endoreg-db 0.8.6.1__py3-none-any.whl → 0.8.8.0__py3-none-any.whl

endoreg_db/services/anonymization.py

@@ -1,31 +1,33 @@
 # endoreg_db/services/anonymization.py
+import logging
 from pathlib import Path
+from typing import Optional
+
 from django.db import transaction
-from django.conf import settings
-from endoreg_db.models import VideoFile, RawPdfFile
-from endoreg_db.services.video_import import VideoImportService
+
+from endoreg_db.models import RawPdfFile, VideoFile
 from endoreg_db.services.pdf_import import PdfImportService
+from endoreg_db.services.video_import import VideoImportService
 from endoreg_db.utils.paths import STORAGE_DIR
-import logging
+from endoreg_db.utils.storage import ensure_local_file, file_exists
 
 logger = logging.getLogger(__name__)
 
+
 class AnonymizationService:
     """
     Orchestrates long‑running anonymization tasks so the view only
     does HTTP <-> Service translation.
     """
-    
-    def __init__(self, project_root: Path = None):
+
+    def __init__(self, project_root: Optional[Path] = None):
         """
         Initialize the AnonymizationService with service instances.
-        
+
         Args:
             project_root: Path to the project root. If None, uses settings.BASE_DIR
         """
-        if project_root is None:
-            project_root = STORAGE_DIR
-        
+        self.project_root: Path = project_root or STORAGE_DIR
         self.video_service = VideoImportService()
         self.pdf_service = PdfImportService()
 
@@ -34,7 +36,7 @@ class AnonymizationService:
     def get_status(file_id: int):
         """
         Retrieve the anonymization status and media type for a file by its ID.
-        
+
         Returns:
             dict or None: A dictionary containing the file's media type and anonymization status if found, or None if no matching file exists.
         """
@@ -43,7 +45,7 @@ class AnonymizationService:
             return {
                 "mediaType": "video",
                 "anonymizationStatus": vf.state.anonymization_status if vf.state else "not_started",
-                "fileExists": bool(vf.raw_file and hasattr(vf.raw_file, 'path')),
+                "fileExists": file_exists(vf.raw_file),
                 "uuid": str(vf.uuid) if vf.uuid else None,
             }
 
@@ -52,7 +54,7 @@ class AnonymizationService:
             return {
                 "mediaType": "pdf",
                 "anonymizationStatus": pdf.state.anonymization_status if pdf.state else "not_started",
-                "fileExists": bool(pdf.file and hasattr(pdf.file, 'path')),
+                "fileExists": file_exists(pdf.file),
                 "hash": pdf.pdf_hash,
             }
         return None
@@ -62,10 +64,10 @@ class AnonymizationService:
     def start(self, file_id: int):
         """
         Start anonymization process for a file by its ID.
-        
+
         Args:
             file_id: The ID of the file to anonymize
-            
+
         Returns:
             str or None: Media type if successful, None if file not found
         """
@@ -74,45 +76,42 @@ class AnonymizationService:
         if vf:
             try:
                 logger.info(f"Starting video anonymization for VideoFile ID: {file_id}")
-                
+
                 # Check if already processed
                 if vf.state and vf.state.anonymized:
                     logger.info(f"VideoFile {file_id} already anonymized, skipping")
                     return "video"
-                
+
                 # Get file path
                 file_path = vf.get_raw_file_path()
                 if not file_path or not Path(file_path).exists():
                     logger.error(f"Raw file not found for VideoFile {file_id}: {file_path}")
                     return None
-                
+
                 # Get processor name
                 processor_name = None
                 if vf.video_meta and vf.video_meta.processor:
                     processor_name = vf.video_meta.processor.name
-                elif hasattr(vf, 'processor') and vf.processor:
+                elif hasattr(vf, "processor") and vf.processor:
                     processor_name = vf.processor.name
-                
+
                 # Get center name
                 center_name = vf.center.name if vf.center else "unknown_center"
-                
+
                 # Mark as started
                 if vf.state:
                     vf.state.processing_started = True
                     vf.state.save(update_fields=["processing_started"])
-                
+
                 # Use VideoImportService for anonymization
+                safe_processor_name = processor_name or "unknown_processor"
                 self.video_service.import_and_anonymize(
-                    file_path=file_path,
-                    center_name=center_name,
-                    processor_name=processor_name,
-                    save_video=True,
-                    delete_source=False
+                    file_path=file_path, center_name=center_name, processor_name=safe_processor_name, save_video=True, delete_source=False
                 )
-                
+
                 logger.info(f"Video anonymization completed for VideoFile ID: {file_id}")
                 return "video"
-                
+
             except Exception as e:
                 logger.error(f"Failed to anonymize VideoFile {file_id}: {e}")
                 # Mark as failed if state exists
@@ -126,51 +125,48 @@ class AnonymizationService:
         if pdf:
             try:
                 logger.info(f"Starting PDF processing for RawPdfFile ID: {file_id}")
-                
+
                 # Check if already processed
-                if pdf.state and getattr(pdf.state, 'anonymized', False):
+                if pdf.state and getattr(pdf.state, "anonymized", False):
                     logger.info(f"RawPdfFile {file_id} already processed, skipping")
                     return "pdf"
-                
-                # Get file path
-                if not pdf.file or not hasattr(pdf.file, 'path'):
+
+                file_field = pdf.file
+                if not file_field or not file_field.name:
                     logger.error(f"PDF file not found for RawPdfFile {file_id}")
                     return None
-                
-                file_path = Path(pdf.file.path)
-                if not file_path.exists():
-                    logger.error(f"PDF file does not exist: {file_path}")
+
+                if not file_exists(file_field):
+                    logger.error("PDF file missing from storage for RawPdfFile %s", file_id)
                     return None
-                
+
                 # Get center name
                 center_name = pdf.center.name if pdf.center else "unknown_center"
-                
+
                 # Mark as started
                 if pdf.state:
                     pdf.state.processing_started = True
                     pdf.state.save(update_fields=["processing_started"])
-                elif pdf.sensitive_meta:
+                elif pdf.sensitive_meta and hasattr(pdf.sensitive_meta, "anonymization_started"):
                     pdf.sensitive_meta.anonymization_started = True
                     pdf.sensitive_meta.save(update_fields=["anonymization_started"])
-                
-                
-                # Use PdfImportService for processing
-                # Use PdfImportService for processing
-                self.pdf_service.import_and_anonymize(
-                    file_path=file_path,
-                    center_name=center_name,
-                )
-                
+
+                with ensure_local_file(file_field) as local_path:
+                    self.pdf_service.import_and_anonymize(
+                        file_path=local_path,
+                        center_name=center_name,
+                    )
+
                 logger.info(f"PDF processing completed for RawPdfFile ID: {file_id}")
                 return "pdf"
-                
+
             except Exception as e:
                 logger.error(f"Failed to process RawPdfFile {file_id}: {e}")
                 # Mark as failed if state exists
-                if pdf.state:
+                if pdf.state and hasattr(pdf.state, "processing_failed"):
                     pdf.state.processing_failed = True
                     pdf.state.save(update_fields=["processing_failed"])
-                elif pdf.sensitive_meta:
+                elif pdf.sensitive_meta and hasattr(pdf.sensitive_meta, "processing_failed"):
                     pdf.sensitive_meta.processing_failed = True
                     pdf.sensitive_meta.save(update_fields=["processing_failed"])
                 raise
@@ -183,41 +179,47 @@ class AnonymizationService:
     def validate(file_id: int):
         vf = VideoFile.objects.select_related("state").filter(pk=file_id).first()
         if vf:
-            vf.state.mark_anonymization_validated()
+            state = vf.state or vf.get_or_create_state()
+            if hasattr(state, "mark_anonymization_validated"):
+                state.mark_anonymization_validated()
             return "video"
 
         pdf = RawPdfFile.objects.select_related("state").filter(pk=file_id).first()
         if pdf:
-            pdf.state.mark_anonymization_validated()
+            state = pdf.state or pdf.get_or_create_state()
+            if hasattr(state, "mark_anonymization_validated"):
+                state.mark_anonymization_validated()
             return "pdf"
 
         return None
-    
+
+    @staticmethod
     def list_items():
         video_files = VideoFile.objects.select_related("state").all()
         pdf_files = RawPdfFile.objects.select_related("state").all()  # was sensitive_meta
 
         data = []
         for vf in video_files:
-            data.append({
-                "id": vf.id,
-                "mediaType": "video",
-                "anonymizationStatus": vf.state.anonymization_status if vf.state else "not_started",
-                "createdAt": vf.date_created,
-                "updatedAt": vf.date_modified,
-            })
-            
-            
+            data.append(
+                {
+                    "id": vf.pk,
+                    "mediaType": "video",
+                    "anonymizationStatus": vf.state.anonymization_status if vf.state else "not_started",
+                    "createdAt": vf.date_created,
+                    "updatedAt": vf.date_modified,
+                }
+            )
 
         for pdf in pdf_files:
-            data.append({
-                "id": pdf.id,
-                "mediaType": "pdf",
-                "anonymizationStatus": pdf.state.anonymization_status if pdf.state else "not_started",
-                "createdAt": pdf.date_created,
-                "updatedAt": pdf.date_modified,
-            })
+            data.append(
+                {
+                    "id": pdf.pk,
+                    "mediaType": "pdf",
+                    "anonymizationStatus": pdf.state.anonymization_status if pdf.state else "not_started",
+                    "createdAt": pdf.date_created,
+                    "updatedAt": pdf.date_modified,
+                }
+            )
         return data
 
-
         return data

endoreg_db/services/lookup_service.py

@@ -24,9 +24,10 @@ Architecture:
 # services/lookup_service.py
 from __future__ import annotations
 
-from typing import Any, Dict, List
+import logging
+from typing import Any, Dict, List, Optional
 
-from django.db.models import Prefetch
+from django.db.models import Prefetch, QuerySet
 
 from endoreg_db.models.medical.examination import ExaminationRequirementSet
 from endoreg_db.models.medical.patient.patient_examination import PatientExamination
@@ -88,31 +89,43 @@ def load_patient_exam_for_eval(pk: int) -> PatientExamination:
     )
 
 
-def requirement_sets_for_patient_exam(pe: PatientExamination) -> List[RequirementSet]:
+def requirement_sets_for_patient_exam(
+    pe: PatientExamination, user_tags: Optional[List[str]] = None
+) -> QuerySet:
     """
-    Get all requirement sets applicable to a patient examination.
-
-    This function resolves requirement sets through the examination's requirement set links.
-    It follows the relationship: PatientExamination → Examination → ExaminationRequirementSet → RequirementSet
+    Retrieve all RequirementSets linked to a PatientExamination's examination.
 
     Args:
-        pe: PatientExamination instance to get requirement sets for
+        pe: PatientExamination instance
+        user_tags: Optional list of tag names to filter requirement sets
 
     Returns:
-        List of RequirementSet instances applicable to the examination, with related data prefetched
+        QuerySet of RequirementSet instances
     """
-    exam = pe.examination
-    if not exam:
-        return []
-    return list(
-        RequirementSet.objects.filter(reqset_exam_links__examinations=exam)
-        .select_related("requirement_set_type")
-        .prefetch_related("requirements")
-        .distinct()
-    )
+    if not pe or not pe.examination:
+        from endoreg_db.models import RequirementSet
+
+        return RequirementSet.objects.none()
+
+    # Start with examination-linked requirement sets
+    req_sets = pe.examination.exam_reqset_links.select_related(
+        "requirement_set"
+    ).values_list("requirement_set", flat=True)
+
+    from endoreg_db.models import RequirementSet
 
+    qs = RequirementSet.objects.filter(pk__in=req_sets)
 
-def build_initial_lookup(pe: PatientExamination) -> Dict[str, Any]:
+    # Apply tag filtering if provided
+    if user_tags:
+        qs = qs.filter(tags__name__in=user_tags).distinct()
+
+    return qs
+
+
+def build_initial_lookup(
+    pe: PatientExamination, user_tags: Optional[List[str]] = None
+) -> Dict[str, Any]:
     """
     Build the initial lookup dictionary for a patient examination.
 
@@ -153,7 +166,7 @@ def build_initial_lookup(pe: PatientExamination) -> Dict[str, Any]:
     required_findings: List[int] = []  # fill by scanning requirements below
 
     # Requirement sets: ids + meta
-    rs_objs = requirement_sets_for_patient_exam(pe)
+    rs_objs = requirement_sets_for_patient_exam(pe, user_tags=user_tags)
     requirement_sets = [
         {
             "id": rs.id,
@@ -202,7 +215,9 @@ def build_initial_lookup(pe: PatientExamination) -> Dict[str, Any]:
     }
 
 
-def create_lookup_token_for_pe(pe_id: int) -> str:
+def create_lookup_token_for_pe(
+    pe_id: int, user_tags: Optional[List[str]] = None
+) -> str:
     """
     Create a lookup token for a patient examination.
 
@@ -220,7 +235,7 @@ def create_lookup_token_for_pe(pe_id: int) -> str:
         Exception: For any other errors during initialization
     """
     pe = load_patient_exam_for_eval(pe_id)
-    token = LookupStore().init(build_initial_lookup(pe))
+    token = LookupStore().init(build_initial_lookup(pe, user_tags=user_tags))
     return token
 
 
@@ -255,8 +270,6 @@ def recompute_lookup(token: str) -> Dict[str, Any]:
     Raises:
         ValueError: If lookup data is invalid or patient examination not found
     """
-    import logging
-
     logger = logging.getLogger(__name__)
 
     store = LookupStore(token=token)