mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-08-02 23:42:22 +00:00
Code Issues Packages Projects Releases Wiki Activity

disabled auto file mime type detection, rely on extension

Browse Source
This commit is contained in:
João 2025-01-09 18:24:26 -03:00
parent 9d9ed0716f
commit 47c21a5edc
1 changed files with 3 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
docling/datamodel/document.py
View File

@ -273,7 +273,8 @@ class _DocumentConversionInput(BaseModel):
formats: list[InputFormat] = []
if isinstance(obj, Path):
mime = filetype.guess_mime(str(obj))
# mime = filetype.guess_mime(str(obj)) # We're having too much conflicts with documents being worngly classified as ZIP
mime = None
if mime is None:
ext = obj.suffix[1:]
mime = _DocumentConversionInput._mime_from_extension(ext)
@ -359,7 +360,7 @@ class _DocumentConversionInput(BaseModel):
mime = FormatToMimeType[InputFormat.PPTX][0]
elif ext in FormatToExtensions[InputFormat.XLSX]:
mime = FormatToMimeType[InputFormat.XLSX][0]
return mime
@staticmethod