[3.10] bpo-45467: Fix IncrementalDecoder and StreamReader in the "raw-unicode-escape" codec (GH-28944) (GH-28952)
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.
(cherry picked from commit 39aa98346d5dd8ac591a7cafb467af21c53f1e5d)
Co-authored-by: Serhiy Storchaka <storchaka@gmail.com>
diff --git a/Lib/test/test_codecs.py b/Lib/test/test_codecs.py
index 153912b..f7310fb 100644
--- a/Lib/test/test_codecs.py
+++ b/Lib/test/test_codecs.py
@@ -2471,7 +2471,11 @@ def test_partial(self):
]
)
-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))
@@ -2520,6 +2524,35 @@ def test_decode_errors(self):
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):