apunkt/SurfSense
1
0
Fork 0
mirror of https://github.com/MODSetter/SurfSense.git synced 2026-06-02 19:55:18 +02:00
Code Issues Projects Releases Packages Wiki Activity

refactor: unify file skipping logic across Dropbox, Google Drive, and OneDrive connectors by replacing classification checks with a centralized service-based approach, enhancing maintainability and consistency in file handling

Browse source
This commit is contained in:
Anish Sarkar 2026-04-07 02:19:31 +05:30
parent f03bf05aaa
commit e7beeb2a36
13 changed files with 388 additions and 67 deletions
Download patch file Download diff file Expand all files Collapse all files

8
surfsense_backend/app/connectors/google_drive/file_types.py
View file

@ -1,6 +1,6 @@
"""File type handlers for Google Drive."""
from app.etl_pipeline.file_classifier import FileCategory, classify_file
from app.etl_pipeline.file_classifier import should_skip_for_service
GOOGLE_DOC = "application/vnd.google-apps.document"
GOOGLE_SHEET = "application/vnd.google-apps.spreadsheet"
@ -49,8 +49,10 @@ def should_skip_file(mime_type: str) -> bool:
def should_skip_by_extension(filename: str) -> bool:
"""Return True if the file extension is not parseable by any ETL pipeline."""
return classify_file(filename) == FileCategory.UNSUPPORTED
"""Return True if the file extension is not parseable by the configured ETL service."""
from app.config import config as app_config
return should_skip_for_service(filename, app_config.ETL_SERVICE)
def get_export_mime_type(mime_type: str) -> str | None: