bpo-39337: encodings.normalize_encoding() now ignores non-ASCII characters (GH-22219)
diff --git a/Lib/test/test_codecs.py b/Lib/test/test_codecs.py
index ddf4e08..09ceef7 100644
--- a/Lib/test/test_codecs.py
+++ b/Lib/test/test_codecs.py
@@ -3417,7 +3417,7 @@
class CodecNameNormalizationTest(unittest.TestCase):
"""Test codec name normalization"""
- def test_normalized_encoding(self):
+ def test_codecs_lookup(self):
FOUND = (1, 2, 3, 4)
NOT_FOUND = (None, None, None, None)
def search_function(encoding):
@@ -3439,6 +3439,18 @@
self.assertEqual(NOT_FOUND, codecs.lookup('BBB.8'))
self.assertEqual(NOT_FOUND, codecs.lookup('a\xe9\u20ac-8'))
+ def test_encodings_normalize_encoding(self):
+ # encodings.normalize_encoding() ignores non-ASCII characters.
+ normalize = encodings.normalize_encoding
+ self.assertEqual(normalize('utf_8'), 'utf_8')
+ self.assertEqual(normalize('utf\xE9\u20AC\U0010ffff-8'), 'utf_8')
+ self.assertEqual(normalize('utf 8'), 'utf_8')
+ # encodings.normalize_encoding() doesn't convert
+ # characters to lower case.
+ self.assertEqual(normalize('UTF 8'), 'UTF_8')
+ self.assertEqual(normalize('utf.8'), 'utf.8')
+ self.assertEqual(normalize('utf...8'), 'utf...8')
+
if __name__ == "__main__":
unittest.main()