summaryrefslogtreecommitdiffstats
path: root/Lib/test/test_gzip.py
blob: 52894077c9cd1bb7e61f972bda227147717d9329 (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
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
"""Test script for the gzip module.
"""

import unittest
from test import support
import os
import io
import struct
gzip = support.import_module('gzip')

data1 = b"""  int length=DEFAULTALLOC, err = Z_OK;
  PyObject *RetVal;
  int flushmode = Z_FINISH;
  unsigned long start_total_out;

"""

data2 = b"""/* zlibmodule.c -- gzip-compatible data compression */
/* See http://www.gzip.org/zlib/
/* See http://www.winimage.com/zLibDll for Windows */
"""


class UnseekableIO(io.BytesIO):
    def seekable(self):
        return False

    def tell(self):
        raise io.UnsupportedOperation

    def seek(self, *args):
        raise io.UnsupportedOperation


class BaseTest(unittest.TestCase):
    filename = support.TESTFN

    def setUp(self):
        support.unlink(self.filename)

    def tearDown(self):
        support.unlink(self.filename)


class TestGzip(BaseTest):
    def test_write(self):
        with gzip.GzipFile(self.filename, 'wb') as f:
            f.write(data1 * 50)

            # Try flush and fileno.
            f.flush()
            f.fileno()
            if hasattr(os, 'fsync'):
                os.fsync(f.fileno())
            f.close()

        # Test multiple close() calls.
        f.close()

    def test_read(self):
        self.test_write()
        # Try reading.
        with gzip.GzipFile(self.filename, 'r') as f:
            d = f.read()
        self.assertEqual(d, data1*50)

    def test_read1(self):
        self.test_write()
        blocks = []
        nread = 0
        with gzip.GzipFile(self.filename, 'r') as f:
            while True:
                d = f.read1()
                if not d:
                    break
                blocks.append(d)
                nread += len(d)
                # Check that position was updated correctly (see issue10791).
                self.assertEqual(f.tell(), nread)
        self.assertEqual(b''.join(blocks), data1 * 50)

    def test_io_on_closed_object(self):
        # Test that I/O operations on closed GzipFile objects raise a
        # ValueError, just like the corresponding functions on file objects.

        # Write to a file, open it for reading, then close it.
        self.test_write()
        f = gzip.GzipFile(self.filename, 'r')
        f.close()
        with self.assertRaises(ValueError):
            f.read(1)
        with self.assertRaises(ValueError):
            f.seek(0)
        with self.assertRaises(ValueError):
            f.tell()
        # Open the file for writing, then close it.
        f = gzip.GzipFile(self.filename, 'w')
        f.close()
        with self.assertRaises(ValueError):
            f.write(b'')
        with self.assertRaises(ValueError):
            f.flush()

    def test_append(self):
        self.test_write()
        # Append to the previous file
        with gzip.GzipFile(self.filename, 'ab') as f:
            f.write(data2 * 15)

        with gzip.GzipFile(self.filename, 'rb') as f:
            d = f.read()
        self.assertEqual(d, (data1*50) + (data2*15))

    def test_many_append(self):
        # Bug #1074261 was triggered when reading a file that contained
        # many, many members.  Create such a file and verify that reading it
        # works.
        with gzip.GzipFile(self.filename, 'wb', 9) as f:
            f.write(b'a')
        for i in range(0, 200):
            with gzip.GzipFile(self.filename, "ab", 9) as f: # append
                f.write(b'a')

        # Try reading the file
        with gzip.GzipFile(self.filename, "rb") as zgfile:
            contents = b""
            while 1:
                ztxt = zgfile.read(8192)
                contents += ztxt
                if not ztxt: break
        self.assertEqual(contents, b'a'*201)

    def test_exclusive_write(self):
        with gzip.GzipFile(self.filename, 'xb') as f:
            f.write(data1 * 50)
        with gzip.GzipFile(self.filename, 'rb') as f:
            self.assertEqual(f.read(), data1 * 50)
        with self.assertRaises(FileExistsError):
            gzip.GzipFile(self.filename, 'xb')

    def test_buffered_reader(self):
        # Issue #7471: a GzipFile can be wrapped in a BufferedReader for
        # performance.
        self.test_write()

        with gzip.GzipFile(self.filename, 'rb') as f:
            with io.BufferedReader(f) as r:
                lines = [line for line in r]

        self.assertEqual(lines, 50 * data1.splitlines(keepends=True))

    def test_readline(self):
        self.test_write()
        # Try .readline() with varying line lengths

        with gzip.GzipFile(self.filename, 'rb') as f:
            line_length = 0
            while 1:
                L = f.readline(line_length)
                if not L and line_length != 0: break
                self.assertTrue(len(L) <= line_length)
                line_length = (line_length + 1) % 50

    def test_readlines(self):
        self.test_write()
        # Try .readlines()

        with gzip.GzipFile(self.filename, 'rb') as f:
            L = f.readlines()

        with gzip.GzipFile(self.filename, 'rb') as f:
            while 1:
                L = f.readlines(150)
                if L == []: break

    def test_seek_read(self):
        self.test_write()
        # Try seek, read test

        with gzip.GzipFile(self.filename) as f:
            while 1:
                oldpos = f.tell()
                line1 = f.readline()
                if not line1: break
                newpos = f.tell()
                f.seek(oldpos)  # negative seek
                if len(line1)>10:
                    amount = 10
                else:
                    amount = len(line1)
                line2 = f.read(amount)
                self.assertEqual(line1[:amount], line2)
                f.seek(newpos)  # positive seek

    def test_seek_whence(self):
        self.test_write()
        # Try seek(whence=1), read test

        with gzip.GzipFile(self.filename) as f:
            f.read(10)
            f.seek(10, whence=1)
            y = f.read(10)
        self.assertEqual(y, data1[20:30])

    def test_seek_write(self):
        # Try seek, write test
        with gzip.GzipFile(self.filename, 'w') as f:
            for pos in range(0, 256, 16):
                f.seek(pos)
                f.write(b'GZ\n')

    def test_mode(self):
        self.test_write()
        with gzip.GzipFile(self.filename, 'r') as f:
            self.assertEqual(f.myfileobj.mode, 'rb')
        support.unlink(self.filename)
        with gzip.GzipFile(self.filename, 'x') as f:
            self.assertEqual(f.myfileobj.mode, 'xb')

    def test_1647484(self):
        for mode in ('wb', 'rb'):
            with gzip.GzipFile(self.filename, mode) as f:
                self.assertTrue(hasattr(f, "name"))
                self.assertEqual(f.name, self.filename)

    def test_paddedfile_getattr(self):
        self.test_write()
        with gzip.GzipFile(self.filename, 'rb') as f:
            self.assertTrue(hasattr(f.fileobj, "name"))
            self.assertEqual(f.fileobj.name, self.filename)

    def test_mtime(self):
        mtime = 123456789
        with gzip.GzipFile(self.filename, 'w', mtime = mtime) as fWrite:
            fWrite.write(data1)
        with gzip.GzipFile(self.filename) as fRead:
            dataRead = fRead.read()
            self.assertEqual(dataRead, data1)
            self.assertTrue(hasattr(fRead, 'mtime'))
            self.assertEqual(fRead.mtime, mtime)

    def test_metadata(self):
        mtime = 123456789

        with gzip.GzipFile(self.filename, 'w', mtime = mtime) as fWrite:
            fWrite.write(data1)

        with open(self.filename, 'rb') as fRead:
            # see RFC 1952: http://www.faqs.org/rfcs/rfc1952.html

            idBytes = fRead.read(2)
            self.assertEqual(idBytes, b'\x1f\x8b') # gzip ID

            cmByte = fRead.read(1)
            self.assertEqual(cmByte, b'\x08') # deflate

            flagsByte = fRead.read(1)
            self.assertEqual(flagsByte, b'\x08') # only the FNAME flag is set

            mtimeBytes = fRead.read(4)
            self.assertEqual(mtimeBytes, struct.pack('<i', mtime)) # little-endian

            xflByte = fRead.read(1)
            self.assertEqual(xflByte, b'\x02') # maximum compression

            osByte = fRead.read(1)
            self.assertEqual(osByte, b'\xff') # OS "unknown" (OS-independent)

            # Since the FNAME flag is set, the zero-terminated filename follows.
            # RFC 1952 specifies that this is the name of the input file, if any.
            # However, the gzip module defaults to storing the name of the output
            # file in this field.
            expected = self.filename.encode('Latin-1') + b'\x00'
            nameBytes = fRead.read(len(expected))
            self.assertEqual(nameBytes, expected)

            # Since no other flags were set, the header ends here.
            # Rather than process the compressed data, let's seek to the trailer.
            fRead.seek(os.stat(self.filename).st_size - 8)

            crc32Bytes = fRead.read(4) # CRC32 of uncompressed data [data1]
            self.assertEqual(crc32Bytes, b'\xaf\xd7d\x83')

            isizeBytes = fRead.read(4)
            self.assertEqual(isizeBytes, struct.pack('<i', len(data1)))

    def test_with_open(self):
        # GzipFile supports the context management protocol
        with gzip.GzipFile(self.filename, "wb") as f:
            f.write(b"xxx")
        f = gzip.GzipFile(self.filename, "rb")
        f.close()
        try:
            with f:
                pass
        except ValueError:
            pass
        else:
            self.fail("__enter__ on a closed file didn't raise an exception")
        try:
            with gzip.GzipFile(self.filename, "wb") as f:
                1/0
        except ZeroDivisionError:
            pass
        else:
            self.fail("1/0 didn't raise an exception")

    def test_zero_padded_file(self):
        with gzip.GzipFile(self.filename, "wb") as f:
            f.write(data1 * 50)

        # Pad the file with zeroes
        with open(self.filename, "ab") as f:
            f.write(b"\x00" * 50)

        with gzip.GzipFile(self.filename, "rb") as f:
            d = f.read()
            self.assertEqual(d, data1 * 50, "Incorrect data in file")

    def test_non_seekable_file(self):
        uncompressed = data1 * 50
        buf = UnseekableIO()
        with gzip.GzipFile(fileobj=buf, mode="wb") as f:
            f.write(uncompressed)
        compressed = buf.getvalue()
        buf = UnseekableIO(compressed)
        with gzip.GzipFile(fileobj=buf, mode="rb") as f:
            self.assertEqual(f.read(), uncompressed)

    def test_peek(self):
        uncompressed = data1 * 200
        with gzip.GzipFile(self.filename, "wb") as f:
            f.write(uncompressed)

        def sizes():
            while True:
                for n in range(5, 50, 10):
                    yield n

        with gzip.GzipFile(self.filename, "rb") as f:
            f.max_read_chunk = 33
            nread = 0
            for n in sizes():
                s = f.peek(n)
                if s == b'':
                    break
                self.assertEqual(f.read(len(s)), s)
                nread += len(s)
            self.assertEqual(f.read(100), b'')
            self.assertEqual(nread, len(uncompressed))

    def test_textio_readlines(self):
        # Issue #10791: TextIOWrapper.readlines() fails when wrapping GzipFile.
        lines = (data1 * 50).decode("ascii").splitlines(keepends=True)
        self.test_write()
        with gzip.GzipFile(self.filename, 'r') as f:
            with io.TextIOWrapper(f, encoding="ascii") as t:
                self.assertEqual(t.readlines(), lines)

    def test_fileobj_from_fdopen(self):
        # Issue #13781: Opening a GzipFile for writing fails when using a
        # fileobj created with os.fdopen().
        fd = os.open(self.filename, os.O_WRONLY | os.O_CREAT)
        with os.fdopen(fd, "wb") as f:
            with gzip.GzipFile(fileobj=f, mode="w") as g:
                pass

    def test_bytes_filename(self):
        str_filename = self.filename
        try:
            bytes_filename = str_filename.encode("ascii")
        except UnicodeEncodeError:
            self.skipTest("Temporary file name needs to be ASCII")
        with gzip.GzipFile(bytes_filename, "wb") as f:
            f.write(data1 * 50)
        with gzip.GzipFile(bytes_filename, "rb") as f:
            self.assertEqual(f.read(), data1 * 50)
        # Sanity check that we are actually operating on the right file.
        with gzip.GzipFile(str_filename, "rb") as f:
            self.assertEqual(f.read(), data1 * 50)

    # Testing compress/decompress shortcut functions

    def test_compress(self):
        for data in [data1, data2]:
            for args in [(), (1,), (6,), (9,)]:
                datac = gzip.compress(data, *args)
                self.assertEqual(type(datac), bytes)
                with gzip.GzipFile(fileobj=io.BytesIO(datac), mode="rb") as f:
                    self.assertEqual(f.read(), data)

    def test_decompress(self):
        for data in (data1, data2):
            buf = io.BytesIO()
            with gzip.GzipFile(fileobj=buf, mode="wb") as f:
                f.write(data)
            self.assertEqual(gzip.decompress(buf.getvalue()), data)
            # Roundtrip with compress
            datac = gzip.compress(data)
            self.assertEqual(gzip.decompress(datac), data)

    def test_read_truncated(self):
        data = data1*50
        # Drop the CRC (4 bytes) and file size (4 bytes).
        truncated = gzip.compress(data)[:-8]
        with gzip.GzipFile(fileobj=io.BytesIO(truncated)) as f:
            self.assertRaises(EOFError, f.read)
        with gzip.GzipFile(fileobj=io.BytesIO(truncated)) as f:
            self.assertEqual(f.read(len(data)), data)
            self.assertRaises(EOFError, f.read, 1)
        # Incomplete 10-byte header.
        for i in range(2, 10):
            with gzip.GzipFile(fileobj=io.BytesIO(truncated[:i])) as f:
                self.assertRaises(EOFError, f.read, 1)

    def test_read_with_extra(self):
        # Gzip data with an extra field
        gzdata = (b'\x1f\x8b\x08\x04\xb2\x17cQ\x02\xff'
                  b'\x05\x00Extra'
                  b'\x0bI-.\x01\x002\xd1Mx\x04\x00\x00\x00')
        with gzip.GzipFile(fileobj=io.BytesIO(gzdata)) as f:
            self.assertEqual(f.read(), b'Test')

class TestOpen(BaseTest):
    def test_binary_modes(self):
        uncompressed = data1 * 50

        with gzip.open(self.filename, "wb") as f:
            f.write(uncompressed)
        with open(self.filename, "rb") as f:
            file_data = gzip.decompress(f.read())
            self.assertEqual(file_data, uncompressed)

        with gzip.open(self.filename, "rb") as f:
            self.assertEqual(f.read(), uncompressed)

        with gzip.open(self.filename, "ab") as f:
            f.write(uncompressed)
        with open(self.filename, "rb") as f:
            file_data = gzip.decompress(f.read())
            self.assertEqual(file_data, uncompressed * 2)

        with self.assertRaises(FileExistsError):
            gzip.open(self.filename, "xb")
        support.unlink(self.filename)
        with gzip.open(self.filename, "xb") as f:
            f.write(uncompressed)
        with open(self.filename, "rb") as f:
            file_data = gzip.decompress(f.read())
            self.assertEqual(file_data, uncompressed)

    def test_implicit_binary_modes(self):
        # Test implicit binary modes (no "b" or "t" in mode string).
        uncompressed = data1 * 50

        with gzip.open(self.filename, "w") as f:
            f.write(uncompressed)
        with open(self.filename, "rb") as f:
            file_data = gzip.decompress(f.read())
            self.assertEqual(file_data, uncompressed)

        with gzip.open(self.filename, "r") as f:
            self.assertEqual(f.read(), uncompressed)

        with gzip.open(self.filename, "a") as f:
            f.write(uncompressed)
        with open(self.filename, "rb") as f:
            file_data = gzip.decompress(f.read())
            self.assertEqual(file_data, uncompressed * 2)

        with self.assertRaises(FileExistsError):
            gzip.open(self.filename, "x")
        support.unlink(self.filename)
        with gzip.open(self.filename, "x") as f:
            f.write(uncompressed)
        with open(self.filename, "rb") as f:
            file_data = gzip.decompress(f.read())
            self.assertEqual(file_data, uncompressed)

    def test_text_modes(self):
        uncompressed = data1.decode("ascii") * 50
        uncompressed_raw = uncompressed.replace("\n", os.linesep)
        with gzip.open(self.filename, "wt") as f:
            f.write(uncompressed)
        with open(self.filename, "rb") as f:
            file_data = gzip.decompress(f.read()).decode("ascii")
            self.assertEqual(file_data, uncompressed_raw)
        with gzip.open(self.filename, "rt") as f:
            self.assertEqual(f.read(), uncompressed)
        with gzip.open(self.filename, "at") as f:
            f.write(uncompressed)
        with open(self.filename, "rb") as f:
            file_data = gzip.decompress(f.read()).decode("ascii")
            self.assertEqual(file_data, uncompressed_raw * 2)

    def test_fileobj(self):
        uncompressed_bytes = data1 * 50
        uncompressed_str = uncompressed_bytes.decode("ascii")
        compressed = gzip.compress(uncompressed_bytes)
        with gzip.open(io.BytesIO(compressed), "r") as f:
            self.assertEqual(f.read(), uncompressed_bytes)
        with gzip.open(io.BytesIO(compressed), "rb") as f:
            self.assertEqual(f.read(), uncompressed_bytes)
        with gzip.open(io.BytesIO(compressed), "rt") as f:
            self.assertEqual(f.read(), uncompressed_str)

    def test_bad_params(self):
        # Test invalid parameter combinations.
        with self.assertRaises(TypeError):
            gzip.open(123.456)
        with self.assertRaises(ValueError):
            gzip.open(self.filename, "wbt")
        with self.assertRaises(ValueError):
            gzip.open(self.filename, "xbt")
        with self.assertRaises(ValueError):
            gzip.open(self.filename, "rb", encoding="utf-8")
        with self.assertRaises(ValueError):
            gzip.open(self.filename, "rb", errors="ignore")
        with self.assertRaises(ValueError):
            gzip.open(self.filename, "rb", newline="\n")

    def test_encoding(self):
        # Test non-default encoding.
        uncompressed = data1.decode("ascii") * 50
        uncompressed_raw = uncompressed.replace("\n", os.linesep)
        with gzip.open(self.filename, "wt", encoding="utf-16") as f:
            f.write(uncompressed)
        with open(self.filename, "rb") as f:
            file_data = gzip.decompress(f.read()).decode("utf-16")
            self.assertEqual(file_data, uncompressed_raw)
        with gzip.open(self.filename, "rt", encoding="utf-16") as f:
            self.assertEqual(f.read(), uncompressed)

    def test_encoding_error_handler(self):
        # Test with non-default encoding error handler.
        with gzip.open(self.filename, "wb") as f:
            f.write(b"foo\xffbar")
        with gzip.open(self.filename, "rt", encoding="ascii", errors="ignore") \
                as f:
            self.assertEqual(f.read(), "foobar")

    def test_newline(self):
        # Test with explicit newline (universal newline mode disabled).
        uncompressed = data1.decode("ascii") * 50
        with gzip.open(self.filename, "wt", newline="\n") as f:
            f.write(uncompressed)
        with gzip.open(self.filename, "rt", newline="\r") as f:
            self.assertEqual(f.readlines(), [uncompressed])

def test_main(verbose=None):
    support.run_unittest(TestGzip, TestOpen)

if __name__ == "__main__":
    test_main(verbose=True)