apunkt/SurfSense
1
0
Fork 0
mirror of https://github.com/MODSetter/SurfSense.git synced 2026-05-08 07:12:39 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

refactor: implement file type classification for supported extensions across Dropbox, Google Drive, and OneDrive connectors, enhancing file handling and error management

Browse source
This commit is contained in:
Anish Sarkar 2026-04-06 22:03:47 +05:30
parent 47f4be08d9
commit dc7047f64d
14 changed files with 250 additions and 27 deletions
Download patch file Download diff file Expand all files Collapse all files

9
surfsense_backend/app/connectors/onedrive/file_types.py
View file

@ -1,5 +1,7 @@
"""File type handlers for Microsoft OneDrive."""
from app.etl_pipeline.file_classifier import FileCategory, classify_file
ONEDRIVE_FOLDER_FACET = "folder"
ONENOTE_MIME = "application/msonenote"
@ -39,7 +41,7 @@ def is_folder(item: dict) -> bool:
def should_skip_file(item: dict) -> bool:
"""Skip folders, OneNote files, remote items (shared links), and packages."""
"""Skip folders, OneNote files, remote items (shared links), packages, and unsupported extensions."""
if is_folder(item):
return True
if "remoteItem" in item:
@ -47,4 +49,7 @@ def should_skip_file(item: dict) -> bool:
if "package" in item:
return True
mime = item.get("file", {}).get("mimeType", "")
return mime in SKIP_MIME_TYPES
if mime in SKIP_MIME_TYPES:
return True
name = item.get("name", "")
return classify_file(name) == FileCategory.UNSUPPORTED