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
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
|
import test.test_support, unittest
import sys, codecs, htmlentitydefs, unicodedata
class CodecCallbackTest(unittest.TestCase):
def test_xmlcharrefreplace(self):
# replace unencodable characters which numeric character entities.
# For ascii, latin-1 and charmaps this is completely implemented
# in C and should be reasonably fast.
s = u"\u30b9\u30d1\u30e2 \xe4nd eggs"
self.assertEqual(
s.encode("ascii", "xmlcharrefreplace"),
"スパモ änd eggs"
)
self.assertEqual(
s.encode("latin-1", "xmlcharrefreplace"),
"スパモ \xe4nd eggs"
)
def test_xmlcharnamereplace(self):
# This time use a named character entity for unencodable
# characters, if one is available.
names = {}
for (key, value) in htmlentitydefs.entitydefs.items():
if len(value)==1:
names[unicode(value, "latin-1")] = unicode(key, "latin-1")
else:
names[unichr(int(value[2:-1]))] = unicode(key, "latin-1")
def xmlcharnamereplace(exc):
if not isinstance(exc, UnicodeEncodeError):
raise TypeError("don't know how to handle %r" % exc)
l = []
for c in exc.object[exc.start:exc.end]:
try:
l.append(u"&%s;" % names[c])
except KeyError:
l.append(u"&#%d;" % ord(c))
return (u"".join(l), exc.end)
codecs.register_error(
"test.xmlcharnamereplace", xmlcharnamereplace)
sin = u"\xab\u211c\xbb = \u2329\u1234\u20ac\u232a"
sout = "«ℜ» = ⟨ሴ€⟩"
self.assertEqual(sin.encode("ascii", "test.xmlcharnamereplace"), sout)
sout = "\xabℜ\xbb = ⟨ሴ€⟩"
self.assertEqual(sin.encode("latin-1", "test.xmlcharnamereplace"), sout)
sout = "\xabℜ\xbb = ⟨ሴ\xa4⟩"
self.assertEqual(sin.encode("iso-8859-15", "test.xmlcharnamereplace"), sout)
def test_uninamereplace(self):
# We're using the names from the unicode database this time,
# and we're doing "syntax highlighting" here, i.e. we include
# the replaced text in ANSI escape sequences. For this it is
# useful that the error handler is not called for every single
# unencodable character, but for a complete sequence of
# unencodable characters, otherwise we would output many
# unneccessary escape sequences.
def uninamereplace(exc):
if not isinstance(exc, UnicodeEncodeError):
raise TypeError("don't know how to handle %r" % exc)
l = []
for c in exc.object[exc.start:exc.end]:
l.append(unicodedata.name(c, u"0x%x" % ord(c)))
return (u"\033[1m%s\033[0m" % u", ".join(l), exc.end)
codecs.register_error(
"test.uninamereplace", uninamereplace)
sin = u"\xac\u1234\u20ac\u8000"
sout = "\033[1mNOT SIGN, ETHIOPIC SYLLABLE SEE, EURO SIGN, CJK UNIFIED IDEOGRAPH-8000\033[0m"
self.assertEqual(sin.encode("ascii", "test.uninamereplace"), sout)
sout = "\xac\033[1mETHIOPIC SYLLABLE SEE, EURO SIGN, CJK UNIFIED IDEOGRAPH-8000\033[0m"
self.assertEqual(sin.encode("latin-1", "test.uninamereplace"), sout)
sout = "\xac\033[1mETHIOPIC SYLLABLE SEE\033[0m\xa4\033[1mCJK UNIFIED IDEOGRAPH-8000\033[0m"
self.assertEqual(sin.encode("iso-8859-15", "test.uninamereplace"), sout)
def test_backslashescape(self):
# Does the same as the "unicode-escape" encoding, but with different
# base encodings.
sin = u"a\xac\u1234\u20ac\u8000"
if sys.maxunicode > 0xffff:
sin += unichr(sys.maxunicode)
sout = "a\\xac\\u1234\\u20ac\\u8000"
if sys.maxunicode > 0xffff:
sout += "\\U%08x" % sys.maxunicode
self.assertEqual(sin.encode("ascii", "backslashreplace"), sout)
sout = "a\xac\\u1234\\u20ac\\u8000"
if sys.maxunicode > 0xffff:
sout += "\\U%08x" % sys.maxunicode
self.assertEqual(sin.encode("latin-1", "backslashreplace"), sout)
sout = "a\xac\\u1234\xa4\\u8000"
if sys.maxunicode > 0xffff:
sout += "\\U%08x" % sys.maxunicode
self.assertEqual(sin.encode("iso-8859-15", "backslashreplace"), sout)
def test_relaxedutf8(self):
# This is the test for a decoding callback handler,
# that relaxes the UTF-8 minimal encoding restriction.
# A null byte that is encoded as "\xc0\x80" will be
# decoded as a null byte. All other illegal sequences
# will be handled strictly.
def relaxedutf8(exc):
if not isinstance(exc, UnicodeDecodeError):
raise TypeError("don't know how to handle %r" % exc)
if exc.object[exc.start:exc.end].startswith("\xc0\x80"):
return (u"\x00", exc.start+2) # retry after two bytes
else:
raise exc
codecs.register_error(
"test.relaxedutf8", relaxedutf8)
sin = "a\x00b\xc0\x80c\xc3\xbc\xc0\x80\xc0\x80"
sout = u"a\x00b\x00c\xfc\x00\x00"
self.assertEqual(sin.decode("utf-8", "test.relaxedutf8"), sout)
sin = "\xc0\x80\xc0\x81"
self.assertRaises(UnicodeError, sin.decode, "utf-8", "test.relaxedutf8")
def test_charmapencode(self):
# For charmap encodings the replacement string will be
# mapped through the encoding again. This means, that
# to be able to use e.g. the "replace" handler, the
# charmap has to have a mapping for "?".
charmap = dict([ (ord(c), 2*c.upper()) for c in "abcdefgh"])
sin = u"abc"
sout = "AABBCC"
self.assertEquals(codecs.charmap_encode(sin, "strict", charmap)[0], sout)
sin = u"abcA"
self.assertRaises(UnicodeError, codecs.charmap_encode, sin, "strict", charmap)
charmap[ord("?")] = "XYZ"
sin = u"abcDEF"
sout = "AABBCCXYZXYZXYZ"
self.assertEquals(codecs.charmap_encode(sin, "replace", charmap)[0], sout)
charmap[ord("?")] = u"XYZ"
self.assertRaises(TypeError, codecs.charmap_encode, sin, "replace", charmap)
charmap[ord("?")] = u"XYZ"
self.assertRaises(TypeError, codecs.charmap_encode, sin, "replace", charmap)
def test_callbacks(self):
def handler1(exc):
if not isinstance(exc, UnicodeEncodeError) \
and not isinstance(exc, UnicodeDecodeError):
raise TypeError("don't know how to handle %r" % exc)
l = [u"<%d>" % ord(exc.object[pos]) for pos in xrange(exc.start, exc.end)]
return (u"[%s]" % u"".join(l), exc.end)
codecs.register_error("test.handler1", handler1)
def handler2(exc):
if not isinstance(exc, UnicodeDecodeError):
raise TypeError("don't know how to handle %r" % exc)
l = [u"<%d>" % ord(exc.object[pos]) for pos in xrange(exc.start, exc.end)]
return (u"[%s]" % u"".join(l), exc.end+1) # skip one character
codecs.register_error("test.handler2", handler2)
s = "\x00\x81\x7f\x80\xff"
self.assertEqual(
s.decode("ascii", "test.handler1"),
u"\x00[<129>]\x7f[<128>][<255>]"
)
self.assertEqual(
s.decode("ascii", "test.handler2"),
u"\x00[<129>][<128>]"
)
self.assertEqual(
"\\u3042\u3xxx".decode("unicode-escape", "test.handler1"),
u"\u3042[<92><117><51><120>]xx"
)
self.assertEqual(
"\\u3042\u3xx".decode("unicode-escape", "test.handler1"),
u"\u3042[<92><117><51><120><120>]"
)
self.assertEqual(
codecs.charmap_decode("abc", "test.handler1", {ord("a"): u"z"})[0],
u"z[<98>][<99>]"
)
self.assertEqual(
u"g\xfc\xdfrk".encode("ascii", "test.handler1"),
u"g[<252><223>]rk"
)
self.assertEqual(
u"g\xfc\xdf".encode("ascii", "test.handler1"),
u"g[<252><223>]"
)
def test_longstrings(self):
# test long strings to check for memory overflow problems
errors = [ "strict", "ignore", "replace", "xmlcharrefreplace", "backslashreplace"]
# register the handlers under different names,
# to prevent the codec from recognizing the name
for err in errors:
codecs.register_error("test." + err, codecs.lookup_error(err))
l = 1000
errors += [ "test." + err for err in errors ]
for uni in [ s*l for s in (u"x", u"\u3042", u"a\xe4") ]:
for enc in ("ascii", "latin-1", "iso-8859-1", "iso-8859-15", "utf-8", "utf-7", "utf-16"):
for err in errors:
try:
uni.encode(enc, err)
except UnicodeError:
pass
def check_exceptionobjectargs(self, exctype, args, msg):
# Test UnicodeError subclasses: construction, attribute assignment and __str__ conversion
# check with one missing argument
self.assertRaises(TypeError, exctype, *args[:-1])
# check with one argument too much
self.assertRaises(TypeError, exctype, *(args + ["too much"]))
# check with one argument of the wrong type
wrongargs = [ "spam", u"eggs", 42, 1.0, None ]
for i in xrange(len(args)):
for wrongarg in wrongargs:
if type(wrongarg) is type(args[i]):
continue
# build argument array
callargs = []
for j in xrange(len(args)):
if i==j:
callargs.append(wrongarg)
else:
callargs.append(args[i])
self.assertRaises(TypeError, exctype, *callargs)
# check with the correct number and type of arguments
exc = exctype(*args)
self.assertEquals(str(exc), msg)
def test_unicodeencodeerror(self):
self.check_exceptionobjectargs(
UnicodeEncodeError,
["ascii", u"g\xfcrk", 1, 2, "ouch"],
"'ascii' codec can't encode character '\ufc' in position 1: ouch"
)
self.check_exceptionobjectargs(
UnicodeEncodeError,
["ascii", u"g\xfcrk", 1, 4, "ouch"],
"'ascii' codec can't encode characters in position 1-3: ouch"
)
self.check_exceptionobjectargs(
UnicodeEncodeError,
["ascii", u"\xfcx", 0, 1, "ouch"],
"'ascii' codec can't encode character '\ufc' in position 0: ouch"
)
def test_unicodedecodeerror(self):
self.check_exceptionobjectargs(
UnicodeDecodeError,
["ascii", "g\xfcrk", 1, 2, "ouch"],
"'ascii' codec can't decode byte 0xfc in position 1: ouch"
)
self.check_exceptionobjectargs(
UnicodeDecodeError,
["ascii", "g\xfcrk", 1, 3, "ouch"],
"'ascii' codec can't decode bytes in position 1-2: ouch"
)
def test_unicodetranslateerror(self):
self.check_exceptionobjectargs(
UnicodeTranslateError,
[u"g\xfcrk", 1, 2, "ouch"],
"can't translate character '\\ufc' in position 1: ouch"
)
self.check_exceptionobjectargs(
UnicodeTranslateError,
[u"g\xfcrk", 1, 3, "ouch"],
"can't translate characters in position 1-2: ouch"
)
def test_badandgoodstrictexceptions(self):
# "strict" complains about a non-exception passed in
self.assertRaises(
TypeError,
codecs.strict_errors,
42
)
# "strict" complains about the wrong exception type
self.assertRaises(
Exception,
codecs.strict_errors,
Exception("ouch")
)
# If the correct exception is passed in, "strict" raises it
self.assertRaises(
UnicodeEncodeError,
codecs.strict_errors,
UnicodeEncodeError("ascii", u"\u3042", 0, 1, "ouch")
)
def test_badandgoodignoreexceptions(self):
# "ignore" complains about a non-exception passed in
self.assertRaises(
TypeError,
codecs.ignore_errors,
42
)
# "ignore" complains about the wrong exception type
self.assertRaises(
TypeError,
codecs.ignore_errors,
UnicodeError("ouch")
)
# If the correct exception is passed in, "ignore" returns an empty replacement
self.assertEquals(
codecs.ignore_errors(UnicodeEncodeError("ascii", u"\u3042", 0, 1, "ouch")),
(u"", 1)
)
self.assertEquals(
codecs.ignore_errors(UnicodeDecodeError("ascii", "\xff", 0, 1, "ouch")),
(u"", 1)
)
self.assertEquals(
codecs.ignore_errors(UnicodeTranslateError(u"\u3042", 0, 1, "ouch")),
(u"", 1)
)
def test_badandgoodreplaceexceptions(self):
# "replace" complains about a non-exception passed in
self.assertRaises(
TypeError,
codecs.replace_errors,
42
)
# "replace" complains about the wrong exception type
self.assertRaises(
TypeError,
codecs.replace_errors,
UnicodeError("ouch")
)
# With the correct exception, "ignore" returns an empty replacement
self.assertEquals(
codecs.replace_errors(UnicodeEncodeError("ascii", u"\u3042", 0, 1, "ouch")),
(u"?", 1)
)
self.assertEquals(
codecs.replace_errors(UnicodeDecodeError("ascii", "\xff", 0, 1, "ouch")),
(u"\ufffd", 1)
)
self.assertEquals(
codecs.replace_errors(UnicodeTranslateError(u"\u3042", 0, 1, "ouch")),
(u"\ufffd", 1)
)
def test_badandgoodxmlcharrefreplaceexceptions(self):
# "xmlcharrefreplace" complains about a non-exception passed in
self.assertRaises(
TypeError,
codecs.xmlcharrefreplace_errors,
42
)
# "xmlcharrefreplace" complains about the wrong exception types
self.assertRaises(
TypeError,
codecs.xmlcharrefreplace_errors,
UnicodeError("ouch")
)
# "xmlcharrefreplace" can only be used for encoding
self.assertRaises(
TypeError,
codecs.xmlcharrefreplace_errors,
UnicodeDecodeError("ascii", "\xff", 0, 1, "ouch")
)
self.assertRaises(
TypeError,
codecs.xmlcharrefreplace_errors,
UnicodeTranslateError(u"\u3042", 0, 1, "ouch")
)
# Use the correct exception
self.assertEquals(
codecs.xmlcharrefreplace_errors(UnicodeEncodeError("ascii", u"\u3042", 0, 1, "ouch")),
(u"&#%d;" % 0x3042, 1)
)
def test_badandgoodbackslashreplaceexceptions(self):
# "backslashreplace" complains about a non-exception passed in
self.assertRaises(
TypeError,
codecs.backslashreplace_errors,
42
)
# "backslashreplace" complains about the wrong exception types
self.assertRaises(
TypeError,
codecs.backslashreplace_errors,
UnicodeError("ouch")
)
# "backslashreplace" can only be used for encoding
self.assertRaises(
TypeError,
codecs.backslashreplace_errors,
UnicodeDecodeError("ascii", "\xff", 0, 1, "ouch")
)
self.assertRaises(
TypeError,
codecs.backslashreplace_errors,
UnicodeTranslateError(u"\u3042", 0, 1, "ouch")
)
# Use the correct exception
self.assertEquals(
codecs.backslashreplace_errors(UnicodeEncodeError("ascii", u"\u3042", 0, 1, "ouch")),
(u"\\u3042", 1)
)
self.assertEquals(
codecs.backslashreplace_errors(UnicodeEncodeError("ascii", u"\x00", 0, 1, "ouch")),
(u"\\x00", 1)
)
self.assertEquals(
codecs.backslashreplace_errors(UnicodeEncodeError("ascii", u"\xff", 0, 1, "ouch")),
(u"\\xff", 1)
)
self.assertEquals(
codecs.backslashreplace_errors(UnicodeEncodeError("ascii", u"\u0100", 0, 1, "ouch")),
(u"\\u0100", 1)
)
self.assertEquals(
codecs.backslashreplace_errors(UnicodeEncodeError("ascii", u"\uffff", 0, 1, "ouch")),
(u"\\uffff", 1)
)
if sys.maxunicode>0xffff:
self.assertEquals(
codecs.backslashreplace_errors(UnicodeEncodeError("ascii", u"\U00010000", 0, 1, "ouch")),
(u"\\U00010000", 1)
)
self.assertEquals(
codecs.backslashreplace_errors(UnicodeEncodeError("ascii", u"\U0010ffff", 0, 1, "ouch")),
(u"\\U0010ffff", 1)
)
def test_badhandlerresults(self):
results = ( 42, u"foo", (1,2,3), (u"foo", 1, 3), (u"foo", None), (u"foo",), ("foo", 1, 3), ("foo", None), ("foo",) )
encs = ("ascii", "latin-1", "iso-8859-1", "iso-8859-15")
for res in results:
codecs.register_error("test.badhandler", lambda: res)
for enc in encs:
self.assertRaises(
TypeError,
u"\u3042".encode,
enc,
"test.badhandler"
)
for (enc, bytes) in (
("ascii", "\xff"),
("utf-8", "\xff"),
("utf-7", "+x-")
):
self.assertRaises(
TypeError,
bytes.decode,
enc,
"test.badhandler"
)
def test_lookup(self):
self.assertEquals(codecs.strict_errors, codecs.lookup_error("strict"))
self.assertEquals(codecs.ignore_errors, codecs.lookup_error("ignore"))
self.assertEquals(codecs.strict_errors, codecs.lookup_error("strict"))
self.assertEquals(
codecs.xmlcharrefreplace_errors,
codecs.lookup_error("xmlcharrefreplace")
)
self.assertEquals(
codecs.backslashreplace_errors,
codecs.lookup_error("backslashreplace")
)
def test_unencodablereplacement(self):
def unencrepl(exc):
if isinstance(exc, UnicodeEncodeError):
return (u"\u4242", exc.end)
else:
raise TypeError("don't know how to handle %r" % exc)
codecs.register_error("test.unencreplhandler", unencrepl)
for enc in ("ascii", "iso-8859-1", "iso-8859-15"):
self.assertRaises(
UnicodeEncodeError,
u"\u4242".encode,
enc,
"test.unencreplhandler"
)
def test_badregistercall(self):
# enhance coverage of:
# Modules/_codecsmodule.c::register_error()
# Python/codecs.c::PyCodec_RegisterError()
self.assertRaises(TypeError, codecs.register_error, 42)
self.assertRaises(TypeError, codecs.register_error, "test.dummy", 42)
def test_unknownhandler(self):
# enhance coverage of:
# Modules/_codecsmodule.c::lookup_error()
self.assertRaises(LookupError, codecs.lookup_error, "test.unknown")
def test_xmlcharrefvalues(self):
# enhance coverage of:
# Python/codecs.c::PyCodec_XMLCharRefReplaceErrors()
# and inline implementations
v = (1, 5, 10, 50, 100, 500, 1000, 5000, 10000, 50000)
if sys.maxunicode>=100000:
v += (100000, 500000, 1000000)
s = u"".join([unichr(x) for x in v])
codecs.register_error("test.xmlcharrefreplace", codecs.xmlcharrefreplace_errors)
for enc in ("ascii", "iso-8859-15"):
for err in ("xmlcharrefreplace", "test.xmlcharrefreplace"):
s.encode(enc, err)
def test_decodehelper(self):
# enhance coverage of:
# Objects/unicodeobject.c::unicode_decode_call_errorhandler()
# and callers
self.assertRaises(LookupError, "\xff".decode, "ascii", "test.unknown")
def baddecodereturn1(exc):
return 42
codecs.register_error("test.baddecodereturn1", baddecodereturn1)
self.assertRaises(TypeError, "\xff".decode, "ascii", "test.baddecodereturn1")
self.assertRaises(TypeError, "\\".decode, "unicode-escape", "test.baddecodereturn1")
self.assertRaises(TypeError, "\\x0".decode, "unicode-escape", "test.baddecodereturn1")
self.assertRaises(TypeError, "\\x0y".decode, "unicode-escape", "test.baddecodereturn1")
self.assertRaises(TypeError, "\\Uffffeeee".decode, "unicode-escape", "test.baddecodereturn1")
self.assertRaises(TypeError, "\\uyyyy".decode, "raw-unicode-escape", "test.baddecodereturn1")
def baddecodereturn2(exc):
return (u"?", None)
codecs.register_error("test.baddecodereturn2", baddecodereturn2)
self.assertRaises(TypeError, "\xff".decode, "ascii", "test.baddecodereturn2")
pos = [-42]
def negposreturn(exc):
pos[0] += 1 # use list to work around scoping problem
return (u"?", pos[0])
codecs.register_error("test.negposreturn", negposreturn)
"\xff".decode("ascii", "test.negposreturn")
def hugeposreturn(exc):
return (u"?", 424242)
codecs.register_error("test.hugeposreturn", hugeposreturn)
"\xff".decode("ascii", "test.hugeposreturn")
"\\uyyyy".decode("raw-unicode-escape", "test.hugeposreturn")
class D(dict):
def __getitem__(self, key):
raise ValueError
self.assertRaises(UnicodeError, codecs.charmap_decode, "\xff", "strict", {0xff: None})
self.assertRaises(ValueError, codecs.charmap_decode, "\xff", "strict", D())
self.assertRaises(TypeError, codecs.charmap_decode, "\xff", "strict", {0xff: sys.maxunicode+1})
def test_encodehelper(self):
# enhance coverage of:
# Objects/unicodeobject.c::unicode_encode_call_errorhandler()
# and callers
self.assertRaises(LookupError, u"\xff".encode, "ascii", "test.unknown")
def badencodereturn1(exc):
return 42
codecs.register_error("test.badencodereturn1", badencodereturn1)
self.assertRaises(TypeError, u"\xff".encode, "ascii", "test.badencodereturn1")
def badencodereturn2(exc):
return (u"?", None)
codecs.register_error("test.badencodereturn2", badencodereturn2)
self.assertRaises(TypeError, u"\xff".encode, "ascii", "test.badencodereturn2")
pos = [-42]
def negposreturn(exc):
pos[0] += 1 # use list to work around scoping problem
return (u"?", pos[0])
codecs.register_error("test.negposreturn", negposreturn)
u"\xff".encode("ascii", "test.negposreturn")
def hugeposreturn(exc):
return (u"?", 424242)
codecs.register_error("test.hugeposreturn", hugeposreturn)
u"\xff".encode("ascii", "test.hugeposreturn")
class D(dict):
def __getitem__(self, key):
raise ValueError
for err in ("strict", "replace", "xmlcharrefreplace", "backslashreplace", "test.hugeposreturn"):
self.assertRaises(UnicodeError, codecs.charmap_encode, u"\xff", err, {0xff: None})
self.assertRaises(ValueError, codecs.charmap_encode, u"\xff", err, D())
self.assertRaises(TypeError, codecs.charmap_encode, u"\xff", err, {0xff: 300})
def test_translatehelper(self):
# enhance coverage of:
# Objects/unicodeobject.c::unicode_encode_call_errorhandler()
# and callers
# (Unfortunately the errors argument is not directly accessible
# from Python, so we can't test that much)
class D(dict):
def __getitem__(self, key):
raise ValueError
self.assertRaises(ValueError, u"\xff".translate, D())
self.assertRaises(TypeError, u"\xff".translate, {0xff: sys.maxunicode+1})
self.assertRaises(TypeError, u"\xff".translate, {0xff: ()})
def test_main():
suite = unittest.TestSuite()
suite.addTest(unittest.makeSuite(CodecCallbackTest))
test.test_support.run_suite(suite)
if __name__ == "__main__":
test_main()
|