endoreg-db 0.8.2.7__py3-none-any.whl → 0.8.2.8__py3-none-any.whl

endoreg_db/services/video_import.py

@@ -8,24 +8,26 @@ Changelog:
     October 14, 2025: Added file locking mechanism to prevent race conditions
                       during concurrent video imports (matches PDF import pattern)
 """
-from datetime import date
+
 import logging
-import sys
 import os
+import random
 import shutil
+import sys
 import time
 from contextlib import contextmanager
+from datetime import date
 from pathlib import Path
-from typing import Union, Dict, Any, Optional, List, Tuple
+from typing import TYPE_CHECKING, Any, Dict, Optional, Tuple, Union
+
 from django.db import transaction
-from endoreg_db.models import VideoFile, SensitiveMeta
-from endoreg_db.utils.paths import STORAGE_DIR, RAW_FRAME_DIR, VIDEO_DIR, ANONYM_VIDEO_DIR
-import random
+from django.db.models.fields.files import FieldFile
 from lx_anonymizer.ocr import trocr_full_image_ocr
+
+from endoreg_db.models import SensitiveMeta, VideoFile
+from endoreg_db.models.media.video.video_file_anonymize import _anonymize, _cleanup_raw_assets
 from endoreg_db.utils.hashs import get_video_hash
-from endoreg_db.models.media.video.video_file_anonymize import _cleanup_raw_assets, _anonymize
-from typing import TYPE_CHECKING
-from django.db.models.fields.files import FieldFile
+from endoreg_db.utils.paths import ANONYM_VIDEO_DIR, RAW_FRAME_DIR, STORAGE_DIR, VIDEO_DIR
 
 if TYPE_CHECKING:
     from endoreg_db.models import EndoscopyProcessor
@@ -37,37 +39,36 @@ MAX_LOCK_WAIT_SECONDS = 90  # New: wait up to 90s for a non-stale lock to clear
 logger = logging.getLogger(__name__)
 
 
-class VideoImportService():
+class VideoImportService:
     """
     Service for importing and anonymizing video files.
     Uses a central video instance pattern for cleaner state management.
-    
+
     Features (October 14, 2025):
         - File locking to prevent concurrent processing of the same video
         - Stale lock detection and reclamation (600s timeout)
         - Hash-based duplicate detection
         - Graceful fallback processing without lx_anonymizer
     """
-    
+
     def __init__(self, project_root: Optional[Path] = None):
-        
         # Set up project root path
         if project_root:
             self.project_root = Path(project_root)
         else:
             self.project_root = Path(__file__).parent.parent.parent.parent
-        
+
         # Track processed files to prevent duplicates
         self.processed_files = set(str(file) for file in os.listdir(ANONYM_VIDEO_DIR))
-            
+
         self.STORAGE_DIR = STORAGE_DIR
-        
+
         # Central video instance and processing context
         self.current_video: Optional[VideoFile] = None
         self.processing_context: Dict[str, Any] = {}
-        
+
         self.delete_source = False
-        
+
         self.logger = logging.getLogger(__name__)
 
     def _require_current_video(self) -> VideoFile:
@@ -75,12 +76,12 @@ class VideoImportService():
         if self.current_video is None:
             raise RuntimeError("Current video instance is not set")
         return self.current_video
-    
+
     @contextmanager
     def _file_lock(self, path: Path):
         """
         Create a file lock to prevent duplicate processing of the same video.
-        
+
         This context manager creates a .lock file alongside the video file.
         If the lock file already exists, it checks if it's stale (older than
         STALE_LOCK_SECONDS) and reclaims it if necessary. If it's not stale,
@@ -104,24 +105,21 @@ class VideoImportService():
                     except FileNotFoundError:
                         # Race: lock removed between exists and stat; retry acquire in next loop
                         age = None
-                    
+
                     if age is not None and age > STALE_LOCK_SECONDS:
                         try:
-                            logger.warning(
-                                "Stale lock detected for %s (age %.0fs). Reclaiming lock...",
-                                path, age
-                            )
+                            logger.warning("Stale lock detected for %s (age %.0fs). Reclaiming lock...", path, age)
                             lock_path.unlink()
                         except Exception as e:
                             logger.warning("Failed to remove stale lock %s: %s", lock_path, e)
                         # Loop continues and retries acquire immediately
                         continue
-                    
+
                     # Not stale: wait until deadline, then give up gracefully
                     if time.time() >= deadline:
                         raise ValueError(f"File already being processed: {path}")
                     time.sleep(1.0)
-            
+
             os.write(fd, b"lock")
             os.close(fd)
             fd = None
@@ -134,11 +132,11 @@ class VideoImportService():
                     lock_path.unlink()
             except OSError:
                 pass
-    
+
     def processed(self) -> bool:
         """Indicates if the current file has already been processed."""
-        return getattr(self, '_processed', False)
-                
+        return getattr(self, "_processed", False)
+
     def import_and_anonymize(
         self,
         file_path: Union[Path, str],
@@ -153,9 +151,8 @@ class VideoImportService():
         """
         try:
             # Initialize processing context
-            self._initialize_processing_context(file_path, center_name, processor_name, 
-                                               save_video, delete_source)
-            
+            self._initialize_processing_context(file_path, center_name, processor_name, save_video, delete_source)
+
             # Validate and prepare file (may raise ValueError if another worker holds a non-stale lock)
             try:
                 self._validate_and_prepare_file()
@@ -165,27 +162,24 @@ class VideoImportService():
                     self.logger.info(f"Skipping {file_path}: {ve}")
                     return None
                 raise
-            
-            # Create sensitive meta file, ensure raw is moved out of processing folder watched by file watcher.
-            self._create_sensitive_file()
-            
-            # Create or retrieve video instance
+
+            # Create or retrieve video instance FIRST
             self._create_or_retrieve_video_instance()
-            
+
             # Setup processing environment
             self._setup_processing_environment()
-            
+
             # Process frames and metadata
             self._process_frames_and_metadata()
-            
+
             # Finalize processing
             self._finalize_processing()
-            
+
             # Move files and cleanup
             self._cleanup_and_archive()
-            
+
             return self.current_video
-            
+
         except Exception as e:
             self.logger.error(f"Video import and anonymization failed for {file_path}: {e}")
             self._cleanup_on_error()
@@ -193,94 +187,93 @@ class VideoImportService():
         finally:
             self._cleanup_processing_context()
 
-    def _initialize_processing_context(self, file_path: Union[Path, str], center_name: str, 
-                                     processor_name: str, save_video: bool, delete_source: bool):
+    def _initialize_processing_context(self, file_path: Union[Path, str], center_name: str, processor_name: str, save_video: bool, delete_source: bool):
         """Initialize the processing context for the current video import."""
         self.processing_context = {
-            'file_path': Path(file_path),
-            'center_name': center_name,
-            'processor_name': processor_name,
-            'save_video': save_video,
-            'delete_source': delete_source,
-            'processing_started': False,
-            'frames_extracted': False,
-            'anonymization_completed': False,
-            'error_reason': None
+            "file_path": Path(file_path),
+            "center_name": center_name,
+            "processor_name": processor_name,
+            "save_video": save_video,
+            "delete_source": delete_source,
+            "processing_started": False,
+            "frames_extracted": False,
+            "anonymization_completed": False,
+            "error_reason": None,
         }
-        
+
         self.logger.info(f"Initialized processing context for: {file_path}")
 
     def _validate_and_prepare_file(self):
         """
         Validate the video file and prepare for processing.
-        
+
         Uses file locking to prevent concurrent processing of the same video file.
         This prevents race conditions where multiple workers might try to process
         the same video simultaneously.
-        
+
         The lock is acquired here and held for the entire import process.
         See _file_lock() for lock reclamation logic.
         """
-        file_path = self.processing_context['file_path']
-        
+        file_path = self.processing_context["file_path"]
+
         # Acquire file lock to prevent concurrent processing
         # Lock will be held until finally block in import_and_anonymize()
-        self.processing_context['_lock_context'] = self._file_lock(file_path)
-        self.processing_context['_lock_context'].__enter__()
-        
+        self.processing_context["_lock_context"] = self._file_lock(file_path)
+        self.processing_context["_lock_context"].__enter__()
+
         self.logger.info("Acquired file lock for: %s", file_path)
-        
+
         # Check if already processed (memory-based check)
         if str(file_path) in self.processed_files:
             self.logger.info("File %s already processed, skipping", file_path)
             self._processed = True
             raise ValueError(f"File already processed: {file_path}")
-        
+
         # Check file exists
         if not file_path.exists():
             raise FileNotFoundError(f"Video file not found: {file_path}")
-        
+
         self.logger.info("File validation completed for: %s", file_path)
 
     def _create_or_retrieve_video_instance(self):
         """Create or retrieve the VideoFile instance and move to final storage."""
         # Removed duplicate import of VideoFile (already imported at module level)
-        
+
         self.logger.info("Creating VideoFile instance...")
-        
+
         self.current_video = VideoFile.create_from_file_initialized(
-            file_path=self.processing_context['file_path'],
-            center_name=self.processing_context['center_name'],
-            processor_name=self.processing_context['processor_name'],
-            delete_source=self.processing_context['delete_source'],
-            save_video_file=self.processing_context['save_video'],
+            file_path=self.processing_context["file_path"],
+            center_name=self.processing_context["center_name"],
+            processor_name=self.processing_context["processor_name"],
+            delete_source=self.processing_context["delete_source"],
+            save_video_file=self.processing_context["save_video"],
         )
-        
+
         if not self.current_video:
             raise RuntimeError("Failed to create VideoFile instance")
-        
+
         # Immediately move to final storage locations
         self._move_to_final_storage()
-        
+
         self.logger.info("Created VideoFile with UUID: %s", self.current_video.uuid)
-        
+
         # Get and mark processing state
         state = VideoFile.get_or_create_state(self.current_video)
         if not state:
             raise RuntimeError("Failed to create VideoFile state")
-        
+
         state.mark_processing_started(save=True)
-        self.processing_context['processing_started'] = True
+        self.processing_context["processing_started"] = True
 
     def _move_to_final_storage(self):
         """
         Move video from raw_videos to final storage locations.
-        - Raw video → /data/videos (raw_file_path) 
+        - Raw video → /data/videos (raw_file_path)
         - Processed video will later → /data/anonym_videos (file_path)
         """
         from endoreg_db.utils import data_paths
-        
-        source_path = self.processing_context['file_path']
+
+        source_path = self.processing_context["file_path"]
 
         videos_dir = data_paths["video"]
         videos_dir.mkdir(parents=True, exist_ok=True)
@@ -320,7 +313,7 @@ class VideoImportService():
             filename = f"{uuid_str}{source_suffix}" if uuid_str else Path(source_path).name
             stored_raw_path = videos_dir / filename
 
-        delete_source = bool(self.processing_context.get('delete_source'))
+        delete_source = bool(self.processing_context.get("delete_source"))
         stored_raw_path.parent.mkdir(parents=True, exist_ok=True)
 
         if not stored_raw_path.exists():
@@ -352,19 +345,19 @@ class VideoImportService():
             relative_path = Path(stored_raw_path).relative_to(storage_root)
             if _current_video.raw_file.name != str(relative_path):
                 _current_video.raw_file.name = str(relative_path)
-                _current_video.save(update_fields=['raw_file'])
+                _current_video.save(update_fields=["raw_file"])
                 self.logger.info("Updated raw_file path to: %s", relative_path)
         except Exception as e:
             self.logger.error("Failed to ensure raw_file path is relative: %s", e)
             fallback_relative = Path("videos") / Path(stored_raw_path).name
             if _current_video.raw_file.name != fallback_relative.as_posix():
                 _current_video.raw_file.name = fallback_relative.as_posix()
-                _current_video.save(update_fields=['raw_file'])
+                _current_video.save(update_fields=["raw_file"])
                 self.logger.info("Updated raw_file path using fallback: %s", fallback_relative.as_posix())
 
         # Store paths for later processing
-        self.processing_context['raw_video_path'] = Path(stored_raw_path)
-        self.processing_context['video_filename'] = Path(stored_raw_path).name
+        self.processing_context["raw_video_path"] = Path(stored_raw_path)
+        self.processing_context["video_filename"] = Path(stored_raw_path).name
 
     def _setup_processing_environment(self):
         """Setup the processing environment without file movement."""
@@ -375,32 +368,32 @@ class VideoImportService():
 
         # Initialize frame objects in database
         video.initialize_frames()
-        
+
         # Extract frames BEFORE processing to prevent pipeline 1 conflicts
         self.logger.info("Pre-extracting frames to avoid pipeline conflicts...")
         try:
             frames_extracted = video.extract_frames(overwrite=False)
             if frames_extracted:
-                self.processing_context['frames_extracted'] = True
+                self.processing_context["frames_extracted"] = True
                 self.logger.info("Frame extraction completed successfully")
-                
+
                 # CRITICAL: Immediately save the frames_extracted state to database
                 # to prevent refresh_from_db() in pipeline 1 from overriding it
                 state = video.get_or_create_state()
                 if not state.frames_extracted:
                     state.frames_extracted = True
-                    state.save(update_fields=['frames_extracted'])
+                    state.save(update_fields=["frames_extracted"])
                     self.logger.info("Persisted frames_extracted=True to database")
             else:
                 self.logger.warning("Frame extraction failed, but continuing...")
-                self.processing_context['frames_extracted'] = False
+                self.processing_context["frames_extracted"] = False
         except Exception as e:
             self.logger.warning(f"Frame extraction failed during setup: {e}, but continuing...")
-            self.processing_context['frames_extracted'] = False
-        
+            self.processing_context["frames_extracted"] = False
+
         # Ensure default patient data
         self._ensure_default_patient_data(video_instance=video)
-        
+
         self.logger.info("Processing environment setup completed")
 
     def _process_frames_and_metadata(self):
@@ -419,25 +412,24 @@ class VideoImportService():
 
         try:
             self.logger.info("Starting frame-level anonymization with processor ROI masking...")
-            
+
             # Get processor ROI information
             endoscope_data_roi_nested, endoscope_image_roi = self._get_processor_roi_info()
-            
+
             # Perform frame cleaning with timeout to prevent blocking
-            from concurrent.futures import ThreadPoolExecutor, TimeoutError as FutureTimeoutError
-            
+            from concurrent.futures import ThreadPoolExecutor
+            from concurrent.futures import TimeoutError as FutureTimeoutError
+
             with ThreadPoolExecutor(max_workers=1) as executor:
                 future = executor.submit(self._perform_frame_cleaning, FrameCleaner, endoscope_data_roi_nested, endoscope_image_roi)
                 try:
                     # Increased timeout to better accommodate ffmpeg + OCR
                     future.result(timeout=300)
-                    self.processing_context['anonymization_completed'] = True
+                    self.processing_context["anonymization_completed"] = True
                     self.logger.info("Frame cleaning completed successfully within timeout")
                 except FutureTimeoutError:
                     self.logger.warning("Frame cleaning timed out; entering grace period check for cleaned output")
                     # Grace period: detect if cleaned file appears shortly after timeout
-                    raw_video_path = self.processing_context.get('raw_video_path')
-                    video_filename = self.processing_context.get('video_filename', Path(raw_video_path).name if raw_video_path else "video.mp4")
                     grace_seconds = 60
                     expected_cleaned_path: Optional[Path] = None
                     processed_field = video.processed_file
@@ -450,8 +442,8 @@ class VideoImportService():
                     if expected_cleaned_path is not None:
                         for _ in range(grace_seconds):
                             if expected_cleaned_path.exists():
-                                self.processing_context['cleaned_video_path'] = expected_cleaned_path
-                                self.processing_context['anonymization_completed'] = True
+                                self.processing_context["cleaned_video_path"] = expected_cleaned_path
+                                self.processing_context["anonymization_completed"] = True
                                 self.logger.info("Detected cleaned video during grace period: %s", expected_cleaned_path)
                                 found = True
                                 break
@@ -469,8 +461,8 @@ class VideoImportService():
             except Exception as fallback_error:
                 self.logger.error("Fallback anonymization also failed: %s", fallback_error)
                 # If even fallback fails, mark as not anonymized but continue import
-                self.processing_context['anonymization_completed'] = False
-                self.processing_context['error_reason'] = f"Frame cleaning failed: {e}, Fallback failed: {fallback_error}"
+                self.processing_context["anonymization_completed"] = False
+                self.processing_context["error_reason"] = f"Frame cleaning failed: {e}, Fallback failed: {fallback_error}"
 
     def _save_anonymized_video(self):
         video = self._require_current_video()
@@ -481,9 +473,7 @@ class VideoImportService():
 
         new_processed_hash = get_video_hash(anonymized_video_path)
         if video.__class__.objects.filter(processed_video_hash=new_processed_hash).exclude(pk=video.pk).exists():
-            raise ValueError(
-                f"Processed video hash {new_processed_hash} already exists for another video (Video: {video.uuid})."
-            )
+            raise ValueError(f"Processed video hash {new_processed_hash} already exists for another video (Video: {video.uuid}).")
 
         video.processed_video_hash = new_processed_hash
         video.processed_file.name = anonymized_video_path.relative_to(STORAGE_DIR).as_posix()
@@ -502,11 +492,11 @@ class VideoImportService():
 
             update_fields.extend(["raw_file", "video_hash"])
 
-            transaction.on_commit(lambda: _cleanup_raw_assets(
-                video_uuid=video.uuid,
-                raw_file_path=original_raw_file_path_to_delete,
-                raw_frame_dir=original_raw_frame_dir_to_delete
-            ))
+            transaction.on_commit(
+                lambda: _cleanup_raw_assets(
+                    video_uuid=video.uuid, raw_file_path=original_raw_file_path_to_delete, raw_frame_dir=original_raw_frame_dir_to_delete
+                )
+            )
 
         video.save(update_fields=update_fields)
         video.state.mark_anonymized(save=True)
@@ -525,32 +515,33 @@ class VideoImportService():
                 self.logger.warning("No VideoFile instance available for fallback anonymization")
             else:
                 # Try VideoFile.pipe_2() method if available
-                if hasattr(video, 'pipe_2'):
+                if hasattr(video, "pipe_2"):
                     self.logger.info("Trying VideoFile.pipe_2() method...")
                     if video.pipe_2():
                         self.logger.info("VideoFile.pipe_2() succeeded")
-                        self.processing_context['anonymization_completed'] = True
+                        self.processing_context["anonymization_completed"] = True
                         return
                     self.logger.warning("VideoFile.pipe_2() returned False")
                 # Try direct anonymization via _anonymize
                 if _anonymize(video, delete_original_raw=self.delete_source):
                     self.logger.info("VideoFile._anonymize() succeeded")
-                    self.processing_context['anonymization_completed'] = True
+                    self.processing_context["anonymization_completed"] = True
                     return
 
             # Strategy 2: Simple copy (no processing, just copy raw to processed)
             self.logger.info("Using simple copy fallback (raw video will be used as 'processed' video)")
-            self.processing_context['anonymization_completed'] = False
-            self.processing_context['use_raw_as_processed'] = True
+            self.processing_context["anonymization_completed"] = False
+            self.processing_context["use_raw_as_processed"] = True
             self.logger.warning("Fallback: Video will be imported without anonymization (raw copy used)")
         except Exception as e:
             self.logger.error(f"Error during fallback anonymization: {e}", exc_info=True)
-            self.processing_context['anonymization_completed'] = False
-            self.processing_context['error_reason'] = str(e)
+            self.processing_context["anonymization_completed"] = False
+            self.processing_context["error_reason"] = str(e)
+
     def _finalize_processing(self):
         """Finalize processing and update video state."""
         self.logger.info("Updating video processing state...")
-        
+
         with transaction.atomic():
             video = self._require_current_video()
             try:
@@ -559,36 +550,33 @@ class VideoImportService():
                 self.logger.warning("Could not refresh VideoFile %s from DB: %s", video.uuid, refresh_error)
 
             state = video.get_or_create_state()
-            
+
             # Only mark frames as extracted if they were successfully extracted
-            if self.processing_context.get('frames_extracted', False):
+            if self.processing_context.get("frames_extracted", False):
                 state.frames_extracted = True
                 self.logger.info("Marked frames as extracted in state")
             else:
                 self.logger.warning("Frames were not extracted, not updating state")
-                
+
             # Always mark these as true (metadata extraction attempts were made)
             state.frames_initialized = True
             state.video_meta_extracted = True
             state.text_meta_extracted = True
-            
+
             # ✅ FIX: Only mark as processed if anonymization actually completed
-            anonymization_completed = self.processing_context.get('anonymization_completed', False)
+            anonymization_completed = self.processing_context.get("anonymization_completed", False)
             if anonymization_completed:
                 state.mark_sensitive_meta_processed(save=False)
                 self.logger.info("Anonymization completed - marking sensitive meta as processed")
             else:
-                self.logger.warning(
-                    "Anonymization NOT completed - NOT marking as processed. "
-                    f"Reason: {self.processing_context.get('error_reason', 'Unknown')}"
-                )
+                self.logger.warning(f"Anonymization NOT completed - NOT marking as processed. Reason: {self.processing_context.get('error_reason', 'Unknown')}")
                 # Explicitly mark as NOT processed
                 state.sensitive_meta_processed = False
-            
+
             # Save all state changes
             state.save()
             self.logger.info("Video processing state updated")
-        
+
         # Signal completion
         self._signal_completion()
 
@@ -602,12 +590,12 @@ class VideoImportService():
         video = self._require_current_video()
 
         processed_video_path = None
-        if 'cleaned_video_path' in self.processing_context:
-            processed_video_path = self.processing_context['cleaned_video_path']
+        if "cleaned_video_path" in self.processing_context:
+            processed_video_path = self.processing_context["cleaned_video_path"]
         else:
-            raw_video_path = self.processing_context.get('raw_video_path')
+            raw_video_path = self.processing_context.get("raw_video_path")
             if raw_video_path and Path(raw_video_path).exists():
-                video_filename = self.processing_context.get('video_filename', Path(raw_video_path).name)
+                video_filename = self.processing_context.get("video_filename", Path(raw_video_path).name)
                 processed_filename = f"processed_{video_filename}"
                 processed_video_path = Path(raw_video_path).parent / processed_filename
                 try:
@@ -636,13 +624,13 @@ class VideoImportService():
                     except Exception as exc:
                         self.logger.error("Failed to update processed_file path: %s", exc)
                         video.processed_file.name = f"anonym_videos/{anonym_video_filename}"
-                        video.save(update_fields=['processed_file'])
+                        video.save(update_fields=["processed_file"])
                         self.logger.info(
                             "Updated processed_file path using fallback: %s",
                             f"anonym_videos/{anonym_video_filename}",
                         )
 
-                    self.processing_context['anonymization_completed'] = True
+                    self.processing_context["anonymization_completed"] = True
                 else:
                     self.logger.warning("Processed video file not found after move: %s", anonym_target_path)
             except Exception as exc:
@@ -652,13 +640,14 @@ class VideoImportService():
 
         try:
             from endoreg_db.utils.paths import RAW_FRAME_DIR
+
             shutil.rmtree(RAW_FRAME_DIR, ignore_errors=True)
             self.logger.debug("Cleaned up temporary frames directory: %s", RAW_FRAME_DIR)
         except Exception as exc:
             self.logger.warning("Failed to remove directory %s: %s", RAW_FRAME_DIR, exc)
 
-        source_path = self.processing_context['file_path']
-        if self.processing_context['delete_source'] and Path(source_path).exists():
+        source_path = self.processing_context["file_path"]
+        if self.processing_context["delete_source"] and Path(source_path).exists():
             try:
                 os.remove(source_path)
                 self.logger.info("Removed remaining source file: %s", source_path)
@@ -669,25 +658,25 @@ class VideoImportService():
             self.logger.warning("No processed_file found after cleanup - video will be unprocessed")
             try:
                 video.anonymize(delete_original_raw=self.delete_source)
-                video.save(update_fields=['processed_file'])
+                video.save(update_fields=["processed_file"])
                 self.logger.info("Late-stage anonymization succeeded")
             except Exception as e:
                 self.logger.error("Late-stage anonymization failed: %s", e)
-                self.processing_context['anonymization_completed'] = False
+                self.processing_context["anonymization_completed"] = False
 
         self.logger.info("Cleanup and archiving completed")
 
-        self.processed_files.add(str(self.processing_context['file_path']))
+        self.processed_files.add(str(self.processing_context["file_path"]))
 
         with transaction.atomic():
             video.refresh_from_db()
-            if hasattr(video, 'state') and self.processing_context.get('anonymization_completed'):
+            if hasattr(video, "state") and self.processing_context.get("anonymization_completed"):
                 video.state.mark_sensitive_meta_processed(save=True)
 
         self.logger.info("Import and anonymization completed for VideoFile UUID: %s", video.uuid)
         self.logger.info("Raw video stored in: /data/videos")
         self.logger.info("Processed video stored in: /data/anonym_videos")
-    
+
     def _create_sensitive_file(
         self,
         video_instance: VideoFile | None = None,
@@ -750,7 +739,7 @@ class VideoImportService():
         self.logger.info("Created sensitive file for %s at %s", video.uuid, target_file_path)
         return target_file_path
 
-    def _get_processor_roi_info(self) -> Tuple[Optional[List[List[Dict[str, Any]]]], Optional[Dict[str, Any]]]:
+    def _get_processor_roi_info(self) -> Tuple[Optional[Any], Optional[Dict[str, Any]]]:
         """Get processor ROI information for masking."""
         endoscope_data_roi_nested = None
         endoscope_image_roi = None
@@ -824,75 +813,67 @@ class VideoImportService():
                 except Exception as exc:
                     self.logger.error("Failed to update SensitiveMeta for video %s: %s", video.uuid, exc)
 
-
-
     def _ensure_frame_cleaning_available(self):
         """
         Ensure frame cleaning modules are available by adding lx-anonymizer to path.
-        
+
         Returns:
             Tuple of (availability_flag, FrameCleaner_class, ReportReader_class)
         """
         try:
             # Check if we can find the lx-anonymizer directory
             from importlib import resources
+
             lx_anonymizer_path = resources.files("lx_anonymizer")
 
             # make sure lx_anonymizer_path is a Path object
             lx_anonymizer_path = Path(str(lx_anonymizer_path))
-            
+
             if lx_anonymizer_path.exists():
                 # Add to Python path temporarily
                 if str(lx_anonymizer_path) not in sys.path:
                     sys.path.insert(0, str(lx_anonymizer_path))
-                
+
                 # Try simple import
                 from lx_anonymizer import FrameCleaner, ReportReader
-                
+
                 self.logger.info("Successfully imported lx_anonymizer modules")
-                
+
                 # Remove from path to avoid conflicts
                 if str(lx_anonymizer_path) in sys.path:
                     sys.path.remove(str(lx_anonymizer_path))
-                    
+
                 return True, FrameCleaner, ReportReader
-            
+
             else:
-                self.logger.warning(f"lx-anonymizer path not found: {lx_anonymizer_path}") 
-                
+                self.logger.warning(f"lx-anonymizer path not found: {lx_anonymizer_path}")
+
         except Exception as e:
             self.logger.warning(f"Frame cleaning not available: {e}")
-        
-        return False, None, None
 
-    
+        return False, None, None
 
     def _perform_frame_cleaning(self, FrameCleaner, endoscope_data_roi_nested, endoscope_image_roi):
         """Perform frame cleaning and anonymization."""
         # Instantiate frame cleaner
         frame_cleaner = FrameCleaner()
-        
+
         # Prepare parameters for frame cleaning
-        raw_video_path = self.processing_context.get('raw_video_path')
-        
+        raw_video_path = self.processing_context.get("raw_video_path")
+
         if not raw_video_path or not Path(raw_video_path).exists():
             raise RuntimeError(f"Raw video path not found: {raw_video_path}")
-        
-        # Get processor name safely
-        video = self._require_current_video()
-        video_meta = getattr(video, "video_meta", None)
-        processor = getattr(video_meta, "processor", None) if video_meta else None
-        device_name = processor.name if processor else self.processing_context['processor_name']
-                
+
         # Create temporary output path for cleaned video
-        video_filename = self.processing_context.get('video_filename', Path(raw_video_path).name)
+        video = self._require_current_video()
+        video_filename = self.processing_context.get("video_filename", Path(raw_video_path).name)
         cleaned_filename = f"cleaned_{video_filename}"
         cleaned_video_path = Path(raw_video_path).parent / cleaned_filename
-        
-        processor_roi, endoscope_roi = self._get_processor_roi_info(video)
-        
+
+        processor_roi, endoscope_roi = self._get_processor_roi_info()
+
         # Processor roi can be used later to OCR preknown regions.
-        
+
         # Clean video with ROI masking (heavy I/O operation)
         actual_cleaned_path, extracted_metadata = frame_cleaner.clean_video(
             video_path=Path(raw_video_path),
@@ -900,9 +881,9 @@ class VideoImportService():
             endoscope_image_roi=endoscope_image_roi,
             endoscope_data_roi_nested=endoscope_data_roi_nested,
             output_path=cleaned_video_path,
-            technique="mask_overlay"
+            technique="mask_overlay",
         )
-        
+
         # Optional: enrich metadata using TrOCR+LLM on one random extracted frame
         try:
             # Prefer frames belonging to this video (UUID in path), else pick any frame
@@ -916,9 +897,7 @@ class VideoImportService():
                     llm_metadata = frame_cleaner.extract_metadata(ocr_text)
                     if llm_metadata:
                         # Merge with already extracted frame-level metadata
-                        extracted_metadata = frame_cleaner.frame_metadata_extractor.merge_metadata(
-                            extracted_metadata or {}, llm_metadata
-                        )
+                        extracted_metadata = frame_cleaner.frame_metadata_extractor.merge_metadata(extracted_metadata or {}, llm_metadata)
                         self.logger.info("LLM metadata extraction (random frame) successful")
                     else:
                         self.logger.info("LLM metadata extraction (random frame) found no data")
@@ -926,15 +905,15 @@ class VideoImportService():
                     self.logger.info("No text extracted by TrOCR on random frame")
         except Exception as e:
             self.logger.error(f"LLM metadata enrichment step failed: {e}")
-        
+
         # Store cleaned video path for later use in _cleanup_and_archive
-        self.processing_context['cleaned_video_path'] = actual_cleaned_path
-        self.processing_context['extracted_metadata'] = extracted_metadata
-        
+        self.processing_context["cleaned_video_path"] = actual_cleaned_path
+        self.processing_context["extracted_metadata"] = extracted_metadata
+
         # Update sensitive metadata with extracted information
         self._update_sensitive_metadata(extracted_metadata)
         self.logger.info(f"Extracted metadata from frame cleaning: {extracted_metadata}")
-        
+
         self.logger.info(f"Frame cleaning with ROI masking completed: {actual_cleaned_path}")
         self.logger.info("Cleaned video will be moved to anonym_videos during cleanup")
 
@@ -952,13 +931,13 @@ class VideoImportService():
 
         sm = sensitive_meta
         updated_fields = []
-        
+
         try:
             sm.update_from_dict(extracted_metadata)
             updated_fields = list(extracted_metadata.keys())
         except KeyError as e:
             self.logger.warning(f"Failed to update SensitiveMeta field {e}")
-            
+
         if updated_fields:
             sm.save(update_fields=updated_fields)
             self.logger.info("Updated SensitiveMeta fields for video %s: %s", video.uuid, updated_fields)
@@ -982,22 +961,18 @@ class VideoImportService():
                 except (ValueError, OSError):
                     raw_exists = False
 
-            video_processing_complete = (
-                video.sensitive_meta is not None and
-                video.video_meta is not None and
-                raw_exists
-            )
+            video_processing_complete = video.sensitive_meta is not None and video.video_meta is not None and raw_exists
 
             if video_processing_complete:
                 self.logger.info("Video %s processing completed successfully - ready for validation", video.uuid)
 
                 # Update completion flags if they exist
                 completion_fields = []
-                for field_name in ['import_completed', 'processing_complete', 'ready_for_validation']:
+                for field_name in ["import_completed", "processing_complete", "ready_for_validation"]:
                     if hasattr(video, field_name):
                         setattr(video, field_name, True)
                         completion_fields.append(field_name)
-                
+
                 if completion_fields:
                     video.save(update_fields=completion_fields)
                     self.logger.info("Updated completion flags: %s", completion_fields)
@@ -1006,15 +981,15 @@ class VideoImportService():
                     "Video %s processing incomplete - missing required components",
                     video.uuid,
                 )
-                
+
         except Exception as e:
             self.logger.warning(f"Failed to signal completion status: {e}")
 
     def _cleanup_on_error(self):
         """Cleanup processing context on error."""
-        if self.current_video and hasattr(self.current_video, 'state'):
+        if self.current_video and hasattr(self.current_video, "state"):
             try:
-                if self.processing_context.get('processing_started'):
+                if self.processing_context.get("processing_started"):
                     self.current_video.state.frames_extracted = False
                     self.current_video.state.frames_initialized = False
                     self.current_video.state.video_meta_extracted = False
@@ -1026,31 +1001,28 @@ class VideoImportService():
     def _cleanup_processing_context(self):
         """
         Cleanup processing context and release file lock.
-        
+
         This method is always called in the finally block of import_and_anonymize()
         to ensure the file lock is released even if processing fails.
         """
         try:
             # Release file lock if it was acquired
-            lock_context = self.processing_context.get('_lock_context')
+            lock_context = self.processing_context.get("_lock_context")
             if lock_context is not None:
                 try:
                     lock_context.__exit__(None, None, None)
                     self.logger.info("Released file lock")
                 except Exception as e:
                     self.logger.warning(f"Error releasing file lock: {e}")
-            
+
             # Remove file from processed set if processing failed
-            file_path = self.processing_context.get('file_path')
-            if file_path and not self.processing_context.get('anonymization_completed'):
+            file_path = self.processing_context.get("file_path")
+            if file_path and not self.processing_context.get("anonymization_completed"):
                 file_path_str = str(file_path)
                 if file_path_str in self.processed_files:
                     self.processed_files.remove(file_path_str)
                     self.logger.info(f"Removed {file_path_str} from processed files (failed processing)")
-            
-                 
-            
-            
+
         except Exception as e:
             self.logger.warning(f"Error during context cleanup: {e}")
         finally:
@@ -1058,6 +1030,7 @@ class VideoImportService():
             self.current_video = None
             self.processing_context = {}
 
+
 # Convenience function for callers/tests that expect a module-level import_and_anonymize
 def import_and_anonymize(
     file_path,
@@ -1076,4 +1049,4 @@ def import_and_anonymize(
         processor_name=processor_name,
         save_video=save_video,
         delete_source=delete_source,
-    )
+    )

{endoreg_db-0.8.2.7.dist-info → endoreg_db-0.8.2.8.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: endoreg-db
-Version: 0.8.2.7
+Version: 0.8.2.8
 Summary: EndoReg Db Django App
 Project-URL: Homepage, https://info.coloreg.de
 Project-URL: Repository, https://github.com/wg-lux/endoreg-db

{endoreg_db-0.8.2.7.dist-info → endoreg_db-0.8.2.8.dist-info}/RECORD

@@ -600,7 +600,7 @@ endoreg_db/services/pseudonym_service.py,sha256=CJhbtRa6K6SPbphgCZgEMi8AFQtB18CU
 endoreg_db/services/requirements_object.py,sha256=290zf8AEbVtCoHhW4Jr7_ud-RvrqYmb1Nz9UBHtTnc0,6164
 endoreg_db/services/segment_sync.py,sha256=YgHvIHkbW4mqCu0ACf3zjRSZnNfxWwt4gh5syUVXuE0,6400
 endoreg_db/services/storage_aware_video_processor.py,sha256=kKFK64vXLeBSVkp1YJonU3gFDTeXZ8C4qb9QZZB99SE,13420
-endoreg_db/services/video_import.py,sha256=X20FQkEO5QGcfuacAz8jX1_LW1GhwbF33JGPpmypEyk,50161
+endoreg_db/services/video_import.py,sha256=NhQ9eJRUUNo9-j6c6ru921xt-oBgGMY0KN2zsRpskGI,48239
 endoreg_db/tasks/upload_tasks.py,sha256=OJq7DhNwcbWdXzHY8jz5c51BCVkPN5gSWOz-6Fx6W5M,7799
 endoreg_db/tasks/video_ingest.py,sha256=kxFuYkHijINV0VabQKCFVpJRv6eCAw07tviONurDgg8,5265
 endoreg_db/tasks/video_processing_tasks.py,sha256=KjcERRJ1TZzmavBpvr6OsvSTUViU0PR1ECWnEdzu2Js,14140
@@ -784,7 +784,7 @@ endoreg_db/views/video/video_meta.py,sha256=C1wBMTtQb_yzEUrhFGAy2UHEWMk_CbU75WXX
 endoreg_db/views/video/video_processing_history.py,sha256=mhFuS8RG5GV8E-lTtuD0qrq-bIpnUFp8vy9aERfC-J8,770
 endoreg_db/views/video/video_remove_frames.py,sha256=2FmvNrSPM0fUXiBxINN6vBUUDCqDlBkNcGR3WsLDgKo,1696
 endoreg_db/views/video/video_stream.py,sha256=kLyuf0ORTmsLeYUQkTQ6iRYqlIQozWhMMR3Lhfe_trk,12148
-endoreg_db-0.8.2.7.dist-info/METADATA,sha256=BCQcbq7ZExYZF5gBfmkDflNtysGjAt36WUMKmqfA-48,14719
-endoreg_db-0.8.2.7.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-endoreg_db-0.8.2.7.dist-info/licenses/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
-endoreg_db-0.8.2.7.dist-info/RECORD,,
+endoreg_db-0.8.2.8.dist-info/METADATA,sha256=uKCJOlsyIekOWKARAh7y3eO9Ch5KBe0RmcgRM38o4UE,14719
+endoreg_db-0.8.2.8.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+endoreg_db-0.8.2.8.dist-info/licenses/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
+endoreg_db-0.8.2.8.dist-info/RECORD,,