summaryrefslogtreecommitdiffstats
path: root/Lib/gzip.py
blob: 917c3f5279f33e731dd36dd1d041c6a48726d7ab (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
"""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
import zlib
import builtins

__all__ = ["GzipFile","open"]

FTEXT, FHCRC, FEXTRA, FNAME, FCOMMENT = 1, 2, 4, 8, 16

READ, WRITE = 1, 2

def U32(i):
    """Return i as an unsigned integer, assuming it fits in 32 bits.

    If it's >= 2GB when viewed as a 32-bit unsigned int, return a long.
    """
    if i < 0:
        i += 1 << 32
    return i

def LOWU32(i):
    """Return the low-order 32 bits of an int, as a non-negative int."""
    return i & 0xFFFFFFFF

def write32(output, value):
    output.write(struct.pack("<l", value))

def write32u(output, value):
    # The L format writes the bit pattern correctly whether signed
    # or unsigned.
    output.write(struct.pack("<L", value))

def read32(input):
    return struct.unpack("<l", input.read(4))[0]

def open(filename, mode="rb", compresslevel=9):
    """Shorthand for GzipFile(filename, mode, compresslevel).

    The filename argument is required; mode defaults to 'rb'
    and compresslevel defaults to 9.

    """
    return GzipFile(filename, mode, compresslevel)

class GzipFile:
    """The GzipFile class simulates most of the methods of a file object with
    the exception of the readinto() and truncate() methods.

    """

    myfileobj = None
    max_read_chunk = 10 * 1024 * 1024   # 10Mb

    def __init__(self, filename=None, mode=None,
                 compresslevel=9, fileobj=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, a StringIO 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 includes 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', or 'wb',
        depending on whether the file will be read or written.  The default
        is the mode of fileobj if discernible; otherwise, the default is 'rb'.
        Be aware that only the 'rb', 'ab', and 'wb' values should be used
        for cross-platform portability.

        The compresslevel argument is an integer from 1 to 9 controlling the
        level of compression; 1 is fastest and produces the least compression,
        and 9 is slowest and produces the most compression.  The default is 9.

        """

        # guarantee the file is opened in binary mode on platforms
        # that care about that sort of thing
        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:
            if hasattr(fileobj, 'name'): filename = fileobj.name
            else: filename = ''
        if mode is None:
            if hasattr(fileobj, 'mode'): mode = fileobj.mode
            else: mode = 'rb'

        if mode[0:1] == 'r':
            self.mode = READ
            # Set flag indicating start of a new member
            self._new_member = True
            self.extrabuf = b""
            self.extrasize = 0
            self.name = filename
            # Starts small, scales exponentially
            self.min_readsize = 100

        elif mode[0:1] == 'w' or mode[0:1] == 'a':
            self.mode = WRITE
            self._init_write(filename)
            self.compress = zlib.compressobj(compresslevel,
                                             zlib.DEFLATED,
                                             -zlib.MAX_WBITS,
                                             zlib.DEF_MEM_LEVEL,
                                             0)
        else:
            raise IOError("Mode " + mode + " not supported")

        self.fileobj = fileobj
        self.offset = 0

        if self.mode == WRITE:
            self._write_gzip_header()

    @property
    def filename(self):
        import warnings
        warnings.warn("use the name attribute", DeprecationWarning)
        if self.mode == WRITE and self.name[-3:] != ".gz":
            return self.name + ".gz"
        return self.name

    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("")
        self.size = 0
        self.writebuf = []
        self.bufsize = 0

    def _write_gzip_header(self):
        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 = self.name.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'))
        write32u(self.fileobj, int(time.time()))
        self.fileobj.write(b'\002')
        self.fileobj.write(b'\377')
        if fname:
            self.fileobj.write(fname + b'\000')

    def _init_read(self):
        self.crc = zlib.crc32("")
        self.size = 0

    def _read_gzip_header(self):
        magic = self.fileobj.read(2)
        if magic != b'\037\213':
            raise IOError('Not a gzipped file')
        method = ord( self.fileobj.read(1) )
        if method != 8:
            raise IOError('Unknown compression method')
        flag = ord( self.fileobj.read(1) )
        # modtime = self.fileobj.read(4)
        # extraflag = self.fileobj.read(1)
        # os = self.fileobj.read(1)
        self.fileobj.read(6)

        if flag & FEXTRA:
            # Read & discard the extra field, if present
            xlen = ord(self.fileobj.read(1))
            xlen = xlen + 256*ord(self.fileobj.read(1))
            self.fileobj.read(xlen)
        if flag & FNAME:
            # Read and discard a null-terminated string containing the filename
            while True:
                s = self.fileobj.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 = self.fileobj.read(1)
                if not s or s==b'\000':
                    break
        if flag & FHCRC:
            self.fileobj.read(2)     # Read & discard the 16-bit header CRC


    def write(self,data):
        if self.mode != WRITE:
            import errno
            raise IOError(errno.EBADF, "write() on read-only GzipFile object")

        if self.fileobj is None:
            raise ValueError("write() on closed GzipFile object")
        if len(data) > 0:
            self.size = self.size + len(data)
            self.crc = zlib.crc32(data, self.crc)
            self.fileobj.write( self.compress.compress(data) )
            self.offset += len(data)

    def read(self, size=-1):
        if self.mode != READ:
            import errno
            raise IOError(errno.EBADF, "read() on write-only GzipFile object")

        if self.extrasize <= 0 and self.fileobj is None:
            return b''

        readsize = 1024
        if size < 0:        # get the whole thing
            try:
                while True:
                    self._read(readsize)
                    readsize = min(self.max_read_chunk, readsize * 2)
            except EOFError:
                size = self.extrasize
        else:               # just get some more of it
            try:
                while size > self.extrasize:
                    self._read(readsize)
                    readsize = min(self.max_read_chunk, readsize * 2)
            except EOFError:
                if size > self.extrasize:
                    size = self.extrasize

        chunk = self.extrabuf[:size]
        self.extrabuf = self.extrabuf[size:]
        self.extrasize = self.extrasize - size

        self.offset += size
        return chunk

    def _unread(self, buf):
        self.extrabuf = buf + self.extrabuf
        self.extrasize = len(buf) + self.extrasize
        self.offset -= len(buf)

    def _read(self, size=1024):
        if self.fileobj is None:
            raise EOFError("Reached EOF")

        if self._new_member:
            # If the _new_member flag is set, we have to
            # jump to the next member, if there is one.
            #
            # First, check if we're at the end of the file;
            # if so, it's time to stop; no more members to read.
            pos = self.fileobj.tell()   # Save current position
            self.fileobj.seek(0, 2)     # Seek to end of file
            if pos == self.fileobj.tell():
                raise EOFError("Reached EOF")
            else:
                self.fileobj.seek( pos ) # Return to original position

            self._init_read()
            self._read_gzip_header()
            self.decompress = zlib.decompressobj(-zlib.MAX_WBITS)
            self._new_member = False

        # Read a chunk of data from the file
        buf = self.fileobj.read(size)

        # If the EOF has been reached, flush the decompression object
        # and mark this object as finished.

        if buf == b"":
            uncompress = self.decompress.flush()
            self._read_eof()
            self._add_read_data( uncompress )
            raise EOFError('Reached EOF')

        uncompress = self.decompress.decompress(buf)
        self._add_read_data( uncompress )

        if self.decompress.unused_data != b"":
            # Ending case: we've come to the end of a member in the file,
            # so seek back to the start of the unused data, finish up
            # this member, and read a new gzip header.
            # (The number of bytes to seek back is the length of the unused
            # data, minus 8 because _read_eof() will rewind a further 8 bytes)
            self.fileobj.seek( -len(self.decompress.unused_data)+8, 1)

            # Check the CRC and file size, and set the flag so we read
            # a new member on the next call
            self._read_eof()
            self._new_member = True

    def _add_read_data(self, data):
        self.crc = zlib.crc32(data, self.crc)
        self.extrabuf = self.extrabuf + data
        self.extrasize = self.extrasize + len(data)
        self.size = self.size + len(data)

    def _read_eof(self):
        # We've read to the end of the file, so we have to rewind in order
        # to reread the 8 bytes containing the CRC and the file size.
        # We check the 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.
        self.fileobj.seek(-8, 1)
        crc32 = read32(self.fileobj)
        isize = U32(read32(self.fileobj))   # may exceed 2GB
        if U32(crc32) != U32(self.crc):
            raise IOError("CRC check failed")
        elif isize != LOWU32(self.size):
            raise IOError("Incorrect length of data produced")

    def close(self):
        if self.mode == WRITE:
            self.fileobj.write(self.compress.flush())
            # The native zlib crc is an unsigned 32-bit integer, but
            # the Python wrapper implicitly casts that to a signed C
            # long.  So, on a 32-bit box self.crc may "look negative",
            # while the same crc on a 64-bit box may "look positive".
            # To avoid irksome warnings from the `struct` module, force
            # it to look positive on all boxes.
            write32u(self.fileobj, LOWU32(self.crc))
            # self.size may exceed 2GB, or even 4GB
            write32u(self.fileobj, LOWU32(self.size))
            self.fileobj = None
        elif self.mode == READ:
            self.fileobj = None
        if self.myfileobj:
            self.myfileobj.close()
            self.myfileobj = None

    def __del__(self):
        try:
            if (self.myfileobj is None and
                self.fileobj is None):
                return
        except AttributeError:
            return
        self.close()

    def flush(self,zlib_mode=zlib.Z_SYNC_FLUSH):
        if self.mode == WRITE:
            # 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 isatty(self):
        return False

    def tell(self):
        return self.offset

    def rewind(self):
        '''Return the uncompressed stream file position indicator to the
        beginning of the file'''
        if self.mode != READ:
            raise IOError("Can't rewind in write mode")
        self.fileobj.seek(0)
        self._new_member = True
        self.extrabuf = b""
        self.extrasize = 0
        self.offset = 0

    def seek(self, offset, whence=0):
        if whence:
            if whence == 1:
                offset = self.offset + offset
            else:
                raise ValueError('Seek from end not supported')
        if self.mode == WRITE:
            if offset < self.offset:
                raise IOError('Negative seek in write mode')
            count = offset - self.offset
            chunk = bytes(1024)
            for i in range(count // 1024):
                self.write(chunk)
            self.write(bytes(count % 1024))
        elif self.mode == READ:
            if offset < self.offset:
                # for negative seek, rewind and do positive seek
                self.rewind()
            count = offset - self.offset
            for i in range(count // 1024):
                self.read(1024)
            self.read(count % 1024)

    def readline(self, size=-1):
        if size < 0:
            size = sys.maxsize
            readsize = self.min_readsize
        else:
            readsize = size
        bufs = []
        while size != 0:
            c = self.read(readsize)
            i = c.find(b'\n')

            # We set i=size to break out of the loop under two
            # conditions: 1) there's no newline, and the chunk is
            # larger than size, or 2) there is a newline, but the
            # resulting line would be longer than 'size'.
            if (size <= i) or (i == -1 and len(c) > size):
                i = size - 1

            if i >= 0 or c == b'':
                bufs.append(c[:i + 1])    # Add portion of last chunk
                self._unread(c[i + 1:])   # Push back rest of chunk
                break

            # Append chunk to list, decrease 'size',
            bufs.append(c)
            size = size - len(c)
            readsize = min(size, readsize * 2)
        if readsize > self.min_readsize:
            self.min_readsize = min(readsize, self.min_readsize * 2, 512)
        return b''.join(bufs) # Return resulting line

    def readlines(self, sizehint=0):
        # Negative numbers result in reading all the lines
        if sizehint <= 0:
            sizehint = sys.maxsize
        L = []
        while sizehint > 0:
            line = self.readline()
            if line == b"":
                break
            L.append(line)
            sizehint = sizehint - len(line)

        return L

    def writelines(self, L):
        for line in L:
            self.write(line)

    def __iter__(self):
        return self

    def __next__(self):
        line = self.readline()
        if line:
            return line
        else:
            raise StopIteration


def _test():
    # Act like gzip; with -d, act like gunzip.
    # The input file is not deleted, however, nor are any other gzip
    # options or features supported.
    args = sys.argv[1:]
    decompress = args and args[0] == "-d"
    if decompress:
        args = args[1:]
    if not args:
        args = ["-"]
    for arg in args:
        if decompress:
            if arg == "-":
                f = GzipFile(filename="", mode="rb", fileobj=sys.stdin)
                g = sys.stdout
            else:
                if arg[-3:] != ".gz":
                    print("filename doesn't end in .gz:", repr(arg))
                    continue
                f = open(arg, "rb")
                g = builtins.open(arg[:-3], "wb")
        else:
            if arg == "-":
                f = sys.stdin
                g = GzipFile(filename="", mode="wb", fileobj=sys.stdout)
            else:
                f = builtins.open(arg, "rb")
                g = open(arg + ".gz", "wb")
        while True:
            chunk = f.read(1024)
            if not chunk:
                break
            g.write(chunk)
        if g is not sys.stdout:
            g.close()
        if f is not sys.stdin:
            f.close()

if __name__ == '__main__':
    _test()