gh-94808: Cover `%p` in `PyUnicode_FromFormat` (#96677)

Co-authored-by: Jelle Zijlstra <jelle.zijlstra@gmail.com>
This commit is contained in:
Nikita Sobolev 2022-10-07 19:53:42 +03:00 committed by GitHub
parent be4099e55d
commit 72c166add8
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 19 additions and 0 deletions

View File

@ -2807,6 +2807,25 @@ class CAPITest(unittest.TestCase):
check_format('repr=abc',
b'repr=%V', 'abc', b'xyz')
# test %p
# We cannot test the exact result,
# because it returns a hex representation of a C pointer,
# which is going to be different each time. But, we can test the format.
p_format_regex = r'^0x[a-zA-Z0-9]{8,}$'
p_format1 = PyUnicode_FromFormat(b'%p', 'abc')
self.assertIsInstance(p_format1, str)
self.assertRegex(p_format1, p_format_regex)
p_format2 = PyUnicode_FromFormat(b'%p %p', '123456', b'xyz')
self.assertIsInstance(p_format2, str)
self.assertRegex(p_format2,
r'0x[a-zA-Z0-9]{8,} 0x[a-zA-Z0-9]{8,}')
# Extra args are ignored:
p_format3 = PyUnicode_FromFormat(b'%p', '123456', None, b'xyz')
self.assertIsInstance(p_format3, str)
self.assertRegex(p_format3, p_format_regex)
# Test string decode from parameter of %s using utf-8.
# b'\xe4\xba\xba\xe6\xb0\x91' is utf-8 encoded byte sequence of
# '\u4eba\u6c11'