highperfocused/danswer
1
0
Fork 0
mirror of https://github.com/danswer-ai/danswer.git synced 2025-04-09 20:39:29 +02:00
Code Issues Packages Projects Releases Wiki Activity

Google Drive Plaintext Types (#2371)

Browse Source
This commit is contained in:
Sebastian Müller 2024-09-10 00:37:47 +02:00 committed by GitHub
parent dbd56f946f
commit a4dcae57cd
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 12 additions and 16 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

28
backend/danswer/connectors/google_drive/connector.py
View File

@ -317,27 +317,23 @@ def extract_text(file: dict[str, str], service: discovery.Resource) -> str:
GDriveMimeType.DOC.value,
GDriveMimeType.PPT.value,
GDriveMimeType.SPREADSHEET.value,
GDriveMimeType.PLAIN_TEXT.value,
GDriveMimeType.MARKDOWN.value,
]:
export_mime_type = "text/plain"
if mime_type == GDriveMimeType.SPREADSHEET.value:
export_mime_type = "text/csv"
elif mime_type == GDriveMimeType.PPT.value:
export_mime_type = "text/plain"
elif mime_type in [
GDriveMimeType.PLAIN_TEXT.value,
GDriveMimeType.MARKDOWN.value,
]:
export_mime_type = mime_type
response = (
export_mime_type = (
"text/plain"
if mime_type != GDriveMimeType.SPREADSHEET.value
else "text/csv"
)
return (
service.files()
.export(fileId=file["id"], mimeType=export_mime_type)
.execute()
.decode("utf-8")
)
return response.decode("utf-8")
elif mime_type in [
GDriveMimeType.PLAIN_TEXT.value,
GDriveMimeType.MARKDOWN.value,
]:
return service.files().get_media(fileId=file["id"]).execute().decode("utf-8")
elif mime_type == GDriveMimeType.WORD_DOC.value:
response = service.files().get_media(fileId=file["id"]).execute()
return docx_to_text(file=io.BytesIO(response))