[3.11] gh-94808: Cover %p in PyUnicode_FromFormat (GH-96677) (#98033)

Co-authored-by: Nikita Sobolev <mail@sobolevn.me>
Co-authored-by: Jelle Zijlstra <jelle.zijlstra@gmail.com>

(cherry picked from commit 72c166add8)
This commit is contained in:
Miss Islington (bot) 2022-10-07 17:09:53 -07:00 committed by GitHub
parent c2f21af42a
commit 46aa5d2c2d
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23

View file

@ -2809,6 +2809,25 @@ def check_format(expected, format, *args):
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]{3,}$'
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]{3,} 0x[a-zA-Z0-9]{3,}')
# 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'