Repository navigation
Expand file tree
/
Copy pathtest_multibytecodec.py
More file actions
551 lines (479 loc) · 22.1 KB
/
Copy pathtest_multibytecodec.py
File metadata and controls
551 lines (479 loc) · 22.1 KB
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
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
#
# test_multibytecodec.py
# Unit test for multibytecodec itself
#
import _multibytecodec
import codecs
import io
import sys
import textwrap
import unittest
from test import support
from test.support import os_helper
from test.support.os_helper import TESTFN
from test.support.import_helper import import_module
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_hz_tilde_at_buffer_boundary(self):
text = 'a' + '中a' * 6 + '~'
self.assertEqual(text.encode('hz').decode('hz'), text)
def test_str_decode(self):
for enc in ALL_CJKENCODINGS:
self.assertEqual('abcd'.encode(enc), b'abcd')
def test_nonbmp_pair_modifier(self):
cases = [('big5hkscs', '\u00ca', '\u0304')]
cases.extend((encoding, '\u304b', '\u309a') for encoding in (
'euc_jis_2004', 'euc_jisx0213', 'shift_jis_2004', 'shift_jisx0213',
'iso2022_jp_2004', 'iso2022_jp_3'))
for encoding, base, modifier in cases:
with self.subTest(encoding=encoding):
pair = base + modifier
self.assertEqual(pair.encode(encoding).decode(encoding), pair)
nonbmp = base + chr(0x10000 + ord(modifier))
self.assertRaises(UnicodeEncodeError, nonbmp.encode, encoding)
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_errorcallback_custom_ignore(self):
# Issue #23215: MemoryError with custom error handlers and multibyte codecs
data = 100 * "\udc00"
codecs.register_error("test.ignore", codecs.ignore_errors)
for enc in ALL_CJKENCODINGS:
self.assertEqual(data.encode(enc, "test.ignore"), b'')
def test_codingspec(self):
try:
for enc in ALL_CJKENCODINGS:
code = '# coding: {}\n'.format(enc)
exec(code)
finally:
os_helper.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 a unicode string should raise a TypeError
for enc in ALL_CJKENCODINGS:
self.assertRaises(TypeError, codecs.getdecoder(enc), "")
class Test_IncrementalEncoder(unittest.TestCase):
def test_iso2022_kr_reset(self):
encoder = codecs.getincrementalencoder('iso2022_kr')()
encoder.encode('가')
encoder.reset()
self.assertEqual(encoder.encode('가', final=True), '가'.encode('iso2022_kr'))
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 code points. 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_state_methods_with_buffer_state(self):
# euc_jis_2004 stores state as a buffer of pending bytes
encoder = codecs.getincrementalencoder('euc_jis_2004')()
initial_state = encoder.getstate()
self.assertEqual(encoder.encode('\u00e6\u0300'), b'\xab\xc4')
encoder.setstate(initial_state)
self.assertEqual(encoder.encode('\u00e6\u0300'), b'\xab\xc4')
self.assertEqual(encoder.encode('\u00e6'), b'')
partial_state = encoder.getstate()
self.assertEqual(encoder.encode('\u0300'), b'\xab\xc4')
encoder.setstate(partial_state)
self.assertEqual(encoder.encode('\u0300'), b'\xab\xc4')
def test_state_methods_with_non_buffer_state(self):
# iso2022_jp stores state without using a buffer
encoder = codecs.getincrementalencoder('iso2022_jp')()
self.assertEqual(encoder.encode('z'), b'z')
en_state = encoder.getstate()
self.assertEqual(encoder.encode('\u3042'), b'\x1b\x24\x42\x24\x22')
jp_state = encoder.getstate()
self.assertEqual(encoder.encode('z'), b'\x1b\x28\x42z')
encoder.setstate(jp_state)
self.assertEqual(encoder.encode('\u3042'), b'\x24\x22')
encoder.setstate(en_state)
self.assertEqual(encoder.encode('z'), b'z')
def test_getstate_returns_expected_value(self):
# Note: getstate is implemented such that these state values
# are expected to be the same across all builds of Python,
# regardless of x32/64 bit, endianness and compiler.
# euc_jis_2004 stores state as a buffer of pending bytes
buffer_state_encoder = codecs.getincrementalencoder('euc_jis_2004')()
self.assertEqual(buffer_state_encoder.getstate(), 0)
buffer_state_encoder.encode('\u00e6')
self.assertEqual(buffer_state_encoder.getstate(),
int.from_bytes(
b"\x02"
b"\xc3\xa6"
b"\x00\x00\x00\x00\x00\x00\x00\x00",
'little'))
buffer_state_encoder.encode('\u0300')
self.assertEqual(buffer_state_encoder.getstate(), 0)
# iso2022_jp stores state without using a buffer
non_buffer_state_encoder = codecs.getincrementalencoder('iso2022_jp')()
self.assertEqual(non_buffer_state_encoder.getstate(),
int.from_bytes(
b"\x00"
b"\x42\x42\x00\x00\x00\x00\x00\x00",
'little'))
non_buffer_state_encoder.encode('\u3042')
self.assertEqual(non_buffer_state_encoder.getstate(),
int.from_bytes(
b"\x00"
b"\xc2\x42\x00\x00\x00\x00\x00\x00",
'little'))
def test_setstate_validates_input_size(self):
encoder = codecs.getincrementalencoder('euc_jp')()
pending_size_nine = int.from_bytes(
b"\x09"
b"\x00\x00\x00\x00\x00\x00\x00\x00"
b"\x00\x00\x00\x00\x00\x00\x00\x00",
'little')
self.assertRaises(UnicodeError, encoder.setstate, pending_size_nine)
def test_setstate_validates_input_bytes(self):
encoder = codecs.getincrementalencoder('euc_jp')()
invalid_utf8 = int.from_bytes(
b"\x01"
b"\xff"
b"\x00\x00\x00\x00\x00\x00\x00\x00",
'little')
self.assertRaises(UnicodeDecodeError, encoder.setstate, invalid_utf8)
def test_issue5640(self):
encoder = codecs.getincrementalencoder('shift-jis')('backslashreplace')
self.assertEqual(encoder.encode('\xff'), b'\\xff')
self.assertEqual(encoder.encode('\n'), b'\n')
@support.cpython_only
def test_subinterp(self):
# bpo-42846: Test a CJK codec in a subinterpreter
_testcapi = import_module("_testcapi")
encoding = 'cp932'
text = "Python の開発は、1990 年ごろから開始されています。"
code = textwrap.dedent("""
import codecs
encoding = %r
text = %r
encoder = codecs.getincrementalencoder(encoding)()
text2 = encoder.encode(text).decode(encoding)
if text2 != text:
raise ValueError(f"encoding issue: {text2!a} != {text!a}")
""") % (encoding, text)
res = _testcapi.run_in_subinterp(code)
self.assertEqual(res, 0)
class Test_IncrementalDecoder(unittest.TestCase):
def test_iso2022_split_escape(self):
raw = b'\x1b$0000000B'
decoder = codecs.getincrementaldecoder('iso2022_jp')('replace')
decoded = decoder.decode(raw[:-1]) + decoder.decode(raw[-1:], final=True)
self.assertEqual(decoded, raw.decode('iso2022_jp', 'replace'))
def test_iso2022_reset(self):
decoder = codecs.getincrementaldecoder('iso2022_jp')()
decoder.decode(b'\x1b%')
decoder.reset()
with self.assertRaises(UnicodeDecodeError):
decoder.decode(b'\xff', final=True)
def test_dbcs(self):
# cp949 decoder is simple with only 1 or 2 bytes sequences.
decoder = codecs.getincrementaldecoder('cp949')()
self.assertEqual(decoder.decode(b'\xc6\xc4\xc0\xcc\xbd'),
'\ud30c\uc774')
self.assertEqual(decoder.decode(b'\xe3 \xb8\xb6\xc0\xbb'),
'\uc36c \ub9c8\uc744')
self.assertEqual(decoder.decode(b''), '')
def test_dbcs_keep_buffer(self):
decoder = codecs.getincrementaldecoder('cp949')()
self.assertEqual(decoder.decode(b'\xc6\xc4\xc0'), '\ud30c')
self.assertRaises(UnicodeDecodeError, decoder.decode, b'', True)
self.assertEqual(decoder.decode(b'\xcc'), '\uc774')
self.assertEqual(decoder.decode(b'\xc6\xc4\xc0'), '\ud30c')
self.assertRaises(UnicodeDecodeError, decoder.decode,
b'\xcc\xbd', True)
self.assertEqual(decoder.decode(b'\xcc'), '\uc774')
def test_iso2022(self):
decoder = codecs.getincrementaldecoder('iso2022-jp')()
ESC = b'\x1b'
self.assertEqual(decoder.decode(ESC + b'('), '')
self.assertEqual(decoder.decode(b'B', True), '')
self.assertEqual(decoder.decode(ESC + b'$'), '')
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_hz_keep_buffer(self):
# A trailing '~' shouldn't read past the end of the input.
decoder = codecs.getincrementaldecoder('hz')()
self.assertEqual(decoder.decode(b'~'), '')
self.assertRaises(UnicodeDecodeError, decoder.decode, b'', True)
self.assertEqual(decoder.decode(b'~'), '~')
self.assertEqual(decoder.decode(b'~'), '')
self.assertEqual(decoder.decode(b'\n', True), '')
def test_decode_unicode(self):
# Trying to decode a unicode string should raise a TypeError
for enc in ALL_CJKENCODINGS:
decoder = codecs.getincrementaldecoder(enc)()
self.assertRaises(TypeError, decoder.decode, "")
def test_state_methods(self):
decoder = codecs.getincrementaldecoder('euc_jp')()
# Decode a complete input sequence
self.assertEqual(decoder.decode(b'\xa4\xa6'), '\u3046')
pending1, _ = decoder.getstate()
self.assertEqual(pending1, b'')
# Decode first half of a partial input sequence
self.assertEqual(decoder.decode(b'\xa4'), '')
pending2, flags2 = decoder.getstate()
self.assertEqual(pending2, b'\xa4')
# Decode second half of a partial input sequence
self.assertEqual(decoder.decode(b'\xa6'), '\u3046')
pending3, _ = decoder.getstate()
self.assertEqual(pending3, b'')
# Jump back and decode second half of partial input sequence again
decoder.setstate((pending2, flags2))
self.assertEqual(decoder.decode(b'\xa6'), '\u3046')
pending4, _ = decoder.getstate()
self.assertEqual(pending4, b'')
# Ensure state values are preserved correctly
decoder.setstate((b'abc', 123456789))
self.assertEqual(decoder.getstate(), (b'abc', 123456789))
def test_setstate_validates_input(self):
decoder = codecs.getincrementaldecoder('euc_jp')()
self.assertRaises(TypeError, decoder.setstate, 123)
self.assertRaises(TypeError, decoder.setstate, ("invalid", 0))
self.assertRaises(TypeError, decoder.setstate, (b"1234", "invalid"))
self.assertRaises(UnicodeDecodeError, decoder.setstate, (b"0" * 17, 0))
def test_setstate_invalid_designation(self):
# gh-153603: an unknown charset designation in the state must not crash
# the decoder. 0xff is not a registered charset mark and 0x21 ('!') is
# a GL byte that triggers the designation lookup.
for name in ('iso-2022-jp', 'iso-2022-kr'):
with self.subTest(codec=name):
decoder = codecs.getincrementaldecoder(name)()
decoder.setstate((b'', 0xff))
with self.assertRaises(UnicodeDecodeError) as cm:
decoder.decode(b'!', final=True)
self.assertEqual(cm.exception.reason,
'illegal multibyte sequence')
self.assertEqual((cm.exception.start, cm.exception.end), (0, 1))
# One illegal byte is reported, so error handlers still work.
decoder = codecs.getincrementaldecoder(name)(errors='replace')
decoder.setstate((b'', 0xff))
self.assertEqual(decoder.decode(b'!', final=True), '\ufffd')
class Test_StreamReader(unittest.TestCase):
def test_bug1728403(self):
try:
f = open(TESTFN, 'wb')
try:
f.write(b'\xa1')
finally:
f.close()
with self.assertWarns(DeprecationWarning):
f = codecs.open(TESTFN, encoding='cp949')
try:
self.assertRaises(UnicodeDecodeError, f.read, 2)
finally:
f.close()
finally:
os_helper.unlink(TESTFN)
class Test_StreamWriter(unittest.TestCase):
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('\uac00\u00ac')
self.assertEqual(s.getvalue(),
b'123\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')
c.write('\uac00\u00ac')
self.assertEqual(s.getvalue(),
b'123\xf0\x92\x8d\x85'
b'\xea\xb0\x80\xc2\xac')
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))
@support.requires_resource('cpu')
def test_bug1572832(self):
for x in range(0x10000, 0x110000):
# Any ISO 2022 codec will cause the segfault
chr(x).encode('iso_2022_jp', 'ignore')
class TestStateful(unittest.TestCase):
text = '\u4E16\u4E16'
encoding = 'iso-2022-jp'
expected = b'\x1b$B@$@$'
reset = b'\x1b(B'
expected_reset = expected + reset
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)
self.assertEqual(encoder.encode('', final=True), self.reset)
self.assertEqual(encoder.encode('', final=True), b'')
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)
self.assertEqual(encoder.encode('', final=True), b'')
def test_streamwriter_reset(self):
stream = io.BytesIO()
writer = codecs.getwriter(self.encoding)(stream)
writer.reset()
self.assertEqual(stream.getvalue(), b'')
writer.write(self.text)
self.assertEqual(stream.getvalue(), self.expected)
writer.reset()
self.assertEqual(stream.getvalue(), self.expected_reset)
writer.reset()
self.assertEqual(stream.getvalue(), self.expected_reset)
writer.write(self.text)
writer.reset()
self.assertEqual(stream.getvalue(), self.expected_reset * 2)
def test_streamwriter_seek0(self):
# The reset sequence is written before the stream is rewound.
info = codecs.lookup(self.encoding)
for wrap in (
info.streamwriter,
lambda stream: codecs.StreamReaderWriter(
stream, info.streamreader, info.streamwriter),
lambda stream: codecs.EncodedFile(stream, 'utf-8', self.encoding),
):
stream = io.BytesIO()
writer = wrap(stream)
text = self.text
if isinstance(writer, codecs.StreamRecoder):
text = text.encode()
writer.write(text)
writer.seek(0)
self.assertEqual(stream.tell(), 0)
self.assertEqual(stream.getvalue(), self.expected_reset)
writer.write(text)
self.assertEqual(stream.getvalue(), self.expected_reset)
def test_incrementalencoder_error(self):
# The output of a failed encode() is lost, so the shift state
# must not be changed.
encoder = codecs.getincrementalencoder(self.encoding)()
state = encoder.getstate()
for final in False, True:
self.assertRaises(UnicodeEncodeError, encoder.encode,
self.text + '\U0001f600', final)
self.assertEqual(encoder.getstate(), state)
self.assertEqual(encoder.encode(self.text), self.expected)
state = encoder.getstate()
for final in False, True:
self.assertRaises(UnicodeEncodeError, encoder.encode,
'a\U0001f600', final)
self.assertEqual(encoder.getstate(), state)
self.assertEqual(encoder.encode('a'), self.reset + b'a')
def test_streamwriter_error(self):
stream = io.BytesIO()
writer = codecs.getwriter(self.encoding)(stream)
self.assertRaises(UnicodeEncodeError, writer.write,
self.text + '\U0001f600')
self.assertEqual(stream.getvalue(), b'')
writer.write(self.text)
self.assertEqual(stream.getvalue(), self.expected)
def test_textiowrapper_error(self):
raw = io.BytesIO()
with io.TextIOWrapper(raw, encoding=self.encoding) as f:
self.assertRaises(UnicodeEncodeError, f.write,
self.text + '\U0001f600')
f.write(self.text)
f.flush()
self.assertEqual(raw.getvalue(), self.expected)
class TestISO2022KRStateful(TestStateful):
text = '\uac00\uac00'
encoding = 'iso-2022-kr'
expected = b'\x1b$)C\x0e0!0!'
reset = b'\x0f'
expected_reset = expected + reset
class TestHZStateful(TestStateful):
text = '\u804a\u804a'
encoding = 'hz'
expected = b'~{ADAD'
reset = b'~}'
expected_reset = expected + reset
if __name__ == "__main__":
unittest.main()