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

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 GitHub
parent 7c705739f9
commit bcb29caf96
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
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())
mime = mime or _DocumentConversionInput._detect_html_xhtml(content) mime = mime or _DocumentConversionInput._detect_html_xhtml(content)
mime = mime or _DocumentConversionInput._detect_csv(content) mime = mime or _DocumentConversionInput._detect_csv(content)
@ -368,6 +368,8 @@ 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