Improved regex in strip_tags

Thanks Pablo Recio for the report. Refs #19237.

django/utils/html.py

@@ -33,7 +33,7 @@ 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)
 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')
-strip_tags_re = re.compile(r'</?\S([^=]*=(\s*"[^"]*"|\s*\'[^\']*\'|\S*)|[^>])*?>', re.IGNORECASE)
+strip_tags_re = re.compile(r'</?\S([^=>]*=(\s*"[^"]*"|\s*\'[^\']*\'|\S*)|[^>])*?>', re.IGNORECASE)
 
 
 def escape(text):

tests/regressiontests/utils/html.py

@@ -68,6 +68,7 @@ class TestUtilsHtml(unittest.TestCase):
             ('a<p onclick="alert(\'<test>\')">b</p>c', 'abc'),
             ('a<p a >b</p>c', 'abc'),
             ('d<a:b c:d>e</p>f', 'def'),
+            ('<strong>foo</strong><a href="http://example.com">bar</a>', 'foobar'),
         )
         for value, output in items:
             self.check_output(f, value, output)