summaryrefslogtreecommitdiffstats
path: root/Lib/test/test_multibytecodec.py
blob: 86c68dcd9a6f2856ce7c5f75001d16a608cd12b9 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
#!/usr/bin/env python3
#
# test_multibytecodec.py
#   Unit test for multibytecodec itself
#

from test import support
from test.support import TESTFN
import unittest, io, codecs, sys, os
import _multibytecodec

ALL_CJKENCODINGS = [
# _codecs_cn
    'gb2312', 'gbk', 'gb18030', 'hz',
# _codecs_hk
    'big5hkscs',
# _codecs_jp
    'cp932', 'shift_jis', 'euc_jp', 'euc_jisx0213', 'shift_jisx0213',
    'euc_jis_2004', 'shift_jis_2004',
# _codecs_kr
    'cp949', 'euc_kr', 'johab',
# _codecs_tw
    'big5', 'cp950',
# _codecs_iso2022
    'iso2022_jp', 'iso2022_jp_1', 'iso2022_jp_2', 'iso2022_jp_2004',
    'iso2022_jp_3', 'iso2022_jp_ext', 'iso2022_kr',
]

class Test_MultibyteCodec(unittest.TestCase):

    def test_nullcoding(self):
        for enc in ALL_CJKENCODINGS:
            self.assertEqual(b''.decode(enc), '')
            self.assertEqual(str(b'', enc), '')
            self.assertEqual(''.encode(enc), b'')

    def test_str_decode(self):
        for enc in ALL_CJKENCODINGS:
            self.assertEqual('abcd'.encode(enc), b'abcd')

    def test_errorcallback_longindex(self):
        dec = codecs.getdecoder('euc-kr')
        myreplace  = lambda exc: ('', sys.maxsize+1)
        codecs.register_error('test.cjktest', myreplace)
        self.assertRaises(IndexError, dec,
                          b'apple\x92ham\x93spam', 'test.cjktest')

    def test_codingspec(self):
        try:
            for enc in ALL_CJKENCODINGS:
                code = '# coding: {}\n'.format(enc)
                exec(code)
        finally:
            support.unlink(TESTFN)

    def test_init_segfault(self):
        # bug #3305: this used to segfault
        self.assertRaises(AttributeError,
                          _multibytecodec.MultibyteStreamReader, None)
        self.assertRaises(AttributeError,
                          _multibytecodec.MultibyteStreamWriter, None)

    def test_decode_unicode(self):
        # Trying to decode an unicode string should raise a TypeError
        for enc in ALL_CJKENCODINGS:
            self.assertRaises(TypeError, codecs.getdecoder(enc), "")

class Test_IncrementalEncoder(unittest.TestCase):

    def test_stateless(self):
        # cp949 encoder isn't stateful at all.
        encoder = codecs.getincrementalencoder('cp949')()
        self.assertEqual(encoder.encode('\ud30c\uc774\uc36c \ub9c8\uc744'),
                         b'\xc6\xc4\xc0\xcc\xbd\xe3 \xb8\xb6\xc0\xbb')
        self.assertEqual(encoder.reset(), None)
        self.assertEqual(encoder.encode('\u2606\u223c\u2606', True),
                         b'\xa1\xd9\xa1\xad\xa1\xd9')
        self.assertEqual(encoder.reset(), None)
        self.assertEqual(encoder.encode('', True), b'')
        self.assertEqual(encoder.encode('', False), b'')
        self.assertEqual(encoder.reset(), None)

    def test_stateful(self):
        # jisx0213 encoder is stateful for a few codepoints. eg)
        #   U+00E6 => A9DC
        #   U+00E6 U+0300 => ABC4
        #   U+0300 => ABDC

        encoder = codecs.getincrementalencoder('jisx0213')()
        self.assertEqual(encoder.encode('\u00e6\u0300'), b'\xab\xc4')
        self.assertEqual(encoder.encode('\u00e6'), b'')
        self.assertEqual(encoder.encode('\u0300'), b'\xab\xc4')
        self.assertEqual(encoder.encode('\u00e6', True), b'\xa9\xdc')

        self.assertEqual(encoder.reset(), None)
        self.assertEqual(encoder.encode('\u0300'), b'\xab\xdc')

        self.assertEqual(encoder.encode('\u00e6'), b'')
        self.assertEqual(encoder.encode('', True), b'\xa9\xdc')
        self.assertEqual(encoder.encode('', True), b'')

    def test_stateful_keep_buffer(self):
        encoder = codecs.getincrementalencoder('jisx0213')()
        self.assertEqual(encoder.encode('\u00e6'), b'')
        self.assertRaises(UnicodeEncodeError, encoder.encode, '\u0123')
        self.assertEqual(encoder.encode('\u0300\u00e6'), b'\xab\xc4')
        self.assertRaises(UnicodeEncodeError, encoder.encode, '\u0123')
        self.assertEqual(encoder.reset(), None)
        self.assertEqual(encoder.encode('\u0300'), b'\xab\xdc')
        self.assertEqual(encoder.encode('\u00e6'), b'')
        self.assertRaises(UnicodeEncodeError, encoder.encode, '\u0123')
        self.assertEqual(encoder.encode('', True), b'\xa9\xdc')

    def test_issue5640(self):
        encoder = codecs.getincrementalencoder('shift-jis')('backslashreplace')
        self.assertEqual(encoder.encode('\xff'), b'\\xff')
        self.assertEqual(encoder.encode('\n'), b'\n')

class Test_IncrementalDecoder(unittest.TestCase):

    def test_dbcs(self):
        # cp949 decoder is simple with only 1 or 2 bytes sequences.
        decoder = codecs.getincrementaldecoder('cp949')()
        self.assertEqual(decoder.decode(b'\xc6\xc4\xc0\xcc\xbd'),
                         '\ud30c\uc774')
        self.assertEqual(decoder.decode(b'\xe3 \xb8\xb6\xc0\xbb'),
                         '\uc36c \ub9c8\uc744')
        self.assertEqual(decoder.decode(b''), '')

    def test_dbcs_keep_buffer(self):
        decoder = codecs.getincrementaldecoder('cp949')()
        self.assertEqual(decoder.decode(b'\xc6\xc4\xc0'), '\ud30c')
        self.assertRaises(UnicodeDecodeError, decoder.decode, b'', True)
        self.assertEqual(decoder.decode(b'\xcc'), '\uc774')

        self.assertEqual(decoder.decode(b'\xc6\xc4\xc0'), '\ud30c')
        self.assertRaises(UnicodeDecodeError, decoder.decode,
                          b'\xcc\xbd', True)
        self.assertEqual(decoder.decode(b'\xcc'), '\uc774')

    def test_iso2022(self):
        decoder = codecs.getincrementaldecoder('iso2022-jp')()
        ESC = b'\x1b'
        self.assertEqual(decoder.decode(ESC + b'('), '')
        self.assertEqual(decoder.decode(b'B', True), '')
        self.assertEqual(decoder.decode(ESC + b'$'), '')
        self.assertEqual(decoder.decode(b'B@$'), '\u4e16')
        self.assertEqual(decoder.decode(b'@$@'), '\u4e16')
        self.assertEqual(decoder.decode(b'$', True), '\u4e16')
        self.assertEqual(decoder.reset(), None)
        self.assertEqual(decoder.decode(b'@$'), '@$')
        self.assertEqual(decoder.decode(ESC + b'$'), '')
        self.assertRaises(UnicodeDecodeError, decoder.decode, b'', True)
        self.assertEqual(decoder.decode(b'B@$'), '\u4e16')

    def test_decode_unicode(self):
        # Trying to decode an unicode string should raise a TypeError
        for enc in ALL_CJKENCODINGS:
            decoder = codecs.getincrementaldecoder(enc)()
            self.assertRaises(TypeError, decoder.decode, "")

class Test_StreamReader(unittest.TestCase):
    def test_bug1728403(self):
        try:
            f = open(TESTFN, 'wb')
            try:
                f.write(b'\xa1')
            finally:
                f.close()
            f = codecs.open(TESTFN, encoding='cp949')
            try:
                self.assertRaises(UnicodeDecodeError, f.read, 2)
            finally:
                f.close()
        finally:
            support.unlink(TESTFN)

class Test_StreamWriter(unittest.TestCase):
    if len('\U00012345') == 2: # UCS2
        def test_gb18030(self):
            s= io.BytesIO()
            c = codecs.getwriter('gb18030')(s)
            c.write('123')
            self.assertEqual(s.getvalue(), b'123')
            c.write('\U00012345')
            self.assertEqual(s.getvalue(), b'123\x907\x959')
            c.write('\U00012345'[0])
            self.assertEqual(s.getvalue(), b'123\x907\x959')
            c.write('\U00012345'[1] + '\U00012345' + '\uac00\u00ac')
            self.assertEqual(s.getvalue(),
                    b'123\x907\x959\x907\x959\x907\x959\x827\xcf5\x810\x851')
            c.write('\U00012345'[0])
            self.assertEqual(s.getvalue(),
                    b'123\x907\x959\x907\x959\x907\x959\x827\xcf5\x810\x851')
            self.assertRaises(UnicodeError, c.reset)
            self.assertEqual(s.getvalue(),
                    b'123\x907\x959\x907\x959\x907\x959\x827\xcf5\x810\x851')

        def test_utf_8(self):
            s= io.BytesIO()
            c = codecs.getwriter('utf-8')(s)
            c.write('123')
            self.assertEqual(s.getvalue(), b'123')
            c.write('\U00012345')
            self.assertEqual(s.getvalue(), b'123\xf0\x92\x8d\x85')

            # Python utf-8 codec can't buffer surrogate pairs yet.
            if 0:
                c.write('\U00012345'[0])
                self.assertEqual(s.getvalue(), b'123\xf0\x92\x8d\x85')
                c.write('\U00012345'[1] + '\U00012345' + '\uac00\u00ac')
                self.assertEqual(s.getvalue(),
                    b'123\xf0\x92\x8d\x85\xf0\x92\x8d\x85\xf0\x92\x8d\x85'
                    b'\xea\xb0\x80\xc2\xac')
                c.write('\U00012345'[0])
                self.assertEqual(s.getvalue(),
                    b'123\xf0\x92\x8d\x85\xf0\x92\x8d\x85\xf0\x92\x8d\x85'
                    b'\xea\xb0\x80\xc2\xac')
                c.reset()
                self.assertEqual(s.getvalue(),
                    b'123\xf0\x92\x8d\x85\xf0\x92\x8d\x85\xf0\x92\x8d\x85'
                    b'\xea\xb0\x80\xc2\xac\xed\xa0\x88')
                c.write('\U00012345'[1])
                self.assertEqual(s.getvalue(),
                    b'123\xf0\x92\x8d\x85\xf0\x92\x8d\x85\xf0\x92\x8d\x85'
                    b'\xea\xb0\x80\xc2\xac\xed\xa0\x88\xed\xbd\x85')

    else: # UCS4
        pass

    def test_streamwriter_strwrite(self):
        s = io.BytesIO()
        wr = codecs.getwriter('gb18030')(s)
        wr.write('abcd')
        self.assertEqual(s.getvalue(), b'abcd')

class Test_ISO2022(unittest.TestCase):
    def test_g2(self):
        iso2022jp2 = b'\x1b(B:hu4:unit\x1b.A\x1bNi de famille'
        uni = ':hu4:unit\xe9 de famille'
        self.assertEqual(iso2022jp2.decode('iso2022-jp-2'), uni)

    def test_iso2022_jp_g0(self):
        self.assertNotIn(b'\x0e', '\N{SOFT HYPHEN}'.encode('iso-2022-jp-2'))
        for encoding in ('iso-2022-jp-2004', 'iso-2022-jp-3'):
            e = '\u3406'.encode(encoding)
            self.assertFalse(any(x > 0x80 for x in e))

    def test_bug1572832(self):
        if sys.maxunicode >= 0x10000:
            myunichr = chr
        else:
            myunichr = lambda x: chr(0xD7C0+(x>>10)) + chr(0xDC00+(x&0x3FF))

        for x in range(0x10000, 0x110000):
            # Any ISO 2022 codec will cause the segfault
            myunichr(x).encode('iso_2022_jp', 'ignore')

class TestStateful(unittest.TestCase):
    text = '\u4E16\u4E16'
    encoding = 'iso-2022-jp'
    expected = b'\x1b$B@$@$'
    expected_reset = b'\x1b$B@$@$\x1b(B'

    def test_encode(self):
        self.assertEqual(self.text.encode(self.encoding), self.expected_reset)

    def test_incrementalencoder(self):
        encoder = codecs.getincrementalencoder(self.encoding)()
        output = b''.join(
            encoder.encode(char)
            for char in self.text)
        self.assertEqual(output, self.expected)

    def test_incrementalencoder_final(self):
        encoder = codecs.getincrementalencoder(self.encoding)()
        last_index = len(self.text) - 1
        output = b''.join(
            encoder.encode(char, index == last_index)
            for index, char in enumerate(self.text))
        self.assertEqual(output, self.expected_reset)

class TestHZStateful(TestStateful):
    text = '\u804a\u804a'
    encoding = 'hz'
    expected = b'~{ADAD'
    expected_reset = b'~{ADAD~}'

def test_main():
    support.run_unittest(__name__)

if __name__ == "__main__":
    test_main()