Fixed some missed auto-escaping and URL quoting cases in the urlize filter.

git-svn-id: http://code.djangoproject.com/svn/django/trunk@6683 bcc190cf-cafb-0310-a4f2-bffc1f526a37

django/utils/html.py

@@ -6,6 +6,7 @@ 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;']
@@ -101,14 +102,24 @@ def urlize(text, trim_url_limit=None, nofollow=False, autoescape=False):
             if middle.startswith('www.') or ('@' not in middle and not middle.startswith('http://') and \
                     len(middle) > 0 and middle[0] in string.letters + string.digits and \
                     (middle.endswith('.org') or middle.endswith('.net') or middle.endswith('.com'))):
-                middle = '<a href="http://%s"%s>%s</a>' % (middle, nofollow_attr, trim_url(middle))
+                middle = '<a href="http://%s"%s>%s</a>' % (
+                        urlquote(middle, safe='/&=:;#?+'),  nofollow_attr,
+                        trim_url(middle))
             if middle.startswith('http://') or middle.startswith('https://'):
-                middle = '<a href="%s"%s>%s</a>' % (middle, nofollow_attr, trim_url(middle))
+                middle = '<a href="%s"%s>%s</a>' % (
-            if '@' in middle and not middle.startswith('www.') and not ':' in middle \
+                        urlquote(middle, safe='/&=:;#?+'), nofollow_attr,
-                and simple_email_re.match(middle):
+                        trim_url(middle))
+            if '@' in middle and not middle.startswith('www.') and \
+                    not ':' in middle and simple_email_re.match(middle):
                 middle = '<a href="mailto:%s">%s</a>' % (middle, middle)
             if lead + middle + trail != word:
                 words[i] = lead + middle + trail
+            elif autoescape and not safe_input:
+                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)
 

tests/regressiontests/templates/filters.py

@@ -94,6 +94,11 @@ def get_filter_tests():
         'filter-urlize03': ('{% autoescape off %}{{ a|urlize }}{% endautoescape %}', {"a": mark_safe("a & b")}, 'a & b'),
         'filter-urlize04': ('{{ a|urlize }}', {"a": mark_safe("a & b")}, 'a & b'),
 
+        # This will lead to a nonsense result, but at least it won't be
+        # exploitable for XSS purposes when auto-escaping is on.
+        'filter-urlize05': ('{% autoescape off %}{{ a|urlize }}{% endautoescape %}', {"a": "<script>alert('foo')</script>"}, "<script>alert('foo')</script>"),
+        'filter-urlize06': ('{{ a|urlize }}', {"a": "<script>alert('foo')</script>"}, '&lt;script&gt;alert(&#39;foo&#39;)&lt;/script&gt;'),
+
         'filter-urlizetrunc01': ('{% autoescape off %}{{ a|urlizetrunc:"8" }} {{ b|urlizetrunc:"8" }}{% endautoescape %}', {"a": "http://example.com/x=&y=", "b": mark_safe("http://example.com?x=&y=")}, u'<a href="http://example.com/x=&y=" rel="nofollow">http:...</a> <a href="http://example.com?x=&y=" rel="nofollow">http:...</a>'),
         'filter-urlizetrunc02': ('{{ a|urlizetrunc:"8" }} {{ b|urlizetrunc:"8" }}', {"a": "http://example.com/x=&y=", "b": mark_safe("http://example.com?x=&y=")}, u'<a href="http://example.com/x=&y=" rel="nofollow">http:...</a> <a href="http://example.com?x=&y=" rel="nofollow">http:...</a>'),