mirror of
https://github.com/python/cpython
synced 2024-09-16 00:07:33 +00:00
511ca94520
Integer to and from text conversions via CPython's bignum `int` type is not safe against denial of service attacks due to malicious input. Very large input strings with hundred thousands of digits can consume several CPU seconds. This PR comes fresh from a pile of work done in our private PSRT security response team repo. Signed-off-by: Christian Heimes [Red Hat] <christian@python.org> Tons-of-polishing-up-by: Gregory P. Smith [Google] <greg@krypto.org> Reviews via the private PSRT repo via many others (see the NEWS entry in the PR). <!-- gh-issue-number: gh-95778 --> * Issue: gh-95778 <!-- /gh-issue-number --> I wrote up [a one pager for the release managers](https://docs.google.com/document/d/1KjuF_aXlzPUxTK4BMgezGJ2Pn7uevfX7g0_mvgHlL7Y/edit#). Much of that text wound up in the Issue. Backports PRs already exist. See the issue for links.
696 lines
25 KiB
Python
696 lines
25 KiB
Python
import sys
|
|
|
|
import unittest
|
|
from test import support
|
|
from test.test_grammar import (VALID_UNDERSCORE_LITERALS,
|
|
INVALID_UNDERSCORE_LITERALS)
|
|
|
|
L = [
|
|
('0', 0),
|
|
('1', 1),
|
|
('9', 9),
|
|
('10', 10),
|
|
('99', 99),
|
|
('100', 100),
|
|
('314', 314),
|
|
(' 314', 314),
|
|
('314 ', 314),
|
|
(' \t\t 314 \t\t ', 314),
|
|
(repr(sys.maxsize), sys.maxsize),
|
|
(' 1x', ValueError),
|
|
(' 1 ', 1),
|
|
(' 1\02 ', ValueError),
|
|
('', ValueError),
|
|
(' ', ValueError),
|
|
(' \t\t ', ValueError),
|
|
("\u0200", ValueError)
|
|
]
|
|
|
|
class IntSubclass(int):
|
|
pass
|
|
|
|
class IntTestCases(unittest.TestCase):
|
|
|
|
def test_basic(self):
|
|
self.assertEqual(int(314), 314)
|
|
self.assertEqual(int(3.14), 3)
|
|
# Check that conversion from float truncates towards zero
|
|
self.assertEqual(int(-3.14), -3)
|
|
self.assertEqual(int(3.9), 3)
|
|
self.assertEqual(int(-3.9), -3)
|
|
self.assertEqual(int(3.5), 3)
|
|
self.assertEqual(int(-3.5), -3)
|
|
self.assertEqual(int("-3"), -3)
|
|
self.assertEqual(int(" -3 "), -3)
|
|
self.assertEqual(int("\N{EM SPACE}-3\N{EN SPACE}"), -3)
|
|
# Different base:
|
|
self.assertEqual(int("10",16), 16)
|
|
# Test conversion from strings and various anomalies
|
|
for s, v in L:
|
|
for sign in "", "+", "-":
|
|
for prefix in "", " ", "\t", " \t\t ":
|
|
ss = prefix + sign + s
|
|
vv = v
|
|
if sign == "-" and v is not ValueError:
|
|
vv = -v
|
|
try:
|
|
self.assertEqual(int(ss), vv)
|
|
except ValueError:
|
|
pass
|
|
|
|
s = repr(-1-sys.maxsize)
|
|
x = int(s)
|
|
self.assertEqual(x+1, -sys.maxsize)
|
|
self.assertIsInstance(x, int)
|
|
# should return int
|
|
self.assertEqual(int(s[1:]), sys.maxsize+1)
|
|
|
|
# should return int
|
|
x = int(1e100)
|
|
self.assertIsInstance(x, int)
|
|
x = int(-1e100)
|
|
self.assertIsInstance(x, int)
|
|
|
|
|
|
# SF bug 434186: 0x80000000/2 != 0x80000000>>1.
|
|
# Worked by accident in Windows release build, but failed in debug build.
|
|
# Failed in all Linux builds.
|
|
x = -1-sys.maxsize
|
|
self.assertEqual(x >> 1, x//2)
|
|
|
|
x = int('1' * 600)
|
|
self.assertIsInstance(x, int)
|
|
|
|
|
|
self.assertRaises(TypeError, int, 1, 12)
|
|
|
|
self.assertEqual(int('0o123', 0), 83)
|
|
self.assertEqual(int('0x123', 16), 291)
|
|
|
|
# Bug 1679: "0x" is not a valid hex literal
|
|
self.assertRaises(ValueError, int, "0x", 16)
|
|
self.assertRaises(ValueError, int, "0x", 0)
|
|
|
|
self.assertRaises(ValueError, int, "0o", 8)
|
|
self.assertRaises(ValueError, int, "0o", 0)
|
|
|
|
self.assertRaises(ValueError, int, "0b", 2)
|
|
self.assertRaises(ValueError, int, "0b", 0)
|
|
|
|
# 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), 4294967296)
|
|
self.assertEqual(int('102002022201221111211', 3), 4294967296)
|
|
self.assertEqual(int('10000000000000000', 4), 4294967296)
|
|
self.assertEqual(int('32244002423141', 5), 4294967296)
|
|
self.assertEqual(int('1550104015504', 6), 4294967296)
|
|
self.assertEqual(int('211301422354', 7), 4294967296)
|
|
self.assertEqual(int('40000000000', 8), 4294967296)
|
|
self.assertEqual(int('12068657454', 9), 4294967296)
|
|
self.assertEqual(int('4294967296', 10), 4294967296)
|
|
self.assertEqual(int('1904440554', 11), 4294967296)
|
|
self.assertEqual(int('9ba461594', 12), 4294967296)
|
|
self.assertEqual(int('535a79889', 13), 4294967296)
|
|
self.assertEqual(int('2ca5b7464', 14), 4294967296)
|
|
self.assertEqual(int('1a20dcd81', 15), 4294967296)
|
|
self.assertEqual(int('100000000', 16), 4294967296)
|
|
self.assertEqual(int('a7ffda91', 17), 4294967296)
|
|
self.assertEqual(int('704he7g4', 18), 4294967296)
|
|
self.assertEqual(int('4f5aff66', 19), 4294967296)
|
|
self.assertEqual(int('3723ai4g', 20), 4294967296)
|
|
self.assertEqual(int('281d55i4', 21), 4294967296)
|
|
self.assertEqual(int('1fj8b184', 22), 4294967296)
|
|
self.assertEqual(int('1606k7ic', 23), 4294967296)
|
|
self.assertEqual(int('mb994ag', 24), 4294967296)
|
|
self.assertEqual(int('hek2mgl', 25), 4294967296)
|
|
self.assertEqual(int('dnchbnm', 26), 4294967296)
|
|
self.assertEqual(int('b28jpdm', 27), 4294967296)
|
|
self.assertEqual(int('8pfgih4', 28), 4294967296)
|
|
self.assertEqual(int('76beigg', 29), 4294967296)
|
|
self.assertEqual(int('5qmcpqg', 30), 4294967296)
|
|
self.assertEqual(int('4q0jto4', 31), 4294967296)
|
|
self.assertEqual(int('4000000', 32), 4294967296)
|
|
self.assertEqual(int('3aokq94', 33), 4294967296)
|
|
self.assertEqual(int('2qhxjli', 34), 4294967296)
|
|
self.assertEqual(int('2br45qb', 35), 4294967296)
|
|
self.assertEqual(int('1z141z4', 36), 4294967296)
|
|
|
|
# tests with base 0
|
|
# this fails on 3.0, but in 2.x the old octal syntax is allowed
|
|
self.assertEqual(int(' 0o123 ', 0), 83)
|
|
self.assertEqual(int(' 0o123 ', 0), 83)
|
|
self.assertEqual(int('000', 0), 0)
|
|
self.assertEqual(int('0o123', 0), 83)
|
|
self.assertEqual(int('0x123', 0), 291)
|
|
self.assertEqual(int('0b100', 0), 4)
|
|
self.assertEqual(int(' 0O123 ', 0), 83)
|
|
self.assertEqual(int(' 0X123 ', 0), 291)
|
|
self.assertEqual(int(' 0B100 ', 0), 4)
|
|
|
|
# without base still base 10
|
|
self.assertEqual(int('0123'), 123)
|
|
self.assertEqual(int('0123', 10), 123)
|
|
|
|
# tests with prefix and base != 0
|
|
self.assertEqual(int('0x123', 16), 291)
|
|
self.assertEqual(int('0o123', 8), 83)
|
|
self.assertEqual(int('0b100', 2), 4)
|
|
self.assertEqual(int('0X123', 16), 291)
|
|
self.assertEqual(int('0O123', 8), 83)
|
|
self.assertEqual(int('0B100', 2), 4)
|
|
|
|
# the code has special checks for the first character after the
|
|
# type prefix
|
|
self.assertRaises(ValueError, int, '0b2', 2)
|
|
self.assertRaises(ValueError, int, '0b02', 2)
|
|
self.assertRaises(ValueError, int, '0B2', 2)
|
|
self.assertRaises(ValueError, int, '0B02', 2)
|
|
self.assertRaises(ValueError, int, '0o8', 8)
|
|
self.assertRaises(ValueError, int, '0o08', 8)
|
|
self.assertRaises(ValueError, int, '0O8', 8)
|
|
self.assertRaises(ValueError, int, '0O08', 8)
|
|
self.assertRaises(ValueError, int, '0xg', 16)
|
|
self.assertRaises(ValueError, int, '0x0g', 16)
|
|
self.assertRaises(ValueError, int, '0Xg', 16)
|
|
self.assertRaises(ValueError, int, '0X0g', 16)
|
|
|
|
# SF bug 1334662: int(string, base) wrong answers
|
|
# Checks for proper evaluation of 2**32 + 1
|
|
self.assertEqual(int('100000000000000000000000000000001', 2), 4294967297)
|
|
self.assertEqual(int('102002022201221111212', 3), 4294967297)
|
|
self.assertEqual(int('10000000000000001', 4), 4294967297)
|
|
self.assertEqual(int('32244002423142', 5), 4294967297)
|
|
self.assertEqual(int('1550104015505', 6), 4294967297)
|
|
self.assertEqual(int('211301422355', 7), 4294967297)
|
|
self.assertEqual(int('40000000001', 8), 4294967297)
|
|
self.assertEqual(int('12068657455', 9), 4294967297)
|
|
self.assertEqual(int('4294967297', 10), 4294967297)
|
|
self.assertEqual(int('1904440555', 11), 4294967297)
|
|
self.assertEqual(int('9ba461595', 12), 4294967297)
|
|
self.assertEqual(int('535a7988a', 13), 4294967297)
|
|
self.assertEqual(int('2ca5b7465', 14), 4294967297)
|
|
self.assertEqual(int('1a20dcd82', 15), 4294967297)
|
|
self.assertEqual(int('100000001', 16), 4294967297)
|
|
self.assertEqual(int('a7ffda92', 17), 4294967297)
|
|
self.assertEqual(int('704he7g5', 18), 4294967297)
|
|
self.assertEqual(int('4f5aff67', 19), 4294967297)
|
|
self.assertEqual(int('3723ai4h', 20), 4294967297)
|
|
self.assertEqual(int('281d55i5', 21), 4294967297)
|
|
self.assertEqual(int('1fj8b185', 22), 4294967297)
|
|
self.assertEqual(int('1606k7id', 23), 4294967297)
|
|
self.assertEqual(int('mb994ah', 24), 4294967297)
|
|
self.assertEqual(int('hek2mgm', 25), 4294967297)
|
|
self.assertEqual(int('dnchbnn', 26), 4294967297)
|
|
self.assertEqual(int('b28jpdn', 27), 4294967297)
|
|
self.assertEqual(int('8pfgih5', 28), 4294967297)
|
|
self.assertEqual(int('76beigh', 29), 4294967297)
|
|
self.assertEqual(int('5qmcpqh', 30), 4294967297)
|
|
self.assertEqual(int('4q0jto5', 31), 4294967297)
|
|
self.assertEqual(int('4000001', 32), 4294967297)
|
|
self.assertEqual(int('3aokq95', 33), 4294967297)
|
|
self.assertEqual(int('2qhxjlj', 34), 4294967297)
|
|
self.assertEqual(int('2br45qc', 35), 4294967297)
|
|
self.assertEqual(int('1z141z5', 36), 4294967297)
|
|
|
|
def test_underscores(self):
|
|
for lit in VALID_UNDERSCORE_LITERALS:
|
|
if any(ch in lit for ch in '.eEjJ'):
|
|
continue
|
|
self.assertEqual(int(lit, 0), eval(lit))
|
|
self.assertEqual(int(lit, 0), int(lit.replace('_', ''), 0))
|
|
for lit in INVALID_UNDERSCORE_LITERALS:
|
|
if any(ch in lit for ch in '.eEjJ'):
|
|
continue
|
|
self.assertRaises(ValueError, int, lit, 0)
|
|
# Additional test cases with bases != 0, only for the constructor:
|
|
self.assertEqual(int("1_00", 3), 9)
|
|
self.assertEqual(int("0_100"), 100) # not valid as a literal!
|
|
self.assertEqual(int(b"1_00"), 100) # byte underscore
|
|
self.assertRaises(ValueError, int, "_100")
|
|
self.assertRaises(ValueError, int, "+_100")
|
|
self.assertRaises(ValueError, int, "1__00")
|
|
self.assertRaises(ValueError, int, "100_")
|
|
|
|
@support.cpython_only
|
|
def test_small_ints(self):
|
|
# Bug #3236: Return small longs from PyLong_FromString
|
|
self.assertIs(int('10'), 10)
|
|
self.assertIs(int('-1'), -1)
|
|
self.assertIs(int(b'10'), 10)
|
|
self.assertIs(int(b'-1'), -1)
|
|
|
|
def test_no_args(self):
|
|
self.assertEqual(int(), 0)
|
|
|
|
def test_keyword_args(self):
|
|
# Test invoking int() using keyword arguments.
|
|
self.assertEqual(int('100', base=2), 4)
|
|
with self.assertRaisesRegex(TypeError, 'keyword argument'):
|
|
int(x=1.2)
|
|
with self.assertRaisesRegex(TypeError, 'keyword argument'):
|
|
int(x='100', base=2)
|
|
self.assertRaises(TypeError, int, base=10)
|
|
self.assertRaises(TypeError, int, base=0)
|
|
|
|
def test_int_base_limits(self):
|
|
"""Testing the supported limits of the int() base parameter."""
|
|
self.assertEqual(int('0', 5), 0)
|
|
with self.assertRaises(ValueError):
|
|
int('0', 1)
|
|
with self.assertRaises(ValueError):
|
|
int('0', 37)
|
|
with self.assertRaises(ValueError):
|
|
int('0', -909) # An old magic value base from Python 2.
|
|
with self.assertRaises(ValueError):
|
|
int('0', base=0-(2**234))
|
|
with self.assertRaises(ValueError):
|
|
int('0', base=2**234)
|
|
# Bases 2 through 36 are supported.
|
|
for base in range(2,37):
|
|
self.assertEqual(int('0', base=base), 0)
|
|
|
|
def test_int_base_bad_types(self):
|
|
"""Not integer types are not valid bases; issue16772."""
|
|
with self.assertRaises(TypeError):
|
|
int('0', 5.5)
|
|
with self.assertRaises(TypeError):
|
|
int('0', 5.0)
|
|
|
|
def test_int_base_indexable(self):
|
|
class MyIndexable(object):
|
|
def __init__(self, value):
|
|
self.value = value
|
|
def __index__(self):
|
|
return self.value
|
|
|
|
# Check out of range bases.
|
|
for base in 2**100, -2**100, 1, 37:
|
|
with self.assertRaises(ValueError):
|
|
int('43', base)
|
|
|
|
# Check in-range bases.
|
|
self.assertEqual(int('101', base=MyIndexable(2)), 5)
|
|
self.assertEqual(int('101', base=MyIndexable(10)), 101)
|
|
self.assertEqual(int('101', base=MyIndexable(36)), 1 + 36**2)
|
|
|
|
def test_non_numeric_input_types(self):
|
|
# Test possible non-numeric types for the argument x, including
|
|
# subclasses of the explicitly documented accepted types.
|
|
class CustomStr(str): pass
|
|
class CustomBytes(bytes): pass
|
|
class CustomByteArray(bytearray): pass
|
|
|
|
factories = [
|
|
bytes,
|
|
bytearray,
|
|
lambda b: CustomStr(b.decode()),
|
|
CustomBytes,
|
|
CustomByteArray,
|
|
memoryview,
|
|
]
|
|
try:
|
|
from array import array
|
|
except ImportError:
|
|
pass
|
|
else:
|
|
factories.append(lambda b: array('B', b))
|
|
|
|
for f in factories:
|
|
x = f(b'100')
|
|
with self.subTest(type(x)):
|
|
self.assertEqual(int(x), 100)
|
|
if isinstance(x, (str, bytes, bytearray)):
|
|
self.assertEqual(int(x, 2), 4)
|
|
else:
|
|
msg = "can't convert non-string"
|
|
with self.assertRaisesRegex(TypeError, msg):
|
|
int(x, 2)
|
|
with self.assertRaisesRegex(ValueError, 'invalid literal'):
|
|
int(f(b'A' * 0x10))
|
|
|
|
def test_int_memoryview(self):
|
|
self.assertEqual(int(memoryview(b'123')[1:3]), 23)
|
|
self.assertEqual(int(memoryview(b'123\x00')[1:3]), 23)
|
|
self.assertEqual(int(memoryview(b'123 ')[1:3]), 23)
|
|
self.assertEqual(int(memoryview(b'123A')[1:3]), 23)
|
|
self.assertEqual(int(memoryview(b'1234')[1:3]), 23)
|
|
|
|
def test_string_float(self):
|
|
self.assertRaises(ValueError, int, '1.2')
|
|
|
|
def test_intconversion(self):
|
|
# Test __int__()
|
|
class ClassicMissingMethods:
|
|
pass
|
|
self.assertRaises(TypeError, int, ClassicMissingMethods())
|
|
|
|
class MissingMethods(object):
|
|
pass
|
|
self.assertRaises(TypeError, int, MissingMethods())
|
|
|
|
class Foo0:
|
|
def __int__(self):
|
|
return 42
|
|
|
|
self.assertEqual(int(Foo0()), 42)
|
|
|
|
class Classic:
|
|
pass
|
|
for base in (object, Classic):
|
|
class IntOverridesTrunc(base):
|
|
def __int__(self):
|
|
return 42
|
|
def __trunc__(self):
|
|
return -12
|
|
self.assertEqual(int(IntOverridesTrunc()), 42)
|
|
|
|
class JustTrunc(base):
|
|
def __trunc__(self):
|
|
return 42
|
|
with self.assertWarns(DeprecationWarning):
|
|
self.assertEqual(int(JustTrunc()), 42)
|
|
|
|
class ExceptionalTrunc(base):
|
|
def __trunc__(self):
|
|
1 / 0
|
|
with self.assertRaises(ZeroDivisionError), \
|
|
self.assertWarns(DeprecationWarning):
|
|
int(ExceptionalTrunc())
|
|
|
|
for trunc_result_base in (object, Classic):
|
|
class Index(trunc_result_base):
|
|
def __index__(self):
|
|
return 42
|
|
|
|
class TruncReturnsNonInt(base):
|
|
def __trunc__(self):
|
|
return Index()
|
|
with self.assertWarns(DeprecationWarning):
|
|
self.assertEqual(int(TruncReturnsNonInt()), 42)
|
|
|
|
class Intable(trunc_result_base):
|
|
def __int__(self):
|
|
return 42
|
|
|
|
class TruncReturnsNonIndex(base):
|
|
def __trunc__(self):
|
|
return Intable()
|
|
with self.assertWarns(DeprecationWarning):
|
|
self.assertEqual(int(TruncReturnsNonInt()), 42)
|
|
|
|
class NonIntegral(trunc_result_base):
|
|
def __trunc__(self):
|
|
# Check that we avoid infinite recursion.
|
|
return NonIntegral()
|
|
|
|
class TruncReturnsNonIntegral(base):
|
|
def __trunc__(self):
|
|
return NonIntegral()
|
|
try:
|
|
with self.assertWarns(DeprecationWarning):
|
|
int(TruncReturnsNonIntegral())
|
|
except TypeError as e:
|
|
self.assertEqual(str(e),
|
|
"__trunc__ returned non-Integral"
|
|
" (type NonIntegral)")
|
|
else:
|
|
self.fail("Failed to raise TypeError with %s" %
|
|
((base, trunc_result_base),))
|
|
|
|
# Regression test for bugs.python.org/issue16060.
|
|
class BadInt(trunc_result_base):
|
|
def __int__(self):
|
|
return 42.0
|
|
|
|
class TruncReturnsBadInt(base):
|
|
def __trunc__(self):
|
|
return BadInt()
|
|
|
|
with self.assertRaises(TypeError), \
|
|
self.assertWarns(DeprecationWarning):
|
|
int(TruncReturnsBadInt())
|
|
|
|
def test_int_subclass_with_index(self):
|
|
class MyIndex(int):
|
|
def __index__(self):
|
|
return 42
|
|
|
|
class BadIndex(int):
|
|
def __index__(self):
|
|
return 42.0
|
|
|
|
my_int = MyIndex(7)
|
|
self.assertEqual(my_int, 7)
|
|
self.assertEqual(int(my_int), 7)
|
|
|
|
self.assertEqual(int(BadIndex()), 0)
|
|
|
|
def test_int_subclass_with_int(self):
|
|
class MyInt(int):
|
|
def __int__(self):
|
|
return 42
|
|
|
|
class BadInt(int):
|
|
def __int__(self):
|
|
return 42.0
|
|
|
|
my_int = MyInt(7)
|
|
self.assertEqual(my_int, 7)
|
|
self.assertEqual(int(my_int), 42)
|
|
|
|
my_int = BadInt(7)
|
|
self.assertEqual(my_int, 7)
|
|
self.assertRaises(TypeError, int, my_int)
|
|
|
|
def test_int_returns_int_subclass(self):
|
|
class BadIndex:
|
|
def __index__(self):
|
|
return True
|
|
|
|
class BadIndex2(int):
|
|
def __index__(self):
|
|
return True
|
|
|
|
class BadInt:
|
|
def __int__(self):
|
|
return True
|
|
|
|
class BadInt2(int):
|
|
def __int__(self):
|
|
return True
|
|
|
|
class TruncReturnsBadIndex:
|
|
def __trunc__(self):
|
|
return BadIndex()
|
|
|
|
class TruncReturnsBadInt:
|
|
def __trunc__(self):
|
|
return BadInt()
|
|
|
|
class TruncReturnsIntSubclass:
|
|
def __trunc__(self):
|
|
return True
|
|
|
|
bad_int = BadIndex()
|
|
with self.assertWarns(DeprecationWarning):
|
|
n = int(bad_int)
|
|
self.assertEqual(n, 1)
|
|
self.assertIs(type(n), int)
|
|
|
|
bad_int = BadIndex2()
|
|
n = int(bad_int)
|
|
self.assertEqual(n, 0)
|
|
self.assertIs(type(n), int)
|
|
|
|
bad_int = BadInt()
|
|
with self.assertWarns(DeprecationWarning):
|
|
n = int(bad_int)
|
|
self.assertEqual(n, 1)
|
|
self.assertIs(type(n), int)
|
|
|
|
bad_int = BadInt2()
|
|
with self.assertWarns(DeprecationWarning):
|
|
n = int(bad_int)
|
|
self.assertEqual(n, 1)
|
|
self.assertIs(type(n), int)
|
|
|
|
bad_int = TruncReturnsBadIndex()
|
|
with self.assertWarns(DeprecationWarning):
|
|
n = int(bad_int)
|
|
self.assertEqual(n, 1)
|
|
self.assertIs(type(n), int)
|
|
|
|
bad_int = TruncReturnsBadInt()
|
|
with self.assertWarns(DeprecationWarning):
|
|
self.assertRaises(TypeError, int, bad_int)
|
|
|
|
good_int = TruncReturnsIntSubclass()
|
|
with self.assertWarns(DeprecationWarning):
|
|
n = int(good_int)
|
|
self.assertEqual(n, 1)
|
|
self.assertIs(type(n), int)
|
|
with self.assertWarns(DeprecationWarning):
|
|
n = IntSubclass(good_int)
|
|
self.assertEqual(n, 1)
|
|
self.assertIs(type(n), IntSubclass)
|
|
|
|
def test_error_message(self):
|
|
def check(s, base=None):
|
|
with self.assertRaises(ValueError,
|
|
msg="int(%r, %r)" % (s, base)) as cm:
|
|
if base is None:
|
|
int(s)
|
|
else:
|
|
int(s, base)
|
|
self.assertEqual(cm.exception.args[0],
|
|
"invalid literal for int() with base %d: %r" %
|
|
(10 if base is None else base, s))
|
|
|
|
check('\xbd')
|
|
check('123\xbd')
|
|
check(' 123 456 ')
|
|
|
|
check('123\x00')
|
|
# SF bug 1545497: embedded NULs were not detected with explicit base
|
|
check('123\x00', 10)
|
|
check('123\x00 245', 20)
|
|
check('123\x00 245', 16)
|
|
check('123\x00245', 20)
|
|
check('123\x00245', 16)
|
|
# byte string with embedded NUL
|
|
check(b'123\x00')
|
|
check(b'123\x00', 10)
|
|
# non-UTF-8 byte string
|
|
check(b'123\xbd')
|
|
check(b'123\xbd', 10)
|
|
# lone surrogate in Unicode string
|
|
check('123\ud800')
|
|
check('123\ud800', 10)
|
|
|
|
def test_issue31619(self):
|
|
self.assertEqual(int('1_0_1_0_1_0_1_0_1_0_1_0_1_0_1_0_1_0_1_0_1_0_1_0_1_0_1_0_1_0_1', 2),
|
|
0b1010101010101010101010101010101)
|
|
self.assertEqual(int('1_2_3_4_5_6_7_0_1_2_3', 8), 0o12345670123)
|
|
self.assertEqual(int('1_2_3_4_5_6_7_8_9', 16), 0x123456789)
|
|
self.assertEqual(int('1_2_3_4_5_6_7', 32), 1144132807)
|
|
|
|
|
|
class IntStrDigitLimitsTests(unittest.TestCase):
|
|
|
|
int_class = int # Override this in subclasses to reuse the suite.
|
|
|
|
def setUp(self):
|
|
super().setUp()
|
|
self._previous_limit = sys.get_int_max_str_digits()
|
|
sys.set_int_max_str_digits(2048)
|
|
|
|
def tearDown(self):
|
|
sys.set_int_max_str_digits(self._previous_limit)
|
|
super().tearDown()
|
|
|
|
def test_disabled_limit(self):
|
|
self.assertGreater(sys.get_int_max_str_digits(), 0)
|
|
self.assertLess(sys.get_int_max_str_digits(), 20_000)
|
|
with support.adjust_int_max_str_digits(0):
|
|
self.assertEqual(sys.get_int_max_str_digits(), 0)
|
|
i = self.int_class('1' * 20_000)
|
|
str(i)
|
|
self.assertGreater(sys.get_int_max_str_digits(), 0)
|
|
|
|
def test_max_str_digits_edge_cases(self):
|
|
"""Ignore the +/- sign and space padding."""
|
|
int_class = self.int_class
|
|
maxdigits = sys.get_int_max_str_digits()
|
|
|
|
int_class('1' * maxdigits)
|
|
int_class(' ' + '1' * maxdigits)
|
|
int_class('1' * maxdigits + ' ')
|
|
int_class('+' + '1' * maxdigits)
|
|
int_class('-' + '1' * maxdigits)
|
|
self.assertEqual(len(str(10 ** (maxdigits - 1))), maxdigits)
|
|
|
|
def check(self, i, base=None):
|
|
with self.assertRaises(ValueError):
|
|
if base is None:
|
|
self.int_class(i)
|
|
else:
|
|
self.int_class(i, base)
|
|
|
|
def test_max_str_digits(self):
|
|
maxdigits = sys.get_int_max_str_digits()
|
|
|
|
self.check('1' * (maxdigits + 1))
|
|
self.check(' ' + '1' * (maxdigits + 1))
|
|
self.check('1' * (maxdigits + 1) + ' ')
|
|
self.check('+' + '1' * (maxdigits + 1))
|
|
self.check('-' + '1' * (maxdigits + 1))
|
|
self.check('1' * (maxdigits + 1))
|
|
|
|
i = 10 ** maxdigits
|
|
with self.assertRaises(ValueError):
|
|
str(i)
|
|
|
|
def test_power_of_two_bases_unlimited(self):
|
|
"""The limit does not apply to power of 2 bases."""
|
|
maxdigits = sys.get_int_max_str_digits()
|
|
|
|
for base in (2, 4, 8, 16, 32):
|
|
with self.subTest(base=base):
|
|
self.int_class('1' * (maxdigits + 1), base)
|
|
assert maxdigits < 100_000
|
|
self.int_class('1' * 100_000, base)
|
|
|
|
def test_underscores_ignored(self):
|
|
maxdigits = sys.get_int_max_str_digits()
|
|
|
|
triples = maxdigits // 3
|
|
s = '111' * triples
|
|
s_ = '1_11' * triples
|
|
self.int_class(s) # succeeds
|
|
self.int_class(s_) # succeeds
|
|
self.check(f'{s}111')
|
|
self.check(f'{s_}_111')
|
|
|
|
def test_sign_not_counted(self):
|
|
int_class = self.int_class
|
|
max_digits = sys.get_int_max_str_digits()
|
|
s = '5' * max_digits
|
|
i = int_class(s)
|
|
pos_i = int_class(f'+{s}')
|
|
assert i == pos_i
|
|
neg_i = int_class(f'-{s}')
|
|
assert -pos_i == neg_i
|
|
str(pos_i)
|
|
str(neg_i)
|
|
|
|
def _other_base_helper(self, base):
|
|
int_class = self.int_class
|
|
max_digits = sys.get_int_max_str_digits()
|
|
s = '2' * max_digits
|
|
i = int_class(s, base)
|
|
if base > 10:
|
|
with self.assertRaises(ValueError):
|
|
str(i)
|
|
elif base < 10:
|
|
str(i)
|
|
with self.assertRaises(ValueError) as err:
|
|
int_class(f'{s}1', base)
|
|
|
|
def test_int_from_other_bases(self):
|
|
base = 3
|
|
with self.subTest(base=base):
|
|
self._other_base_helper(base)
|
|
base = 36
|
|
with self.subTest(base=base):
|
|
self._other_base_helper(base)
|
|
|
|
|
|
class IntSubclassStrDigitLimitsTests(IntStrDigitLimitsTests):
|
|
int_class = IntSubclass
|
|
|
|
|
|
if __name__ == "__main__":
|
|
unittest.main()
|