Repository navigation
Expand file tree
/
Copy pathgzip.py
More file actions
694 lines (580 loc) · 24.3 KB
/
Copy pathgzip.py
File metadata and controls
694 lines (580 loc) · 24.3 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
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
"""Functions that read and write gzipped files.
The user of the file doesn't have to worry about the compression,
but random access is not allowed."""
# based on Andrew Kuchling's minigzip.py distributed with the zlib module
import struct, sys, time, os
import zlib
import builtins
import io
import _compression
__all__ = ["BadGzipFile", "GzipFile", "open", "compress", "decompress"]
FTEXT, FHCRC, FEXTRA, FNAME, FCOMMENT = 1, 2, 4, 8, 16
READ, WRITE = 1, 2
_COMPRESS_LEVEL_FAST = 1
_COMPRESS_LEVEL_TRADEOFF = 6
_COMPRESS_LEVEL_BEST = 9
READ_BUFFER_SIZE = 128 * 1024
_WRITE_BUFFER_SIZE = 4 * io.DEFAULT_BUFFER_SIZE
def open(filename, mode="rb", compresslevel=_COMPRESS_LEVEL_BEST,
encoding=None, errors=None, newline=None):
"""Open a gzip-compressed file in binary or text mode.
The filename argument can be an actual filename (a str or bytes object), or
an existing file object to read from or write to.
The mode argument can be "r", "rb", "w", "wb", "x", "xb", "a" or "ab" for
binary mode, or "rt", "wt", "xt" or "at" for text mode. The default mode is
"rb", and the default compresslevel is 9.
For binary mode, this function is equivalent to the GzipFile constructor:
GzipFile(filename, mode, compresslevel). In this case, the encoding, errors
and newline arguments must not be provided.
For text mode, a GzipFile object is created, and wrapped in an
io.TextIOWrapper instance with the specified encoding, error handling
behavior, and line ending(s).
"""
if "t" in mode:
if "b" in mode:
raise ValueError("Invalid mode: %r" % (mode,))
else:
if encoding is not None:
raise ValueError("Argument 'encoding' not supported in binary mode")
if errors is not None:
raise ValueError("Argument 'errors' not supported in binary mode")
if newline is not None:
raise ValueError("Argument 'newline' not supported in binary mode")
gz_mode = mode.replace("t", "")
if isinstance(filename, (str, bytes, os.PathLike)):
binary_file = GzipFile(filename, gz_mode, compresslevel)
elif hasattr(filename, "read") or hasattr(filename, "write"):
binary_file = GzipFile(None, gz_mode, compresslevel, filename)
else:
raise TypeError("filename must be a str or bytes object, or a file")
if "t" in mode:
encoding = io.text_encoding(encoding)
return io.TextIOWrapper(binary_file, encoding, errors, newline)
else:
return binary_file
def write32u(output, value):
# The L format writes the bit pattern correctly whether signed
# or unsigned.
output.write(struct.pack("<L", value))
class _PaddedFile:
"""Minimal read-only file object that prepends a string to the contents
of an actual file. Shouldn't be used outside of gzip.py, as it lacks
essential functionality."""
def __init__(self, f, prepend=b''):
self._buffer = prepend
self._length = len(prepend)
self.file = f
self._read = 0
def read(self, size):
if self._read is None:
return self.file.read(size)
if self._read + size <= self._length:
read = self._read
self._read += size
return self._buffer[read:self._read]
else:
read = self._read
self._read = None
return self._buffer[read:] + \
self.file.read(size-self._length+read)
def prepend(self, prepend=b''):
if self._read is None:
self._buffer = prepend
else: # Assume data was read since the last prepend() call
self._read -= len(prepend)
return
self._length = len(self._buffer)
self._read = 0
def seek(self, off):
self._read = None
self._buffer = None
return self.file.seek(off)
def seekable(self):
return True # Allows fast-forwarding even in unseekable streams
class BadGzipFile(OSError):
"""Exception raised in some cases for invalid gzip files."""
class _WriteBufferStream(io.RawIOBase):
"""Minimal object to pass WriteBuffer flushes into GzipFile"""
def __init__(self, gzip_file):
self.gzip_file = gzip_file
def write(self, data):
return self.gzip_file._write_raw(data)
def seekable(self):
return False
def writable(self):
return True
class GzipFile(_compression.BaseStream):
"""The GzipFile class simulates most of the methods of a file object with
the exception of the truncate() method.
This class only supports opening files in binary mode. If you need to open a
compressed file in text mode, use the gzip.open() function.
"""
# Overridden with internal file object to be closed, if only a filename
# is passed in
myfileobj = None
def __init__(self, filename=None, mode=None,
compresslevel=_COMPRESS_LEVEL_BEST, fileobj=None, mtime=None):
"""Constructor for the GzipFile class.
At least one of fileobj and filename must be given a
non-trivial value.
The new class instance is based on fileobj, which can be a regular
file, an io.BytesIO object, or any other object which simulates a file.
It defaults to None, in which case filename is opened to provide
a file object.
When fileobj is not None, the filename argument is only used to be
included in the gzip file header, which may include the original
filename of the uncompressed file. It defaults to the filename of
fileobj, if discernible; otherwise, it defaults to the empty string,
and in this case the original filename is not included in the header.
The mode argument can be any of 'r', 'rb', 'a', 'ab', 'w', 'wb', 'x', or
'xb' depending on whether the file will be read or written. The default
is the mode of fileobj if discernible; otherwise, the default is 'rb'.
A mode of 'r' is equivalent to one of 'rb', and similarly for 'w' and
'wb', 'a' and 'ab', and 'x' and 'xb'.
The compresslevel argument is an integer from 0 to 9 controlling the
level of compression; 1 is fastest and produces the least compression,
and 9 is slowest and produces the most compression. 0 is no compression
at all. The default is 9.
The mtime argument is an optional numeric timestamp to be written
to the last modification time field in the stream when compressing.
If omitted or None, the current time is used.
"""
if mode and ('t' in mode or 'U' in mode):
raise ValueError("Invalid mode: {!r}".format(mode))
if mode and 'b' not in mode:
mode += 'b'
if fileobj is None:
fileobj = self.myfileobj = builtins.open(filename, mode or 'rb')
if filename is None:
filename = getattr(fileobj, 'name', '')
if not isinstance(filename, (str, bytes)):
filename = ''
else:
filename = os.fspath(filename)
origmode = mode
if mode is None:
mode = getattr(fileobj, 'mode', 'rb')
if mode.startswith('r'):
self.mode = READ
raw = _GzipReader(fileobj)
self._buffer = io.BufferedReader(raw)
self.name = filename
elif mode.startswith(('w', 'a', 'x')):
if origmode is None:
import warnings
warnings.warn(
"GzipFile was opened for writing, but this will "
"change in future Python releases. "
"Specify the mode argument for opening it for writing.",
FutureWarning, 2)
self.mode = WRITE
self._init_write(filename)
self.compress = zlib.compressobj(compresslevel,
zlib.DEFLATED,
-zlib.MAX_WBITS,
zlib.DEF_MEM_LEVEL,
0)
self._write_mtime = mtime
self._buffer_size = _WRITE_BUFFER_SIZE
self._buffer = io.BufferedWriter(_WriteBufferStream(self),
buffer_size=self._buffer_size)
else:
raise ValueError("Invalid mode: {!r}".format(mode))
self.fileobj = fileobj
if self.mode == WRITE:
self._write_gzip_header(compresslevel)
@property
def mtime(self):
"""Last modification time read from stream, or None"""
return self._buffer.raw._last_mtime
def __repr__(self):
s = repr(self.fileobj)
return '<gzip ' + s[1:-1] + ' ' + hex(id(self)) + '>'
def _init_write(self, filename):
self.name = filename
self.crc = zlib.crc32(b"")
self.size = 0
self.writebuf = []
self.bufsize = 0
self.offset = 0 # Current file offset for seek(), tell(), etc
def tell(self):
self._check_not_closed()
self._buffer.flush()
return super().tell()
def _write_gzip_header(self, compresslevel):
self.fileobj.write(b'\037\213') # magic header
self.fileobj.write(b'\010') # compression method
try:
# RFC 1952 requires the FNAME field to be Latin-1. Do not
# include filenames that cannot be represented that way.
fname = os.path.basename(self.name)
if not isinstance(fname, bytes):
fname = fname.encode('latin-1')
if fname.endswith(b'.gz'):
fname = fname[:-3]
except UnicodeEncodeError:
fname = b''
flags = 0
if fname:
flags = FNAME
self.fileobj.write(chr(flags).encode('latin-1'))
mtime = self._write_mtime
if mtime is None:
mtime = time.time()
write32u(self.fileobj, int(mtime))
if compresslevel == _COMPRESS_LEVEL_BEST:
xfl = b'\002'
elif compresslevel == _COMPRESS_LEVEL_FAST:
xfl = b'\004'
else:
xfl = b'\000'
self.fileobj.write(xfl)
self.fileobj.write(b'\377')
if fname:
self.fileobj.write(fname + b'\000')
def write(self,data):
self._check_not_closed()
if self.mode != WRITE:
import errno
raise OSError(errno.EBADF, "write() on read-only GzipFile object")
if self.fileobj is None:
raise ValueError("write() on closed GzipFile object")
return self._buffer.write(data)
def _write_raw(self, data):
# Called by our self._buffer underlying WriteBufferStream.
if isinstance(data, (bytes, bytearray)):
length = len(data)
else:
# accept any data that supports the buffer protocol
data = memoryview(data)
length = data.nbytes
if length > 0:
self.fileobj.write(self.compress.compress(data))
self.size += length
self.crc = zlib.crc32(data, self.crc)
self.offset += length
return length
def read(self, size=-1):
self._check_not_closed()
if self.mode != READ:
import errno
raise OSError(errno.EBADF, "read() on write-only GzipFile object")
return self._buffer.read(size)
def read1(self, size=-1):
"""Implements BufferedIOBase.read1()
Reads up to a buffer's worth of data if size is negative."""
self._check_not_closed()
if self.mode != READ:
import errno
raise OSError(errno.EBADF, "read1() on write-only GzipFile object")
if size < 0:
size = io.DEFAULT_BUFFER_SIZE
return self._buffer.read1(size)
def peek(self, n):
self._check_not_closed()
if self.mode != READ:
import errno
raise OSError(errno.EBADF, "peek() on write-only GzipFile object")
return self._buffer.peek(n)
@property
def closed(self):
return self.fileobj is None
def close(self):
fileobj = self.fileobj
if fileobj is None:
return
try:
if self.mode == WRITE:
self._buffer.flush()
fileobj.write(self.compress.flush())
write32u(fileobj, self.crc)
# self.size may exceed 2 GiB, or even 4 GiB
write32u(fileobj, self.size & 0xffffffff)
elif self.mode == READ:
self._buffer.close()
finally:
self.fileobj = None
myfileobj = self.myfileobj
if myfileobj:
self.myfileobj = None
myfileobj.close()
def flush(self,zlib_mode=zlib.Z_SYNC_FLUSH):
self._check_not_closed()
if self.mode == WRITE:
self._buffer.flush()
# Ensure the compressor's buffer is flushed
self.fileobj.write(self.compress.flush(zlib_mode))
self.fileobj.flush()
def fileno(self):
"""Invoke the underlying file object's fileno() method.
This will raise AttributeError if the underlying file object
doesn't support fileno().
"""
return self.fileobj.fileno()
def rewind(self):
'''Return the uncompressed stream file position indicator to the
beginning of the file'''
if self.mode != READ:
raise OSError("Can't rewind in write mode")
self._buffer.seek(0)
def readable(self):
return self.mode == READ
def writable(self):
return self.mode == WRITE
def seekable(self):
return True
def seek(self, offset, whence=io.SEEK_SET):
if self.mode == WRITE:
self._check_not_closed()
# Flush buffer to ensure validity of self.offset
self._buffer.flush()
if whence != io.SEEK_SET:
if whence == io.SEEK_CUR:
offset = self.offset + offset
else:
raise ValueError('Seek from end not supported')
if offset < self.offset:
raise OSError('Negative seek in write mode')
count = offset - self.offset
chunk = b'\0' * self._buffer_size
for i in range(count // self._buffer_size):
self.write(chunk)
self.write(b'\0' * (count % self._buffer_size))
elif self.mode == READ:
self._check_not_closed()
return self._buffer.seek(offset, whence)
return self.offset
def readline(self, size=-1):
self._check_not_closed()
return self._buffer.readline(size)
def _read_exact(fp, n):
'''Read exactly *n* bytes from `fp`
This method is required because fp may be unbuffered,
i.e. return short reads.
'''
data = fp.read(n)
while len(data) < n:
b = fp.read(n - len(data))
if not b:
raise EOFError("Compressed file ended before the "
"end-of-stream marker was reached")
data += b
return data
def _read_gzip_header(fp):
'''Read a gzip header from `fp` and progress to the end of the header.
Returns last mtime if header was present or None otherwise.
'''
magic = fp.read(2)
if magic == b'':
return None
if magic != b'\037\213':
raise BadGzipFile('Not a gzipped file (%r)' % magic)
(method, flag, last_mtime) = struct.unpack("<BBIxx", _read_exact(fp, 8))
if method != 8:
raise BadGzipFile('Unknown compression method')
if flag & FEXTRA:
# Read & discard the extra field, if present
extra_len, = struct.unpack("<H", _read_exact(fp, 2))
_read_exact(fp, extra_len)
if flag & FNAME:
# Read and discard a null-terminated string containing the filename
while True:
s = fp.read(1)
if not s or s==b'\000':
break
if flag & FCOMMENT:
# Read and discard a null-terminated string containing a comment
while True:
s = fp.read(1)
if not s or s==b'\000':
break
if flag & FHCRC:
_read_exact(fp, 2) # Read & discard the 16-bit header CRC
return last_mtime
class _GzipReader(_compression.DecompressReader):
def __init__(self, fp):
super().__init__(_PaddedFile(fp), zlib._ZlibDecompressor,
wbits=-zlib.MAX_WBITS)
# Set flag indicating start of a new member
self._new_member = True
self._last_mtime = None
def _init_read(self):
self._crc = zlib.crc32(b"")
self._stream_size = 0 # Decompressed size of unconcatenated stream
def _read_gzip_header(self):
last_mtime = _read_gzip_header(self._fp)
if last_mtime is None:
return False
self._last_mtime = last_mtime
return True
def read(self, size=-1):
if size < 0:
return self.readall()
# size=0 is special because decompress(max_length=0) is not supported
if not size:
return b""
# For certain input data, a single
# call to decompress() may not return
# any data. In this case, retry until we get some data or reach EOF.
while True:
if self._decompressor.eof:
# Ending case: we've come to the end of a member in the file,
# so finish up this member, and read a new gzip header.
# Check the CRC and file size, and set the flag so we read
# a new member
self._read_eof()
self._new_member = True
self._decompressor = self._decomp_factory(
**self._decomp_args)
if self._new_member:
# If the _new_member flag is set, we have to
# jump to the next member, if there is one.
self._init_read()
if not self._read_gzip_header():
self._size = self._pos
return b""
self._new_member = False
# Read a chunk of data from the file
if self._decompressor.needs_input:
buf = self._fp.read(READ_BUFFER_SIZE)
uncompress = self._decompressor.decompress(buf, size)
else:
uncompress = self._decompressor.decompress(b"", size)
if self._decompressor.unused_data != b"":
# Prepend the already read bytes to the fileobj so they can
# be seen by _read_eof() and _read_gzip_header()
self._fp.prepend(self._decompressor.unused_data)
if uncompress != b"":
break
if buf == b"":
raise EOFError("Compressed file ended before the "
"end-of-stream marker was reached")
self._crc = zlib.crc32(uncompress, self._crc)
self._stream_size += len(uncompress)
self._pos += len(uncompress)
return uncompress
def _read_eof(self):
# We've read to the end of the file
# We check that the computed CRC and size of the
# uncompressed data matches the stored values. Note that the size
# stored is the true file size mod 2**32.
crc32, isize = struct.unpack("<II", _read_exact(self._fp, 8))
if crc32 != self._crc:
raise BadGzipFile("CRC check failed %s != %s" % (hex(crc32),
hex(self._crc)))
elif isize != (self._stream_size & 0xffffffff):
raise BadGzipFile("Incorrect length of data produced")
# Gzip files can be padded with zeroes and still have archives.
# Consume all zero bytes and set the file position to the first
# non-zero byte. See http://www.gzip.org/#faq8
c = b"\x00"
while c == b"\x00":
c = self._fp.read(1)
if c:
self._fp.prepend(c)
def _rewind(self):
super()._rewind()
self._new_member = True
def _create_simple_gzip_header(compresslevel: int,
mtime = None) -> bytes:
"""
Write a simple gzip header with no extra fields.
:param compresslevel: Compresslevel used to determine the xfl bytes.
:param mtime: The mtime (must support conversion to a 32-bit integer).
:return: A bytes object representing the gzip header.
"""
if mtime is None:
mtime = time.time()
if compresslevel == _COMPRESS_LEVEL_BEST:
xfl = 2
elif compresslevel == _COMPRESS_LEVEL_FAST:
xfl = 4
else:
xfl = 0
# Pack ID1 and ID2 magic bytes, method (8=deflate), header flags (no extra
# fields added to header), mtime, xfl and os (255 for unknown OS).
return struct.pack("<BBBBLBB", 0x1f, 0x8b, 8, 0, int(mtime), xfl, 255)
def compress(data, compresslevel=_COMPRESS_LEVEL_BEST, *, mtime=None):
"""Compress data in one shot and return the compressed string.
compresslevel sets the compression level in range of 0-9.
mtime can be used to set the modification time. The modification time is
set to the current time by default.
"""
if mtime == 0:
# Use zlib as it creates the header with 0 mtime by default.
# This is faster and with less overhead.
return zlib.compress(data, level=compresslevel, wbits=31)
header = _create_simple_gzip_header(compresslevel, mtime)
trailer = struct.pack("<LL", zlib.crc32(data), (len(data) & 0xffffffff))
# Wbits=-15 creates a raw deflate block.
return (header + zlib.compress(data, level=compresslevel, wbits=-15) +
trailer)
def decompress(data):
"""Decompress a gzip compressed string in one shot.
Return the decompressed string.
"""
decompressed_members = []
while True:
fp = io.BytesIO(data)
if _read_gzip_header(fp) is None:
return b"".join(decompressed_members)
# Use a zlib raw deflate compressor
do = zlib.decompressobj(wbits=-zlib.MAX_WBITS)
# Read all the data except the header
decompressed = do.decompress(data[fp.tell():])
if not do.eof or len(do.unused_data) < 8:
raise EOFError("Compressed file ended before the end-of-stream "
"marker was reached")
crc, length = struct.unpack("<II", do.unused_data[:8])
if crc != zlib.crc32(decompressed):
raise BadGzipFile("CRC check failed")
if length != (len(decompressed) & 0xffffffff):
raise BadGzipFile("Incorrect length of data produced")
decompressed_members.append(decompressed)
data = do.unused_data[8:].lstrip(b"\x00")
def main():
from argparse import ArgumentParser
parser = ArgumentParser(description=
"A simple command line interface for the gzip module: act like gzip, "
"but do not delete the input file.")
group = parser.add_mutually_exclusive_group()
group.add_argument('--fast', action='store_true', help='compress faster')
group.add_argument('--best', action='store_true', help='compress better')
group.add_argument("-d", "--decompress", action="store_true",
help="act like gunzip instead of gzip")
parser.add_argument("args", nargs="*", default=["-"], metavar='file')
args = parser.parse_args()
compresslevel = _COMPRESS_LEVEL_TRADEOFF
if args.fast:
compresslevel = _COMPRESS_LEVEL_FAST
elif args.best:
compresslevel = _COMPRESS_LEVEL_BEST
for arg in args.args:
if args.decompress:
if arg == "-":
f = GzipFile(filename="", mode="rb", fileobj=sys.stdin.buffer)
g = sys.stdout.buffer
else:
if arg[-3:] != ".gz":
sys.exit(f"filename doesn't end in .gz: {arg!r}")
f = open(arg, "rb")
g = builtins.open(arg[:-3], "wb")
else:
if arg == "-":
f = sys.stdin.buffer
g = GzipFile(filename="", mode="wb", fileobj=sys.stdout.buffer,
compresslevel=compresslevel)
else:
f = builtins.open(arg, "rb")
g = open(arg + ".gz", "wb")
while True:
chunk = f.read(READ_BUFFER_SIZE)
if not chunk:
break
g.write(chunk)
if g is not sys.stdout.buffer:
g.close()
if f is not sys.stdin.buffer:
f.close()
if __name__ == '__main__':
main()