compress

UNIX下FILE命令的实现源码

#------------------------------------------------------------------------------
# compress:  file(1) magic for pure-compression formats (no archives)
#
# compress, gzip, pack, compact, huf, squeeze, crunch, freeze, yabba, etc.
#
# Formats for various forms of compressed data
# Formats for "compress" proper have been moved into "compress.c",
# because it tries to uncompress it to figure out what's inside.

# standard unix compress
0	string		\037\235	compress'd data
>2	byte&0x80	>0		block compressed
>2	byte&0x1f	x		%d bits

# gzip (GNU zip, not to be confused with Info-ZIP or PKWARE zip archiver)
0       string          \037\213        gzip compressed data
>2      byte            <8              \b, reserved method,
>2      byte            8               \b, deflated,
>3	byte		&0x01		ASCII,
>3	byte		&0x02		continuation,
>3	byte		&0x04		extra field,
>3	byte		&0x08		original filename,
>>10    string          x               `%s',
>3	byte		&0x10		comment,
>3	byte		&0x20		encrypted,
>4	ledate		x		last modified: %s,
>8	byte		2		max compression,
>8	byte		4		max speed,
>9	byte		=0x00		os: MS-DOS
>9	byte		=0x01		os: Amiga
>9	byte		=0x02		os: VMS
>9	byte		=0x03		os: Unix
>9	byte		=0x05		os: Atari
>9	byte		=0x06		os: OS/2
>9	byte		=0x07		os: MacOS
>9	byte		=0x0A		os: Tops/20
>9	byte		=0x0B		os: Win/32

# packed data, Huffman (minimum redundancy) codes on a byte-by-byte basis
0	string		\037\036	packed data
>2	belong		>1		\b, %d characters originally
>2	belong		=1		\b, %d character originally
#
# This magic number is byte-order-independent.  XXX - Does that mean this
# is big-endian, little-endian, either, or that you can't tell?
# this short is valid for SunOS
0	short		017437		old packed data

# XXX - why *two* entries for "compacted data", one of which is
# byte-order independent, and one of which is byte-order dependent?
#
0	short		0x1fff		compacted data
# This string is valid for SunOS (BE) and a matching "short" is listed
# in the Ultrix (LE) magic file.
0	string		\377\037	compacted data
0	short		0145405		huf output

# bzip2
0	string		BZh		bzip2 compressed data
>3	byte		>47		\b, block size = %c00k

# squeeze and crunch
# Michael Haardt <[e-mail]>
0	beshort		0x76FF		squeezed data,
>4	string		x		original name %s
0	beshort		0x76FE		crunched data,
>2	string		x		original name %s
0	beshort		0x76FD		LZH compressed data,
>2	string		x		original name %s

# Freeze
0	string		\037\237	frozen file 2.1
0	string		\037\236	frozen file 1.0 (or gzip 0.5)

# SCO compress -H (LZH)
0	string		\037\240	SCO compress -H (LZH) data

# European GSM 06.10 is a provisional standard for full-rate speech
# transcoding, prI-ETS 300 036, which uses RPE/LTP (residual pulse
# excitation/long term prediction) coding at 13 kbit/s.
#
# There's only a magic nibble (4 bits); that nibble repeats every 33
# bytes.  This isn't suited for use, but maybe we can use it someday.
#
# This will cause very short GSM files to be declared as data and
# mismatches to be declared as data too!
#0	byte&0xF0	0xd0		data
#>33	byte&0xF0	0xd0
#>66	byte&0xF0	0xd0
#>99	byte&0xF0	0xd0
#>132	byte&0xF0	0xd0		GSM 06.10 compressed audio

# bzip	a block-sorting file compressor
#	by Julian Seward <[e-mail]> and others
#
0	string		BZ		bzip compressed data
>2	byte		x		\b, version: %c
>3	string		=1		\b, compression block size 100k
>3	string		=2		\b, compression block size 200k
>3	string		=3		\b, compression block size 300k
>3	string		=4		\b, compression block size 400k
>3	string		=5		\b, compression block size 500k
>3	string		=6		\b, compression block size 600k
>3	string		=7		\b, compression block size 700k
>3	string		=8		\b, compression block size 800k
>3	string		=9		\b, compression block size 900k

# lzop from <[e-mail]>
0	string		\x89\x4c\x5a\x4f\x00\x0d\x0a\x1a\x0a	lzop compressed data
>9	beshort		<0x0940
>>9	byte&0xf0	=0x00		- version 0.
>>9	beshort&0x0fff	x		\b%03x,
>>13	byte		1		LZO1X-1,
>>13	byte		2		LZO1X-1(15),
>>13	byte		3		LZO1X-999,
## >>22	bedate		>0		last modified: %s,
>>14	byte		=0x00		os: MS-DOS
>>14	byte		=0x01		os: Amiga
>>14	byte		=0x02		os: VMS
>>14	byte		=0x03		os: Unix
>>14	byte		=0x05		os: Atari
>>14	byte		=0x06		os: OS/2
>>14	byte		=0x07		os: MacOS
>>14	byte		=0x0A		os: Tops/20
>>14	byte		=0x0B		os: WinNT
>>14	byte		=0x0E		os: Win32
>9	beshort		>0x0939
>>9	byte&0xf0	=0x00		- version 0.
>>9	byte&0xf0	=0x10		- version 1.
>>9	byte&0xf0	=0x20		- version 2.
>>9	beshort&0x0fff	x		\b%03x,
>>15	byte		1		LZO1X-1,
>>15	byte		2		LZO1X-1(15),
>>15	byte		3		LZO1X-999,
## >>25	bedate		>0		last modified: %s,
>>17	byte		=0x00		os: MS-DOS
>>17	byte		=0x01		os: Amiga
>>17	byte		=0x02		os: VMS
>>17	byte		=0x03		os: Unix
>>17	byte		=0x05		os: Atari
>>17	byte		=0x06		os: OS/2
>>17	byte		=0x07		os: MacOS
>>17	byte		=0x0A		os: Tops/20
>>17	byte		=0x0B		os: WinNT
>>17	byte		=0x0E		os: Win32