highperfocused/danswer
1
0
Fork 0
mirror of https://github.com/danswer-ai/danswer.git synced 2025-09-19 20:24:32 +02:00
Code Issues Packages Projects Releases Wiki Activity

Add support for google slides (#2083)

Browse Source 
* add support for google slides

* remove log + account for dead code

* squash
This commit is contained in:
pablodanswer
2024-08-09 10:12:51 -07:00
committed by GitHub
parent b230082891
commit 7bfa99766d
1 changed files with 16 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files

30
backend/danswer/connectors/google_drive/connector.py
View File

@@ -306,24 +306,29 @@ def get_all_files_batched(
def extract_text(file: dict[str, str], service: discovery.Resource) -> str:
mime_type = file["mimeType"]
if mime_type not in set(item.value for item in GDriveMimeType):
# Unsupported file types can still have a title, finding this way is still useful
return UNSUPPORTED_FILE_TYPE_CONTENT
if mime_type == GDriveMimeType.DOC.value:
return (
if mime_type in [
GDriveMimeType.DOC.value,
GDriveMimeType.PPT.value,
GDriveMimeType.SPREADSHEET.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"
response = (
service.files()
.export(fileId=file["id"], mimeType="text/plain")
.export(fileId=file["id"], mimeType=export_mime_type)
.execute()
.decode("utf-8")
)
elif mime_type == GDriveMimeType.SPREADSHEET.value:
return (
service.files()
.export(fileId=file["id"], mimeType="text/csv")
.execute()
.decode("utf-8")
)
return response.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))
@@ -333,9 +338,6 @@ def extract_text(file: dict[str, str], service: discovery.Resource) -> str:
elif mime_type == GDriveMimeType.POWERPOINT.value:
response = service.files().get_media(fileId=file["id"]).execute()
return pptx_to_text(file=io.BytesIO(response))
elif mime_type == GDriveMimeType.PPT.value:
response = service.files().get_media(fileId=file["id"]).execute()
return pptx_to_text(file=io.BytesIO(response))
return UNSUPPORTED_FILE_TYPE_CONTENT