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

apply to other ms office zip formats

Browse Source 
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
This commit is contained in:
Michele Dolfi 2025-04-14 07:06:46 +02:00
parent 492680f468
commit a09273ecb8
1 changed files with 7 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
docling/datamodel/document.py
View File

@ -283,14 +283,13 @@ class _DocumentConversionInput(BaseModel):
if mime is None: # must guess from if mime is None: # must guess from
with obj.open("rb") as f: with obj.open("rb") as f:
content = f.read(1024) # Read first 1KB content = f.read(1024) # Read first 1KB
if ( if mime is not None and mime.lower() == "application/zip":
mime is not None if obj.suffixes[-1].lower() == ".xlsx":
and mime.lower() == "application/zip" mime = "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet"
and obj.suffixes[-1].lower() == ".xlsx" elif obj.suffixes[-1].lower() == ".docx":
): mime = "application/vnd.openxmlformats-officedocument.wordprocessingml.document"
mime = ( elif obj.suffixes[-1].lower() == ".pptx":
"application/vnd.openxmlformats-officedocument.spreadsheetml.sheet" mime = "application/vnd.openxmlformats-officedocument.presentationml.presentation"
)
elif isinstance(obj, DocumentStream): elif isinstance(obj, DocumentStream):
content = obj.stream.read(8192) content = obj.stream.read(8192)