diff options
author | Miss Islington (bot) <31488909+miss-islington@users.noreply.github.com> | 2022-10-08 00:09:53 (GMT) |
---|---|---|
committer | GitHub <noreply@github.com> | 2022-10-08 00:09:53 (GMT) |
commit | 46aa5d2c2dc60da50291dfdfc00126b14cd92676 (patch) | |
tree | 74c8f8166c710e6dc32a124dce80e95cae70b4a2 /Lib/test/test_unicode.py | |
parent | c2f21af42a50b36e0ef2fce9caaf3a36e946431c (diff) | |
download | cpython-46aa5d2c2dc60da50291dfdfc00126b14cd92676.zip cpython-46aa5d2c2dc60da50291dfdfc00126b14cd92676.tar.gz cpython-46aa5d2c2dc60da50291dfdfc00126b14cd92676.tar.bz2 |
[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 72c166add89a0cd992d66f75ce94eee5eb675a99)
Diffstat (limited to 'Lib/test/test_unicode.py')
-rw-r--r-- | Lib/test/test_unicode.py | 19 |
1 files changed, 19 insertions, 0 deletions
diff --git a/Lib/test/test_unicode.py b/Lib/test/test_unicode.py index 90bd75f..9b0e4b2 100644 --- a/Lib/test/test_unicode.py +++ b/Lib/test/test_unicode.py @@ -2809,6 +2809,25 @@ 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]{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' |