[1.11.x] Fixed CVE-2019-14233 -- Prevented excessive HTMLParser recursion in strip_tags() when handling incomplete HTML entities.

Thanks to Guido Vranken for initial report.

Author: apollo13

django/utils/html.py

@@ -169,8 +169,8 @@ def strip_tags(value):
     value = force_text(value)
     while '<' in value and '>' in value:
         new_value = _strip_once(value)
-        if len(new_value) >= len(value):
-            # _strip_once was not able to detect more tags or length increased
+        if len(new_value) >= len(value) or value.count('<') == new_value.count('<'):
+            # _strip_once wasn't able to detect more tags, or line length increased.
             # due to http://bugs.python.org/issue20288
             # (affects Python 2 < 2.7.7 and Python 3 < 3.3.5)
             break

docs/releases/1.11.23.txt

@@ -19,3 +19,20 @@ filters, which were thus vulnerable.
 The regular expressions used by ``Truncator`` have been simplified in order to
 avoid potential backtracking issues. As a consequence, trailing punctuation may
 now at times be included in the truncated output.
+
+CVE-2019-14233: Denial-of-service possibility in ``strip_tags()``
+=================================================================
+
+Due to the behavior of the underlying ``HTMLParser``,
+:func:`django.utils.html.strip_tags` would be extremely slow to evaluate
+certain inputs containing large sequences of nested incomplete HTML entities.
+The ``strip_tags()`` method is used to implement the corresponding
+:tfilter:`striptags` template filter, which was thus also vulnerable.
+
+``strip_tags()`` now avoids recursive calls to ``HTMLParser`` when progress
+removing tags, but necessarily incomplete HTML entities, stops being made.
+
+Remember that absolutely NO guarantee is provided about the results of
+``strip_tags()`` being HTML safe. So NEVER mark safe the result of a
+``strip_tags()`` call without escaping it first, for example with
+:func:`django.utils.html.escape`.

tests/utils_tests/test_html.py

@@ -86,6 +86,8 @@ def test_strip_tags(self):
             # caused infinite loop on Pythons not patched with
             # http://bugs.python.org/issue20288
             ('&gotcha&#;<>', '&gotcha&#;<>'),
+            ('><!' + ('&' * 16000) + 'D', '><!' + ('&' * 16000) + 'D'),
+            ('X<<<<br>br>br>br>X', 'XX'),
         )
         for value, output in items:
             self.check_output(f, value, output)