diff --git a/django/utils/html.py b/django/utils/html.py index 5e39ac9183..d04e75f856 100644 --- a/django/utils/html.py +++ b/django/utils/html.py @@ -11,8 +11,8 @@ from django.utils.functional import allow_lazy from django.utils.text import normalize_newlines # Configuration for urlize() function. -LEADING_PUNCTUATION = ['(', '<', '<'] -TRAILING_PUNCTUATION = ['.', ',', ')', '>', '\n', '>'] +TRAILING_PUNCTUATION = ['.', ',', ':', ';'] +WRAPPING_PUNCTUATION = [('(', ')'), ('<', '>'), ('<', '>')] # List of possible strings used for bullets in bulleted lists. DOTS = [u'·', u'*', u'\u2022', u'•', u'•', u'•'] @@ -20,9 +20,6 @@ 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+)') -punctuation_re = re.compile('^(?P(?:%s)*)(?P.*?)(?P(?:%s)*)$' % \ - ('|'.join([re.escape(x) for x in LEADING_PUNCTUATION]), - '|'.join([re.escape(x) for x in TRAILING_PUNCTUATION]))) simple_url_re = re.compile(r'^https?://\w') simple_url_2_re = re.compile(r'^www\.|^(?!http)\w[^@]+\.(com|edu|gov|int|mil|net|org|[a-z]{2})$') simple_email_re = re.compile(r'^\S+@\S+\.\S+$') @@ -147,9 +144,22 @@ def urlize(text, trim_url_limit=None, nofollow=False, autoescape=False): 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() + # 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 '' @@ -162,6 +172,7 @@ def urlize(text, trim_url_limit=None, nofollow=False, autoescape=False): domain = domain.encode('idna') url = 'mailto:%s@%s' % (local, domain) nofollow_attr = '' + # Make link. if url: trimmed = trim_url(middle) diff --git a/tests/regressiontests/defaultfilters/tests.py b/tests/regressiontests/defaultfilters/tests.py index d79965fee1..00807b0360 100644 --- a/tests/regressiontests/defaultfilters/tests.py +++ b/tests/regressiontests/defaultfilters/tests.py @@ -253,6 +253,14 @@ class DefaultFiltersTests(TestCase): u'' u'http://en.wikipedia.org/wiki/CafĂ©') + # Check urlize keeps balanced parentheses - see #11911 + self.assertEqual(urlize('http://en.wikipedia.org/wiki/Django_(web_framework)'), + u'' + u'http://en.wikipedia.org/wiki/Django_(web_framework)') + self.assertEqual(urlize('(see http://en.wikipedia.org/wiki/Django_(web_framework))'), + u'(see ' + u'http://en.wikipedia.org/wiki/Django_(web_framework))') + # Check urlize adds nofollow properly - see #12183 self.assertEqual(urlize('foo@bar.com or www.bar.com'), u'foo@bar.com or '