Ticket #16395: urlize_malformed_urls.diff

django/utils/html.py

@@ -25 +25 @@
 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>(?:&nbsp;|\s|<br \/>)*?</p>\s*)+\Z')
+startswith_http_re = re.compile(r'^https?://\w')
 del x # Temporary variable
 
 def escape(html):
@@ -128 +129 @@
             lead, middle, trail = match.groups()
             # Make URL we want to point to.
             url = None
-            if middle.startswith('http://') or middle.startswith('https://'):
+            if re.match(startswith_http_re, middle):
                 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'))):
+                    (middle.endswith('.org') or middle.endswith('.net') or middle.endswith('.com')) and \
+                    (not middle.startswith('http'))):
                 url = urlquote('http://%s' % middle, safe='/&=:;#?+*')
             elif '@' in middle and not ':' in middle and simple_email_re.match(middle):
                 url = 'mailto:%s' % middle

tests/regressiontests/defaultfilters/tests.py

@@ -217 +217 @@
         self.assertEqual(urlize('https://google.com'),
             u'<a href="https://google.com" rel="nofollow">https://google.com</a>')
 
+        # malformed URIs
+        self.assertEqual(urlize('http://///www.google.fr/?f=1'),
+            u'http://///www.google.fr/?f=1')
+        self.assertEqual(urlize('http://....google.com'),
+            u'http://....google.com')
+
     def test_wordcount(self):
         self.assertEqual(wordcount(''), 0)
         self.assertEqual(wordcount(u'oneword'), 1)