feature: more omprovments phase 3

processors/tv_processor.py

@@ -3,7 +3,6 @@ TV Series Processor for NFOGuard
 Handles TV series processing and episode management
 """
 import os
-import glob
 import re
 from pathlib import Path
 from typing import Optional, Dict, List, Set, Tuple, Any
@@ -16,6 +15,11 @@ from clients.sonarr_client import SonarrClient
 from clients.external_clients import ExternalClientManager
 from config.settings import config
 from utils.logging import _log
+from utils.file_utils import (
+    find_media_path_by_imdb_and_title,
+    find_episodes_on_disk,
+    extract_title_from_directory_name
+)
 
 
 class TVProcessor:
@@ -32,36 +36,14 @@ class TVProcessor:
         self.external_clients = ExternalClientManager()
     
     def find_series_path(self, series_title: str, imdb_id: str, sonarr_path: str = None) -> Optional[Path]:
-        """Find series directory path"""
-        # Try webhook path first
-        if sonarr_path:
-            container_path = self.path_mapper.sonarr_path_to_container_path(sonarr_path)
-            path_obj = Path(container_path)
-            if path_obj.exists():
-                return path_obj
-        
-        # Search by IMDb ID or title
-        for media_path in config.tv_paths:
-            if not media_path.exists():
-                continue
-            
-            # Search by IMDb ID
-            if imdb_id:
-                pattern = str(media_path / f"*[imdb-{imdb_id}]*")
-                matches = glob.glob(pattern)
-                if matches:
-                    return Path(matches[0])
-            
-            # Search by title
-            if series_title:
-                title_clean = series_title.lower().replace(" ", "").replace("-", "")
-                for item in media_path.iterdir():
-                    if item.is_dir() and "[imdb-" in item.name.lower():
-                        item_clean = item.name.lower().replace(" ", "").replace("-", "")
-                        if title_clean in item_clean:
-                            return item
-        
-        return None
+        """Find series directory path using unified file utilities"""
+        return find_media_path_by_imdb_and_title(
+            title=series_title,
+            imdb_id=imdb_id,
+            search_paths=config.tv_paths,
+            webhook_path=sonarr_path,
+            path_mapper=self.path_mapper
+        )
     
     def process_series(self, series_path: Path) -> None:
         """Process a TV series directory"""
@@ -76,7 +58,7 @@ class TVProcessor:
         self.db.upsert_series(imdb_id, str(series_path))
         
         # Find video files
-        disk_episodes = self._find_disk_episodes(series_path)
+        disk_episodes = find_episodes_on_disk(series_path)
         _log("INFO", f"Found {len(disk_episodes)} episodes on disk")
         
         # Get episode dates
@@ -108,55 +90,9 @@ class TVProcessor:
         _log("INFO", f"Completed processing TV series: {series_path.name}")
     
     def _extract_series_title_from_path(self, series_path: Path) -> Optional[str]:
-        """Extract series title from directory path, removing year and IMDb ID"""
-        name = series_path.name
-        
-        # Remove IMDb ID part: [imdb-ttXXXXXX] or [ttXXXXXX]
-        name = re.sub(r'\s*\[imdb-?tt\d+\]', '', name, flags=re.IGNORECASE)
-        name = re.sub(r'\s*\[tt\d+\]', '', name, flags=re.IGNORECASE)
-        
-        # Remove year in parentheses: (YYYY)
-        name = re.sub(r'\s*\(\d{4}\)', '', name)
-        
-        # Clean up extra spaces
-        name = ' '.join(name.split())
-        
-        return name.strip() if name.strip() else None
+        """Extract series title from directory path using unified file utilities"""
+        return extract_title_from_directory_name(series_path.name)
     
-    def _find_disk_episodes(self, series_path: Path) -> Dict[Tuple[int, int], List[Path]]:
-        """Find all episodes on disk and return mapping of (season, episode) -> [video_files]"""
-        episodes = {}
-        
-        if not series_path.exists():
-            return episodes
-        
-        video_extensions = {'.mkv', '.mp4', '.avi', '.m4v', '.mov', '.ts'}
-        
-        # Define regex pattern for episode files
-        episode_pattern = re.compile(
-            r'.*[sS](\d{1,2})[eE](\d{1,3}).*|.*(\d{1,2})x(\d{1,3}).*'
-        )
-        
-        for item in series_path.rglob('*'):
-            if item.is_file() and item.suffix.lower() in video_extensions:
-                # Try to extract season/episode from filename
-                match = episode_pattern.match(item.name)
-                if match:
-                    if match.group(1) and match.group(2):  # SxxExx format
-                        season = int(match.group(1))
-                        episode = int(match.group(2))
-                    elif match.group(3) and match.group(4):  # NxNN format
-                        season = int(match.group(3))
-                        episode = int(match.group(4))
-                    else:
-                        continue
-                    
-                    key = (season, episode)
-                    if key not in episodes:
-                        episodes[key] = []
-                    episodes[key].append(item)
-        
-        return episodes
     
     def _gather_episode_dates(self, series_path: Path, imdb_id: str, disk_episodes: Dict[Tuple[int, int], List[Path]]) -> Dict[Tuple[int, int], Tuple[Optional[str], Optional[str], str]]:
         """Gather episode air dates and date added information"""
@@ -251,7 +187,7 @@ class TVProcessor:
         _log("INFO", f"Processing season {season_num} of series: {series_path_obj.name}")
         
         # Find episodes in this season
-        disk_episodes = self._find_disk_episodes(series_path_obj)
+        disk_episodes = find_episodes_on_disk(series_path_obj)
         season_episodes = {k: v for k, v in disk_episodes.items() if k[0] == season_num}
         
         if not season_episodes: