class Test_HZ(multibytecodec_support.TestBase, unittest.TestCase):
encoding = 'hz'
tstring = multibytecodec_support.load_teststring('hz')
codectests = (
# test '~\n' (3 lines)
(b'This sentence is in ASCII.\n'
b'The next sentence is in GB.~{<:Ky2;S{#,~}~\n'
b'~{NpJ)l6HK!#~}Bye.\n', 'strict', 'This sentence is in ASCII.\n'
'The next sentence is in GB.'
'\u5df1\u6240\u4e0d\u6b32\uff0c\u52ff\u65bd\u65bc\u4eba\u3002'
'Bye.\n'),
# test '~\n' (4 lines)
(b'This sentence is in ASCII.\n'
b'The next sentence is in GB.~\n'
b'~{<:Ky2;S{#,NpJ)l6HK!#~}~\n'
b'Bye.\n', 'strict', 'This sentence is in ASCII.\n'
'The next sentence is in GB.'
'\u5df1\u6240\u4e0d\u6b32\uff0c\u52ff\u65bd\u65bc\u4eba\u3002'
'Bye.\n'),
# invalid bytes
(b'ab~cd', 'replace', 'ab\uFFFDcd'),
(b'ab\xffcd', 'replace', 'ab\uFFFDcd'),
(b'ab~{\x81\x81\x41\x44~}cd', 'replace', 'ab\uFFFD\uFFFD\u804Acd'),
(b'ab~{\x41\x44~}cd', 'replace', 'ab\u804Acd'),
(b"ab~{\x79\x79\x41\x44~}cd", "replace", "ab\ufffd\ufffd\u804acd"),
# issue 30003
('ab~cd', 'strict', b'ab~~cd'), # escape ~
(b'~{Dc~~:C~}', 'strict', None), # ~~ only in ASCII mode
(b'~{Dc~\n:C~}', 'strict', None), # ~\n only in ASCII mode
)
class Test_SJIS_COMPAT(multibytecodec_support.TestBase, unittest.TestCase):
encoding = 'shift_jis'
tstring = multibytecodec_support.load_teststring('shift_jis')
codectests = shiftjis_commonenctests + (
("\\\x7e", "strict", u"\\\x7e"),
("\x81\x5f\x81\x61\x81\x7c", "strict", u"\uff3c\u2016\u2212"),
)
class Test_GB2312(multibytecodec_support.TestBase, unittest.TestCase):
encoding = 'gb2312'
tstring = multibytecodec_support.load_teststring('gb2312')
codectests = (b'abc\x81\x81\xc1\xc4', 'strict', None), (b'abc\xc8',
'strict', None), (b'abc\x81\x81\xc1\xc4', 'replace', 'abc��聊'), (
b'abc\x81\x81\xc1\xc4\xc8', 'replace', 'abc��聊�'), (
b'abc\x81\x81\xc1\xc4', 'ignore', 'abc聊'), (b'\xc1d', 'strict', None)
class Test_EUC_JP_COMPAT(multibytecodec_support.TestBase, unittest.TestCase):
encoding = 'euc_jp'
tstring = multibytecodec_support.load_teststring('euc_jp')
codectests = euc_commontests + (
("\xa5", "strict", b"\x5c"),
("\u203e", "strict", b"\x7e"),
)
class Test_CP949(multibytecodec_support.TestBase, unittest.TestCase):
encoding = 'cp949'
tstring = multibytecodec_support.load_teststring('cp949')
codectests = (b'abc\x80\x80\xc1\xc4', 'strict', None), (b'abc\xc8',
'strict', None), (b'abc\x80\x80\xc1\xc4', 'replace', 'abc��좔'), (
b'abc\x80\x80\xc1\xc4\xc8', 'replace', 'abc��좔�'), (
b'abc\x80\x80\xc1\xc4', 'ignore', 'abc좔')
class Test_EUCKR(multibytecodec_support.TestBase, unittest.TestCase):
encoding = 'euc_kr'
tstring = multibytecodec_support.load_teststring('euc_kr')
codectests = (
# invalid bytes
(b"abc\x80\x80\xc1\xc4", "strict", None),
(b"abc\xc8", "strict", None),
(b"abc\x80\x80\xc1\xc4", "replace", 'abc\ufffd\ufffd\uc894'),
(b"abc\x80\x80\xc1\xc4\xc8", "replace", "abc\ufffd\ufffd\uc894\ufffd"),
(b"abc\x80\x80\xc1\xc4", "ignore", "abc\uc894"),
# composed make-up sequence errors
(b"\xa4\xd4", "strict", None),
(b"\xa4\xd4\xa4", "strict", None),
(b"\xa4\xd4\xa4\xb6", "strict", None),
(b"\xa4\xd4\xa4\xb6\xa4", "strict", None),
(b"\xa4\xd4\xa4\xb6\xa4\xd0", "strict", None),
(b"\xa4\xd4\xa4\xb6\xa4\xd0\xa4", "strict", None),
(b"\xa4\xd4\xa4\xb6\xa4\xd0\xa4\xd4", "strict", "\uc4d4"),
(b"\xa4\xd4\xa4\xb6\xa4\xd0\xa4\xd4x", "strict", "\uc4d4x"),
(b"a\xa4\xd4\xa4\xb6\xa4", "replace", 'a\ufffd'),
(b"\xa4\xd4\xa3\xb6\xa4\xd0\xa4\xd4", "strict", None),
(b"\xa4\xd4\xa4\xb6\xa3\xd0\xa4\xd4", "strict", None),
(b"\xa4\xd4\xa4\xb6\xa4\xd0\xa3\xd4", "strict", None),
(b"\xa4\xd4\xa4\xff\xa4\xd0\xa4\xd4", "replace",
'\ufffd\u6e21\ufffd\u3160\ufffd'),
(b"\xa4\xd4\xa4\xb6\xa4\xff\xa4\xd4", "replace",
'\ufffd\u6e21\ub544\ufffd\ufffd'),
(b"\xa4\xd4\xa4\xb6\xa4\xd0\xa4\xff", "replace",
'\ufffd\u6e21\ub544\u572d\ufffd'),
(b"\xa4\xd4\xff\xa4\xd4\xa4\xb6\xa4\xd0\xa4\xd4", "replace",
'\ufffd\ufffd\ufffd\uc4d4'),
(b"\xc1\xc4", "strict", "\uc894"),
)
class Test_SJISX0213(multibytecodec_support.TestBase, unittest.TestCase):
encoding = 'shift_jisx0213'
tstring = multibytecodec_support.load_teststring('shift_jisx0213')
codectests = shiftjis_commonenctests + (
(b'abc\x80\x80\x82\x84', 'replace', 'abc��ｄ'),
(b'abc\x80\x80\x82\x84\x88', 'replace', 'abc��ｄ�'),
(b'\\~', 'replace', '¥‾'), (b'\x81_\x81a\x81|', 'replace', '\\‖−'))
xmlcharnametest = '«ℜ» = 〈ሴ〉', b'\x85Gℜ\x85Q = ⟨ሴ⟩'
class Test_Big5HKSCS(multibytecodec_support.TestBase, unittest.TestCase):
encoding = 'big5hkscs'
tstring = multibytecodec_support.load_teststring('big5hkscs')
codectests = (b'abc\x80\x80\xc1\xc4', 'strict', None), (
b'abc\xc8', 'strict',
None), (b'abc\x80\x80\xc1\xc4', 'replace',
'abc��謐'), (b'abc\x80\x80\xc1\xc4\xc8', 'replace',
'abc��謐�'), (b'abc\x80\x80\xc1\xc4', 'ignore',
'abc謐')
class Test_ISO2022_KR(multibytecodec_support.TestBase, unittest.TestCase):
encoding = 'iso2022_kr'
tstring = multibytecodec_support.load_teststring('iso2022_kr')
codectests = COMMON_CODEC_TESTS + ((b'ab\x1bNdef', 'replace',
'ab\x1bNdef'),)
@unittest.skip('iso2022_kr.txt cannot be used to test "chunk coding"')
def test_chunkcoding(self):
pass
class Test_JOHAB(multibytecodec_support.TestBase, unittest.TestCase):
encoding = 'johab'
tstring = multibytecodec_support.load_teststring('johab')
codectests = (b'abc\x80\x80\xc1\xc4', 'strict', None), (b'abc\xc8',
'strict', None), (b'abc\x80\x80\xc1\xc4', 'replace', 'abc��촧'), (
b'abc\x80\x80\xc1\xc4\xc8', 'replace', 'abc��촧�'), (
b'abc\x80\x80\xc1\xc4', 'ignore', 'abc촧'), (b'\xd8abc', 'replace',
'�abc'), (b'\xd8\xffabc', 'replace', '��abc'), (b'\x84bxy',
'replace', '�bxy'), (b'\x8cBxy', 'replace', '�Bxy')
class Test_SJIS_COMPAT(multibytecodec_support.TestBase, unittest.TestCase):
encoding = 'shift_jis'
tstring = multibytecodec_support.load_teststring('shift_jis')
codectests = shiftjis_commonenctests + (
(b'abc\x80\x80\x82\x84', 'replace', 'abc��ｄ'),
(b'abc\x80\x80\x82\x84\x88', 'replace', 'abc��ｄ�'),
(b'\\~', 'strict', '\\~'), (b'\x81_\x81a\x81|', 'strict', '＼‖−'),
(b'abc\x819', 'replace', 'abc�9'),
(b'abc\xea\xfc', 'replace', 'abc��'),
(b'abc\xffX', 'replace', 'abc�X'))
class Test_JOHAB(multibytecodec_support.TestBase, unittest.TestCase):
encoding = 'johab'
tstring = multibytecodec_support.load_teststring('johab')
codectests = (
# invalid bytes
("abc\x80\x80\xc1\xc4", "strict", None),
("abc\xc8", "strict", None),
("abc\x80\x80\xc1\xc4", "replace", u"abc\ufffd\ucd27"),
("abc\x80\x80\xc1\xc4\xc8", "replace", u"abc\ufffd\ucd27\ufffd"),
("abc\x80\x80\xc1\xc4", "ignore", u"abc\ucd27"),
)
class Test_SJIS_2004(multibytecodec_support.TestBase, unittest.TestCase):
encoding = 'shift_jis_2004'
tstring = multibytecodec_support.load_teststring('shift_jis')
codectests = shiftjis_commonenctests + (
(b'\\~', 'strict', '¥‾'), (b'\x81_\x81a\x81|', 'strict', '\\‖−'),
(b'abc\xea\xfc', 'strict', 'abc撿'), (b'\x819xy', 'replace', '�9xy'),
(b'\xffXxy', 'replace', '�Xxy'),
(b'\x80\x80\x82\x84xy', 'replace', '��ｄxy'),
(b'\x80\x80\x82\x84\x88xy', 'replace', '��ｄ塤y'),
(b'\xfc\xfbxy', 'replace', '�閴y'))
xmlcharnametest = '«ℜ» = 〈ሴ〉', b'\x85Gℜ\x85Q = ⟨ሴ⟩'
class Test_ISO2022_KR(multibytecodec_support.TestBase, unittest.TestCase):
encoding = 'iso2022_kr'
tstring = multibytecodec_support.load_teststring('iso2022_kr')
codectests = COMMON_CODEC_TESTS + (
(b'ab\x1BNdef', 'replace', 'ab\x1BNdef'), )
# iso2022_kr.txt cannot be used to test "chunk coding": the escape
# sequence is only written on the first line
@unittest.skip('iso2022_kr.txt cannot be used to test "chunk coding"')
def test_chunkcoding(self):
pass
class Test_CP949(multibytecodec_support.TestBase, unittest.TestCase):
encoding = 'cp949'
tstring = multibytecodec_support.load_teststring('cp949')
codectests = (
# invalid bytes
(b"abc\x80\x80\xc1\xc4", "strict", None),
(b"abc\xc8", "strict", None),
(b"abc\x80\x80\xc1\xc4", "replace", "abc\ufffd\ufffd\uc894"),
(b"abc\x80\x80\xc1\xc4\xc8", "replace", "abc\ufffd\ufffd\uc894\ufffd"),
(b"abc\x80\x80\xc1\xc4", "ignore", "abc\uc894"),
)
class Test_Big5HKSCS(multibytecodec_support.TestBase, unittest.TestCase):
encoding = 'big5hkscs'
tstring = multibytecodec_support.load_teststring('big5hkscs')
codectests = (
# invalid bytes
("abc\x80\x80\xc1\xc4", "strict", None),
("abc\xc8", "strict", None),
("abc\x80\x80\xc1\xc4", "replace", u"abc\ufffd\u8b10"),
("abc\x80\x80\xc1\xc4\xc8", "replace", u"abc\ufffd\u8b10\ufffd"),
("abc\x80\x80\xc1\xc4", "ignore", u"abc\u8b10"),
)
class Test_SJIS_COMPAT(multibytecodec_support.TestBase, unittest.TestCase):
encoding = 'shift_jis'
tstring = multibytecodec_support.load_teststring('shift_jis')
codectests = shiftjis_commonenctests + (
(b"abc\x80\x80\x82\x84", "replace", "abc\ufffd\ufffd\uff44"),
(b"abc\x80\x80\x82\x84\x88", "replace", "abc\ufffd\ufffd\uff44\ufffd"),
(b"\\\x7e", "strict", "\\\x7e"),
(b"\x81\x5f\x81\x61\x81\x7c", "strict", "\uff3c\u2016\u2212"),
(b"abc\x81\x39", "replace", "abc\ufffd9"),
(b"abc\xEA\xFC", "replace", "abc\ufffd\ufffd"),
(b"abc\xFF\x58", "replace", "abc\ufffdX"),
)
class Test_GB2312(multibytecodec_support.TestBase, unittest.TestCase):
encoding = 'gb2312'
tstring = multibytecodec_support.load_teststring('gb2312')
codectests = (
# invalid bytes
(b"abc\x81\x81\xc1\xc4", "strict", None),
(b"abc\xc8", "strict", None),
(b"abc\x81\x81\xc1\xc4", "replace", "abc\ufffd\ufffd\u804a"),
(b"abc\x81\x81\xc1\xc4\xc8", "replace", "abc\ufffd\ufffd\u804a\ufffd"),
(b"abc\x81\x81\xc1\xc4", "ignore", "abc\u804a"),
(b"\xc1\x64", "strict", None),
)
class Test_SJISX0213(multibytecodec_support.TestBase, unittest.TestCase):
encoding = 'shift_jisx0213'
tstring = multibytecodec_support.load_teststring('shift_jisx0213')
codectests = shiftjis_commonenctests + (
(b"abc\x80\x80\x82\x84", "replace", "abc\ufffd\ufffd\uff44"),
(b"abc\x80\x80\x82\x84\x88", "replace", "abc\ufffd\ufffd\uff44\ufffd"),
# sjis vs cp932
(b"\\\x7e", "replace", "\xa5\u203e"),
(b"\x81\x5f\x81\x61\x81\x7c", "replace", "\x5c\u2016\u2212"),
)
xmlcharnametest = ("\xab\u211c\xbb = \u2329\u1234\u232a",
b"\x85Gℜ\x85Q = ⟨ሴ⟩")
class Test_GBK(multibytecodec_support.TestBase, unittest.TestCase):
encoding = 'gbk'
tstring = multibytecodec_support.load_teststring('gbk')
codectests = (
# invalid bytes
(b"abc\x80\x80\xc1\xc4", "strict", None),
(b"abc\xc8", "strict", None),
(b"abc\x80\x80\xc1\xc4", "replace", "abc\ufffd\ufffd\u804a"),
(b"abc\x80\x80\xc1\xc4\xc8", "replace", "abc\ufffd\ufffd\u804a\ufffd"),
(b"abc\x80\x80\xc1\xc4", "ignore", "abc\u804a"),
(b"\x83\x34\x83\x31", "strict", None),
("\u30fb", "strict", None),
)
class Test_CP932(multibytecodec_support.TestBase, unittest.TestCase):
encoding = 'cp932'
tstring = multibytecodec_support.load_teststring('shift_jis')
codectests = (b'abc\x81\x00\x81\x00\x82\x84', 'strict', None), (
b'abc\xf8', 'strict',
None), (b'abc\x81\x00\x82\x84', 'replace', 'abc�\x00ｄ'), (
b'abc\x81\x00\x82\x84\x88', 'replace', 'abc�\x00ｄ�'), (
b'abc\x81\x00\x82\x84', 'ignore',
'abc\x00ｄ'), (b'ab\xebxy', 'replace',
'ab�xy'), (b'ab\xf09xy', 'replace', 'ab�9xy'), (
b'ab\xea\xf0xy', 'replace',
'ab�\ue038y'), (b'\\~', 'replace',
'\\~'), (b'\x81_\x81a\x81|',
'replace', '＼∥－')
class Test_CP932(multibytecodec_support.TestBase, unittest.TestCase):
encoding = 'cp932'
tstring = multibytecodec_support.load_teststring('shift_jis')
codectests = (
# invalid bytes
("abc\x81\x00\x81\x00\x82\x84", "strict", None),
("abc\xf8", "strict", None),
("abc\x81\x00\x82\x84", "replace", u"abc\ufffd\uff44"),
("abc\x81\x00\x82\x84\x88", "replace", u"abc\ufffd\uff44\ufffd"),
("abc\x81\x00\x82\x84", "ignore", u"abc\uff44"),
# sjis vs cp932
("\\\x7e", "replace", u"\\\x7e"),
("\x81\x5f\x81\x61\x81\x7c", "replace", u"\uff3c\u2225\uff0d"),
)
class Test_SJIS_2004(multibytecodec_support.TestBase, unittest.TestCase):
encoding = 'shift_jis_2004'
tstring = multibytecodec_support.load_teststring('shift_jis')
codectests = shiftjis_commonenctests + (
(b"\\\x7e", "strict", "\xa5\u203e"),
(b"\x81\x5f\x81\x61\x81\x7c", "strict", "\\\u2016\u2212"),
(b"abc\xEA\xFC", "strict", "abc\u64bf"),
(b"\x81\x39xy", "replace", "\ufffd9xy"),
(b"\xFF\x58xy", "replace", "\ufffdXxy"),
(b"\x80\x80\x82\x84xy", "replace", "\ufffd\ufffd\uff44xy"),
(b"\x80\x80\x82\x84\x88xy", "replace", "\ufffd\ufffd\uff44\u5864y"),
(b"\xFC\xFBxy", "replace", '\ufffd\u95b4y'),
)
xmlcharnametest = ("\xab\u211c\xbb = \u2329\u1234\u232a",
b"\x85Gℜ\x85Q = ⟨ሴ⟩")
class Test_JOHAB(multibytecodec_support.TestBase, unittest.TestCase):
encoding = 'johab'
tstring = multibytecodec_support.load_teststring('johab')
codectests = (
# invalid bytes
(b"abc\x80\x80\xc1\xc4", "strict", None),
(b"abc\xc8", "strict", None),
(b"abc\x80\x80\xc1\xc4", "replace", "abc\ufffd\ufffd\ucd27"),
(b"abc\x80\x80\xc1\xc4\xc8", "replace", "abc\ufffd\ufffd\ucd27\ufffd"),
(b"abc\x80\x80\xc1\xc4", "ignore", "abc\ucd27"),
(b"\xD8abc", "replace", "\uFFFDabc"),
(b"\xD8\xFFabc", "replace", "\uFFFD\uFFFDabc"),
(b"\x84bxy", "replace", "\uFFFDbxy"),
(b"\x8CBxy", "replace", "\uFFFDBxy"),
)
class Test_GB18030(multibytecodec_support.TestBase, unittest.TestCase):
encoding = 'gb18030'
tstring = multibytecodec_support.load_teststring('gb18030')
codectests = (b'abc\x80\x80\xc1\xc4', 'strict', None), (b'abc\xc8',
'strict', None), (b'abc\x80\x80\xc1\xc4', 'replace', 'abc��聊'), (
b'abc\x80\x80\xc1\xc4\xc8', 'replace', 'abc��聊�'), (
b'abc\x80\x80\xc1\xc4', 'ignore', 'abc聊'), (b'abc\x849\x849\xc1\xc4',
'replace', 'abc�9�9聊'), ('・', 'strict', b'\x819\xa79'), (
b'abc\x842\x80\x80def', 'replace', 'abc�2��def'), (b'abc\x810\x810def',
'strict', 'abc\x80def'), (b'abc\x860\x810def', 'replace', 'abc�0�0def'
), (b'\xff0\x810', 'strict', None), (b'\x810\xff0', 'strict', None), (
b'abc\x819\xff9\xc1\xc4', 'replace', 'abc�9�9聊'), (b'abc\xab6\xff0def',
'replace', 'abc�6�0def'), (b'abc\xbf8\xff2\xc1\xc4', 'ignore', 'abc82聊'
)
has_iso10646 = True
class Test_EUC_JISX0213(multibytecodec_support.TestBase, unittest.TestCase):
encoding = 'euc_jisx0213'
tstring = multibytecodec_support.load_teststring('euc_jisx0213')
codectests = (
# invalid bytes
("abc\x80\x80\xc1\xc4", "strict", None),
("abc\xc8", "strict", None),
("abc\x80\x80\xc1\xc4", "replace", u"abc\ufffd\u7956"),
("abc\x80\x80\xc1\xc4\xc8", "replace", u"abc\ufffd\u7956\ufffd"),
("abc\x80\x80\xc1\xc4", "ignore", u"abc\u7956"),
("abc\x8f\x83\x83", "replace", u"abc\ufffd"),
("\xc1\x64", "strict", None),
("\xa1\xc0", "strict", u"\uff3c"),
)
xmlcharnametest = (u"\xab\u211c\xbb = \u2329\u1234\u232a",
"\xa9\xa8ℜ\xa9\xb2 = ⟨ሴ⟩")
class Test_SJISX0213(multibytecodec_support.TestBase, unittest.TestCase):
encoding = 'shift_jisx0213'
tstring = multibytecodec_support.load_teststring('shift_jisx0213')
codectests = (
# invalid bytes
("abc\x80\x80\x82\x84", "strict", None),
("abc\xf8", "strict", None),
("abc\x80\x80\x82\x84", "replace", u"abc\ufffd\uff44"),
("abc\x80\x80\x82\x84\x88", "replace", u"abc\ufffd\uff44\ufffd"),
("abc\x80\x80\x82\x84def", "ignore", u"abc\uff44def"),
# sjis vs cp932
("\\\x7e", "replace", u"\xa5\u203e"),
("\x81\x5f\x81\x61\x81\x7c", "replace", u"\x5c\u2016\u2212"),
)
xmlcharnametest = (u"\xab\u211c\xbb = \u2329\u1234\u232a",
"\x85Gℜ\x85Q = ⟨ሴ⟩")
class Test_CP932(multibytecodec_support.TestBase, unittest.TestCase):
encoding = 'cp932'
tstring = multibytecodec_support.load_teststring('shift_jis')
codectests = (
# invalid bytes
(b"abc\x81\x00\x81\x00\x82\x84", "strict", None),
(b"abc\xf8", "strict", None),
(b"abc\x81\x00\x82\x84", "replace", "abc\ufffd\x00\uff44"),
(b"abc\x81\x00\x82\x84\x88", "replace", "abc\ufffd\x00\uff44\ufffd"),
(b"abc\x81\x00\x82\x84", "ignore", "abc\x00\uff44"),
(b"ab\xEBxy", "replace", "ab\uFFFDxy"),
(b"ab\xF0\x39xy", "replace", "ab\uFFFD9xy"),
(b"ab\xEA\xF0xy", "replace", 'ab\ufffd\ue038y'),
# sjis vs cp932
(b"\\\x7e", "replace", "\\\x7e"),
(b"\x81\x5f\x81\x61\x81\x7c", "replace", "\uff3c\u2225\uff0d"),
)
class Test_GB18030(multibytecodec_support.TestBase, unittest.TestCase):
encoding = 'gb18030'
tstring = multibytecodec_support.load_teststring('gb18030')
codectests = (
# invalid bytes
(b"abc\x80\x80\xc1\xc4", "strict", None),
(b"abc\xc8", "strict", None),
(b"abc\x80\x80\xc1\xc4", "replace", "abc\ufffd\ufffd\u804a"),
(b"abc\x80\x80\xc1\xc4\xc8", "replace", "abc\ufffd\ufffd\u804a\ufffd"),
(b"abc\x80\x80\xc1\xc4", "ignore", "abc\u804a"),
(b"abc\x84\x39\x84\x39\xc1\xc4", "replace", "abc\ufffd9\ufffd9\u804a"),
("\u30fb", "strict", b"\x819\xa79"),
(b"abc\x84\x32\x80\x80def", "replace", 'abc\ufffd2\ufffd\ufffddef'),
(b"abc\x81\x30\x81\x30def", "strict", 'abc\x80def'),
(b"abc\x86\x30\x81\x30def", "replace", 'abc\ufffd0\ufffd0def'),
)
has_iso10646 = True
class Test_HZ(multibytecodec_support.TestBase, unittest.TestCase):
encoding = 'hz'
tstring = multibytecodec_support.load_teststring('hz')
codectests = (
b'This sentence is in ASCII.\nThe next sentence is in GB.~{<:Ky2;S{#,~}~\n~{NpJ)l6HK!#~}Bye.\n'
, 'strict',
"""This sentence is in ASCII.
The next sentence is in GB.己所不欲，勿施於人。Bye.
"""
), (
b'This sentence is in ASCII.\nThe next sentence is in GB.~\n~{<:Ky2;S{#,NpJ)l6HK!#~}~\nBye.\n'
, 'strict',
"""This sentence is in ASCII.
The next sentence is in GB.己所不欲，勿施於人。Bye.
"""
), (b'ab~cd', 'replace', 'ab�cd'), (b'ab\xffcd', 'replace', 'ab�cd'), (
b'ab~{\x81\x81AD~}cd', 'replace', 'ab��聊cd'), (b'ab~{AD~}cd',
'replace', 'ab聊cd'), (b'ab~{yyAD~}cd', 'replace', 'ab��聊cd'), ('ab~cd',
'strict', b'ab~~cd'), (b'~{Dc~~:C~}', 'strict', None), (b'~{Dc~\n:C~}',
'strict', None)
