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
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
|
import unittest
from test import support
import binascii
import pickle
import random
import sys
from test.support import bigmemtest, _1G, _4G
zlib = support.import_module('zlib')
requires_Compress_copy = unittest.skipUnless(
hasattr(zlib.compressobj(), "copy"),
'requires Compress.copy()')
requires_Decompress_copy = unittest.skipUnless(
hasattr(zlib.decompressobj(), "copy"),
'requires Decompress.copy()')
class VersionTestCase(unittest.TestCase):
def test_library_version(self):
# Test that the major version of the actual library in use matches the
# major version that we were compiled against. We can't guarantee that
# the minor versions will match (even on the machine on which the module
# was compiled), and the API is stable between minor versions, so
# testing only the major versions avoids spurious failures.
self.assertEqual(zlib.ZLIB_RUNTIME_VERSION[0], zlib.ZLIB_VERSION[0])
class ChecksumTestCase(unittest.TestCase):
# checksum test cases
def test_crc32start(self):
self.assertEqual(zlib.crc32(b""), zlib.crc32(b"", 0))
self.assertTrue(zlib.crc32(b"abc", 0xffffffff))
def test_crc32empty(self):
self.assertEqual(zlib.crc32(b"", 0), 0)
self.assertEqual(zlib.crc32(b"", 1), 1)
self.assertEqual(zlib.crc32(b"", 432), 432)
def test_adler32start(self):
self.assertEqual(zlib.adler32(b""), zlib.adler32(b"", 1))
self.assertTrue(zlib.adler32(b"abc", 0xffffffff))
def test_adler32empty(self):
self.assertEqual(zlib.adler32(b"", 0), 0)
self.assertEqual(zlib.adler32(b"", 1), 1)
self.assertEqual(zlib.adler32(b"", 432), 432)
def test_penguins(self):
self.assertEqual(zlib.crc32(b"penguin", 0), 0x0e5c1a120)
self.assertEqual(zlib.crc32(b"penguin", 1), 0x43b6aa94)
self.assertEqual(zlib.adler32(b"penguin", 0), 0x0bcf02f6)
self.assertEqual(zlib.adler32(b"penguin", 1), 0x0bd602f7)
self.assertEqual(zlib.crc32(b"penguin"), zlib.crc32(b"penguin", 0))
self.assertEqual(zlib.adler32(b"penguin"),zlib.adler32(b"penguin",1))
def test_crc32_adler32_unsigned(self):
foo = b'abcdefghijklmnop'
# explicitly test signed behavior
self.assertEqual(zlib.crc32(foo), 2486878355)
self.assertEqual(zlib.crc32(b'spam'), 1138425661)
self.assertEqual(zlib.adler32(foo+foo), 3573550353)
self.assertEqual(zlib.adler32(b'spam'), 72286642)
def test_same_as_binascii_crc32(self):
foo = b'abcdefghijklmnop'
crc = 2486878355
self.assertEqual(binascii.crc32(foo), crc)
self.assertEqual(zlib.crc32(foo), crc)
self.assertEqual(binascii.crc32(b'spam'), zlib.crc32(b'spam'))
# Issue #10276 - check that inputs >=4GB are handled correctly.
class ChecksumBigBufferTestCase(unittest.TestCase):
@bigmemtest(size=_4G + 4, memuse=1, dry_run=False)
def test_big_buffer(self, size):
data = b"nyan" * (_1G + 1)
self.assertEqual(zlib.crc32(data), 1044521549)
self.assertEqual(zlib.adler32(data), 2256789997)
class ExceptionTestCase(unittest.TestCase):
# make sure we generate some expected errors
def test_badlevel(self):
# specifying compression level out of range causes an error
# (but -1 is Z_DEFAULT_COMPRESSION and apparently the zlib
# accepts 0 too)
self.assertRaises(zlib.error, zlib.compress, b'ERROR', 10)
def test_badargs(self):
self.assertRaises(TypeError, zlib.adler32)
self.assertRaises(TypeError, zlib.crc32)
self.assertRaises(TypeError, zlib.compress)
self.assertRaises(TypeError, zlib.decompress)
for arg in (42, None, '', 'abc', (), []):
self.assertRaises(TypeError, zlib.adler32, arg)
self.assertRaises(TypeError, zlib.crc32, arg)
self.assertRaises(TypeError, zlib.compress, arg)
self.assertRaises(TypeError, zlib.decompress, arg)
def test_badcompressobj(self):
# verify failure on building compress object with bad params
self.assertRaises(ValueError, zlib.compressobj, 1, zlib.DEFLATED, 0)
# specifying total bits too large causes an error
self.assertRaises(ValueError,
zlib.compressobj, 1, zlib.DEFLATED, zlib.MAX_WBITS + 1)
def test_baddecompressobj(self):
# verify failure on building decompress object with bad params
self.assertRaises(ValueError, zlib.decompressobj, -1)
def test_decompressobj_badflush(self):
# verify failure on calling decompressobj.flush with bad params
self.assertRaises(ValueError, zlib.decompressobj().flush, 0)
self.assertRaises(ValueError, zlib.decompressobj().flush, -1)
@support.cpython_only
def test_overflow(self):
with self.assertRaisesRegex(OverflowError, 'int too large'):
zlib.decompress(b'', 15, sys.maxsize + 1)
with self.assertRaisesRegex(OverflowError, 'int too large'):
zlib.decompressobj().flush(sys.maxsize + 1)
class BaseCompressTestCase(object):
def check_big_compress_buffer(self, size, compress_func):
_1M = 1024 * 1024
# Generate 10MB worth of random, and expand it by repeating it.
# The assumption is that zlib's memory is not big enough to exploit
# such spread out redundancy.
data = b''.join([random.getrandbits(8 * _1M).to_bytes(_1M, 'little')
for i in range(10)])
data = data * (size // len(data) + 1)
try:
compress_func(data)
finally:
# Release memory
data = None
def check_big_decompress_buffer(self, size, decompress_func):
data = b'x' * size
try:
compressed = zlib.compress(data, 1)
finally:
# Release memory
data = None
data = decompress_func(compressed)
# Sanity check
try:
self.assertEqual(len(data), size)
self.assertEqual(len(data.strip(b'x')), 0)
finally:
data = None
class CompressTestCase(BaseCompressTestCase, unittest.TestCase):
# Test compression in one go (whole message compression)
def test_speech(self):
x = zlib.compress(HAMLET_SCENE)
self.assertEqual(zlib.decompress(x), HAMLET_SCENE)
def test_keywords(self):
x = zlib.compress(data=HAMLET_SCENE, level=3)
self.assertEqual(zlib.decompress(x), HAMLET_SCENE)
def test_speech128(self):
# compress more data
data = HAMLET_SCENE * 128
x = zlib.compress(data)
self.assertEqual(zlib.compress(bytearray(data)), x)
for ob in x, bytearray(x):
self.assertEqual(zlib.decompress(ob), data)
def test_incomplete_stream(self):
# A useful error message is given
x = zlib.compress(HAMLET_SCENE)
self.assertRaisesRegex(zlib.error,
"Error -5 while decompressing data: incomplete or truncated stream",
zlib.decompress, x[:-1])
# Memory use of the following functions takes into account overallocation
@bigmemtest(size=_1G + 1024 * 1024, memuse=3)
def test_big_compress_buffer(self, size):
compress = lambda s: zlib.compress(s, 1)
self.check_big_compress_buffer(size, compress)
@bigmemtest(size=_1G + 1024 * 1024, memuse=2)
def test_big_decompress_buffer(self, size):
self.check_big_decompress_buffer(size, zlib.decompress)
@bigmemtest(size=_4G + 100, memuse=1, dry_run=False)
def test_length_overflow(self, size):
data = b'x' * size
try:
self.assertRaises(OverflowError, zlib.compress, data, 1)
self.assertRaises(OverflowError, zlib.decompress, data)
finally:
data = None
@bigmemtest(size=_4G, memuse=1)
def test_large_bufsize(self, size):
# Test decompress(bufsize) parameter greater than the internal limit
data = HAMLET_SCENE * 10
compressed = zlib.compress(data, 1)
self.assertEqual(zlib.decompress(compressed, 15, size), data)
def test_custom_bufsize(self):
data = HAMLET_SCENE * 10
compressed = zlib.compress(data, 1)
self.assertEqual(zlib.decompress(compressed, 15, CustomInt()), data)
class CompressObjectTestCase(BaseCompressTestCase, unittest.TestCase):
# Test compression object
def test_pair(self):
# straightforward compress/decompress objects
datasrc = HAMLET_SCENE * 128
datazip = zlib.compress(datasrc)
# should compress both bytes and bytearray data
for data in (datasrc, bytearray(datasrc)):
co = zlib.compressobj()
x1 = co.compress(data)
x2 = co.flush()
self.assertRaises(zlib.error, co.flush) # second flush should not work
self.assertEqual(x1 + x2, datazip)
for v1, v2 in ((x1, x2), (bytearray(x1), bytearray(x2))):
dco = zlib.decompressobj()
y1 = dco.decompress(v1 + v2)
y2 = dco.flush()
self.assertEqual(data, y1 + y2)
self.assertIsInstance(dco.unconsumed_tail, bytes)
self.assertIsInstance(dco.unused_data, bytes)
def test_compressoptions(self):
# specify lots of options to compressobj()
level = 2
method = zlib.DEFLATED
wbits = -12
memLevel = 9
strategy = zlib.Z_FILTERED
co = zlib.compressobj(level, method, wbits, memLevel, strategy)
x1 = co.compress(HAMLET_SCENE)
x2 = co.flush()
dco = zlib.decompressobj(wbits)
y1 = dco.decompress(x1 + x2)
y2 = dco.flush()
self.assertEqual(HAMLET_SCENE, y1 + y2)
# keyword arguments should also be supported
zlib.compressobj(level=level, method=method, wbits=wbits,
memLevel=memLevel, strategy=strategy, zdict=b"")
def test_compressincremental(self):
# compress object in steps, decompress object as one-shot
data = HAMLET_SCENE * 128
co = zlib.compressobj()
bufs = []
for i in range(0, len(data), 256):
bufs.append(co.compress(data[i:i+256]))
bufs.append(co.flush())
combuf = b''.join(bufs)
dco = zlib.decompressobj()
y1 = dco.decompress(b''.join(bufs))
y2 = dco.flush()
self.assertEqual(data, y1 + y2)
def test_decompinc(self, flush=False, source=None, cx=256, dcx=64):
# compress object in steps, decompress object in steps
source = source or HAMLET_SCENE
data = source * 128
co = zlib.compressobj()
bufs = []
for i in range(0, len(data), cx):
bufs.append(co.compress(data[i:i+cx]))
bufs.append(co.flush())
combuf = b''.join(bufs)
decombuf = zlib.decompress(combuf)
# Test type of return value
self.assertIsInstance(decombuf, bytes)
self.assertEqual(data, decombuf)
dco = zlib.decompressobj()
bufs = []
for i in range(0, len(combuf), dcx):
bufs.append(dco.decompress(combuf[i:i+dcx]))
self.assertEqual(b'', dco.unconsumed_tail, ########
"(A) uct should be b'': not %d long" %
len(dco.unconsumed_tail))
self.assertEqual(b'', dco.unused_data)
if flush:
bufs.append(dco.flush())
else:
while True:
chunk = dco.decompress(b'')
if chunk:
bufs.append(chunk)
else:
break
self.assertEqual(b'', dco.unconsumed_tail, ########
"(B) uct should be b'': not %d long" %
len(dco.unconsumed_tail))
self.assertEqual(b'', dco.unused_data)
self.assertEqual(data, b''.join(bufs))
# Failure means: "decompressobj with init options failed"
def test_decompincflush(self):
self.test_decompinc(flush=True)
def test_decompimax(self, source=None, cx=256, dcx=64):
# compress in steps, decompress in length-restricted steps
source = source or HAMLET_SCENE
# Check a decompression object with max_length specified
data = source * 128
co = zlib.compressobj()
bufs = []
for i in range(0, len(data), cx):
bufs.append(co.compress(data[i:i+cx]))
bufs.append(co.flush())
combuf = b''.join(bufs)
self.assertEqual(data, zlib.decompress(combuf),
'compressed data failure')
dco = zlib.decompressobj()
bufs = []
cb = combuf
while cb:
#max_length = 1 + len(cb)//10
chunk = dco.decompress(cb, dcx)
self.assertFalse(len(chunk) > dcx,
'chunk too big (%d>%d)' % (len(chunk), dcx))
bufs.append(chunk)
cb = dco.unconsumed_tail
bufs.append(dco.flush())
self.assertEqual(data, b''.join(bufs), 'Wrong data retrieved')
def test_decompressmaxlen(self, flush=False):
# Check a decompression object with max_length specified
data = HAMLET_SCENE * 128
co = zlib.compressobj()
bufs = []
for i in range(0, len(data), 256):
bufs.append(co.compress(data[i:i+256]))
bufs.append(co.flush())
combuf = b''.join(bufs)
self.assertEqual(data, zlib.decompress(combuf),
'compressed data failure')
dco = zlib.decompressobj()
bufs = []
cb = combuf
while cb:
max_length = 1 + len(cb)//10
chunk = dco.decompress(cb, max_length)
self.assertFalse(len(chunk) > max_length,
'chunk too big (%d>%d)' % (len(chunk),max_length))
bufs.append(chunk)
cb = dco.unconsumed_tail
if flush:
bufs.append(dco.flush())
else:
while chunk:
chunk = dco.decompress(b'', max_length)
self.assertFalse(len(chunk) > max_length,
'chunk too big (%d>%d)' % (len(chunk),max_length))
bufs.append(chunk)
self.assertEqual(data, b''.join(bufs), 'Wrong data retrieved')
def test_decompressmaxlenflush(self):
self.test_decompressmaxlen(flush=True)
def test_maxlenmisc(self):
# Misc tests of max_length
dco = zlib.decompressobj()
self.assertRaises(ValueError, dco.decompress, b"", -1)
self.assertEqual(b'', dco.unconsumed_tail)
def test_maxlen_large(self):
# Sizes up to sys.maxsize should be accepted, although zlib is
# internally limited to expressing sizes with unsigned int
data = HAMLET_SCENE * 10
self.assertGreater(len(data), zlib.DEF_BUF_SIZE)
compressed = zlib.compress(data, 1)
dco = zlib.decompressobj()
self.assertEqual(dco.decompress(compressed, sys.maxsize), data)
def test_maxlen_custom(self):
data = HAMLET_SCENE * 10
compressed = zlib.compress(data, 1)
dco = zlib.decompressobj()
self.assertEqual(dco.decompress(compressed, CustomInt()), data[:100])
def test_clear_unconsumed_tail(self):
# Issue #12050: calling decompress() without providing max_length
# should clear the unconsumed_tail attribute.
cdata = b"x\x9cKLJ\x06\x00\x02M\x01" # "abc"
dco = zlib.decompressobj()
ddata = dco.decompress(cdata, 1)
ddata += dco.decompress(dco.unconsumed_tail)
self.assertEqual(dco.unconsumed_tail, b"")
def test_flushes(self):
# Test flush() with the various options, using all the
# different levels in order to provide more variations.
sync_opt = ['Z_NO_FLUSH', 'Z_SYNC_FLUSH', 'Z_FULL_FLUSH']
sync_opt = [getattr(zlib, opt) for opt in sync_opt
if hasattr(zlib, opt)]
data = HAMLET_SCENE * 8
for sync in sync_opt:
for level in range(10):
obj = zlib.compressobj( level )
a = obj.compress( data[:3000] )
b = obj.flush( sync )
c = obj.compress( data[3000:] )
d = obj.flush()
self.assertEqual(zlib.decompress(b''.join([a,b,c,d])),
data, ("Decompress failed: flush "
"mode=%i, level=%i") % (sync, level))
del obj
@unittest.skipUnless(hasattr(zlib, 'Z_SYNC_FLUSH'),
'requires zlib.Z_SYNC_FLUSH')
def test_odd_flush(self):
# Test for odd flushing bugs noted in 2.0, and hopefully fixed in 2.1
import random
# Testing on 17K of "random" data
# Create compressor and decompressor objects
co = zlib.compressobj(zlib.Z_BEST_COMPRESSION)
dco = zlib.decompressobj()
# Try 17K of data
# generate random data stream
try:
# In 2.3 and later, WichmannHill is the RNG of the bug report
gen = random.WichmannHill()
except AttributeError:
try:
# 2.2 called it Random
gen = random.Random()
except AttributeError:
# others might simply have a single RNG
gen = random
gen.seed(1)
data = genblock(1, 17 * 1024, generator=gen)
# compress, sync-flush, and decompress
first = co.compress(data)
second = co.flush(zlib.Z_SYNC_FLUSH)
expanded = dco.decompress(first + second)
# if decompressed data is different from the input data, choke.
self.assertEqual(expanded, data, "17K random source doesn't match")
def test_empty_flush(self):
# Test that calling .flush() on unused objects works.
# (Bug #1083110 -- calling .flush() on decompress objects
# caused a core dump.)
co = zlib.compressobj(zlib.Z_BEST_COMPRESSION)
self.assertTrue(co.flush()) # Returns a zlib header
dco = zlib.decompressobj()
self.assertEqual(dco.flush(), b"") # Returns nothing
def test_dictionary(self):
h = HAMLET_SCENE
# Build a simulated dictionary out of the words in HAMLET.
words = h.split()
random.shuffle(words)
zdict = b''.join(words)
# Use it to compress HAMLET.
co = zlib.compressobj(zdict=zdict)
cd = co.compress(h) + co.flush()
# Verify that it will decompress with the dictionary.
dco = zlib.decompressobj(zdict=zdict)
self.assertEqual(dco.decompress(cd) + dco.flush(), h)
# Verify that it fails when not given the dictionary.
dco = zlib.decompressobj()
self.assertRaises(zlib.error, dco.decompress, cd)
def test_dictionary_streaming(self):
# This simulates the reuse of a compressor object for compressing
# several separate data streams.
co = zlib.compressobj(zdict=HAMLET_SCENE)
do = zlib.decompressobj(zdict=HAMLET_SCENE)
piece = HAMLET_SCENE[1000:1500]
d0 = co.compress(piece) + co.flush(zlib.Z_SYNC_FLUSH)
d1 = co.compress(piece[100:]) + co.flush(zlib.Z_SYNC_FLUSH)
d2 = co.compress(piece[:-100]) + co.flush(zlib.Z_SYNC_FLUSH)
self.assertEqual(do.decompress(d0), piece)
self.assertEqual(do.decompress(d1), piece[100:])
self.assertEqual(do.decompress(d2), piece[:-100])
def test_decompress_incomplete_stream(self):
# This is 'foo', deflated
x = b'x\x9cK\xcb\xcf\x07\x00\x02\x82\x01E'
# For the record
self.assertEqual(zlib.decompress(x), b'foo')
self.assertRaises(zlib.error, zlib.decompress, x[:-5])
# Omitting the stream end works with decompressor objects
# (see issue #8672).
dco = zlib.decompressobj()
y = dco.decompress(x[:-5])
y += dco.flush()
self.assertEqual(y, b'foo')
def test_decompress_eof(self):
x = b'x\x9cK\xcb\xcf\x07\x00\x02\x82\x01E' # 'foo'
dco = zlib.decompressobj()
self.assertFalse(dco.eof)
dco.decompress(x[:-5])
self.assertFalse(dco.eof)
dco.decompress(x[-5:])
self.assertTrue(dco.eof)
dco.flush()
self.assertTrue(dco.eof)
def test_decompress_eof_incomplete_stream(self):
x = b'x\x9cK\xcb\xcf\x07\x00\x02\x82\x01E' # 'foo'
dco = zlib.decompressobj()
self.assertFalse(dco.eof)
dco.decompress(x[:-5])
self.assertFalse(dco.eof)
dco.flush()
self.assertFalse(dco.eof)
def test_decompress_unused_data(self):
# Repeated calls to decompress() after EOF should accumulate data in
# dco.unused_data, instead of just storing the arg to the last call.
source = b'abcdefghijklmnopqrstuvwxyz'
remainder = b'0123456789'
y = zlib.compress(source)
x = y + remainder
for maxlen in 0, 1000:
for step in 1, 2, len(y), len(x):
dco = zlib.decompressobj()
data = b''
for i in range(0, len(x), step):
if i < len(y):
self.assertEqual(dco.unused_data, b'')
if maxlen == 0:
data += dco.decompress(x[i : i + step])
self.assertEqual(dco.unconsumed_tail, b'')
else:
data += dco.decompress(
dco.unconsumed_tail + x[i : i + step], maxlen)
data += dco.flush()
self.assertTrue(dco.eof)
self.assertEqual(data, source)
self.assertEqual(dco.unconsumed_tail, b'')
self.assertEqual(dco.unused_data, remainder)
# issue27164
def test_decompress_raw_with_dictionary(self):
zdict = b'abcdefghijklmnopqrstuvwxyz'
co = zlib.compressobj(wbits=-zlib.MAX_WBITS, zdict=zdict)
comp = co.compress(zdict) + co.flush()
dco = zlib.decompressobj(wbits=-zlib.MAX_WBITS, zdict=zdict)
uncomp = dco.decompress(comp) + dco.flush()
self.assertEqual(zdict, uncomp)
def test_flush_with_freed_input(self):
# Issue #16411: decompressor accesses input to last decompress() call
# in flush(), even if this object has been freed in the meanwhile.
input1 = b'abcdefghijklmnopqrstuvwxyz'
input2 = b'QWERTYUIOPASDFGHJKLZXCVBNM'
data = zlib.compress(input1)
dco = zlib.decompressobj()
dco.decompress(data, 1)
del data
data = zlib.compress(input2)
self.assertEqual(dco.flush(), input1[1:])
@bigmemtest(size=_4G, memuse=1)
def test_flush_large_length(self, size):
# Test flush(length) parameter greater than internal limit UINT_MAX
input = HAMLET_SCENE * 10
data = zlib.compress(input, 1)
dco = zlib.decompressobj()
dco.decompress(data, 1)
self.assertEqual(dco.flush(size), input[1:])
def test_flush_custom_length(self):
input = HAMLET_SCENE * 10
data = zlib.compress(input, 1)
dco = zlib.decompressobj()
dco.decompress(data, 1)
self.assertEqual(dco.flush(CustomInt()), input[1:])
@requires_Compress_copy
def test_compresscopy(self):
# Test copying a compression object
data0 = HAMLET_SCENE
data1 = bytes(str(HAMLET_SCENE, "ascii").swapcase(), "ascii")
c0 = zlib.compressobj(zlib.Z_BEST_COMPRESSION)
bufs0 = []
bufs0.append(c0.compress(data0))
c1 = c0.copy()
bufs1 = bufs0[:]
bufs0.append(c0.compress(data0))
bufs0.append(c0.flush())
s0 = b''.join(bufs0)
bufs1.append(c1.compress(data1))
bufs1.append(c1.flush())
s1 = b''.join(bufs1)
self.assertEqual(zlib.decompress(s0),data0+data0)
self.assertEqual(zlib.decompress(s1),data0+data1)
@requires_Compress_copy
def test_badcompresscopy(self):
# Test copying a compression object in an inconsistent state
c = zlib.compressobj()
c.compress(HAMLET_SCENE)
c.flush()
self.assertRaises(ValueError, c.copy)
@requires_Decompress_copy
def test_decompresscopy(self):
# Test copying a decompression object
data = HAMLET_SCENE
comp = zlib.compress(data)
# Test type of return value
self.assertIsInstance(comp, bytes)
d0 = zlib.decompressobj()
bufs0 = []
bufs0.append(d0.decompress(comp[:32]))
d1 = d0.copy()
bufs1 = bufs0[:]
bufs0.append(d0.decompress(comp[32:]))
s0 = b''.join(bufs0)
bufs1.append(d1.decompress(comp[32:]))
s1 = b''.join(bufs1)
self.assertEqual(s0,s1)
self.assertEqual(s0,data)
@requires_Decompress_copy
def test_baddecompresscopy(self):
# Test copying a compression object in an inconsistent state
data = zlib.compress(HAMLET_SCENE)
d = zlib.decompressobj()
d.decompress(data)
d.flush()
self.assertRaises(ValueError, d.copy)
def test_compresspickle(self):
for proto in range(pickle.HIGHEST_PROTOCOL + 1):
with self.assertRaises((TypeError, pickle.PicklingError)):
pickle.dumps(zlib.compressobj(zlib.Z_BEST_COMPRESSION), proto)
def test_decompresspickle(self):
for proto in range(pickle.HIGHEST_PROTOCOL + 1):
with self.assertRaises((TypeError, pickle.PicklingError)):
pickle.dumps(zlib.decompressobj(), proto)
# Memory use of the following functions takes into account overallocation
@bigmemtest(size=_1G + 1024 * 1024, memuse=3)
def test_big_compress_buffer(self, size):
c = zlib.compressobj(1)
compress = lambda s: c.compress(s) + c.flush()
self.check_big_compress_buffer(size, compress)
@bigmemtest(size=_1G + 1024 * 1024, memuse=2)
def test_big_decompress_buffer(self, size):
d = zlib.decompressobj()
decompress = lambda s: d.decompress(s) + d.flush()
self.check_big_decompress_buffer(size, decompress)
@bigmemtest(size=_4G + 100, memuse=1, dry_run=False)
def test_length_overflow(self, size):
data = b'x' * size
c = zlib.compressobj(1)
d = zlib.decompressobj()
try:
self.assertRaises(OverflowError, c.compress, data)
self.assertRaises(OverflowError, d.decompress, data)
finally:
data = None
def test_wbits(self):
# wbits=0 only supported since zlib v1.2.3.5
# Register "1.2.3" as "1.2.3.0"
v = (zlib.ZLIB_RUNTIME_VERSION + ".0").split(".", 4)
supports_wbits_0 = int(v[0]) > 1 or int(v[0]) == 1 \
and (int(v[1]) > 2 or int(v[1]) == 2
and (int(v[2]) > 3 or int(v[2]) == 3 and int(v[3]) >= 5))
co = zlib.compressobj(level=1, wbits=15)
zlib15 = co.compress(HAMLET_SCENE) + co.flush()
self.assertEqual(zlib.decompress(zlib15, 15), HAMLET_SCENE)
if supports_wbits_0:
self.assertEqual(zlib.decompress(zlib15, 0), HAMLET_SCENE)
self.assertEqual(zlib.decompress(zlib15, 32 + 15), HAMLET_SCENE)
with self.assertRaisesRegex(zlib.error, 'invalid window size'):
zlib.decompress(zlib15, 14)
dco = zlib.decompressobj(wbits=32 + 15)
self.assertEqual(dco.decompress(zlib15), HAMLET_SCENE)
dco = zlib.decompressobj(wbits=14)
with self.assertRaisesRegex(zlib.error, 'invalid window size'):
dco.decompress(zlib15)
co = zlib.compressobj(level=1, wbits=9)
zlib9 = co.compress(HAMLET_SCENE) + co.flush()
self.assertEqual(zlib.decompress(zlib9, 9), HAMLET_SCENE)
self.assertEqual(zlib.decompress(zlib9, 15), HAMLET_SCENE)
if supports_wbits_0:
self.assertEqual(zlib.decompress(zlib9, 0), HAMLET_SCENE)
self.assertEqual(zlib.decompress(zlib9, 32 + 9), HAMLET_SCENE)
dco = zlib.decompressobj(wbits=32 + 9)
self.assertEqual(dco.decompress(zlib9), HAMLET_SCENE)
co = zlib.compressobj(level=1, wbits=-15)
deflate15 = co.compress(HAMLET_SCENE) + co.flush()
self.assertEqual(zlib.decompress(deflate15, -15), HAMLET_SCENE)
dco = zlib.decompressobj(wbits=-15)
self.assertEqual(dco.decompress(deflate15), HAMLET_SCENE)
co = zlib.compressobj(level=1, wbits=-9)
deflate9 = co.compress(HAMLET_SCENE) + co.flush()
self.assertEqual(zlib.decompress(deflate9, -9), HAMLET_SCENE)
self.assertEqual(zlib.decompress(deflate9, -15), HAMLET_SCENE)
dco = zlib.decompressobj(wbits=-9)
self.assertEqual(dco.decompress(deflate9), HAMLET_SCENE)
co = zlib.compressobj(level=1, wbits=16 + 15)
gzip = co.compress(HAMLET_SCENE) + co.flush()
self.assertEqual(zlib.decompress(gzip, 16 + 15), HAMLET_SCENE)
self.assertEqual(zlib.decompress(gzip, 32 + 15), HAMLET_SCENE)
dco = zlib.decompressobj(32 + 15)
self.assertEqual(dco.decompress(gzip), HAMLET_SCENE)
def genblock(seed, length, step=1024, generator=random):
"""length-byte stream of random data from a seed (in step-byte blocks)."""
if seed is not None:
generator.seed(seed)
randint = generator.randint
if length < step or step < 2:
step = length
blocks = bytes()
for i in range(0, length, step):
blocks += bytes(randint(0, 255) for x in range(step))
return blocks
def choose_lines(source, number, seed=None, generator=random):
"""Return a list of number lines randomly chosen from the source"""
if seed is not None:
generator.seed(seed)
sources = source.split('\n')
return [generator.choice(sources) for n in range(number)]
HAMLET_SCENE = b"""
LAERTES
O, fear me not.
I stay too long: but here my father comes.
Enter POLONIUS
A double blessing is a double grace,
Occasion smiles upon a second leave.
LORD POLONIUS
Yet here, Laertes! aboard, aboard, for shame!
The wind sits in the shoulder of your sail,
And you are stay'd for. There; my blessing with thee!
And these few precepts in thy memory
See thou character. Give thy thoughts no tongue,
Nor any unproportioned thought his act.
Be thou familiar, but by no means vulgar.
Those friends thou hast, and their adoption tried,
Grapple them to thy soul with hoops of steel;
But do not dull thy palm with entertainment
Of each new-hatch'd, unfledged comrade. Beware
Of entrance to a quarrel, but being in,
Bear't that the opposed may beware of thee.
Give every man thy ear, but few thy voice;
Take each man's censure, but reserve thy judgment.
Costly thy habit as thy purse can buy,
But not express'd in fancy; rich, not gaudy;
For the apparel oft proclaims the man,
And they in France of the best rank and station
Are of a most select and generous chief in that.
Neither a borrower nor a lender be;
For loan oft loses both itself and friend,
And borrowing dulls the edge of husbandry.
This above all: to thine ownself be true,
And it must follow, as the night the day,
Thou canst not then be false to any man.
Farewell: my blessing season this in thee!
LAERTES
Most humbly do I take my leave, my lord.
LORD POLONIUS
The time invites you; go; your servants tend.
LAERTES
Farewell, Ophelia; and remember well
What I have said to you.
OPHELIA
'Tis in my memory lock'd,
And you yourself shall keep the key of it.
LAERTES
Farewell.
"""
class CustomInt:
def __int__(self):
return 100
if __name__ == "__main__":
unittest.main()
|