Normalize the encoding names for Latin-1 and UTF-8 to
'latin-1' and 'utf-8'.
These are optimized in the Python Unicode implementation
to result in more direct processing, bypassing the codec
registry.
Also see issue11303.
diff --git a/Lib/test/test_codecs.py b/Lib/test/test_codecs.py
index d560d7a..67a5aed 100644
--- a/Lib/test/test_codecs.py
+++ b/Lib/test/test_codecs.py
@@ -1250,7 +1250,7 @@
self.assertEqual(ef.read(), b'\\\xd5\n\x00\x00\xae')
f = io.BytesIO()
- ef = codecs.EncodedFile(f, 'utf-8', 'latin1')
+ ef = codecs.EncodedFile(f, 'utf-8', 'latin-1')
ef.write(b'\xc3\xbc')
self.assertEqual(f.getvalue(), b'\xfc')
@@ -1611,7 +1611,7 @@
def test_latin1(self):
# Issue6373
- self.assertEqual("\udce4\udceb\udcef\udcf6\udcfc".encode("latin1", "surrogateescape"),
+ self.assertEqual("\udce4\udceb\udcef\udcf6\udcfc".encode("latin-1", "surrogateescape"),
b"\xe4\xeb\xef\xf6\xfc")