file/magic/Magdir/compress

#------------------------------------------------------------------------------
# $File: compress,v 1.53 2014/01/05 15:55:21 christos Exp $
# 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
!:mime	application/x-compress
!:apple	LZIVZIVU
>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)
#   Edited by Chris Chittleborough <cchittleborough@yahoo.com.au>, March 2002
#	* Original filename is only at offset 10 if "extra field" absent
#	* Produce shorter output - notably, only report compression methods
#         other than 8 ("deflate", the only method defined in RFC 1952).
0       string          \037\213        gzip compressed data
!:mime	application/x-gzip
!:strength * 2
>2	byte		<8		\b, reserved method
>2	byte		>8		\b, unknown method
>3	byte		&0x01		\b, ASCII
>3	byte		&0x02		\b, has CRC
>3	byte		&0x04		\b, extra field
>3	byte&0xC	=0x08
>>10	string		x		\b, was "%s"
>3	byte		&0x10		\b, has comment
>3	byte		&0x20		\b, encrypted
>4	ledate		>0		\b, last modified: %s
>8	byte		2		\b, max compression
>8	byte		4		\b, max speed
>9	byte		=0x00		\b, from FAT filesystem (MS-DOS, OS/2, NT)
>9	byte		=0x01		\b, from Amiga
>9	byte		=0x02		\b, from VMS
>9	byte		=0x03		\b, from Unix
>9	byte		=0x04		\b, from VM/CMS
>9	byte		=0x05		\b, from Atari
>9	byte		=0x06		\b, from HPFS filesystem (OS/2, NT)
>9	byte		=0x07		\b, from MacOS
>9	byte		=0x08		\b, from Z-System
>9	byte		=0x09		\b, from CP/M
>9	byte		=0x0A		\b, from TOPS/20
>9	byte		=0x0B		\b, from NTFS filesystem (NT)
>9	byte		=0x0C		\b, from QDOS
>9	byte		=0x0D		\b, from Acorn RISCOS

# packed data, Huffman (minimum redundancy) codes on a byte-by-byte basis
0	string		\037\036	packed data
!:mime	application/octet-stream
>2	belong		>1		\b, %d characters originally
>2	belong		=1		\b, %d character originally
#
# This magic number is byte-order-independent.
0	short		0x1f1f		old packed data
!:mime	application/octet-stream

# 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
!:mime	application/octet-stream
# 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
!:mime	application/octet-stream
0	short		0145405		huf output
!:mime	application/octet-stream

# bzip2
0	string		BZh		bzip2 compressed data
!:mime	application/x-bzip2
>3	byte		>47		\b, block size = %c00k

# lzip
0	string		LZIP		lzip compressed data
!:mime application/x-lzip
>4	byte		x		\b, version: %d

# squeeze and crunch
# Michael Haardt <michael@cantor.informatik.rwth-aachen.de>
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 <sewardj@cs.man.ac.uk> 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 <markus.oberhumer@jk.uni-linz.ac.at>
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

# 4.3BSD-Quasijarus Strong Compression
# http://minnie.tuhs.org/Quasijarus/compress.html
0	string		\037\241	Quasijarus strong compressed data

# From: Cory Dikkers <cdikkers@swbell.net>
0	string		XPKF		Amiga xpkf.library compressed data
0	string		PP11		Power Packer 1.1 compressed data
0	string		PP20		Power Packer 2.0 compressed data,
>4	belong		0x09090909	fast compression
>4	belong		0x090A0A0A	mediocre compression
>4	belong		0x090A0B0B	good compression
>4	belong		0x090A0C0C	very good compression
>4	belong		0x090A0C0D	best compression

# 7-zip archiver, from Thomas Klausner (wiz@danbala.tuwien.ac.at)
# http://www.7-zip.org or DOC/7zFormat.txt
#
0	string		7z\274\257\047\034	7-zip archive data,
>6	byte		x			version %d
>7	byte		x			\b.%d
!:mime	application/x-7z-compressed

# Type: LZMA
0	lelong&0xffffff	=0x5d
!:mime	application/x-lzma
>12	leshort		0xff			LZMA compressed data,
>>5	lequad		=0xffffffffffffffff	streamed
>>5	lequad		!0xffffffffffffffff	non-streamed, size %lld
>12	leshort		0			LZMA compressed data,
>>5	lequad		=0xffffffffffffffff	streamed
>>5	lequad		!0xffffffffffffffff	non-streamed, size %lld

# http://tukaani.org/xz/xz-file-format.txt
0	ustring		\xFD7zXZ\x00		XZ compressed data
!:mime	application/x-xz

# https://github.com/ckolivas/lrzip/blob/master/doc/magic.header.txt
0	string		LRZI			LRZIP compressed data
>4	byte		x			- version %d
>5	byte		x			\b.%d
!:mime	application/x-lrzip

# http://fastcompression.blogspot.fi/2013/04/lz4-streaming-format-final.html
0	lelong		0x184d2204	LZ4 compressed data
!:mime	application/x-lz4
0	lelong		0x184c2102	LZ4 compressed data, legacy format
!:mime	application/x-lz4

# AFX compressed files (Wolfram Kleff)
2	string		-afx-		AFX compressed file data

# Supplementary magic data for the file(1) command to support
# rzip(1).  The format is described in magic(5).
#
# Copyright (C) 2003 by Andrew Tridgell.  You may do whatever you want with
# this file.
#
0	string		RZIP		rzip compressed data
>4	byte		x		- version %d
>5	byte		x		\b.%d
>6	belong		x		(%d bytes)

0	string		ArC\x01		FreeArc archive <http://freearc.org>

# Type:	DACT compressed files
0	long	0x444354C3	DACT compressed data
>4	byte	>-1		(version %i.
>5	byte	>-1		%i.
>6	byte	>-1		%i)
>7	long	>0		, original size: %i bytes
>15	long	>30		, block size: %i bytes

# Valve Pack (VPK) files
0	lelong	0x55aa1234	Valve Pak file
>0x4	lelong	x		\b, version %u
>0x8	lelong	x		\b, %u entries