Prevent difflib REDOS (CVE-2018-1061)

The default regex for IS_LINE_JUNK is susceptible to catastrophic backtracking. This is a potential DOS vector. Replace it with an equivalent non-vulnerable regex. Also introduce unit and REDOS tests for difflib. Co-authored-by: Tim Peters <tim.peters@gmail.com> Co-authored-by: Christian Heimes <christian@python.org>

Author: 3 people

Lib/difflib.py

@@ -1083,7 +1083,7 @@ def _qformat(self, aline, bline, atags, btags):
 
 import re
 
-def IS_LINE_JUNK(line, pat=re.compile(r"\s*#?\s*$").match):
+def IS_LINE_JUNK(line, pat=re.compile(r"\s*(?:#\s*)?$").match):
  r"""
  Return 1 for ignorable line: iff `line` is blank or contains a single '#'.
 

Lib/test/test_difflib.py

@@ -466,13 +466,33 @@ def _assert_type_error(self, msg, generator, *args):
  list(generator(*args))
  self.assertEqual(msg, str(ctx.exception))
 
+class TestJunkAPIs(unittest.TestCase):
+ def test_is_line_junk_true(self):
+ for line in ['#', ' ', ' #', '# ', ' # ', '']:
+ self.assertTrue(difflib.IS_LINE_JUNK(line), 'should be junk: {}'.format(line))
+
+ def test_is_line_junk_false(self):
+ for line in ['##', ' ##', '## ', 'abc ', 'abc #', 'abc # ', 'Mr. Moose is up!']:
+ self.assertFalse(difflib.IS_LINE_JUNK(line), 'should not be junk: {}'.format(line))
+
+ def test_is_line_junk_REDOS(self):
+ evil_input = ('\t' * 1000000) + '##'
+ self.assertFalse(difflib.IS_LINE_JUNK(evil_input))
+
+ def test_is_character_junk_true(self):
+ for char in [' ', '\t']:
+ self.assertTrue(difflib.IS_CHARACTER_JUNK(char), 'should be junk: {}'.format(char))
+
+ def test_is_character_junk_false(self):
+ for char in ['a', '#', '\n', '\f', '\r', '\v']:
+ self.assertFalse(difflib.IS_CHARACTER_JUNK(char), 'should not be junk: {}'.format(char))
 
 def test_main():
  difflib.HtmlDiff._default_prefix = 0
  Doctests = doctest.DocTestSuite(difflib)
  run_unittest(
  TestWithAscii, TestAutojunk, TestSFpatches, TestSFbugs,
- TestOutputFormat, TestBytes, Doctests)
+ TestOutputFormat, TestBytes, TestJunkAPIs, Doctests)
 
 if __name__ == '__main__':
  test_main()