mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-07-27 04:24:45 +00:00
Code Issues Packages Projects Releases Wiki Activity

bug: auto-recognize .xlsx files

Browse Source 
Signed-off-by: Tim Kellogg <timothy.kellogg@gmail.com>
This commit is contained in:
Tim Kellogg 2025-04-09 06:56:03 -04:00
parent 355d8dc7a6
commit 48d5405db1
1 changed files with 3 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
docling/datamodel/document.py
View File

@ -283,6 +283,9 @@ class _DocumentConversionInput(BaseModel):
if mime is None: # must guess from
with obj.open("rb") as f:
content = f.read(1024) # Read first 1KB
if mime is not None and mime.lower() == "application/zip" and obj.suffixes[-1].lower() == ".xlsx":
mime = "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet"
elif isinstance(obj, DocumentStream):
content = obj.stream.read(8192)