apunkt/SurfSense
1
0
Fork 0
mirror of https://github.com/MODSetter/SurfSense.git synced 2026-05-10 16:22:38 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

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

7
surfsense_backend/app/etl_pipeline/etl_pipeline_service.py
View file

@ -1,6 +1,6 @@
from app.config import config as app_config
from app.etl_pipeline.etl_document import EtlRequest, EtlResult
from app.etl_pipeline.exceptions import EtlServiceUnavailableError
from app.etl_pipeline.exceptions import EtlServiceUnavailableError, EtlUnsupportedFileError
from app.etl_pipeline.file_classifier import FileCategory, classify_file
from app.etl_pipeline.parsers.audio import transcribe_audio
from app.etl_pipeline.parsers.direct_convert import convert_file_directly
@ -13,6 +13,11 @@ class EtlPipelineService:
async def extract(self, request: EtlRequest) -> EtlResult:
category = classify_file(request.filename)
if category == FileCategory.UNSUPPORTED:
raise EtlUnsupportedFileError(
f"File type not supported for parsing: {request.filename}"
)
if category == FileCategory.PLAINTEXT:
content = read_plaintext(request.file_path)
return EtlResult(