refactor: streamline file record creation and duplicate checking in document processing

app/tasks/process_document.py

@@ -46,20 +46,19 @@ def process_document(original_local_file: str):
         mime_type = "application/octet-stream"
 
     # Acquire DB session in the task
-    new_record = None
     with SessionLocal() as db:
+        # Keep all FileRecord operations within this session scope
         task_logger(f"Checking for duplicate files", step_name="check_duplicates", task_id=task_id)
-        existing = db.query(FileRecord).filter_by(filehash=filehash).one_or_none()
-        if existing:
+        existing_record = db.query(FileRecord).filter(FileRecord.filehash == filehash).one_or_none()
+        if existing_record:
             task_logger(f"Duplicate file detected (hash={filehash[:10]}...). Skipping processing.",
-                        step_name="process_document", task_id=task_id, file_id=existing.id, status="success")
+                        step_name="process_document", task_id=task_id, file_id=existing_record.id, status="success")
             return {
                 "status": "duplicate_file",
-                "file_id": existing.id,
+                "file_id": existing_record.id,
                 "detail": "File already processed."
             }
-
-        # Not a duplicate -> insert a new record
+        else:
             task_logger(f"Creating file record for {original_local_file}", step_name="create_file_record", task_id=task_id)
             new_record = FileRecord(
                 filehash=filehash,
@@ -89,6 +88,8 @@ def process_document(original_local_file: str):
             new_record.local_filename = new_local_path
             db.commit()
 
+        # Perform all further interactions with existing_record/new_record here
+
     # 2. Check for embedded text (outside the DB session to avoid long open transactions)
     task_logger(f"Checking for embedded text", step_name="check_embedded_text", task_id=task_id, file_id=new_record.id)
     pdf_doc = fitz.open(new_local_path)