gitea-admin/gh-christianlouis-docuelevate
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Fix file_id propagation through task chain

Browse Source 
- Pass file_id as parameter through all task chains
- Update process_document, extract_metadata_with_gpt, embed_metadata_into_pdf, finalize_document_storage, send_to_all_destinations, rotate_pdf_pages, and process_with_azure_document_intelligence
- Remove unreliable LIKE queries, use explicit file_id passing instead

Co-authored-by: christianlouis <361235+christianlouis@users.noreply.github.com>
This commit is contained in:
copilot-swe-agent[bot]
2026-02-06 22:34:01 +00:00
parent 1903dc5bcd
commit 74680c8849
7 changed files with 61 additions and 54 deletions
Download Patch File Download Diff File Expand all files Collapse all files
app/tasks/embed_metadata_into_pdf.py
+11 -10
View File
@@ -46,7 +46,7 @@ def persist_metadata(metadata, final_pdf_path):
return json_path
@celery.task(base=BaseTaskWithRetry, bind=True)
def embed_metadata_into_pdf(self, local_file_path: str, extracted_text: str, metadata: dict):
def embed_metadata_into_pdf(self, local_file_path: str, extracted_text: str, metadata: dict, file_id: int = None):
"""
Embeds extracted metadata into the PDF's standard metadata fields.
The mapping is as follows:
@@ -62,11 +62,14 @@ def embed_metadata_into_pdf(self, local_file_path: str, extracted_text: str, met
"""
task_id = self.request.id
logger.info(f"[{task_id}] Starting metadata embedding for: {local_file_path}")
log_task_progress(task_id, "embed_metadata_into_pdf", "in_progress", f"Embedding metadata into {os.path.basename(local_file_path)}")
log_task_progress(task_id, "embed_metadata_into_pdf", "in_progress", f"Embedding metadata into {os.path.basename(local_file_path)}", file_id=file_id)
# Get file_id from database
file_id = None
# Check for file existence; if not found, try the known shared tmp directory.
# Get file_id from database if not provided
if file_id is None:
with SessionLocal() as db:
file_record = db.query(FileRecord).filter_by(local_filename=local_file_path).first()
if file_record:
file_id = file_record.id
if not os.path.exists(local_file_path):
alt_path = os.path.join(settings.workdir, "tmp", os.path.basename(local_file_path))
if os.path.exists(alt_path):
@@ -76,10 +79,8 @@ def embed_metadata_into_pdf(self, local_file_path: str, extracted_text: str, met
log_task_progress(task_id, "embed_metadata_into_pdf", "failure", "File not found")
return {"error": "File not found"}
with SessionLocal() as db:
file_record = db.query(FileRecord).filter_by(local_filename=local_file_path).first()
if file_record:
file_id = file_record.id
# Check for file existence; if not found, try the known shared tmp directory.
# Work on a safe copy in a secure temporary directory
original_file = local_file_path
@@ -149,7 +150,7 @@ def embed_metadata_into_pdf(self, local_file_path: str, extracted_text: str, met
# Trigger the next step: final storage.
logger.info(f"[{task_id}] Queueing final storage task")
log_task_progress(task_id, "embed_metadata_into_pdf", "success", "Metadata embedded, queuing finalization", file_id=file_id)
finalize_document_storage.delay(original_file, final_file_path, metadata)
finalize_document_storage.delay(original_file, final_file_path, metadata, file_id)
# After triggering final storage, delete the original file if it is in workdir/tmp.
workdir_tmp = os.path.join(settings.workdir, "tmp")