mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-08-02 15:32:30 +00:00
Code Issues Packages Projects Releases Wiki Activity

add more file types when infering the mime type from extesion

Browse Source
This commit is contained in:
João 2025-01-09 17:49:20 -03:00
parent 82441ed6d2
commit 9d9ed0716f
1 changed files with 10 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
docling/datamodel/document.py
View File

@ -350,6 +350,16 @@ class _DocumentConversionInput(BaseModel):
mime = FormatToMimeType[InputFormat.HTML][0] mime = FormatToMimeType[InputFormat.HTML][0]
elif ext in FormatToExtensions[InputFormat.MD]: elif ext in FormatToExtensions[InputFormat.MD]:
mime = FormatToMimeType[InputFormat.MD][0] mime = FormatToMimeType[InputFormat.MD][0]
elif ext in FormatToExtensions[InputFormat.PDF]:
mime = FormatToMimeType[InputFormat.PDF][0]
elif ext in FormatToExtensions[InputFormat.DOCX]:
mime = FormatToMimeType[InputFormat.DOCX][0]
elif ext in FormatToExtensions[InputFormat.PPTX]:
mime = FormatToMimeType[InputFormat.PPTX][0]
elif ext in FormatToExtensions[InputFormat.XLSX]:
mime = FormatToMimeType[InputFormat.XLSX][0]
return mime return mime
@staticmethod @staticmethod