def test_badandgoodnamereplaceexceptions(self):
# "namereplace" complains about a non-exception passed in
self.assertRaises(TypeError, codecs.namereplace_errors, 42)
# "namereplace" complains about the wrong exception types
self.assertRaises(TypeError, codecs.namereplace_errors,
UnicodeError("ouch"))
# "namereplace" can only be used for encoding
self.assertRaises(
TypeError, codecs.namereplace_errors,
UnicodeDecodeError("ascii", bytearray(b"\xff"), 0, 1, "ouch"))
self.assertRaises(TypeError, codecs.namereplace_errors,
UnicodeTranslateError("\u3042", 0, 1, "ouch"))
# Use the correct exception
tests = [
("\u3042", "\\N{HIRAGANA LETTER A}"),
("\x00", "\\x00"),
("\ufbf9", "\\N{ARABIC LIGATURE UIGHUR KIRGHIZ YEH WITH "
"HAMZA ABOVE WITH ALEF MAKSURA ISOLATED FORM}"),
("\U000e007f", "\\N{CANCEL TAG}"),
("\U0010ffff", "\\U0010ffff"),
# Lone surrogates
("\ud800", "\\ud800"),
("\udfff", "\\udfff"),
("\ud800\udfff", "\\ud800\\udfff"),
]
for s, r in tests:
with self.subTest(str=s):
self.assertEqual(
codecs.namereplace_errors(
UnicodeEncodeError("ascii", "a" + s + "b", 1,
1 + len(s), "ouch")),
(r, 1 + len(s)))
def copyerrors(err):
(escaped, end) = codecs.namereplace_errors(err)
badData = b''
while escaped:
if not is_escape_sequence(escaped[0:6]):
raise err
badData += bytes.fromhex(escaped[2:6])
escaped = escaped[6:]
return (badData, end)
def test_badandgoodnamereplaceexceptions(self):
# "namereplace" complains about a non-exception passed in
self.assertRaises(
TypeError,
codecs.namereplace_errors,
42
)
# "namereplace" complains about the wrong exception types
self.assertRaises(
TypeError,
codecs.namereplace_errors,
UnicodeError("ouch")
)
# "namereplace" can only be used for encoding
self.assertRaises(
TypeError,
codecs.namereplace_errors,
UnicodeDecodeError("ascii", bytearray(b"\xff"), 0, 1, "ouch")
)
self.assertRaises(
TypeError,
codecs.namereplace_errors,
UnicodeTranslateError("\u3042", 0, 1, "ouch")
)
# Use the correct exception
tests = [
("\u3042", "\\N{HIRAGANA LETTER A}"),
("\x00", "\\x00"),
("\ufbf9", "\\N{ARABIC LIGATURE UIGHUR KIRGHIZ YEH WITH "
"HAMZA ABOVE WITH ALEF MAKSURA ISOLATED FORM}"),
("\U000e007f", "\\N{CANCEL TAG}"),
("\U0010ffff", "\\U0010ffff"),
# Lone surrogates
("\ud800", "\\ud800"),
("\udfff", "\\udfff"),
("\ud800\udfff", "\\ud800\\udfff"),
]
for s, r in tests:
with self.subTest(str=s):
self.assertEqual(
codecs.namereplace_errors(
UnicodeEncodeError("ascii", "a" + s + "b",
1, 1 + len(s), "ouch")),
(r, 1 + len(s))
)
def test_badandgoodnamereplaceexceptions(self):
# "namereplace" complains about a non-exception passed in
self.assertRaises(
TypeError,
codecs.namereplace_errors,
42
)
# "namereplace" complains about the wrong exception types
self.assertRaises(
TypeError,
codecs.namereplace_errors,
UnicodeError("ouch")
)
# "namereplace" can only be used for encoding
self.assertRaises(
TypeError,
codecs.namereplace_errors,
UnicodeDecodeError("ascii", bytearray(b"\xff"), 0, 1, "ouch")
)
self.assertRaises(
TypeError,
codecs.namereplace_errors,
UnicodeTranslateError("\u3042", 0, 1, "ouch")
)
# Use the correct exception
self.assertEqual(
codecs.namereplace_errors(
UnicodeEncodeError("ascii", "\u3042", 0, 1, "ouch")),
("\\N{HIRAGANA LETTER A}", 1)
)
self.assertEqual(
codecs.namereplace_errors(
UnicodeEncodeError("ascii", "\x00", 0, 1, "ouch")),
("\\x00", 1)
)
self.assertEqual(
codecs.namereplace_errors(
UnicodeEncodeError("ascii", "\xff", 0, 1, "ouch")),
("\\N{LATIN SMALL LETTER Y WITH DIAERESIS}", 1)
)
self.assertEqual(
codecs.namereplace_errors(
UnicodeEncodeError("ascii", "\u0100", 0, 1, "ouch")),
("\\N{LATIN CAPITAL LETTER A WITH MACRON}", 1)
)
self.assertEqual(
codecs.namereplace_errors(
UnicodeEncodeError("ascii", "\uffff", 0, 1, "ouch")),
("\\uffff", 1)
)
if SIZEOF_WCHAR_T > 0:
self.assertEqual(
codecs.namereplace_errors(
UnicodeEncodeError("ascii", "\U00010000",
0, 1, "ouch")),
("\\N{LINEAR B SYLLABLE B008 A}", 1)
)
self.assertEqual(
codecs.namereplace_errors(
UnicodeEncodeError("ascii", "\U0010ffff",
0, 1, "ouch")),
("\\U0010ffff", 1)
)
# Lone surrogates (regardless of unicode width)
self.assertEqual(
codecs.namereplace_errors(
UnicodeEncodeError("ascii", "\ud800", 0, 1, "ouch")),
("\\ud800", 1)
)
self.assertEqual(
codecs.namereplace_errors(
UnicodeEncodeError("ascii", "\udfff", 0, 1, "ouch")),
("\\udfff", 1)
)
