mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-07-26 20:14:47 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'main' into fix/fix-issue-with-detecting-docx-files

Browse Source 
# Conflicts:
#	docling/datamodel/document.py
This commit is contained in:
Mohey El-Din Badr 2025-05-07 12:02:47 +03:00
commit ec6bd87ab9
1 changed files with 8 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
docling/datamodel/document.py
View File

@ -303,6 +303,14 @@ class _DocumentConversionInput(BaseModel):
else ""
)
mime = _DocumentConversionInput._mime_from_extension(ext.lower())
if mime is not None and mime.lower() == "application/zip":
objname = obj.name.lower()
if objname.endswith(".xlsx"):
mime = "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet"
elif objname.endswith(".docx"):
mime = "application/vnd.openxmlformats-officedocument.wordprocessingml.document"
elif objname.endswith(".pptx"):
mime = "application/vnd.openxmlformats-officedocument.presentationml.presentation"
mime = mime or _DocumentConversionInput._detect_html_xhtml(content)
mime = mime or _DocumentConversionInput._detect_csv(content)