: dict):
                             
                             if i % 500 == 0 and i > 0:
                                 elapsed = time.time() - scan_start_time
-                                print(f"📊 Progress: {i}/{len(movie_nfo_files)} Movie NFO files checked in {elapsed:.1f}s, {len(missing_items['movies'])} missing found")
+                                print(f"📊 Progress: {i}/{len(movie_nfo_files)} Movie NFO files checked in {elapsed:.1f}s, {len(missing_movie_nfo_files)} missing found")
                             
                             # Timeout check
                             if time.time() - scan_start_time > 300:  # 5 minutes total
@@ -2538,25 +2538,7 @@ def register_routes(app, dependencies: dict):
                                 
                                 # If grep returns non-zero, dateadded is missing
                                 if grep_result.returncode != 0:
-                                    # Extract movie info from file path
+                                    missing_movie_nfo_files.append(nfo_file)
-                                    # Example: /media/Movies/movies/Knives Out (2019) [imdb-tt8946378]/movie.nfo
-                                    movie_dir = os.path.dirname(nfo_file)
-                                    movie_folder_name = os.path.basename(movie_dir)
-                                    
-                                    # Extract IMDb ID from NFO content
-                                    imdb_id = extract_imdb_from_nfo_content(nfo_file, is_episode=False)
-                                    
-                                    # Clean movie title (remove year and imdb parts)
-                                    clean_movie_title = re.sub(r'\s*\(\d{4}\)\s*\[imdb-[^]]+\]', '', movie_folder_name).strip()
-                                    
-                                    missing_items["movies"].append({
-                                        "imdb_id": imdb_id,
-                                        "title": clean_movie_title,
-                                        "path": movie_dir,
-                                        "dateadded": None,
-                                        "nfo_path": nfo_file,
-                                        "reason": "NFO missing dateadded element (filesystem scan)"
-                                    })
                                         
                             except subprocess.TimeoutExpired:
                                 print(f"⏰ Timeout checking {nfo_file}")
@@ -2575,6 +2557,34 @@ def register_routes(app, dependencies: dict):
             else:
                 print(f"❌ Movie path does not exist: {movie_path}")
             
+            # Process missing movie NFO files
+            print(f"📊 Found {len(missing_movie_nfo_files)} Movie NFO files missing dateadded elements")
+            
+            for nfo_file in missing_movie_nfo_files:
+                try:
+                    # Extract movie info from file path
+                    # Example: /media/Movies/movies/Knives Out (2019) [imdb-tt8946378]/movie.nfo
+                    movie_dir = os.path.dirname(nfo_file)
+                    movie_folder_name = os.path.basename(movie_dir)
+                    
+                    # Extract IMDb ID from NFO content
+                    imdb_id = extract_imdb_from_nfo_content(nfo_file, is_episode=False)
+                    
+                    # Clean movie title (remove year and imdb parts)
+                    clean_movie_title = re.sub(r'\s*\(\d{4}\)\s*\[imdb-[^]]+\]', '', movie_folder_name).strip()
+                    
+                    missing_items["movies"].append({
+                        "imdb_id": imdb_id,
+                        "title": clean_movie_title,
+                        "path": movie_dir,
+                        "dateadded": None,
+                        "nfo_path": nfo_file,
+                        "reason": "NFO missing dateadded element (filesystem scan)"
+                    })
+                except Exception as e:
+                    print(f"⚠️ Error parsing movie NFO file path {nfo_file}: {e}")
+                    continue
+            
             # Database lookup to get actual dateadded values for missing items
             print("🔍 Looking up dateadded values from database for missing items...")
             
@@ -2765,6 +2775,19 @@ def register_routes(app, dependencies: dict):
                         dateadded_elem = ET.SubElement(root, "dateadded")
                         dateadded_elem.text = nfo_dateadded
                         
+                        # Add source attribution (similar to what NFOGuard normally adds)
+                        # Check if source element exists, if not create it
+                        source_elem = root.find("source")
+                        if source_elem is None:
+                            source_elem = ET.SubElement(root, "source")
+                        source_elem.text = f"NFOGuard repair - {episode.get('source', 'database')}"
+                        
+                        # Add addedby attribution if not present
+                        addedby_elem = root.find("addedby")
+                        if addedby_elem is None:
+                            addedby_elem = ET.SubElement(root, "addedby")
+                        addedby_elem.text = "NFOGuard"
+                        
                         # Write back to file
                         tree.write(nfo_path, encoding='utf-8', xml_declaration=True)
                         
@@ -2851,6 +2874,18 @@ def register_routes(app, dependencies: dict):
                         dateadded_elem = ET.SubElement(root, "dateadded")
                         dateadded_elem.text = nfo_dateadded
                         
+                        # Add source attribution (similar to what NFOGuard normally adds)
+                        source_elem = root.find("source")
+                        if source_elem is None:
+                            source_elem = ET.SubElement(root, "source")
+                        source_elem.text = f"NFOGuard repair - {movie.get('source', 'database')}"
+                        
+                        # Add addedby attribution if not present
+                        addedby_elem = root.find("addedby")
+                        if addedby_elem is None:
+                            addedby_elem = ET.SubElement(root, "addedby")
+                        addedby_elem.text = "NFOGuard"
+                        
                         # Write back to file
                         tree.write(nfo_path, encoding='utf-8', xml_declaration=True)