Created
February 23, 2012 11:31
-
-
Save informationsea/1892476 to your computer and use it in GitHub Desktop.
Random Readable Compressed File (Licensed by GPL3 or later)
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python2.7 | |
__author__ = 'informationsea' | |
__copyright__ = 'Copyright (C) 2012 informationsea All Rights Reserved.' | |
import bz2 | |
import gzip | |
import struct | |
class RandomZip(object): | |
""" | |
""" | |
def __init__(self, filepath, mode, compress=9, | |
algorithm='bz2', compress_block_size = 1024*1024): | |
""" | |
Arguments: | |
- `filepath`: | |
- `mode`: | |
- `compress`: | |
- `algorithm`: | |
- `compress_block_size`: | |
""" | |
self._filepath = filepath | |
self._mode = mode | |
self._compress = compress | |
self._algorithm = algorithm | |
self._compress_block_size = compress_block_size | |
self._file = None | |
self._buffer = '' | |
self._filepos = list() | |
self._read_pointer = 0 | |
self._read_buffer_index = 0 | |
self._read_pointer_in_buffer = 0 | |
def open(self): | |
""" | |
Arguments: | |
- `self`: | |
""" | |
if not self._file: | |
self._file = file(self._filepath, self._mode) | |
if self._mode == 'w': | |
self._file.write('RZIP') | |
elif self._mode == 'r': | |
header = self._file.read(4) | |
if header != 'RZIP': | |
self._file.close() | |
raise StandardError('Not rzip') | |
header = self._file.read(8*2) | |
current_pointer = 4 | |
current_raw_pointer = 0 | |
while header: | |
compressed_length, raw_length = struct.unpack('QQ', header) | |
self._filepos.append((current_pointer, current_raw_pointer, compressed_length)) | |
#print compressed_length, raw_length | |
current_pointer += compressed_length+8*2 | |
current_raw_pointer += raw_length | |
self._file.seek(current_pointer) | |
header = self._file.read(8*2) | |
else: | |
raise StandardError('Uknown mode') | |
def close(self): | |
""" | |
Arguments: | |
- `self`: | |
""" | |
if self._mode == 'w': | |
if len(self._buffer): | |
compressed = bz2.compress(self._buffer, self._compress) | |
self._file.write(struct.pack('QQ', len(compressed), len(self._buffer))) | |
self._file.write(compressed) | |
self._file.close() | |
def write(self, data): | |
""" | |
Arguments: | |
- `data`: | |
""" | |
if self._mode != 'w': | |
raise StandardError('Not write mode') | |
self._buffer += data | |
while len(self._buffer) >= self._compress_block_size: | |
compressed = bz2.compress(self._buffer[:self._compress_block_size], self._compress) | |
self._file.write(struct.pack('QQ', len(compressed), self._compress_block_size)) | |
self._file.write(compressed) | |
#print 'write', len(compressed), self._compress_block_size | |
self._buffer = self._buffer[self._compress_block_size:] | |
def seek(self, pos): | |
""" | |
Arguments: | |
- `self`: | |
- `pos`: | |
""" | |
for i, (compressed_pointer, raw_pointer, x) in enumerate(self._filepos): | |
if pos < raw_pointer: | |
self._read_buffer_index = i - 1 | |
self._read_pointer = pos | |
self._read_pointer_in_buffer = pos - self._filepos[self._read_buffer_index][1] | |
self._file.seek(self._filepos[self._read_buffer_index][0] + 8*2) | |
self._buffer = bz2.decompress(self._file.read(self._filepos[self._read_buffer_index][2])) | |
#print self._read_buffer_index, self._read_pointer_in_buffer, len(self._buffer) | |
#print self._buffer | |
break | |
else: | |
i = len(self._filepos) | |
self._read_buffer_index = i - 1 | |
self._read_pointer = pos | |
self._read_pointer_in_buffer = pos - self._filepos[self._read_buffer_index][1] | |
self._file.seek(self._filepos[self._read_buffer_index][0] + 8*2) | |
self._buffer = bz2.decompress(self._file.read(self._filepos[self._read_buffer_index][2])) | |
def read(self, size): | |
""" | |
Arguments: | |
- `self`: | |
- `size`: | |
""" | |
remain_length = size | |
buf = '' | |
while remain_length: | |
if remain_length < len(self._buffer) - self._read_pointer_in_buffer: | |
buf += self._buffer[self._read_pointer_in_buffer:self._read_pointer_in_buffer+remain_length] | |
self._read_pointer += remain_length | |
self._read_pointer_in_buffer += remain_length | |
remain_length = 0 | |
else: | |
buf += self._buffer[self._read_pointer_in_buffer:] | |
remain_length -= len(self._buffer) - self._read_pointer_in_buffer | |
if len(self._filepos)-1 <= self._read_buffer_index: | |
return buf | |
self._read_buffer_index += 1 | |
self._read_pointer_in_buffer = 0 | |
self._read_pointer += len(self._buffer) - self._read_pointer_in_buffer | |
self._file.seek(self._filepos[self._read_buffer_index][0] + 8*2) | |
self._buffer = bz2.decompress(self._file.read(self._filepos[self._read_buffer_index][2])) | |
return buf | |
if __name__ == '__main__': | |
import argparse | |
parser = argparse.ArgumentParser(description='Random accessable zip') | |
parser.add_argument('files', help='files', nargs='+') | |
parser.add_argument('-d', '--decompress', help='decompress', action='store_true') | |
parser.add_argument('-s', '--start-from', help='decompress start position', type=int, default=0) | |
parser.add_argument('-l', '--length', help='decompress length', type=int, default=100) | |
parser.add_argument('-c', '--compress-block-size', type=int, default=1024*1024) | |
options = parser.parse_args() | |
if options.decompress: | |
for one in options.files: | |
r = RandomZip(one, 'r') | |
r.open() | |
r.seek(options.start_from) | |
print r.read(options.length) | |
else: | |
for one in options.files: | |
with file(one, 'r') as f: | |
r = RandomZip(one+'.rz', 'w', compress_block_size=options.compress_block_size) | |
r.open() | |
buf = f.read(1000*1000) | |
while buf: | |
r.write(buf) | |
buf = f.read(1000*1000) | |
r.close() | |
pass |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment