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
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
|
# (c) 2005 Ian Bicking and contributors; written for Paste (http://pythonpaste.org)
# Licensed under the MIT license: http://www.opensource.org/licenses/mit-license.php
import cgi
import six
import re
from six.moves import html_entities
from six.moves.urllib.parse import quote, unquote
__all__ = ['html_quote', 'html_unquote', 'url_quote', 'url_unquote',
'strip_html']
default_encoding = 'UTF-8'
def html_quote(v, encoding=None):
r"""
Quote the value (turned to a string) as HTML. This quotes <, >,
and quotes:
>>> html_quote(1)
'1'
>>> html_quote(None)
''
>>> html_quote('<hey!>')
'<hey!>'
>>> html_quote(u'\u1029')
'\xe1\x80\xa9'
"""
encoding = encoding or default_encoding
if v is None:
return ''
elif isinstance(v, str):
return cgi.escape(v, 1)
elif isinstance(v, six.text_type):
return cgi.escape(v.encode(encoding), 1)
else:
return cgi.escape(six.text_type(v).encode(encoding), 1)
_unquote_re = re.compile(r'&([a-zA-Z]+);')
def _entity_subber(match, name2c=html_entities.name2codepoint):
code = name2c.get(match.group(1))
if code:
return unichr(code)
else:
return match.group(0)
def html_unquote(s, encoding=None):
r"""
Decode the value.
>>> html_unquote('<hey you>')
u'<hey\xa0you>'
>>> html_unquote('')
u''
>>> html_unquote('&blahblah;')
u'&blahblah;'
>>> html_unquote('\xe1\x80\xa9')
u'\u1029'
"""
if isinstance(s, str):
if s == '':
# workaround re.sub('', '', u'') returning '' < 2.5.2
# instead of u'' >= 2.5.2
return u''
s = s.decode(encoding or default_encoding)
return _unquote_re.sub(_entity_subber, s)
def strip_html(s):
# should this use html_unquote?
s = re.sub('<.*?>', '', s)
s = html_unquote(s)
return s
def no_quote(s):
"""
Quoting that doesn't do anything
"""
return s
_comment_quote_re = re.compile(r'\-\s*\>')
# Everything but \r, \n, \t:
_bad_chars_re = re.compile('[\x00-\x08\x0b-\x0c\x0e-\x1f]')
def comment_quote(s):
"""
Quote that makes sure text can't escape a comment
"""
comment = str(s)
#comment = _bad_chars_re.sub('', comment)
#print 'in ', repr(str(s))
#print 'out', repr(comment)
comment = _comment_quote_re.sub('->', comment)
return comment
url_quote = quote
url_unquote = unquote
if __name__ == '__main__':
import doctest
doctest.testmod()
|
