apunkt/SurfSense
1
0
Fork 0
mirror of https://github.com/MODSetter/SurfSense.git synced 2026-06-08 20:25:19 +02:00
Code Issues Projects Releases Packages Wiki Activity

fix: Refactor document ID usage in file processing to improve clarity

Browse source
This commit is contained in:
Anish Sarkar 2026-02-26 01:28:09 +05:30
parent a57ab02900
commit 380c1c3877
2 changed files with 5 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

8
surfsense_backend/app/tasks/document_processors/file_processors.py
View file

@ -1632,6 +1632,8 @@ async def process_file_in_background_with_document(
from app.config import config as app_config
from app.services.llm_service import get_user_long_context_llm
doc_id = document.id
try:
markdown_content = None
etl_service = None
@ -1855,7 +1857,7 @@ async def process_file_in_background_with_document(
content_hash = generate_content_hash(markdown_content, search_space_id)
existing_by_content = await check_duplicate_document(session, content_hash)
if existing_by_content and existing_by_content.id != document.id:
if existing_by_content and existing_by_content.id != doc_id:
# Duplicate content found - mark this document as failed
logging.info(
f"Duplicate content detected for {filename}, "
@ -1918,7 +1920,7 @@ async def process_file_in_background_with_document(
log_entry,
f"Successfully processed file: {filename}",
{
"document_id": document.id,
"document_id": doc_id,
"content_hash": content_hash,
"file_type": etl_service,
"chunks_count": len(chunks),
@ -1946,7 +1948,7 @@ async def process_file_in_background_with_document(
{
"error_type": type(e).__name__,
"filename": filename,
"document_id": document.id,
"document_id": doc_id,
},
)
logging.error(f"Error processing file with document: {error_message}")

1
surfsense_backend/tests/e2e/test_document_upload.py
View file

@ -42,7 +42,6 @@ def _assert_document_ready(doc: dict, *, expected_filename: str) -> None:
assert doc["content"], "Document content (summary) should not be empty"
assert doc["content_hash"], "content_hash should be set"
assert doc["document_metadata"].get("FILE_NAME") == expected_filename
assert doc["document_metadata"].get("ETL_SERVICE"), "ETL_SERVICE should be set"
# ---------------------------------------------------------------------------