summaryrefslogtreecommitdiff
path: root/Lib/test/test_zlib.py
blob: 3718ca7533f891083298acd03962883bfe27507a (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
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
import unittest
from test import support
import binascii
import random

zlib = support.import_module('zlib')


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 assertEqual32(self, seen, expected):
        # 32-bit values masked -- checksums on 32- vs 64- bit machines
        # This is important if bit 31 (0x08000000L) is set.
        self.assertEqual(seen & 0x0FFFFFFFF, expected & 0x0FFFFFFFF)

    def test_penguins(self):
        self.assertEqual32(zlib.crc32(b"penguin", 0), 0x0e5c1a120)
        self.assertEqual32(zlib.crc32(b"penguin", 1), 0x43b6aa94)
        self.assertEqual32(zlib.adler32(b"penguin", 0), 0x0bcf02f6)
        self.assertEqual32(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 = 'abcdefghijklmnop'
        # explicitly test signed behavior
        self.assertEqual(zlib.crc32(foo), 2486878355)
        self.assertEqual(zlib.crc32('spam'), 1138425661)
        self.assertEqual(zlib.adler32(foo+foo), 3573550353)
        self.assertEqual(zlib.adler32('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'))



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, 'ERROR', 10)

    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, 0)

    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)



class CompressTestCase(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_speech128(self):
        # compress more data
        data = HAMLET_SCENE * 128
        x = zlib.compress(data)
        self.assertEqual(zlib.decompress(x), data)




class CompressObjectTestCase(unittest.TestCase):
    # Test compression object
    def test_pair(self):
        # straightforward compress/decompress objects
        data = HAMLET_SCENE * 128
        co = zlib.compressobj()
        x1 = co.compress(data)
        x2 = co.flush()
        self.assertRaises(zlib.error, co.flush) # second flush should not work
        dco = zlib.decompressobj()
        y1 = dco.decompress(x1 + x2)
        y2 = dco.flush()
        self.assertEqual(data, y1 + y2)
        self.assertTrue(isinstance(dco.unconsumed_tail, bytes))
        self.assertTrue(isinstance(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)

    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.assertTrue(isinstance(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('')
                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('', 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, "", -1)
        self.assertEqual(b'', dco.unconsumed_tail)

    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

    def test_odd_flush(self):
        # Test for odd flushing bugs noted in 2.0, and hopefully fixed in 2.1
        import random

        if hasattr(zlib, 'Z_SYNC_FLUSH'):
            # 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

    if hasattr(zlib.compressobj(), "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)

        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)

    if hasattr(zlib.decompressobj(), "copy"):
        def test_decompresscopy(self):
            # Test copying a decompression object
            data = HAMLET_SCENE
            comp = zlib.compress(data)
            # Test type of return value
            self.assertTrue(isinstance(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)

        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 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.
"""


def test_main():
    support.run_unittest(
        ChecksumTestCase,
        ExceptionTestCase,
        CompressTestCase,
        CompressObjectTestCase
    )

if __name__ == "__main__":
    unittest.main() # XXX
    ###test_main()