apunkt/SurfSense
1
0
Fork 0
mirror of https://github.com/MODSetter/SurfSense.git synced 2026-07-16 23:01:06 +02:00
Code Issues Projects Releases Packages Wiki Activity

refactor: enhance Google Drive indexer to support file extension filtering, improving file handling and error reporting

Browse source
This commit is contained in:
Anish Sarkar 2026-04-06 22:34:49 +05:30
parent 0fb92b7c56
commit f03bf05aaa
3 changed files with 46 additions and 15 deletions
Download patch file Download diff file Expand all files Collapse all files

7
surfsense_backend/app/tasks/connector_indexers/google_drive_indexer.py
View file

@ -25,7 +25,10 @@ from app.connectors.google_drive import (
get_files_in_folder,
get_start_page_token,
)
from app.connectors.google_drive.file_types import should_skip_file as skip_mime
from app.connectors.google_drive.file_types import (
should_skip_by_extension,
should_skip_file as skip_mime,
)
from app.db import Document, DocumentStatus, DocumentType, SearchSourceConnectorType
from app.indexing_pipeline.connector_document import ConnectorDocument
from app.indexing_pipeline.document_hashing import compute_identifier_hash
@ -78,6 +81,8 @@ async def _should_skip_file(
if skip_mime(mime_type):
return True, "folder/shortcut"
if should_skip_by_extension(file_name):
return True, "unsupported extension"
if not file_id:
return True, "missing file_id"