+++ /dev/null
-#!/usr/bin/env python\r
-#\r
-# test_multibytecodec.py\r
-# Unit test for multibytecodec itself\r
-#\r
-\r
-from test import test_support\r
-from test.test_support import TESTFN\r
-import unittest, StringIO, codecs, sys, os\r
-import _multibytecodec\r
-\r
-ALL_CJKENCODINGS = [\r
-# _codecs_cn\r
- 'gb2312', 'gbk', 'gb18030', 'hz',\r
-# _codecs_hk\r
- 'big5hkscs',\r
-# _codecs_jp\r
- 'cp932', 'shift_jis', 'euc_jp', 'euc_jisx0213', 'shift_jisx0213',\r
- 'euc_jis_2004', 'shift_jis_2004',\r
-# _codecs_kr\r
- 'cp949', 'euc_kr', 'johab',\r
-# _codecs_tw\r
- 'big5', 'cp950',\r
-# _codecs_iso2022\r
- 'iso2022_jp', 'iso2022_jp_1', 'iso2022_jp_2', 'iso2022_jp_2004',\r
- 'iso2022_jp_3', 'iso2022_jp_ext', 'iso2022_kr',\r
-]\r
-\r
-class Test_MultibyteCodec(unittest.TestCase):\r
-\r
- def test_nullcoding(self):\r
- for enc in ALL_CJKENCODINGS:\r
- self.assertEqual(''.decode(enc), u'')\r
- self.assertEqual(unicode('', enc), u'')\r
- self.assertEqual(u''.encode(enc), '')\r
-\r
- def test_str_decode(self):\r
- for enc in ALL_CJKENCODINGS:\r
- self.assertEqual('abcd'.encode(enc), 'abcd')\r
-\r
- def test_errorcallback_longindex(self):\r
- dec = codecs.getdecoder('euc-kr')\r
- myreplace = lambda exc: (u'', sys.maxint+1)\r
- codecs.register_error('test.cjktest', myreplace)\r
- self.assertRaises(IndexError, dec,\r
- 'apple\x92ham\x93spam', 'test.cjktest')\r
-\r
- def test_codingspec(self):\r
- for enc in ALL_CJKENCODINGS:\r
- code = '# coding: {}\n'.format(enc)\r
- exec code\r
-\r
- def test_init_segfault(self):\r
- # bug #3305: this used to segfault\r
- self.assertRaises(AttributeError,\r
- _multibytecodec.MultibyteStreamReader, None)\r
- self.assertRaises(AttributeError,\r
- _multibytecodec.MultibyteStreamWriter, None)\r
-\r
-\r
-class Test_IncrementalEncoder(unittest.TestCase):\r
-\r
- def test_stateless(self):\r
- # cp949 encoder isn't stateful at all.\r
- encoder = codecs.getincrementalencoder('cp949')()\r
- self.assertEqual(encoder.encode(u'\ud30c\uc774\uc36c \ub9c8\uc744'),\r
- '\xc6\xc4\xc0\xcc\xbd\xe3 \xb8\xb6\xc0\xbb')\r
- self.assertEqual(encoder.reset(), None)\r
- self.assertEqual(encoder.encode(u'\u2606\u223c\u2606', True),\r
- '\xa1\xd9\xa1\xad\xa1\xd9')\r
- self.assertEqual(encoder.reset(), None)\r
- self.assertEqual(encoder.encode(u'', True), '')\r
- self.assertEqual(encoder.encode(u'', False), '')\r
- self.assertEqual(encoder.reset(), None)\r
-\r
- def test_stateful(self):\r
- # jisx0213 encoder is stateful for a few codepoints. eg)\r
- # U+00E6 => A9DC\r
- # U+00E6 U+0300 => ABC4\r
- # U+0300 => ABDC\r
-\r
- encoder = codecs.getincrementalencoder('jisx0213')()\r
- self.assertEqual(encoder.encode(u'\u00e6\u0300'), '\xab\xc4')\r
- self.assertEqual(encoder.encode(u'\u00e6'), '')\r
- self.assertEqual(encoder.encode(u'\u0300'), '\xab\xc4')\r
- self.assertEqual(encoder.encode(u'\u00e6', True), '\xa9\xdc')\r
-\r
- self.assertEqual(encoder.reset(), None)\r
- self.assertEqual(encoder.encode(u'\u0300'), '\xab\xdc')\r
-\r
- self.assertEqual(encoder.encode(u'\u00e6'), '')\r
- self.assertEqual(encoder.encode('', True), '\xa9\xdc')\r
- self.assertEqual(encoder.encode('', True), '')\r
-\r
- def test_stateful_keep_buffer(self):\r
- encoder = codecs.getincrementalencoder('jisx0213')()\r
- self.assertEqual(encoder.encode(u'\u00e6'), '')\r
- self.assertRaises(UnicodeEncodeError, encoder.encode, u'\u0123')\r
- self.assertEqual(encoder.encode(u'\u0300\u00e6'), '\xab\xc4')\r
- self.assertRaises(UnicodeEncodeError, encoder.encode, u'\u0123')\r
- self.assertEqual(encoder.reset(), None)\r
- self.assertEqual(encoder.encode(u'\u0300'), '\xab\xdc')\r
- self.assertEqual(encoder.encode(u'\u00e6'), '')\r
- self.assertRaises(UnicodeEncodeError, encoder.encode, u'\u0123')\r
- self.assertEqual(encoder.encode(u'', True), '\xa9\xdc')\r
-\r
- def test_issue5640(self):\r
- encoder = codecs.getincrementalencoder('shift-jis')('backslashreplace')\r
- self.assertEqual(encoder.encode(u'\xff'), b'\\xff')\r
- self.assertEqual(encoder.encode(u'\n'), b'\n')\r
-\r
-class Test_IncrementalDecoder(unittest.TestCase):\r
-\r
- def test_dbcs(self):\r
- # cp949 decoder is simple with only 1 or 2 bytes sequences.\r
- decoder = codecs.getincrementaldecoder('cp949')()\r
- self.assertEqual(decoder.decode('\xc6\xc4\xc0\xcc\xbd'),\r
- u'\ud30c\uc774')\r
- self.assertEqual(decoder.decode('\xe3 \xb8\xb6\xc0\xbb'),\r
- u'\uc36c \ub9c8\uc744')\r
- self.assertEqual(decoder.decode(''), u'')\r
-\r
- def test_dbcs_keep_buffer(self):\r
- decoder = codecs.getincrementaldecoder('cp949')()\r
- self.assertEqual(decoder.decode('\xc6\xc4\xc0'), u'\ud30c')\r
- self.assertRaises(UnicodeDecodeError, decoder.decode, '', True)\r
- self.assertEqual(decoder.decode('\xcc'), u'\uc774')\r
-\r
- self.assertEqual(decoder.decode('\xc6\xc4\xc0'), u'\ud30c')\r
- self.assertRaises(UnicodeDecodeError, decoder.decode, '\xcc\xbd', True)\r
- self.assertEqual(decoder.decode('\xcc'), u'\uc774')\r
-\r
- def test_iso2022(self):\r
- decoder = codecs.getincrementaldecoder('iso2022-jp')()\r
- ESC = '\x1b'\r
- self.assertEqual(decoder.decode(ESC + '('), u'')\r
- self.assertEqual(decoder.decode('B', True), u'')\r
- self.assertEqual(decoder.decode(ESC + '$'), u'')\r
- self.assertEqual(decoder.decode('B@$'), u'\u4e16')\r
- self.assertEqual(decoder.decode('@$@'), u'\u4e16')\r
- self.assertEqual(decoder.decode('$', True), u'\u4e16')\r
- self.assertEqual(decoder.reset(), None)\r
- self.assertEqual(decoder.decode('@$'), u'@$')\r
- self.assertEqual(decoder.decode(ESC + '$'), u'')\r
- self.assertRaises(UnicodeDecodeError, decoder.decode, '', True)\r
- self.assertEqual(decoder.decode('B@$'), u'\u4e16')\r
-\r
-class Test_StreamReader(unittest.TestCase):\r
- def test_bug1728403(self):\r
- try:\r
- open(TESTFN, 'w').write('\xa1')\r
- f = codecs.open(TESTFN, encoding='cp949')\r
- self.assertRaises(UnicodeDecodeError, f.read, 2)\r
- finally:\r
- try: f.close()\r
- except: pass\r
- os.unlink(TESTFN)\r
-\r
-class Test_StreamWriter(unittest.TestCase):\r
- if len(u'\U00012345') == 2: # UCS2\r
- def test_gb18030(self):\r
- s = StringIO.StringIO()\r
- c = codecs.getwriter('gb18030')(s)\r
- c.write(u'123')\r
- self.assertEqual(s.getvalue(), '123')\r
- c.write(u'\U00012345')\r
- self.assertEqual(s.getvalue(), '123\x907\x959')\r
- c.write(u'\U00012345'[0])\r
- self.assertEqual(s.getvalue(), '123\x907\x959')\r
- c.write(u'\U00012345'[1] + u'\U00012345' + u'\uac00\u00ac')\r
- self.assertEqual(s.getvalue(),\r
- '123\x907\x959\x907\x959\x907\x959\x827\xcf5\x810\x851')\r
- c.write(u'\U00012345'[0])\r
- self.assertEqual(s.getvalue(),\r
- '123\x907\x959\x907\x959\x907\x959\x827\xcf5\x810\x851')\r
- self.assertRaises(UnicodeError, c.reset)\r
- self.assertEqual(s.getvalue(),\r
- '123\x907\x959\x907\x959\x907\x959\x827\xcf5\x810\x851')\r
-\r
- def test_utf_8(self):\r
- s= StringIO.StringIO()\r
- c = codecs.getwriter('utf-8')(s)\r
- c.write(u'123')\r
- self.assertEqual(s.getvalue(), '123')\r
- c.write(u'\U00012345')\r
- self.assertEqual(s.getvalue(), '123\xf0\x92\x8d\x85')\r
-\r
- # Python utf-8 codec can't buffer surrogate pairs yet.\r
- if 0:\r
- c.write(u'\U00012345'[0])\r
- self.assertEqual(s.getvalue(), '123\xf0\x92\x8d\x85')\r
- c.write(u'\U00012345'[1] + u'\U00012345' + u'\uac00\u00ac')\r
- self.assertEqual(s.getvalue(),\r
- '123\xf0\x92\x8d\x85\xf0\x92\x8d\x85\xf0\x92\x8d\x85'\r
- '\xea\xb0\x80\xc2\xac')\r
- c.write(u'\U00012345'[0])\r
- self.assertEqual(s.getvalue(),\r
- '123\xf0\x92\x8d\x85\xf0\x92\x8d\x85\xf0\x92\x8d\x85'\r
- '\xea\xb0\x80\xc2\xac')\r
- c.reset()\r
- self.assertEqual(s.getvalue(),\r
- '123\xf0\x92\x8d\x85\xf0\x92\x8d\x85\xf0\x92\x8d\x85'\r
- '\xea\xb0\x80\xc2\xac\xed\xa0\x88')\r
- c.write(u'\U00012345'[1])\r
- self.assertEqual(s.getvalue(),\r
- '123\xf0\x92\x8d\x85\xf0\x92\x8d\x85\xf0\x92\x8d\x85'\r
- '\xea\xb0\x80\xc2\xac\xed\xa0\x88\xed\xbd\x85')\r
-\r
- else: # UCS4\r
- pass\r
-\r
- def test_streamwriter_strwrite(self):\r
- s = StringIO.StringIO()\r
- wr = codecs.getwriter('gb18030')(s)\r
- wr.write('abcd')\r
- self.assertEqual(s.getvalue(), 'abcd')\r
-\r
-class Test_ISO2022(unittest.TestCase):\r
- def test_g2(self):\r
- iso2022jp2 = '\x1b(B:hu4:unit\x1b.A\x1bNi de famille'\r
- uni = u':hu4:unit\xe9 de famille'\r
- self.assertEqual(iso2022jp2.decode('iso2022-jp-2'), uni)\r
-\r
- def test_iso2022_jp_g0(self):\r
- self.assertNotIn('\x0e', u'\N{SOFT HYPHEN}'.encode('iso-2022-jp-2'))\r
- for encoding in ('iso-2022-jp-2004', 'iso-2022-jp-3'):\r
- e = u'\u3406'.encode(encoding)\r
- self.assertFalse(filter(lambda x: x >= '\x80', e))\r
-\r
- def test_bug1572832(self):\r
- if sys.maxunicode >= 0x10000:\r
- myunichr = unichr\r
- else:\r
- myunichr = lambda x: unichr(0xD7C0+(x>>10)) + unichr(0xDC00+(x&0x3FF))\r
-\r
- for x in xrange(0x10000, 0x110000):\r
- # Any ISO 2022 codec will cause the segfault\r
- myunichr(x).encode('iso_2022_jp', 'ignore')\r
-\r
-class TestStateful(unittest.TestCase):\r
- text = u'\u4E16\u4E16'\r
- encoding = 'iso-2022-jp'\r
- expected = b'\x1b$B@$@$'\r
- expected_reset = b'\x1b$B@$@$\x1b(B'\r
-\r
- def test_encode(self):\r
- self.assertEqual(self.text.encode(self.encoding), self.expected_reset)\r
-\r
- def test_incrementalencoder(self):\r
- encoder = codecs.getincrementalencoder(self.encoding)()\r
- output = b''.join(\r
- encoder.encode(char)\r
- for char in self.text)\r
- self.assertEqual(output, self.expected)\r
-\r
- def test_incrementalencoder_final(self):\r
- encoder = codecs.getincrementalencoder(self.encoding)()\r
- last_index = len(self.text) - 1\r
- output = b''.join(\r
- encoder.encode(char, index == last_index)\r
- for index, char in enumerate(self.text))\r
- self.assertEqual(output, self.expected_reset)\r
-\r
-class TestHZStateful(TestStateful):\r
- text = u'\u804a\u804a'\r
- encoding = 'hz'\r
- expected = b'~{ADAD'\r
- expected_reset = b'~{ADAD~}'\r
-\r
-def test_main():\r
- test_support.run_unittest(__name__)\r
-\r
-if __name__ == "__main__":\r
- test_main()\r