diff options
author | Serhiy Storchaka <storchaka@gmail.com> | 2015-12-03 01:04:37 +0200 |
---|---|---|
committer | Serhiy Storchaka <storchaka@gmail.com> | 2015-12-03 01:04:37 +0200 |
commit | 4e41a9e6be13d6bc7f74ac406636826a26178151 (patch) | |
tree | 42330fb7b62913cd4bfe1d30949acc64c3aa7f11 /Lib/test/test_unicode.py | |
parent | fcd2a6abf32b35f54b47f69b674aaf20e9e8dc1d (diff) | |
parent | 780433327f85f13c380ae42a27a9cbf390c1a5d7 (diff) | |
download | cpython-4e41a9e6be13d6bc7f74ac406636826a26178151.tar.gz |
Issue #25709: Fixed problem with in-place string concatenation and utf-8 cache.
Diffstat (limited to 'Lib/test/test_unicode.py')
-rw-r--r-- | Lib/test/test_unicode.py | 17 |
1 files changed, 17 insertions, 0 deletions
diff --git a/Lib/test/test_unicode.py b/Lib/test/test_unicode.py index ce8df40d16..fac8b7b602 100644 --- a/Lib/test/test_unicode.py +++ b/Lib/test/test_unicode.py @@ -2702,6 +2702,23 @@ class UnicodeTest(string_tests.CommonTest, self.assertTrue(astral >= bmp2) self.assertFalse(astral >= astral2) + @support.cpython_only + def test_pep393_utf8_caching_bug(self): + # Issue #25709: Problem with string concatenation and utf-8 cache + from _testcapi import getargs_s_hash + for k in 0x24, 0xa4, 0x20ac, 0x1f40d: + s = '' + for i in range(5): + # Due to CPython specific optimization the 's' string can be + # resized in-place. + s += chr(k) + # Parsing with the "s#" format code calls indirectly + # PyUnicode_AsUTF8AndSize() which creates the UTF-8 + # encoded string cached in the Unicode object. + self.assertEqual(getargs_s_hash(s), chr(k).encode() * (i + 1)) + # Check that the second call returns the same result + self.assertEqual(getargs_s_hash(s), chr(k).encode() * (i + 1)) + class StringModuleTest(unittest.TestCase): def test_formatter_parser(self): |