1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
|
import re
from urllib.parse import quote
from html import _replace_charref
_expand_tab_re = re.compile(r'^( {0,3})\t', flags=re.M)
def expand_leading_tab(text, width=4):
def repl(m):
s = m.group(1)
return s + ' ' * (width - len(s))
return _expand_tab_re.sub(repl, text)
def expand_tab(text, space=' '):
repl = r'\1' + space
return _expand_tab_re.sub(repl, text)
def escape(s, quote=True):
"""Escape characters of ``&<>``. If quote=True, ``"`` will be
converted to ``"e;``."""
s = s.replace("&", "&")
s = s.replace("<", "<")
s = s.replace(">", ">")
if quote:
s = s.replace('"', """)
return s
def escape_url(link):
"""Escape URL for safety."""
safe = (
':/?#@' # gen-delims - '[]' (rfc3986)
'!$&()*+,;=' # sub-delims - "'" (rfc3986)
'%' # leave already-encoded octets alone
)
return escape(quote(unescape(link), safe=safe))
def safe_entity(s):
"""Escape characters for safety."""
return escape(unescape(s))
def unikey(s):
"""Generate a unique key for links and footnotes."""
key = ' '.join(s.split()).strip()
return key.lower().upper()
_charref_re = re.compile(
r'&(#[0-9]{1,7};'
r'|#[xX][0-9a-fA-F]+;'
r'|[^\t\n\f <&#;]{1,32};)'
)
def unescape(s):
"""
Copy from `html.unescape`, but `_charref` is different. CommonMark
does not accept entity references without a trailing semicolon
"""
if '&' not in s:
return s
return _charref_re.sub(_replace_charref, s)
_striptags_re = re.compile(r'(<!--.*?-->|<[^>]*>)')
def striptags(s):
return _striptags_re.sub('', s)
_strip_end_re = re.compile(r'\n\s+$')
def strip_end(src):
return _strip_end_re.sub('\n', src)
|
