1
0
mirror of https://github.com/haiwen/seahub.git synced 2025-04-27 11:01:14 +00:00
seahub/seahub/base/utils.py
2013-05-02 19:27:17 +08:00

87 lines
3.8 KiB
Python

import re
import string
from django.utils.safestring import SafeData, mark_safe
from django.utils.encoding import force_unicode
from django.utils.functional import allow_lazy
from django.utils.http import urlquote
# Configuration for urlize() function.
LEADING_PUNCTUATION = ['(', '<', '&lt;']
TRAILING_PUNCTUATION = ['.', ',', ')', '>', '\n', '&gt;']
word_split_re = re.compile(r'(\s+)')
punctuation_re = re.compile('^(?P<lead>(?:%s)*)(?P<middle>.*?)(?P<trail>(?:%s)*)$' % \
('|'.join([re.escape(x) for x in LEADING_PUNCTUATION]),
'|'.join([re.escape(x) for x in TRAILING_PUNCTUATION])))
simple_email_re = re.compile(r'^\S+@[a-zA-Z0-9._-]+\.[a-zA-Z0-9._-]+$')
def escape(html):
"""
Returns the given HTML with ampersands, quotes and angle brackets encoded.
"""
return mark_safe(force_unicode(html).replace('&', '&amp;').replace('<', '&lt;').replace('>', '&gt;').replace('"', '&quot;').replace("'", '&#39;'))
escape = allow_lazy(escape, unicode)
## modification of django's urlize, add '%' to safe:
## urlquote('http://%s' % middle, safe='/&=:;#?+*%')
## the origin is
## urlquote('http://%s' % middle, safe='/&=:;#?+*')
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 links ending in .org, .net or
.com. 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))
nofollow_attr = nofollow and ' rel="nofollow"' or ''
for i, word in enumerate(words):
match = None
if '.' in word or '@' in word or ':' in word:
match = punctuation_re.match(word)
if match:
lead, middle, trail = match.groups()
# Make URL we want to point to.
url = None
if middle.startswith('http://') or middle.startswith('https://'):
url = urlquote(middle, safe='/&=:;#?+*%')
elif middle.startswith('www.') or ('@' not in middle and \
middle and middle[0] in string.ascii_letters + string.digits and \
(middle.endswith('.org') or middle.endswith('.net') or middle.endswith('.com'))):
url = urlquote('http://%s' % middle, safe='/&=:;#?+*%')
# elif '@' in middle and not ':' in middle and simple_email_re.match(middle):
# url = 'mailto:%s' % middle
# 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 target="_blank" 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)