diff options
| author | Miss Islington (bot) <31488909+miss-islington@users.noreply.github.com> | 2024-01-10 13:21:50 (GMT) |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-01-10 13:21:50 (GMT) |
| commit | 84677ff19c0ffdc328203cdb25d16053e9c5a910 (patch) | |
| tree | 42aa3119f1ee7c5f165a9391faa7850b7a85cd6f /Lib/test | |
| parent | 082998c3af5bfd163da5c0198cd10acf588a44ba (diff) | |
| download | cpython-84677ff19c0ffdc328203cdb25d16053e9c5a910.zip cpython-84677ff19c0ffdc328203cdb25d16053e9c5a910.tar.gz cpython-84677ff19c0ffdc328203cdb25d16053e9c5a910.tar.bz2 | |
[3.12] gh-113594: Fix UnicodeEncodeError in TokenList.fold() (GH-113730) (GH-113907)
It occurred when try to re-encode an unknown-8bit part combined with non-unknown-8bit part.
(cherry picked from commit e9d5b6ea2d68564f176fdf70c2d7028e060c62b5)
Co-authored-by: Serhiy Storchaka <storchaka@gmail.com>
Diffstat (limited to 'Lib/test')
| -rw-r--r-- | Lib/test/test_email/test__header_value_parser.py | 39 |
1 files changed, 39 insertions, 0 deletions
diff --git a/Lib/test/test_email/test__header_value_parser.py b/Lib/test/test_email/test__header_value_parser.py index 854f2ff..bdb0e55 100644 --- a/Lib/test/test_email/test__header_value_parser.py +++ b/Lib/test/test_email/test__header_value_parser.py @@ -2915,6 +2915,45 @@ class TestFolding(TestEmailBase): "mich. And that's\n" " all I'm sayin.\n") + def test_unicode_after_unknown_not_combined(self): + self._test(parser.get_unstructured("=?unknown-8bit?q?=A4?=\xa4"), + "=?unknown-8bit?q?=A4?==?utf-8?q?=C2=A4?=\n") + prefix = "0123456789 "*5 + self._test(parser.get_unstructured(prefix + "=?unknown-8bit?q?=A4?=\xa4"), + prefix + "=?unknown-8bit?q?=A4?=\n =?utf-8?q?=C2=A4?=\n") + + def test_ascii_after_unknown_not_combined(self): + self._test(parser.get_unstructured("=?unknown-8bit?q?=A4?=abc"), + "=?unknown-8bit?q?=A4?=abc\n") + prefix = "0123456789 "*5 + self._test(parser.get_unstructured(prefix + "=?unknown-8bit?q?=A4?=abc"), + prefix + "=?unknown-8bit?q?=A4?=\n =?utf-8?q?abc?=\n") + + def test_unknown_after_unicode_not_combined(self): + self._test(parser.get_unstructured("\xa4" + "=?unknown-8bit?q?=A4?="), + "=?utf-8?q?=C2=A4?==?unknown-8bit?q?=A4?=\n") + prefix = "0123456789 "*5 + self._test(parser.get_unstructured(prefix + "\xa4=?unknown-8bit?q?=A4?="), + prefix + "=?utf-8?q?=C2=A4?=\n =?unknown-8bit?q?=A4?=\n") + + def test_unknown_after_ascii_not_combined(self): + self._test(parser.get_unstructured("abc" + "=?unknown-8bit?q?=A4?="), + "abc=?unknown-8bit?q?=A4?=\n") + prefix = "0123456789 "*5 + self._test(parser.get_unstructured(prefix + "abcd=?unknown-8bit?q?=A4?="), + prefix + "abcd\n =?unknown-8bit?q?=A4?=\n") + + def test_unknown_after_unknown(self): + self._test(parser.get_unstructured("=?unknown-8bit?q?=C2?=" + "=?unknown-8bit?q?=A4?="), + "=?unknown-8bit?q?=C2=A4?=\n") + prefix = "0123456789 "*5 + self._test(parser.get_unstructured(prefix + "=?unknown-8bit?q?=C2?=" + "=?unknown-8bit?q?=A4?="), + prefix + "=?unknown-8bit?q?=C2?=\n =?unknown-8bit?q?=A4?=\n") + # XXX Need test of an encoded word so long that it needs to be wrapped def test_simple_address(self): |