[1.8.x] Fixed CVE-2018-7537 -- Fixed catastrophic backtracking in django.utils.text.Truncator.

Thanks James Davis for suggesting the fix.

django/utils/text.py

@@ -27,7 +27,7 @@ capfirst = allow_lazy(capfirst, six.text_type)
 # Set up regular expressions
 re_words = re.compile(r'<.*?>|((?:\w[-\w]*|&.*?;)+)', re.U | re.S)
 re_chars = re.compile(r'<.*?>|(.)', re.U | re.S)
-re_tag = re.compile(r'<(/)?([^ ]+?)(?:(\s*/)| .*?)?>', re.S)
+re_tag = re.compile(r'<(/)?(\S+?)(?:(\s*/)|\s.*?)?>', re.S)
 re_newlines = re.compile(r'\r\n|\r')  # Used in normalize_newlines
 re_camel_case = re.compile(r'(((?<=[a-z])[A-Z])|([A-Z](?![A-Z]|$)))')
 

docs/releases/1.8.19.txt

@@ -16,3 +16,15 @@ expression. The ``urlize()`` function is used to implement the ``urlize`` and
 
 The problematic regular expression is replaced with parsing logic that behaves
 similarly.
+
+CVE-2018-7537: Denial-of-service possibility in ``truncatechars_html`` and ``truncatewords_html`` template filters
+==================================================================================================================
+
+If ``django.utils.text.Truncator``'s ``chars()`` and ``words()`` methods were
+passed the ``html=True`` argument, they were extremely slow to evaluate certain
+inputs due to a catastrophic backtracking vulnerability in a regular
+expression. The ``chars()`` and ``words()`` methods are used to implement the
+``truncatechars_html`` and ``truncatewords_html`` template filters, which were
+thus vulnerable.
+
+The backtracking problem in the regular expression is fixed.

tests/utils_tests/test_text.py

@@ -144,6 +144,10 @@ class TestUtilsText(SimpleTestCase):
         self.assertEqual('<p>I &lt;3 python...</p>',
             truncator.words(3, '...', html=True))
 
+        re_tag_catastrophic_test = ('</a' + '\t' * 50000) + '//>'
+        truncator = text.Truncator(re_tag_catastrophic_test)
+        self.assertEqual(re_tag_catastrophic_test, truncator.words(500, html=True))
+
     def test_wrap(self):
         digits = '1234 67 9'
         self.assertEqual(text.wrap(digits, 100), '1234 67 9')