bpo-45467: Fix IncrementalDecoder and StreamReader in the "raw-unicode-escape" codec (GH-28944)

They support now splitting escape sequences between input chunks.

Add the third parameter "final" in codecs.raw_unicode_escape_decode().
It is True by default to match the former behavior.
This commit is contained in:
Serhiy Storchaka 2021-10-14 20:04:19 +03:00 committed by GitHub
parent d413c50363
commit 39aa98346d
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
7 changed files with 116 additions and 35 deletions

View file

@ -2483,7 +2483,11 @@ class UnicodeEscapeTest(ReadTest, unittest.TestCase):
]
)
class RawUnicodeEscapeTest(unittest.TestCase):
class RawUnicodeEscapeTest(ReadTest, unittest.TestCase):
encoding = "raw-unicode-escape"
test_lone_surrogates = None
def test_empty(self):
self.assertEqual(codecs.raw_unicode_escape_encode(""), (b"", 0))
self.assertEqual(codecs.raw_unicode_escape_decode(b""), ("", 0))
@ -2532,6 +2536,35 @@ class RawUnicodeEscapeTest(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\t',
'\x00\t\n',
'\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 EscapeEncodeTest(unittest.TestCase):