Issue #14850: Now a chamap decoder treates U+FFFE as "undefined mapping"

in any mapping, not only in an unicode string.
This commit is contained in:
Serhiy Storchaka 2013-01-15 15:30:04 +02:00
commit 55e2cb497b
3 changed files with 82 additions and 19 deletions

View file

@ -1737,6 +1737,10 @@ class CharmapTest(unittest.TestCase):
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)
@ -1793,6 +1797,17 @@ class CharmapTest(unittest.TestCase):
{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'}),
@ -1805,6 +1820,13 @@ class CharmapTest(unittest.TestCase):
("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'}),
@ -1817,6 +1839,13 @@ class CharmapTest(unittest.TestCase):
("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", {}),
@ -1857,18 +1886,35 @@ class CharmapTest(unittest.TestCase):
{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}),
("ab\ufffd", 3)
)
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):