Staging
v0.5.1
v0.5.1
https://github.com/python/cpython
Tip revision: 1da43e5e916949c8e849e656d9d05fa4b9d6836c authored by Benjamin Peterson on 26 June 2009, 13:21:52 UTC
rearrange the sections of the README, so they'll hopefully be more in the order people will interested in
rearrange the sections of the README, so they'll hopefully be more in the order people will interested in
Tip revision: 1da43e5
test_codecencodings_jp.py
#!/usr/bin/env python
#
# test_codecencodings_jp.py
# Codec encoding tests for Japanese encodings.
#
from test import support
from test import test_multibytecodec_support
import unittest
class Test_CP932(test_multibytecodec_support.TestBase, unittest.TestCase):
encoding = 'cp932'
tstring = test_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\uff44"),
(b"abc\x81\x00\x82\x84\x88", "replace", "abc\ufffd\uff44\ufffd"),
(b"abc\x81\x00\x82\x84", "ignore", "abc\uff44"),
# sjis vs cp932
(b"\\\x7e", "replace", "\\\x7e"),
(b"\x81\x5f\x81\x61\x81\x7c", "replace", "\uff3c\u2225\uff0d"),
)
class Test_EUC_JISX0213(test_multibytecodec_support.TestBase,
unittest.TestCase):
encoding = 'euc_jisx0213'
tstring = test_multibytecodec_support.load_teststring('euc_jisx0213')
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\u7956"),
(b"abc\x80\x80\xc1\xc4\xc8", "replace", "abc\ufffd\u7956\ufffd"),
(b"abc\x80\x80\xc1\xc4", "ignore", "abc\u7956"),
(b"abc\x8f\x83\x83", "replace", "abc\ufffd"),
(b"\xc1\x64", "strict", None),
(b"\xa1\xc0", "strict", "\uff3c"),
)
xmlcharnametest = (
"\xab\u211c\xbb = \u2329\u1234\u232a",
b"\xa9\xa8ℜ\xa9\xb2 = ⟨ሴ⟩"
)
eucjp_commontests = (
(b"abc\x80\x80\xc1\xc4", "strict", None),
(b"abc\xc8", "strict", None),
(b"abc\x80\x80\xc1\xc4", "replace", "abc\ufffd\u7956"),
(b"abc\x80\x80\xc1\xc4\xc8", "replace", "abc\ufffd\u7956\ufffd"),
(b"abc\x80\x80\xc1\xc4", "ignore", "abc\u7956"),
(b"abc\x8f\x83\x83", "replace", "abc\ufffd"),
(b"\xc1\x64", "strict", None),
)
class Test_EUC_JP_COMPAT(test_multibytecodec_support.TestBase,
unittest.TestCase):
encoding = 'euc_jp'
tstring = test_multibytecodec_support.load_teststring('euc_jp')
codectests = eucjp_commontests + (
(b"\xa1\xc0\\", "strict", "\uff3c\\"),
("\xa5", "strict", b"\x5c"),
("\u203e", "strict", b"\x7e"),
)
shiftjis_commonenctests = (
(b"abc\x80\x80\x82\x84", "strict", None),
(b"abc\xf8", "strict", None),
(b"abc\x80\x80\x82\x84", "replace", "abc\ufffd\uff44"),
(b"abc\x80\x80\x82\x84\x88", "replace", "abc\ufffd\uff44\ufffd"),
(b"abc\x80\x80\x82\x84def", "ignore", "abc\uff44def"),
)
class Test_SJIS_COMPAT(test_multibytecodec_support.TestBase, unittest.TestCase):
encoding = 'shift_jis'
tstring = test_multibytecodec_support.load_teststring('shift_jis')
codectests = shiftjis_commonenctests + (
(b"\\\x7e", "strict", "\\\x7e"),
(b"\x81\x5f\x81\x61\x81\x7c", "strict", "\uff3c\u2016\u2212"),
)
class Test_SJISX0213(test_multibytecodec_support.TestBase, unittest.TestCase):
encoding = 'shift_jisx0213'
tstring = test_multibytecodec_support.load_teststring('shift_jisx0213')
codectests = (
# invalid bytes
(b"abc\x80\x80\x82\x84", "strict", None),
(b"abc\xf8", "strict", None),
(b"abc\x80\x80\x82\x84", "replace", "abc\ufffd\uff44"),
(b"abc\x80\x80\x82\x84\x88", "replace", "abc\ufffd\uff44\ufffd"),
(b"abc\x80\x80\x82\x84def", "ignore", "abc\uff44def"),
# 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⟩"
)
def test_main():
support.run_unittest(__name__)
if __name__ == "__main__":
test_main()