Bug #1334662 / patch #1335972: int(string, base) wrong answers.

In rare cases of strings specifying true values near sys.maxint,
and oddball bases (not decimal or a power of 2), int(string, base)
could deliver insane answers.  This repairs all such problems, and
also speeds string->int significantly.  On my box, here are %
speedups for decimal strings of various lengths:

length speedup
------ -------
 1       12.4%
 2       15.7%
 3       20.6%
 4       28.1%
 5       33.2%
 6       37.5%
 7       41.9%
 8       46.3%
 9       51.2%
10       19.5%
11       19.9%
12       23.9%
13       23.7%
14       23.3%
15       24.9%
16       25.3%
17       28.3%
18       27.9%
19       35.7%

Note that the difference between 9 and 10 is the difference between
short and long Python ints on a 32-bit box.  The patch doesn't
actually do anything to speed conversion to long:  the speedup is
due to detecting "unsigned long" overflow more quickly.

This is a bugfix candidate, but it's a non-trivial patch and it
would be painful to separate the "bug fix" from the "speed up" parts.

1 files changed, 78 insertions, 0 deletions

diff --git a/Lib/test/test_builtin.py b/Lib/test/test_builtin.py
index 121da24..48d50d8 100644
--- a/Lib/test/test_builtin.py
+++ b/Lib/test/test_builtin.py
@@ -709,6 +709,84 @@ class BuiltinTest(unittest.TestCase):
         self.assertEqual(int('0123', 0), 83)
         self.assertEqual(int('0x123', 16), 291)
 
+        # SF bug 1334662: int(string, base) wrong answers
+        # Various representations of 2**32 evaluated to 0
+        # rather than 2**32 in previous versions
+
+        self.assertEqual(int('100000000000000000000000000000000', 2), 4294967296L)
+        self.assertEqual(int('102002022201221111211', 3), 4294967296L)
+        self.assertEqual(int('10000000000000000', 4), 4294967296L)
+        self.assertEqual(int('32244002423141', 5), 4294967296L)
+        self.assertEqual(int('1550104015504', 6), 4294967296L)
+        self.assertEqual(int('211301422354', 7), 4294967296L)
+        self.assertEqual(int('40000000000', 8), 4294967296L)
+        self.assertEqual(int('12068657454', 9), 4294967296L)
+        self.assertEqual(int('4294967296', 10), 4294967296L)
+        self.assertEqual(int('1904440554', 11), 4294967296L)
+        self.assertEqual(int('9ba461594', 12), 4294967296L)
+        self.assertEqual(int('535a79889', 13), 4294967296L)
+        self.assertEqual(int('2ca5b7464', 14), 4294967296L)
+        self.assertEqual(int('1a20dcd81', 15), 4294967296L)
+        self.assertEqual(int('100000000', 16), 4294967296L)
+        self.assertEqual(int('a7ffda91', 17), 4294967296L)
+        self.assertEqual(int('704he7g4', 18), 4294967296L)
+        self.assertEqual(int('4f5aff66', 19), 4294967296L)
+        self.assertEqual(int('3723ai4g', 20), 4294967296L)
+        self.assertEqual(int('281d55i4', 21), 4294967296L)
+        self.assertEqual(int('1fj8b184', 22), 4294967296L)
+        self.assertEqual(int('1606k7ic', 23), 4294967296L)
+        self.assertEqual(int('mb994ag', 24), 4294967296L)
+        self.assertEqual(int('hek2mgl', 25), 4294967296L)
+        self.assertEqual(int('dnchbnm', 26), 4294967296L)
+        self.assertEqual(int('b28jpdm', 27), 4294967296L)
+        self.assertEqual(int('8pfgih4', 28), 4294967296L)
+        self.assertEqual(int('76beigg', 29), 4294967296L)
+        self.assertEqual(int('5qmcpqg', 30), 4294967296L)
+        self.assertEqual(int('4q0jto4', 31), 4294967296L)
+        self.assertEqual(int('4000000', 32), 4294967296L)
+        self.assertEqual(int('3aokq94', 33), 4294967296L)
+        self.assertEqual(int('2qhxjli', 34), 4294967296L)
+        self.assertEqual(int('2br45qb', 35), 4294967296L)
+        self.assertEqual(int('1z141z4', 36), 4294967296L)
+
+        # SF bug 1334662: int(string, base) wrong answers
+        # Checks for proper evaluation of 2**32 + 1
+        self.assertEqual(int('100000000000000000000000000000001', 2), 4294967297L)
+        self.assertEqual(int('102002022201221111212', 3), 4294967297L)
+        self.assertEqual(int('10000000000000001', 4), 4294967297L)
+        self.assertEqual(int('32244002423142', 5), 4294967297L)
+        self.assertEqual(int('1550104015505', 6), 4294967297L)
+        self.assertEqual(int('211301422355', 7), 4294967297L)
+        self.assertEqual(int('40000000001', 8), 4294967297L)
+        self.assertEqual(int('12068657455', 9), 4294967297L)
+        self.assertEqual(int('4294967297', 10), 4294967297L)
+        self.assertEqual(int('1904440555', 11), 4294967297L)
+        self.assertEqual(int('9ba461595', 12), 4294967297L)
+        self.assertEqual(int('535a7988a', 13), 4294967297L)
+        self.assertEqual(int('2ca5b7465', 14), 4294967297L)
+        self.assertEqual(int('1a20dcd82', 15), 4294967297L)
+        self.assertEqual(int('100000001', 16), 4294967297L)
+        self.assertEqual(int('a7ffda92', 17), 4294967297L)
+        self.assertEqual(int('704he7g5', 18), 4294967297L)
+        self.assertEqual(int('4f5aff67', 19), 4294967297L)
+        self.assertEqual(int('3723ai4h', 20), 4294967297L)
+        self.assertEqual(int('281d55i5', 21), 4294967297L)
+        self.assertEqual(int('1fj8b185', 22), 4294967297L)
+        self.assertEqual(int('1606k7id', 23), 4294967297L)
+        self.assertEqual(int('mb994ah', 24), 4294967297L)
+        self.assertEqual(int('hek2mgm', 25), 4294967297L)
+        self.assertEqual(int('dnchbnn', 26), 4294967297L)
+        self.assertEqual(int('b28jpdn', 27), 4294967297L)
+        self.assertEqual(int('8pfgih5', 28), 4294967297L)
+        self.assertEqual(int('76beigh', 29), 4294967297L)
+        self.assertEqual(int('5qmcpqh', 30), 4294967297L)
+        self.assertEqual(int('4q0jto5', 31), 4294967297L)
+        self.assertEqual(int('4000001', 32), 4294967297L)
+        self.assertEqual(int('3aokq95', 33), 4294967297L)
+        self.assertEqual(int('2qhxjlj', 34), 4294967297L)
+        self.assertEqual(int('2br45qc', 35), 4294967297L)
+        self.assertEqual(int('1z141z5', 36), 4294967297L)
+
     def test_intconversion(self):
         # Test __int__()
         class Foo0: