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

Update document.py

Browse Source 
add docx to the mime types, and for extentions lower the case so they can be compared if they came in Upper case

Signed-off-by: MoheyElDin Badr <56153924+MoheyEl-DinBadr@users.noreply.github.com>
This commit is contained in:
MoheyElDin Badr 2025-05-06 09:40:13 +03:00 committed by MoheyElDin Badr
parent 7c4c356e76
commit 7885c1d751
1 changed files with 3 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
docling/datamodel/document.py
View File

@ -302,7 +302,7 @@ class _DocumentConversionInput(BaseModel):
if ("." in obj.name and not obj.name.startswith(".")) if ("." in obj.name and not obj.name.startswith("."))
else "" else ""
) )
mime = _DocumentConversionInput._mime_from_extension(ext) mime = _DocumentConversionInput._mime_from_extension(ext.lower())
if mime is not None and mime.lower() == "application/zip": if mime is not None and mime.lower() == "application/zip":
objname = obj.name.lower() objname = obj.name.lower()
if objname.endswith(".xlsx"): if objname.endswith(".xlsx"):
@ -376,6 +376,8 @@ class _DocumentConversionInput(BaseModel):
mime = FormatToMimeType[InputFormat.JSON_DOCLING][0] mime = FormatToMimeType[InputFormat.JSON_DOCLING][0]
elif ext in FormatToExtensions[InputFormat.PDF]: elif ext in FormatToExtensions[InputFormat.PDF]:
mime = FormatToMimeType[InputFormat.PDF][0] mime = FormatToMimeType[InputFormat.PDF][0]
elif ext in FormatToExtentions[InputFormat.DOCX]:
mime = FormatToMimeType[InputFormat.DOCX][0]
return mime return mime
@staticmethod @staticmethod