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

refactor: update filename handling in Google Drive connector to include Google Workspace file extensions, improving content extraction accuracy

Browse source
This commit is contained in:
Anish Sarkar 2026-04-07 05:43:34 +05:30
parent 7f32dd068f
commit 5803fe79da
1 changed files with 4 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

6
surfsense_backend/app/connectors/google_drive/content_extractor.py
View file

@ -100,7 +100,8 @@ async def download_and_extract_content(
if error:
return None, drive_metadata, error
markdown = await _parse_file_to_markdown(temp_file_path, file_name)
etl_filename = file_name + extension if is_google_workspace_file(mime_type) else file_name
markdown = await _parse_file_to_markdown(temp_file_path, etl_filename)
return markdown, drive_metadata, None
except Exception as e:
@ -232,10 +233,11 @@ async def download_and_process_file(
"."
)[-1]
etl_filename = file_name + extension if is_google_workspace_file(mime_type) else file_name
logger.info(f"Processing {file_name} with Surfsense's file processor")
await process_file_in_background(
file_path=temp_file_path,
filename=file_name,
filename=etl_filename,
search_space_id=search_space_id,
user_id=user_id,
session=session,