bpo-24214: Fixed the UTF-8 incremental decoder. (GH-12603) (GH-12627)
The bug occurred when the encoded surrogate character is passed
to the incremental decoder in two chunks.
(cherry picked from commit 7a465cb5ee7e298cae626ace1fc3e7d97df79f2e)
Co-authored-by: Serhiy Storchaka <storchaka@gmail.com>
diff --git a/Lib/test/test_codecs.py b/Lib/test/test_codecs.py
index 293dfbc..5ba2c7b 100644
--- a/Lib/test/test_codecs.py
+++ b/Lib/test/test_codecs.py
@@ -401,6 +401,15 @@
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"