Created
November 25, 2009 04:03
-
-
Save mnot/242459 to your computer and use it in GitHub Desktop.
c_zlib.py: zlib for Python using ctypes
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 python | |
""" | |
c_zlib - zlib for Python using ctypes. | |
This is a quick and nasty implementation of zlib using Python ctypes, in order to expose the ability | |
to set a compression dictionary (which isn't available in the zlib module). | |
""" | |
__license__ = """ | |
Copyright (c) 2009-2012 Mark Nottingham <mnot@pobox.com> | |
Permission is hereby granted, free of charge, to any person obtaining a copy | |
of this software and associated documentation files (the "Software"), to deal | |
in the Software without restriction, including without limitation the rights | |
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell | |
copies of the Software, and to permit persons to whom the Software is | |
furnished to do so, subject to the following conditions: | |
The above copyright notice and this permission notice shall be included in all | |
copies or substantial portions of the Software. | |
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR | |
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, | |
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE | |
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER | |
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, | |
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE | |
SOFTWARE. | |
""" | |
import ctypes as C | |
from ctypes import util | |
_zlib = C.cdll.LoadLibrary(util.find_library('z')) | |
assert _zlib._name, "Can't find libz" | |
class _z_stream(C.Structure): | |
_fields_ = [ | |
("next_in", C.POINTER(C.c_ubyte)), | |
("avail_in", C.c_uint), | |
("total_in", C.c_ulong), | |
("next_out", C.POINTER(C.c_ubyte)), | |
("avail_out", C.c_uint), | |
("total_out", C.c_ulong), | |
("msg", C.c_char_p), | |
("state", C.c_void_p), | |
("zalloc", C.c_void_p), | |
("zfree", C.c_void_p), | |
("opaque", C.c_void_p), | |
("data_type", C.c_int), | |
("adler", C.c_ulong), | |
("reserved", C.c_ulong), | |
] | |
# TODO: get zlib version with ctypes | |
ZLIB_VERSION = C.c_char_p("1.2.3") | |
Z_NULL = 0x00 | |
Z_OK = 0x00 | |
Z_STREAM_END = 0x01 | |
Z_NEED_DICT = 0x02 | |
Z_NO_FLUSH = 0x00 | |
Z_FINISH = 0x04 | |
CHUNK = 1024 * 32 | |
def compress(input, level=6, dictionary=None): | |
out = [] | |
st = _z_stream() | |
st.avail_in = len(input) | |
st.next_in = C.cast(C.c_char_p(input), C.POINTER(C.c_ubyte)) | |
st.avail_out = Z_NULL | |
st.next_out = C.cast(Z_NULL, C.POINTER(C.c_ubyte)) | |
err = _zlib.deflateInit_(C.byref(st), level, ZLIB_VERSION, C.sizeof(st)) | |
assert err == Z_OK, err | |
if dictionary: | |
err = _zlib.deflateSetDictionary(C.byref(st), C.cast(C.c_char_p(dictionary), C.POINTER(C.c_ubyte)), len(dictionary)) | |
assert err == Z_OK, err | |
while True: | |
st.avail_out = CHUNK | |
outbuf = C.create_string_buffer(CHUNK) | |
st.next_out = C.cast(outbuf, C.POINTER(C.c_ubyte)) | |
err = _zlib.deflate(C.byref(st), Z_FINISH) | |
out.append(outbuf[:CHUNK-st.avail_out]) | |
if err == Z_STREAM_END: break | |
elif err == Z_OK: pass | |
else: | |
raise AssertionError, err | |
err = _zlib.deflateEnd(C.byref(st)) | |
assert err == Z_OK, err | |
return "".join(out) | |
def decompress(input, dictionary=None): | |
out = [] | |
st = _z_stream() | |
st.avail_in = len(input) | |
st.next_in = C.cast(C.c_char_p(input), C.POINTER(C.c_ubyte)) | |
st.avail_out = Z_NULL | |
st.next_out = C.cast(Z_NULL, C.POINTER(C.c_ubyte)) | |
err = _zlib.inflateInit2_(C.byref(st), 15, ZLIB_VERSION, C.sizeof(st)) | |
assert err == Z_OK, err | |
while True: | |
st.avail_out = CHUNK | |
outbuf = C.create_string_buffer(CHUNK) | |
st.next_out = C.cast(outbuf, C.POINTER(C.c_ubyte)) | |
err = _zlib.inflate(C.byref(st), Z_NO_FLUSH) | |
if err == Z_NEED_DICT: | |
assert dictionary, "no dictionary provided" | |
err = _zlib.inflateSetDictionary(C.byref(st), C.cast(C.c_char_p(dictionary), C.POINTER(C.c_ubyte)), len(dictionary)) | |
assert err == Z_OK, err | |
elif err in [Z_OK, Z_STREAM_END]: | |
out.append(outbuf[:CHUNK-st.avail_out]) | |
else: | |
raise AssertionError, err | |
if err == Z_STREAM_END: | |
break | |
err = _zlib.inflateEnd(C.byref(st)) | |
assert err == Z_OK, err | |
return "".join(out) | |
def _test(): | |
import zlib, time, sys | |
input = open(sys.argv[1]).read() | |
# compression tests | |
start = time.time() | |
ct_archive = compress(input, 6) | |
print "ctypes zlib compress: %2.2f seconds" % (time.time() - start) | |
start = time.time() | |
zl_archive = zlib.compress(input, 6) | |
print "zlib module compress: %2.2f seconds" % (time.time() - start) | |
assert ct_archive == zl_archive, "%s != %s" % (len(ct_archive), len(zl_archive)) | |
# decompressions tests | |
start = time.time() | |
ct_orig = decompress(ct_archive) | |
print "ctypes zlib decompress: %2.2f seconds" % (time.time() - start) | |
start = time.time() | |
zl_orig = zlib.decompress(ct_archive) | |
print "zlib module decompress: %2.2f seconds" % (time.time() - start) | |
assert ct_orig == zl_orig, "%s != %s" % (len(ct_orig), len(zl_orig)) | |
# dictionary compression | |
dictionary = "andofthemyhisherforanother" | |
di_archive = compress(input, 6, dictionary) | |
di_orig = decompress(di_archive, dictionary) | |
assert input == di_orig, "%s != %s" % (len(orig), len(di_orig)) | |
print "done." | |
if __name__ == '__main__': | |
_test() | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Note that Python's zlib default compression level is zlib.Z_DEFAULT_COMPRESSION which on my Mac is -1 rather than the 6 documented on docs.python.org and can give radically different compression levels.