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
|
"HTML utilities suitable for global use."
import re, string
from django.utils.encoding import smart_unicode
# Configuration for urlize() function
LEADING_PUNCTUATION = ['(', '<', '<']
TRAILING_PUNCTUATION = ['.', ',', ')', '>', '\n', '>']
# list of possible strings used for bullets in bulleted lists
DOTS = ['·', '*', '\xe2\x80\xa2', '•', '•', '•']
unencoded_ampersands_re = re.compile(r'&(?!(\w+|#\d+);)')
word_split_re = re.compile(r'(\s+)')
punctuation_re = re.compile('^(?P<lead>(?:%s)*)(?P<middle>.*?)(?P<trail>(?:%s)*)$' % \
('|'.join([re.escape(x) for x in LEADING_PUNCTUATION]),
'|'.join([re.escape(x) for x in TRAILING_PUNCTUATION])))
simple_email_re = re.compile(r'^\S+@[a-zA-Z0-9._-]+\.[a-zA-Z0-9._-]+$')
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 carets encoded"
if not isinstance(html, basestring):
html = str(html)
return html.replace('&', '&').replace('<', '<').replace('>', '>').replace('"', '"').replace("'", ''')
def linebreaks(value):
"Converts newlines into <p> and <br />s"
value = re.sub(r'\r\n|\r|\n', '\n', value) # normalize newlines
paras = re.split('\n{2,}', value)
paras = ['<p>%s</p>' % p.strip().replace('\n', '<br />') for p in paras]
return '\n\n'.join(paras)
def strip_tags(value):
"Returns the given HTML with all tags stripped"
return re.sub(r'<[^>]*?>', '', value)
def strip_spaces_between_tags(value):
"Returns the given HTML with spaces between tags removed"
return re.sub(r'>\s+<', '><', value)
def strip_entities(value):
"Returns the given HTML with all entities (&something;) stripped"
return re.sub(r'&(?:\w+|#\d);', '', value)
def fix_ampersands(value):
"Returns the given HTML with all unencoded ampersands encoded correctly"
return unencoded_ampersands_re.sub('&', value)
def urlize(text, trim_url_limit=None, nofollow=False):
"""
Converts any URLs in text into clickable links. Works on http://, https://
and www. links. 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.
"""
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
words = word_split_re.split(text)
nofollow_attr = nofollow and ' rel="nofollow"' or ''
for i, word in enumerate(words):
match = punctuation_re.match(word)
if match:
lead, middle, trail = match.groups()
if middle.startswith('www.') or ('@' not in middle and not middle.startswith('http://') and \
len(middle) > 0 and middle[0] in string.letters + string.digits and \
(middle.endswith('.org') or middle.endswith('.net') or middle.endswith('.com'))):
middle = '<a href="http://%s"%s>%s</a>' % (middle, nofollow_attr, trim_url(middle))
if middle.startswith('http://') or middle.startswith('https://'):
middle = '<a href="%s"%s>%s</a>' % (middle, nofollow_attr, trim_url(middle))
if '@' in middle and not middle.startswith('www.') and not ':' in middle \
and simple_email_re.match(middle):
middle = '<a href="mailto:%s">%s</a>' % (middle, middle)
if lead + middle + trail != word:
words[i] = lead + middle + trail
return ''.join(words)
def clean_html(text):
"""
Cleans the given HTML. Specifically, it does the following:
* Converts <b> and <i> to <strong> and <em>.
* Encodes all ampersands correctly.
* Removes all "target" attributes from <a> tags.
* Removes extraneous HTML, such as presentational tags that open and
immediately close and <br clear="all">.
* Converts hard-coded bullets into HTML unordered lists.
* Removes 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(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('</p>', '</li>')
for d in DOTS:
s = s.replace('<p>%s' % d, '<li>')
return '<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('', text)
return text
|
