Issue #14850: Now a chamap decoder treates U+FFFE as "undefined mapping"
in any mapping, not only in an unicode string.
diff --git a/Lib/test/test_codecs.py b/Lib/test/test_codecs.py
index acf9f64..1fa9ee0 100644
--- a/Lib/test/test_codecs.py
+++ b/Lib/test/test_codecs.py
@@ -1586,6 +1586,10 @@
codecs.charmap_decode, b"\x00\x01\x02", "strict", "ab"
)
+ self.assertRaises(UnicodeDecodeError,
+ codecs.charmap_decode, b"\x00\x01\x02", "strict", "ab\ufffe"
+ )
+
self.assertEqual(
codecs.charmap_decode(b"\x00\x01\x02", "replace", "ab"),
("ab\ufffd", 3)
@@ -1642,6 +1646,17 @@
{0: 'a', 1: 'b'}
)
+ self.assertRaises(UnicodeDecodeError,
+ codecs.charmap_decode, b"\x00\x01\x02", "strict",
+ {0: 'a', 1: 'b', 2: None}
+ )
+
+ # Issue #14850
+ self.assertRaises(UnicodeDecodeError,
+ codecs.charmap_decode, b"\x00\x01\x02", "strict",
+ {0: 'a', 1: 'b', 2: '\ufffe'}
+ )
+
self.assertEqual(
codecs.charmap_decode(b"\x00\x01\x02", "replace",
{0: 'a', 1: 'b'}),
@@ -1654,6 +1669,13 @@
("ab\ufffd", 3)
)
+ # Issue #14850
+ self.assertEqual(
+ codecs.charmap_decode(b"\x00\x01\x02", "replace",
+ {0: 'a', 1: 'b', 2: '\ufffe'}),
+ ("ab\ufffd", 3)
+ )
+
self.assertEqual(
codecs.charmap_decode(b"\x00\x01\x02", "ignore",
{0: 'a', 1: 'b'}),
@@ -1666,6 +1688,13 @@
("ab", 3)
)
+ # Issue #14850
+ self.assertEqual(
+ codecs.charmap_decode(b"\x00\x01\x02", "ignore",
+ {0: 'a', 1: 'b', 2: '\ufffe'}),
+ ("ab", 3)
+ )
+
allbytes = bytes(range(256))
self.assertEqual(
codecs.charmap_decode(allbytes, "ignore", {}),
@@ -1700,6 +1729,11 @@
{0: a, 1: b},
)
+ self.assertRaises(UnicodeDecodeError,
+ codecs.charmap_decode, b"\x00\x01\x02", "strict",
+ {0: a, 1: b, 2: 0xFFFE},
+ )
+
self.assertEqual(
codecs.charmap_decode(b"\x00\x01\x02", "replace",
{0: a, 1: b}),
@@ -1707,11 +1741,23 @@
)
self.assertEqual(
+ codecs.charmap_decode(b"\x00\x01\x02", "replace",
+ {0: a, 1: b, 2: 0xFFFE}),
+ ("ab\ufffd", 3)
+ )
+
+ self.assertEqual(
codecs.charmap_decode(b"\x00\x01\x02", "ignore",
{0: a, 1: b}),
("ab", 3)
)
+ self.assertEqual(
+ codecs.charmap_decode(b"\x00\x01\x02", "ignore",
+ {0: a, 1: b, 2: 0xFFFE}),
+ ("ab", 3)
+ )
+
class WithStmtTest(unittest.TestCase):
def test_encodedfile(self):