diff options
| author | Serhiy Storchaka <storchaka@gmail.com> | 2021-10-14 20:03:29 +0300 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2021-10-14 20:03:29 +0300 |
| commit | 7c722e32bf582108680f49983cf01eaed710ddb9 (patch) | |
| tree | 13d1aeebf59adeadf1809387ec22f966df6e260b /Lib/test/test_codecs.py | |
| parent | 38fadbc5b9fce409af4f40a093575535709a9bb0 (diff) | |
| download | cpython-git-7c722e32bf582108680f49983cf01eaed710ddb9.tar.gz | |
[3.9] bpo-45461: Fix IncrementalDecoder and StreamReader in the "unicode-escape" codec (GH-28939) (GH-28945)
They support now splitting escape sequences between input chunks.
Add the third parameter "final" in codecs.unicode_escape_decode().
It is True by default to match the former behavior.
(cherry picked from commit c96d1546b11b4c282a7e21737cb1f5d16349656d)
Co-authored-by: Serhiy Storchaka <storchaka@gmail.com>
Diffstat (limited to 'Lib/test/test_codecs.py')
| -rw-r--r-- | Lib/test/test_codecs.py | 44 |
1 files changed, 43 insertions, 1 deletions
diff --git a/Lib/test/test_codecs.py b/Lib/test/test_codecs.py index 8d112a171d..09ab852b39 100644 --- a/Lib/test/test_codecs.py +++ b/Lib/test/test_codecs.py @@ -2327,7 +2327,11 @@ class TypesTest(unittest.TestCase): (r"\x5c\x55\x30\x30\x31\x31\x30\x30\x30\x30", 10)) -class UnicodeEscapeTest(unittest.TestCase): +class UnicodeEscapeTest(ReadTest, unittest.TestCase): + encoding = "unicode-escape" + + test_lone_surrogates = None + def test_empty(self): self.assertEqual(codecs.unicode_escape_encode(""), (b"", 0)) self.assertEqual(codecs.unicode_escape_decode(b""), ("", 0)) @@ -2414,6 +2418,44 @@ class UnicodeEscapeTest(unittest.TestCase): self.assertEqual(decode(br"\U00110000", "ignore"), ("", 10)) self.assertEqual(decode(br"\U00110000", "replace"), ("\ufffd", 10)) + def test_partial(self): + self.check_partial( + "\x00\t\n\r\\\xff\uffff\U00010000", + [ + '', + '', + '', + '\x00', + '\x00', + '\x00\t', + '\x00\t', + '\x00\t\n', + '\x00\t\n', + '\x00\t\n\r', + '\x00\t\n\r', + '\x00\t\n\r\\', + '\x00\t\n\r\\', + '\x00\t\n\r\\', + '\x00\t\n\r\\', + '\x00\t\n\r\\\xff', + '\x00\t\n\r\\\xff', + '\x00\t\n\r\\\xff', + '\x00\t\n\r\\\xff', + '\x00\t\n\r\\\xff', + '\x00\t\n\r\\\xff', + '\x00\t\n\r\\\xff\uffff', + '\x00\t\n\r\\\xff\uffff', + '\x00\t\n\r\\\xff\uffff', + '\x00\t\n\r\\\xff\uffff', + '\x00\t\n\r\\\xff\uffff', + '\x00\t\n\r\\\xff\uffff', + '\x00\t\n\r\\\xff\uffff', + '\x00\t\n\r\\\xff\uffff', + '\x00\t\n\r\\\xff\uffff', + '\x00\t\n\r\\\xff\uffff', + '\x00\t\n\r\\\xff\uffff\U00010000', + ] + ) class RawUnicodeEscapeTest(unittest.TestCase): def test_empty(self): |