apunkt/SurfSense
1
0
Fork 0
mirror of https://github.com/MODSetter/SurfSense.git synced 2026-04-25 16:56:22 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix: update file skipping logic for failed documents in Google Drive indexer

Browse source 
- Modified the `_should_skip_file` function to skip previously failed documents during processing, improving error handling.
- Updated the corresponding test to reflect the new behavior, ensuring that failed documents are correctly identified and skipped during automatic sync.
This commit is contained in:
Anish Sarkar 2026-03-27 20:01:08 +05:30
parent 3ce831d01d
commit 4e0749f907
2 changed files with 6 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

9
surfsense_backend/tests/integration/indexing_pipeline/test_drive_pipeline.py
View file

@ -110,10 +110,10 @@ async def test_drive_legacy_doc_migrated(
assert row.unique_identifier_hash == native_hash
async def test_should_skip_file_does_not_skip_failed_document(
async def test_should_skip_file_skips_failed_document(
db_session, db_search_space, db_user,
):
"""A FAILED document with unchanged md5 must NOT be skipped — it needs reprocessing."""
"""A FAILED document with unchanged md5 must be skipped — user can manually retry via Quick Index."""
import importlib
import sys
import types
@ -164,6 +164,7 @@ async def test_should_skip_file_does_not_skip_failed_document(
incoming_file = {"id": file_id, "name": "Failed File.pdf", "mimeType": "application/pdf", "md5Checksum": md5}
should_skip, _msg = await _should_skip_file(db_session, incoming_file, space_id)
should_skip, msg = await _should_skip_file(db_session, incoming_file, space_id)
assert not should_skip, "FAILED documents must not be skipped even when content is unchanged"
assert should_skip, "FAILED documents must be skipped during automatic sync"
assert "failed" in msg.lower()