bpo-24214: Fixed the UTF-8 incremental decoder. (GH-12603)

The bug occurred when the encoded surrogate character is passed
to the incremental decoder in two chunks.
This commit is contained in:
Serhiy Storchaka 2019-03-30 08:23:38 +02:00 committed by GitHub
parent 38f4e468d4
commit 7a465cb5ee
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
3 changed files with 14 additions and 0 deletions

View file

@ -406,6 +406,15 @@ class ReadTest(MixInCheckStateHandling):
self.assertEqual(test_sequence.decode(self.encoding, "backslashreplace"),
before + backslashreplace + after)
def test_incremental_surrogatepass(self):
# Test incremental decoder for surrogatepass handler:
# see issue #24214
data = '\uD901'.encode(self.encoding, 'surrogatepass')
for i in range(1, len(data)):
dec = codecs.getincrementaldecoder(self.encoding)('surrogatepass')
self.assertEqual(dec.decode(data[:i]), '')
self.assertEqual(dec.decode(data[i:], True), '\uD901')
class UTF32Test(ReadTest, unittest.TestCase):
encoding = "utf-32"