import sys import os import zlib try: import pylzma lzma except importerror: import lzma io import stringio import struct #----------------------------------------------------------------------------------------------------------------------- def read_ui8(c): return struct.unpack('<b', c)[0] def read_ui16(c): return struct.unpack('<h', c)[0] def read_ui32(c): return struct.unpack('<i', c)[0] def parse(input): """parses header information swf file.""" if hasattr(input, 'read'): input.seek(0) else: input = open(input, 'rb') header = { } # read 3-byte signature field header['signature'] = signature = b''.join(struct.unpack('<3c', input.read(3))).decode() # version header['version'] = read_ui8(input.read(1)) # file size (stored 32-bit integer) header['size'] = read_ui32(input.read(4)) # payload if header['signature'] == 'fws': print("the opened file doesn't appear compressed") buffer = input.read(header['size']) elif header['signature'] == 'cws': print("the opened file appears compressed zlib") buffer = zlib.decompress(input.read(header['size'])) elif header['signature'] == 'zws': print("the opened file appears compressed lzma") # zws(lzma) # | 4 bytes | 4 bytes | 4 bytes | 5 bytes | n bytes | 6 bytes | # | 'zws'+version | scriptlen | compressedlen | lzma props | lzma data | lzma end marker | size = read_ui32(input.read(4)) buffer = lzma.decompress(input.read()) # containing rectangle (struct rect) # number of bits used store each of rect values # stored in first 5 bits of first byte. nbits = read_ui8(buffer[0]) >> 3 current_byte, buffer = read_ui8(buffer[0]), buffer[1:] bit_cursor = 5 item in 'xmin', 'xmax', 'ymin', 'ymax': value = 0 value_bit in range(nbits-1, -1, -1): # == reversed(range(nbits)) if (current_byte << bit_cursor) & 0x80: value |= 1 << value_bit # advance bit cursor next bit bit_cursor += 1 if bit_cursor > 7: # we've exhausted current byte, consume next 1 # buffer. current_byte, buffer = read_ui8(buffer[0]), buffer[1:] bit_cursor = 0 # convert value twips pixel value header[item] = value / 20 header['width'] = header['xmax'] - header['xmin'] header['height'] = header['ymax'] - header['ymin'] header['frames'] = read_ui16(buffer[0:2]) header['fps'] = read_ui16(buffer[2:4]) input.close() return header header = parse(sys.argv[1]); print('swf header') print('----------') print('version: %s' % header['version']) print('signature: %s' % header['signature']) print('dimensions: %s x %s' % (header['width'], header['height'])) print('bounding box: (%s, %s, %s, %s)' % (header['xmin'], header['xmax'], header['ymin'], header['ymax'])) print('frames: %s' % header['frames']) print('fps: %s' % header['fps']) i under impression built in python 3.4 lzma module works same python 2.7 pylzma module. code i've provided runs on both 2.7 , 3.4, when run on 3.4 (which doesn't have pylzma resorts inbuilt lzma) following error:
_lzma.lzmaerror: input format not supported decoder why pylzma work python 3.4's lzma doesn't?
while not have answer why 2 modules work differently, have solution.
i unable non-stream lzma lzma.decompress work since not have enough knowledge lzma/xz/swf specs, got lzma.lzmadecompressor work. completeness, believe swf lzma uses header format (not 100% confirmed):
bytes length type endianness description 0- 2 3 ui8 - swf signature: zws 3 1 ui8 - swf version 4- 7 4 ui32 le swf filelength aka file size 8-11 4 ui32 le swf? compressed size (file size - 17) 12 1 - - lzma decoder properties 13-16 4 ui32 le lzma dictionary size 17- - - - lzma compressed data (including rest of swf header) however lzma file format spec says should be:
bytes length type endianness description 0 1 - - lzma decoder properties 1- 4 4 ui32 le lzma dictionary size 5-12 8 ui64 le lzma uncompressed size 13- - - - lzma compressed data i never able head around uncompressed size should (if possible define format). pylzma seems not care this, while python 3.3 lzma does. however, seems explicit unknown size works , may specified ui64 value 2^64, e.g. 8*b'\xff' or 8*'\xff', shuffling around headers bit , instead of using:
buffer = lzma.decompress(input.read()) try:
d = lzma.lzmadecompressor(format=lzma.format_alone) buffer = d.decompress(input.read(5) + 8*b'\xff' + input.read()) note: had no local python3 interpreter available tested online modified read procedure, might not work out of box.
edit: confirmed work in python3 things needed changed, marcus mentioned unpack (easily solved using buffer[0:1] instead of buffer[0]). it's not necessary read whole file either, small chunk, 256 bytes should fine reading whole swf header. frames field bit quirky too, though believe have bit shifting, i.e.:
header['frames'] = read_ui16(buffer[0:2]) >> 8 
Comments
Post a Comment