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 | Demo/zlib/minigzip.py
#!/usr/bin/env python # Demo program for zlib; it compresses or decompresses files, but *doesn't* # delete the original. This doesn't support all of gzip's options. # # The 'gzip' module in the standard library provides a more complete # implementation of gzip-format files. import zlib, sys, os FTEXT, FHCRC, FEXTRA, FNAME, FCOMMENT = 1, 2, 4, 8, 16 def write32(output, value): output.write(chr(value & 255)) ; value=value // 256 output.write(chr(value & 255)) ; value=value // 256 output.write(chr(value & 255)) ; value=value // 256 output.write(chr(value & 255)) def read32(input): v = ord(input.read(1)) v += (ord(input.read(1)) << 8 ) v += (ord(input.read(1)) << 16) v += (ord(input.read(1)) << 24) return v def compress (filename, input, output): output.write('\037\213\010') # Write the header, ... output.write(chr(FNAME)) # ... flag byte ... statval = os.stat(filename) # ... modification time ... mtime = statval[8] write32(output, mtime) output.write('\002') # ... slowest compression alg. ... output.write('\377') # ... OS (=unknown) ... output.write(filename+'\000') # ... original filename ... crcval = zlib.crc32("") compobj = zlib.compressobj(9, zlib.DEFLATED, -zlib.MAX_WBITS, zlib.DEF_MEM_LEVEL, 0) while True: data = input.read(1024) if data == "": break crcval = zlib.crc32(data, crcval) output.write(compobj.compress(data)) output.write(compobj.flush()) write32(output, crcval) # ... the CRC ... write32(output, statval[6]) # and the file size. def decompress (input, output): magic = input.read(2) if magic != '\037\213': print 'Not a gzipped file' sys.exit(0) if ord(input.read(1)) != 8: print 'Unknown compression method' sys.exit(0) flag = ord(input.read(1)) input.read(4+1+1) # Discard modification time, # extra flags, and OS byte. if flag & FEXTRA: # Read & discard the extra field, if present xlen = ord(input.read(1)) xlen += 256*ord(input.read(1)) input.read(xlen) if flag & FNAME: # Read and discard a null-terminated string containing the filename while True: s = input.read(1) if s == '\0': break if flag & FCOMMENT: # Read and discard a null-terminated string containing a comment while True: s=input.read(1) if s=='\0': break if flag & FHCRC: input.read(2) # Read & discard the 16-bit header CRC decompobj = zlib.decompressobj(-zlib.MAX_WBITS) crcval = zlib.crc32("") length = 0 while True: data=input.read(1024) if data == "": break decompdata = decompobj.decompress(data) output.write(decompdata) length += len(decompdata) crcval = zlib.crc32(decompdata, crcval) decompdata = decompobj.flush() output.write(decompdata) length += len(decompdata) crcval = zlib.crc32(decompdata, crcval) # 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. The # decompressor is smart and knows when to stop, so feeding it # extra data is harmless. input.seek(-8, 2) crc32 = read32(input) isize = read32(input) if crc32 != crcval: print 'CRC check failed.' if isize != length: print 'Incorrect length of data produced' def main(): if len(sys.argv)!=2: print 'Usage: minigzip.py <filename>' print ' The file will be compressed or decompressed.' sys.exit(0) filename = sys.argv[1] if filename.endswith('.gz'): compressing = False outputname = filename[:-3] else: compressing = True outputname = filename + '.gz' input = open(filename, 'rb') output = open(outputname, 'wb') if compressing: compress(filename, input, output) else: decompress(input, output) input.close() output.close() if __name__ == '__main__': main() |