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

chore: typo fix

Browse Source 
Signed-off-by: nkh0472 <67589323+nkh0472@users.noreply.github.com>
This commit is contained in:
nkh0472 2025-04-26 17:07:33 +08:00 committed by GitHub
parent 8302a6a2d7
commit 00fc7e5e23
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
docling/backend/xml/uspto_backend.py
View File

@ -1,6 +1,6 @@
"""Backend to parse patents from the United States Patent Office (USPTO). """Backend to parse patents from the United States Patent Office (USPTO).
The parsers included in this module can handle patent grants pubished since 1976 and The parsers included in this module can handle patent grants published since 1976 and
patent applications since 2001. patent applications since 2001.
The original files can be found in https://bulkdata.uspto.gov. The original files can be found in https://bulkdata.uspto.gov.
""" """
@ -440,7 +440,7 @@ class PatentUsptoIce(PatentUspto):
) )
elif name == self.Element.PARAGRAPH.value and text: elif name == self.Element.PARAGRAPH.value and text:
# remmove blank spaces added in paragraphs # remove blank spaces added in paragraphs
text = re.sub("\\s+", " ", text) text = re.sub("\\s+", " ", text)
if self.Element.ABSTRACT.value in self.property: if self.Element.ABSTRACT.value in self.property:
self.abstract = ( self.abstract = (
@ -1697,7 +1697,7 @@ class XmlTable:
class HtmlEntity: class HtmlEntity:
"""Provide utility functions to get the HTML entities of styled characters. """Provide utility functions to get the HTML entities of styled characters.
This class has been developped from: This class has been developed from:
https://unicode-table.com/en/html-entities/ https://unicode-table.com/en/html-entities/
https://www.w3.org/TR/WD-math-970515/table03.html https://www.w3.org/TR/WD-math-970515/table03.html
""" """
@ -1896,7 +1896,7 @@ class HtmlEntity:
"""Get an HTML entity of a greek letter in ISO 8879. """Get an HTML entity of a greek letter in ISO 8879.
Args: Args:
The text to transform, as an ISO 8879 entitiy. The text to transform, as an ISO 8879 entity.
Returns: Returns:
The HTML entity representing a greek letter. If the input text is not The HTML entity representing a greek letter. If the input text is not