Ticket #16656: urlize_tlds.diff

django/template/defaultfilters.py

@@ -315 +315 @@
 
 @register.filter
 @stringfilter
-def urlize(value, autoescape=None):
+def urlize(value, autoescape=None, additional_tlds=None):
     """Converts URLs in plain text into clickable links."""
-    return mark_safe(urlize_impl(value, nofollow=True, autoescape=autoescape))
+    return mark_safe(urlize_impl(value, nofollow=True, autoescape=autoescape, additional_tlds=additional_tlds))
 urlize.is_safe = True
 urlize.needs_autoescape = True
 

django/utils/html.py

@@ -100 +100 @@
     return unencoded_ampersands_re.sub('&', force_unicode(value))
 fix_ampersands = allow_lazy(fix_ampersands, unicode)
 
-def urlize(text, trim_url_limit=None, nofollow=False, autoescape=False):
+def urlize(text, trim_url_limit=None, nofollow=False, autoescape=False, additional_tlds=None):
     """
     Converts any URLs in text into clickable links.
 
@@ -116 +116 @@
     attribute.
 
     If autoescape is True, the link text and URLs will get autoescaped.
+
+    If additional_tlds is passed then URLs ending with the default or custom 
+    TLD will be converted into an anchor.
     """
     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 ''
+
+    # The expected behaviour is that the default TLDs will still be urlized
+    default_tlds = ('.com', '.net', '.org') 
+    if additional_tlds is not None:
+        tlds = default_tlds + additional_tlds
+    else:
+        tlds = default_tlds
+
     for i, word in enumerate(words):
         match = None
         if '.' in word or '@' in word or ':' in word:
@@ -133 +144 @@
                 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(tlds)):
                 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>')
 
+        # Check with custom TLDs
+        self.assertEqual(urlize('http://google.com.au/', additional_tlds=('.com.au', '.co.uk')),
+            u'<a href="http://google.com.au/" rel="nofollow">http://google.com.au/</a>')
+        self.assertEqual(urlize('google.co.uk', additional_tlds=('.com.au', '.co.uk')),
+            u'<a href="http://google.co.uk" rel="nofollow">google.co.uk</a>')
+
+
     def test_wordcount(self):
         self.assertEqual(wordcount(''), 0)
         self.assertEqual(wordcount(u'oneword'), 1)