Commit 27508918 authored by Aymeric Augustin's avatar Aymeric Augustin
Browse files

Fixed #16395 -- Prevented urlize from highlighting some malformed URLs. Thanks... 

Fixed #16395 -- Prevented urlize from highlighting some malformed URLs. Thanks BernhardEssl for the report and initial patch.


git-svn-id: http://code.djangoproject.com/svn/django/trunk@17358 bcc190cf-cafb-0310-a4f2-bffc1f526a37
parent 40f0ecc5

django/utils/html.py

+4 −4
Original line number Diff line number Diff line
@@ -23,6 +23,8 @@ 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_url_re = re.compile(r'^https?://\w')

simple_url_2_re = re.compile(r'^www\.|^(?!http)\w[^@]+\.(com|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)
@@ -150,11 +152,9 @@ def urlize(text, trim_url_limit=None, nofollow=False, autoescape=False): 
            # Make URL we want to point to.

            url = None

            nofollow_attr = ' rel="nofollow"' if nofollow else ''

            if middle.startswith('http://') or middle.startswith('https://'):

            if simple_url_re.match(middle):

                url = smart_urlquote(middle)

            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'))):

            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)

tests/regressiontests/defaultfilters/tests.py

+8 −0
Original line number Diff line number Diff line
@@ -268,6 +268,14 @@ class DefaultFiltersTests(TestCase): 
        self.assertEqual(urlize('info@c✶.org'),

            u'<a href="mailto:info@xn--c-lgq.org">info@c✶.org</a>')



        # Check urlize doesn't highlight malformed URIs - see #16395

        self.assertEqual(urlize('http:///www.google.com'),

           u'http:///www.google.com')

        self.assertEqual(urlize('http://.google.com'),

            u'http://.google.com')

        self.assertEqual(urlize('http://@foo.com'),

            u'http://@foo.com')



    def test_wordcount(self):

        self.assertEqual(wordcount(''), 0)

        self.assertEqual(wordcount(u'oneword'), 1)