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
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
|
"""HTML utilities suitable for global use."""
import re
import string
import urllib
import urlparse
from django.utils.safestring import SafeData, mark_safe
from django.utils.encoding import smart_str, force_unicode
from django.utils.functional import allow_lazy
from django.utils.text import normalize_newlines
# Configuration for urlize() function.
TRAILING_PUNCTUATION = ['.', ',', ':', ';']
WRAPPING_PUNCTUATION = [('(', ')'), ('<', '>'), ('<', '>')]
# List of possible strings used for bullets in bulleted lists.
DOTS = [u'·', u'*', u'\u2022', u'•', u'•', u'•']
unencoded_ampersands_re = re.compile(r'&(?!(\w+|#\d+);)')
unquoted_percents_re = re.compile(r'%(?![0-9A-Fa-f]{2})')
word_split_re = re.compile(r'(\s+)')
simple_url_re = re.compile(r'^https?://\w')
simple_url_2_re = re.compile(r'^www\.|^(?!http)\w[^@]+\.(com|edu|gov|int|mil|net|org)$')
simple_email_re = re.compile(r'^\S+@\S+\.\S+$')
link_target_attribute_re = re.compile(r'(<a [^>]*?)target=[^\s>]+')
html_gunk_re = re.compile(r'(?:<br clear="all">|<i><\/i>|<b><\/b>|<em><\/em>|<strong><\/strong>|<\/?smallcaps>|<\/?uppercase>)', re.IGNORECASE)
hard_coded_bullets_re = re.compile(r'((?:<p>(?:%s).*?[a-zA-Z].*?</p>\s*)+)' % '|'.join([re.escape(x) for x in DOTS]), re.DOTALL)
trailing_empty_content_re = re.compile(r'(?:<p>(?: |\s|<br \/>)*?</p>\s*)+\Z')
del x # Temporary variable
def escape(html):
"""
Returns the given HTML with ampersands, quotes and angle brackets encoded.
"""
return mark_safe(force_unicode(html).replace('&', '&').replace('<', '<').replace('>', '>').replace('"', '"').replace("'", '''))
escape = allow_lazy(escape, unicode)
_base_js_escapes = (
('\\', r'\u005C'),
('\'', r'\u0027'),
('"', r'\u0022'),
('>', r'\u003E'),
('<', r'\u003C'),
('&', r'\u0026'),
('=', r'\u003D'),
('-', r'\u002D'),
(';', r'\u003B'),
(u'\u2028', r'\u2028'),
(u'\u2029', r'\u2029')
)
# Escape every ASCII character with a value less than 32.
_js_escapes = (_base_js_escapes +
tuple([('%c' % z, '\\u%04X' % z) for z in range(32)]))
def escapejs(value):
"""Hex encodes characters for use in JavaScript strings."""
for bad, good in _js_escapes:
value = mark_safe(force_unicode(value).replace(bad, good))
return value
escapejs = allow_lazy(escapejs, unicode)
def conditional_escape(html):
"""
Similar to escape(), except that it doesn't operate on pre-escaped strings.
"""
if isinstance(html, SafeData):
return html
else:
return escape(html)
def linebreaks(value, autoescape=False):
"""Converts newlines into <p> and <br />s."""
value = normalize_newlines(value)
paras = re.split('\n{2,}', value)
if autoescape:
paras = [u'<p>%s</p>' % escape(p).replace('\n', '<br />') for p in paras]
else:
paras = [u'<p>%s</p>' % p.replace('\n', '<br />') for p in paras]
return u'\n\n'.join(paras)
linebreaks = allow_lazy(linebreaks, unicode)
def strip_tags(value):
"""Returns the given HTML with all tags stripped."""
return re.sub(r'<[^>]*?>', '', force_unicode(value))
strip_tags = allow_lazy(strip_tags)
def strip_spaces_between_tags(value):
"""Returns the given HTML with spaces between tags removed."""
return re.sub(r'>\s+<', '><', force_unicode(value))
strip_spaces_between_tags = allow_lazy(strip_spaces_between_tags, unicode)
def strip_entities(value):
"""Returns the given HTML with all entities (&something;) stripped."""
return re.sub(r'&(?:\w+|#\d+);', '', force_unicode(value))
strip_entities = allow_lazy(strip_entities, unicode)
def fix_ampersands(value):
"""Returns the given HTML with all unencoded ampersands encoded correctly."""
return unencoded_ampersands_re.sub('&', force_unicode(value))
fix_ampersands = allow_lazy(fix_ampersands, unicode)
def smart_urlquote(url):
"Quotes a URL if it isn't already quoted."
# Handle IDN before quoting.
scheme, netloc, path, query, fragment = urlparse.urlsplit(url)
try:
netloc = netloc.encode('idna') # IDN -> ACE
except UnicodeError: # invalid domain part
pass
else:
url = urlparse.urlunsplit((scheme, netloc, path, query, fragment))
# An URL is considered unquoted if it contains no % characters or
# contains a % not followed by two hexadecimal digits. See #9655.
if '%' not in url or unquoted_percents_re.search(url):
# See http://bugs.python.org/issue2637
url = urllib.quote(smart_str(url), safe='!*\'();:@&=+$,/?#[]~')
return force_unicode(url)
def urlize(text, trim_url_limit=None, nofollow=False, autoescape=False):
"""
Converts any URLs in text into clickable links.
Works on http://, https://, www. links, and also on links ending in one of
the original seven gTLDs (.com, .edu, .gov, .int, .mil, .net, and .org).
Links can have trailing punctuation (periods, commas, close-parens) and
leading punctuation (opening parens) and it'll still do the right thing.
If trim_url_limit is not None, the URLs in link text longer than this limit
will truncated to trim_url_limit-3 characters and appended with an elipsis.
If nofollow is True, the URLs in link text will get a rel="nofollow"
attribute.
If autoescape is True, the link text and URLs will get autoescaped.
"""
trim_url = lambda x, limit=trim_url_limit: limit is not None and (len(x) > limit and ('%s...' % x[:max(0, limit - 3)])) or x
safe_input = isinstance(text, SafeData)
words = word_split_re.split(force_unicode(text))
for i, word in enumerate(words):
match = None
if '.' in word or '@' in word or ':' in word:
# Deal with punctuation.
lead, middle, trail = '', word, ''
for punctuation in TRAILING_PUNCTUATION:
if middle.endswith(punctuation):
middle = middle[:-len(punctuation)]
trail = punctuation + trail
for opening, closing in WRAPPING_PUNCTUATION:
if middle.startswith(opening):
middle = middle[len(opening):]
lead = lead + opening
# Keep parentheses at the end only if they're balanced.
if (middle.endswith(closing)
and middle.count(closing) == middle.count(opening) + 1):
middle = middle[:-len(closing)]
trail = closing + trail
# Make URL we want to point to.
url = None
nofollow_attr = ' rel="nofollow"' if nofollow else ''
if simple_url_re.match(middle):
url = smart_urlquote(middle)
elif simple_url_2_re.match(middle):
url = smart_urlquote('http://%s' % middle)
elif not ':' in middle and simple_email_re.match(middle):
local, domain = middle.rsplit('@', 1)
try:
domain = domain.encode('idna')
except UnicodeError:
continue
url = 'mailto:%s@%s' % (local, domain)
nofollow_attr = ''
# Make link.
if url:
trimmed = trim_url(middle)
if autoescape and not safe_input:
lead, trail = escape(lead), escape(trail)
url, trimmed = escape(url), escape(trimmed)
middle = '<a href="%s"%s>%s</a>' % (url, nofollow_attr, trimmed)
words[i] = mark_safe('%s%s%s' % (lead, middle, trail))
else:
if safe_input:
words[i] = mark_safe(word)
elif autoescape:
words[i] = escape(word)
elif safe_input:
words[i] = mark_safe(word)
elif autoescape:
words[i] = escape(word)
return u''.join(words)
urlize = allow_lazy(urlize, unicode)
def clean_html(text):
"""
Clean the given HTML. Specifically, do the following:
* Convert <b> and <i> to <strong> and <em>.
* Encode all ampersands correctly.
* Remove all "target" attributes from <a> tags.
* Remove extraneous HTML, such as presentational tags that open and
immediately close and <br clear="all">.
* Convert hard-coded bullets into HTML unordered lists.
* Remove stuff like "<p> </p>", but only if it's at the
bottom of the text.
"""
from django.utils.text import normalize_newlines
text = normalize_newlines(force_unicode(text))
text = re.sub(r'<(/?)\s*b\s*>', '<\\1strong>', text)
text = re.sub(r'<(/?)\s*i\s*>', '<\\1em>', text)
text = fix_ampersands(text)
# Remove all target="" attributes from <a> tags.
text = link_target_attribute_re.sub('\\1', text)
# Trim stupid HTML such as <br clear="all">.
text = html_gunk_re.sub('', text)
# Convert hard-coded bullets into HTML unordered lists.
def replace_p_tags(match):
s = match.group().replace(u'</p>', u'</li>')
for d in DOTS:
s = s.replace(u'<p>%s' % d, u'<li>')
return u'<ul>\n%s\n</ul>' % s
text = hard_coded_bullets_re.sub(replace_p_tags, text)
# Remove stuff like "<p> </p>", but only if it's at the bottom
# of the text.
text = trailing_empty_content_re.sub(u'', text)
return text
clean_html = allow_lazy(clean_html, unicode)
|
