0x2620/python-ox
2
1
Fork 0
Code Issues Pull requests Releases Wiki Activity

Compare commits

base: 0x2620:e9a5bcb8909cce9d1136e00e099e74accd2d1323
Branches Tags
0x2620:master
0x2620:stable
0x2620:3.0
...
compare: 0x2620:99554cb461ba26a57815b2e154bcc0df08abcf3c
Branches Tags
0x2620:master
0x2620:stable
0x2620:3.0

2 commits
e9a5bcb890 ... 99554cb461

Author SHA1 Message Date
j
99554cb461 fix add_link 2024-03-20 12:55:14 +01:00
j
7461719e23 fix links at end of paragraph 2024-03-20 12:50:11 +01:00
1 changed files with 2 additions and 2 deletions
Show stats Expand all files Collapse all files

4
ox/html.py
View file

@ -16,7 +16,7 @@ TRAILING_PUNCTUATION = ['.', ',', ')', '>', '\n', '>', "'", '"']
DOTS = ['·', '*', '\xe2\x80\xa2', '•', '•', '•']
unencoded_ampersands_re = re.compile(r'&(?!(\w+|#\d+);)')
word_split_re = re.compile(r'(\s+)')
word_split_re = re.compile(r'(\s+|<br>)')
punctuation_re = re.compile('^(?P<lead>(?:%s)*)(?P<middle>.*?)(?P<trail>(?:%s)*)$' % (
'|'.join([re.escape(x) for x in LEADING_PUNCTUATION]),
'|'.join([re.escape(x) for x in TRAILING_PUNCTUATION])))
@ -392,8 +392,8 @@ def sanitize_html(html, tags=None, global_attributes=[]):
else:
parts[i] = escape_html(decode_html(part))
html = ''.join(parts)
html = html.replace('\n\n', '<br/><br/>')
html = add_links(html)
html = html.replace('\n\n', '<br><br>')
return sanitize_fragment(html)
def split_tags(string):