- Issue #13703: oCERT-2011-003: add -R command-line option and PYTHONHASHSEED
environment variable, to provide an opt-in way to protect against denial of
service attacks due to hash collisions within the dict and set types. Patch
by David Malcolm, based on work by Victor Stinner.
diff --git a/Lib/test/test_hash.py b/Lib/test/test_hash.py
index 7ce40b9..1a982c4 100644
--- a/Lib/test/test_hash.py
+++ b/Lib/test/test_hash.py
@@ -3,10 +3,18 @@
#
# Also test that hash implementations are inherited as expected
+import os
+import sys
+import struct
+import datetime
import unittest
+import subprocess
+
from test import test_support
from collections import Hashable
+IS_64BIT = (struct.calcsize('l') == 8)
+
class HashEqualityTestCase(unittest.TestCase):
@@ -133,10 +141,100 @@
for obj in self.hashes_to_check:
self.assertEqual(hash(obj), _default_hash(obj))
+class HashRandomizationTests(unittest.TestCase):
+
+ # Each subclass should define a field "repr_", containing the repr() of
+ # an object to be tested
+
+ def get_hash_command(self, repr_):
+ return 'print(hash(%s))' % repr_
+
+ def get_hash(self, repr_, seed=None):
+ env = os.environ.copy()
+ if seed is not None:
+ env['PYTHONHASHSEED'] = str(seed)
+ else:
+ env.pop('PYTHONHASHSEED', None)
+ cmd_line = [sys.executable, '-c', self.get_hash_command(repr_)]
+ p = subprocess.Popen(cmd_line, stdin=subprocess.PIPE,
+ stdout=subprocess.PIPE, stderr=subprocess.STDOUT,
+ env=env)
+ out, err = p.communicate()
+ out = test_support.strip_python_stderr(out)
+ return int(out.strip())
+
+ def test_randomized_hash(self):
+ # two runs should return different hashes
+ run1 = self.get_hash(self.repr_, seed='random')
+ run2 = self.get_hash(self.repr_, seed='random')
+ self.assertNotEqual(run1, run2)
+
+class StringlikeHashRandomizationTests(HashRandomizationTests):
+ def test_null_hash(self):
+ # PYTHONHASHSEED=0 disables the randomized hash
+ if IS_64BIT:
+ known_hash_of_obj = 1453079729188098211
+ else:
+ known_hash_of_obj = -1600925533
+
+ # Randomization is disabled by default:
+ self.assertEqual(self.get_hash(self.repr_), known_hash_of_obj)
+
+ # It can also be disabled by setting the seed to 0:
+ self.assertEqual(self.get_hash(self.repr_, seed=0), known_hash_of_obj)
+
+ def test_fixed_hash(self):
+ # test a fixed seed for the randomized hash
+ # Note that all types share the same values:
+ if IS_64BIT:
+ h = -4410911502303878509
+ else:
+ h = -206076799
+ self.assertEqual(self.get_hash(self.repr_, seed=42), h)
+
+class StrHashRandomizationTests(StringlikeHashRandomizationTests):
+ repr_ = repr('abc')
+
+ def test_empty_string(self):
+ self.assertEqual(hash(""), 0)
+
+class UnicodeHashRandomizationTests(StringlikeHashRandomizationTests):
+ repr_ = repr(u'abc')
+
+ def test_empty_string(self):
+ self.assertEqual(hash(u""), 0)
+
+class BufferHashRandomizationTests(StringlikeHashRandomizationTests):
+ repr_ = 'buffer("abc")'
+
+ def test_empty_string(self):
+ self.assertEqual(hash(buffer("")), 0)
+
+class DatetimeTests(HashRandomizationTests):
+ def get_hash_command(self, repr_):
+ return 'import datetime; print(hash(%s))' % repr_
+
+class DatetimeDateTests(DatetimeTests):
+ repr_ = repr(datetime.date(1066, 10, 14))
+
+class DatetimeDatetimeTests(DatetimeTests):
+ repr_ = repr(datetime.datetime(1, 2, 3, 4, 5, 6, 7))
+
+class DatetimeTimeTests(DatetimeTests):
+ repr_ = repr(datetime.time(0))
+
+
def test_main():
test_support.run_unittest(HashEqualityTestCase,
HashInheritanceTestCase,
- HashBuiltinsTestCase)
+ HashBuiltinsTestCase,
+ StrHashRandomizationTests,
+ UnicodeHashRandomizationTests,
+ BufferHashRandomizationTests,
+ DatetimeDateTests,
+ DatetimeDatetimeTests,
+ DatetimeTimeTests)
+
if __name__ == "__main__":