{{ message }}
-
Notifications
You must be signed in to change notification settings - Fork 1.5k
Expand file tree
/
Copy pathbz2.py
More file actions
352 lines (282 loc) · 11.7 KB
/
Copy pathbz2.py
File metadata and controls
352 lines (282 loc) · 11.7 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
"""Interface to the libbzip2 compression library.
This module provides a file interface, classes for incremental
(de)compression, and functions for one-shot (de)compression.
"""
__all__ = ["BZ2File", "BZ2Compressor", "BZ2Decompressor",
"open", "compress", "decompress"]
__author__ = "Nadeem Vawda <nadeem.vawda@gmail.com>"
from builtins import open as _builtin_open
from compression._common import _streams
import io
import os
from _bz2 import BZ2Compressor, BZ2Decompressor
# Value 0 no longer used
_MODE_READ = 1
# Value 2 no longer used
_MODE_WRITE = 3
class BZ2File(_streams.BaseStream):
"""A file object providing transparent bzip2 (de)compression.
A BZ2File can act as a wrapper for an existing file object, or refer
directly to a named file on disk.
Note that BZ2File provides a *binary* file interface - data read is
returned as bytes, and data to be written should be given as bytes.
"""
def __init__(self, filename, mode="r", *, compresslevel=9):
"""Open a bzip2-compressed file.
If filename is a str, bytes, or PathLike object, it gives the
name of the file to be opened. Otherwise, it should be a file
object, which will be used to read or write the compressed data.
mode can be 'r' for reading (default), 'w' for (over)writing,
'x' for creating exclusively, or 'a' for appending. These can
equivalently be given as 'rb', 'wb', 'xb', and 'ab'.
If mode is 'w', 'x' or 'a', compresslevel can be a number between 1
and 9 specifying the level of compression: 1 produces the least
compression, and 9 (default) produces the most compression.
If mode is 'r', the input file may be the concatenation of
multiple compressed streams.
"""
self._fp = None
self._closefp = False
self._mode = None
if not (1 <= compresslevel <= 9):
raise ValueError("compresslevel must be between 1 and 9")
if mode in ("", "r", "rb"):
mode = "rb"
mode_code = _MODE_READ
elif mode in ("w", "wb"):
mode = "wb"
mode_code = _MODE_WRITE
self._compressor = BZ2Compressor(compresslevel)
elif mode in ("x", "xb"):
mode = "xb"
mode_code = _MODE_WRITE
self._compressor = BZ2Compressor(compresslevel)
elif mode in ("a", "ab"):
mode = "ab"
mode_code = _MODE_WRITE
self._compressor = BZ2Compressor(compresslevel)
else:
raise ValueError("Invalid mode: %r" % (mode,))
if isinstance(filename, (str, bytes, os.PathLike)):
self._fp = _builtin_open(filename, mode)
self._closefp = True
self._mode = mode_code
elif hasattr(filename, "read") or hasattr(filename, "write"):
self._fp = filename
self._mode = mode_code
else:
raise TypeError("filename must be a str, bytes, file or PathLike object")
if self._mode == _MODE_READ:
raw = _streams.DecompressReader(self._fp,
BZ2Decompressor, trailing_error=OSError)
self._buffer = io.BufferedReader(raw)
else:
self._pos = 0
def close(self):
"""Flush and close the file.
May be called more than once without error. Once the file is
closed, any other operation on it will raise a ValueError.
"""
if self.closed:
return
try:
if self._mode == _MODE_READ:
self._buffer.close()
elif self._mode == _MODE_WRITE:
self._fp.write(self._compressor.flush())
self._compressor = None
finally:
try:
if self._closefp:
self._fp.close()
finally:
self._fp = None
self._closefp = False
self._buffer = None
@property
def closed(self):
"""True if this file is closed."""
return self._fp is None
@property
def name(self):
self._check_not_closed()
return self._fp.name
@property
def mode(self):
return 'wb' if self._mode == _MODE_WRITE else 'rb'
def fileno(self):
"""Return the file descriptor for the underlying file."""
self._check_not_closed()
return self._fp.fileno()
def seekable(self):
"""Return whether the file supports seeking."""
return self.readable() and self._buffer.seekable()
def readable(self):
"""Return whether the file was opened for reading."""
self._check_not_closed()
return self._mode == _MODE_READ
def writable(self):
"""Return whether the file was opened for writing."""
self._check_not_closed()
return self._mode == _MODE_WRITE
def peek(self, n=0):
"""Return buffered data without advancing the file position.
Always returns at least one byte of data, unless at EOF.
The exact number of bytes returned is unspecified.
"""
self._check_can_read()
# Relies on the undocumented fact that BufferedReader.peek()
# always returns at least one byte (except at EOF), independent
# of the value of n
return self._buffer.peek(n)
def read(self, size=-1):
"""Read up to size uncompressed bytes from the file.
If size is negative or omitted, read until EOF is reached.
Returns b'' if the file is already at EOF.
"""
self._check_can_read()
return self._buffer.read(size)
def read1(self, size=-1):
"""Read up to size uncompressed bytes, while trying to avoid
making multiple reads from the underlying stream. Reads up to a
buffer's worth of data if size is negative.
Returns b'' if the file is at EOF.
"""
self._check_can_read()
if size < 0:
size = io.DEFAULT_BUFFER_SIZE
return self._buffer.read1(size)
def readinto(self, b):
"""Read bytes into b.
Returns the number of bytes read (0 for EOF).
"""
self._check_can_read()
return self._buffer.readinto(b)
def readline(self, size=-1):
"""Read a line of uncompressed bytes from the file.
The terminating newline (if present) is retained. If size is
non-negative, no more than size bytes will be read (in which
case the line may be incomplete). Returns b'' if already at EOF.
"""
if not isinstance(size, int):
if not hasattr(size, "__index__"):
raise TypeError("Integer argument expected")
size = size.__index__()
self._check_can_read()
return self._buffer.readline(size)
def readlines(self, size=-1):
"""Read a list of lines of uncompressed bytes from the file.
size can be specified to control the number of lines read: no
further lines will be read once the total size of the lines read
so far equals or exceeds size.
"""
if not isinstance(size, int):
if not hasattr(size, "__index__"):
raise TypeError("Integer argument expected")
size = size.__index__()
self._check_can_read()
return self._buffer.readlines(size)
def write(self, data):
"""Write a byte string to the file.
Returns the number of uncompressed bytes written, which is
always the length of data in bytes. Note that due to buffering,
the file on disk may not reflect the data written until close()
is called.
"""
self._check_can_write()
if isinstance(data, (bytes, bytearray)):
length = len(data)
else:
# accept any data that supports the buffer protocol
data = memoryview(data)
length = data.nbytes
compressed = self._compressor.compress(data)
self._fp.write(compressed)
self._pos += length
return length
def writelines(self, seq):
"""Write a sequence of byte strings to the file.
Returns the number of uncompressed bytes written.
seq can be any iterable yielding byte strings.
Line separators are not added between the written byte strings.
"""
return _streams.BaseStream.writelines(self, seq)
def seek(self, offset, whence=io.SEEK_SET):
"""Change the file position.
The new position is specified by offset, relative to the
position indicated by whence. Values for whence are:
0: start of stream (default); offset must not be negative
1: current stream position
2: end of stream; offset must not be positive
Returns the new file position.
Note that seeking is emulated, so depending on the parameters,
this operation may be extremely slow.
"""
self._check_can_seek()
return self._buffer.seek(offset, whence)
def tell(self):
"""Return the current file position."""
self._check_not_closed()
if self._mode == _MODE_READ:
return self._buffer.tell()
return self._pos
def open(filename, mode="rb", compresslevel=9,
encoding=None, errors=None, newline=None):
"""Open a bzip2-compressed file in binary or text mode.
The filename argument can be an actual filename (a str, bytes, or
PathLike 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 BZ2File
constructor: BZ2File(filename, mode, compresslevel). In this case,
the encoding, errors and newline arguments must not be provided.
For text mode, a BZ2File 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")
bz_mode = mode.replace("t", "")
binary_file = BZ2File(filename, bz_mode, compresslevel=compresslevel)
if "t" in mode:
encoding = io.text_encoding(encoding)
return io.TextIOWrapper(binary_file, encoding, errors, newline)
else:
return binary_file
def compress(data, compresslevel=9):
"""Compress a block of data.
compresslevel, if given, must be a number between 1 and 9.
For incremental compression, use a BZ2Compressor object instead.
"""
comp = BZ2Compressor(compresslevel)
return comp.compress(data) + comp.flush()
def decompress(data):
"""Decompress a block of data.
For incremental decompression, use a BZ2Decompressor object instead.
"""
results = []
while data:
decomp = BZ2Decompressor()
try:
res = decomp.decompress(data)
except OSError:
if results:
break # Leftover data is not a valid bzip2 stream; ignore it.
else:
raise # Error on the first iteration; bail out.
results.append(res)
if not decomp.eof:
raise ValueError("Compressed data ended before the "
"end-of-stream marker was reached")
data = decomp.unused_data
return b"".join(results)
You can’t perform that action at this time.