NeoAnd/Docling
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix: UnicodeDecodeError: 'utf-8' codec can't decode byte 0xd0 in position 0: invalid continuation byte (#1665)

Browse Source 
Update document.py

fix: when mime not "application/xml" or "text/plain" raise
UnicodeDecodeError: 'utf-8' codec can't decode byte 0xd0 in position 0: invalid continuation byte

Signed-off-by: DavidLee <yongsheng_li@foxmail.com>
This commit is contained in:
DavidLee 2025-05-27 20:06:05 +08:00 committed by GitHub
parent 2579d89510
commit 51d3450915
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 2 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
docling/datamodel/document.py
View File

@ -334,9 +334,9 @@ class _DocumentConversionInput(BaseModel):
) -> Optional[InputFormat]: ) -> Optional[InputFormat]:
"""Guess the input format of a document by checking part of its content.""" """Guess the input format of a document by checking part of its content."""
input_format: Optional[InputFormat] = None input_format: Optional[InputFormat] = None
content_str = content.decode("utf-8")
if mime == "application/xml": if mime == "application/xml":
content_str = content.decode("utf-8")
match_doctype = re.search(r"<!DOCTYPE [^>]+>", content_str) match_doctype = re.search(r"<!DOCTYPE [^>]+>", content_str)
if match_doctype: if match_doctype:
xml_doctype = match_doctype.group() xml_doctype = match_doctype.group()
@ -358,6 +358,7 @@ class _DocumentConversionInput(BaseModel):
input_format = InputFormat.XML_JATS input_format = InputFormat.XML_JATS
elif mime == "text/plain": elif mime == "text/plain":
content_str = content.decode("utf-8")
if InputFormat.XML_USPTO in formats and content_str.startswith("PATN\r\n"): if InputFormat.XML_USPTO in formats and content_str.startswith("PATN\r\n"):
input_format = InputFormat.XML_USPTO input_format = InputFormat.XML_USPTO