xref: /freebsd/contrib/file/magic/Magdir/archive (revision 40427cca7a9ae77b095936fb1954417c290cfb17)

#------------------------------------------------------------------------------
# $File: archive,v 1.108 2017/08/30 13:45:10 christos Exp $
# archive:  file(1) magic for archive formats (see also "msdos" for self-
#           extracting compressed archives)
#
# cpio, ar, arc, arj, hpack, lha/lharc, rar, squish, uc2, zip, zoo, etc.
# pre-POSIX "tar" archives are handled in the C code.

# POSIX tar archives
257	string		ustar\0		POSIX tar archive
!:mime	application/x-tar # encoding: posix
257	string		ustar\040\040\0	GNU tar archive
!:mime	application/x-tar # encoding: gnu

# Incremental snapshot gnu-tar format from:
# http://www.gnu.org/software/tar/manual/html_node/Snapshot-Files.html
0	string		GNU\ tar-	GNU tar incremental snapshot data
>&0	regex		[0-9]\.[0-9]+-[0-9]+	version %s

# cpio archives
#
# Yes, the top two "cpio archive" formats *are* supposed to just be "short".
# The idea is to indicate archives produced on machines with the same
# byte order as the machine running "file" with "cpio archive", and
# to indicate archives produced on machines with the opposite byte order
# from the machine running "file" with "byte-swapped cpio archive".
#
# The SVR4 "cpio(4)" hints that there are additional formats, but they
# are defined as "short"s; I think all the new formats are
# character-header formats and thus are strings, not numbers.
0	short		070707		cpio archive
!:mime	application/x-cpio
0	short		0143561		byte-swapped cpio archive
!:mime	application/x-cpio # encoding: swapped
0	string		070707		ASCII cpio archive (pre-SVR4 or odc)
0	string		070701		ASCII cpio archive (SVR4 with no CRC)
0	string		070702		ASCII cpio archive (SVR4 with CRC)

#
# Various archive formats used by various versions of the "ar"
# command.
#

#
# Original UNIX archive formats.
# They were written with binary values in host byte order, and
# the magic number was a host "int", which might have been 16 bits
# or 32 bits.  We don't say "PDP-11" or "VAX", as there might have
# been ports to little-endian 16-bit-int or 32-bit-int platforms
# (x86?) using some of those formats; if none existed, feel free
# to use "PDP-11" for little-endian 16-bit and "VAX" for little-endian
# 32-bit.  There might have been big-endian ports of that sort as
# well.
#
0	leshort		0177555		very old 16-bit-int little-endian archive
0	beshort		0177555		very old 16-bit-int big-endian archive
0	lelong		0177555		very old 32-bit-int little-endian archive
0	belong		0177555		very old 32-bit-int big-endian archive

0	leshort		0177545		old 16-bit-int little-endian archive
>2	string		__.SYMDEF	random library
0	beshort		0177545		old 16-bit-int big-endian archive
>2	string		__.SYMDEF	random library
0	lelong		0177545		old 32-bit-int little-endian archive
>4	string		__.SYMDEF	random library
0	belong		0177545		old 32-bit-int big-endian archive
>4	string		__.SYMDEF	random library

#
# From "pdp" (but why a 4-byte quantity?)
#
0	lelong		0x39bed		PDP-11 old archive
0	lelong		0x39bee		PDP-11 4.0 archive

#
# XXX - what flavor of APL used this, and was it a variant of
# some ar archive format?  It's similar to, but not the same
# as, the APL workspace magic numbers in pdp.
#
0	long		0100554		apl workspace

#
# System V Release 1 portable(?) archive format.
#
0	string		=<ar>		System V Release 1 ar archive
!:mime	application/x-archive

#
# Debian package; it's in the portable archive format, and needs to go
# before the entry for regular portable archives, as it's recognized as
# a portable archive whose first member has a name beginning with
# "debian".
#
0	string		=!<arch>\ndebian
>8	string		debian-split	part of multipart Debian package
!:mime	application/vnd.debian.binary-package
>8	string		debian-binary	Debian binary package
!:mime	application/vnd.debian.binary-package
>8	string		!debian
>68	string		>\0		(format %s)
# These next two lines do not work, because a bzip2 Debian archive
# still uses gzip for the control.tar (first in the archive).  Only
# data.tar varies, and the location of its filename varies too.
# file/libmagic does not current have support for ascii-string based
# (offsets) as of 2005-09-15.
#>81	string		bz2		\b, uses bzip2 compression
#>84	string		gz		\b, uses gzip compression
#>136	ledate		x		created: %s

#
# MIPS archive; they're in the portable archive format, and need to go
# before the entry for regular portable archives, as it's recognized as
# a portable archive whose first member has a name beginning with
# "__________E".
#
0	string	=!<arch>\n__________E	MIPS archive
!:mime	application/x-archive
>20	string	U			with MIPS Ucode members
>21	string	L			with MIPSEL members
>21	string	B			with MIPSEB members
>19	string	L			and an EL hash table
>19	string	B			and an EB hash table
>22	string	X			-- out of date

0	search/1	-h-		Software Tools format archive text

#
# BSD/SVR2-and-later portable archive formats.
#
0	string		=!<arch>		current ar archive
!:mime	application/x-archive
>8	string		__.SYMDEF	random library
>68	string		__.SYMDEF\ SORTED	random library

#
# "Thin" archive, as can be produced by GNU ar.
#
0	string		=!<thin>\n	thin archive with
>68	belong		0		no symbol entries
>68	belong		1		%d symbol entry
>68	belong		>1		%d symbol entries

# ARC archiver, from Daniel Quinlan (quinlan@yggdrasil.com)
#
# The first byte is the magic (0x1a), byte 2 is the compression type for
# the first file (0x01 through 0x09), and bytes 3 to 15 are the MS-DOS
# filename of the first file (null terminated).  Since some types collide
# we only test some types on basis of frequency: 0x08 (83%), 0x09 (5%),
# 0x02 (5%), 0x03 (3%), 0x04 (2%), 0x06 (2%).  0x01 collides with terminfo.
0	lelong&0x8080ffff	0x0000081a	ARC archive data, dynamic LZW
!:mime	application/x-arc
0	lelong&0x8080ffff	0x0000091a	ARC archive data, squashed
!:mime	application/x-arc
0	lelong&0x8080ffff	0x0000021a	ARC archive data, uncompressed
!:mime	application/x-arc
0	lelong&0x8080ffff	0x0000031a	ARC archive data, packed
!:mime	application/x-arc
0	lelong&0x8080ffff	0x0000041a	ARC archive data, squeezed
!:mime	application/x-arc
0	lelong&0x8080ffff	0x0000061a	ARC archive data, crunched
!:mime	application/x-arc
# [JW] stuff taken from idarc, obviously ARC successors:
0	lelong&0x8080ffff	0x00000a1a	PAK archive data
!:mime	application/x-arc
0	lelong&0x8080ffff	0x0000141a	ARC+ archive data
!:mime	application/x-arc
0	lelong&0x8080ffff	0x0000481a	HYP archive data
!:mime	application/x-arc

# Acorn archive formats (Disaster prone simpleton, m91dps@ecs.ox.ac.uk)
# I can't create either SPARK or ArcFS archives so I have not tested this stuff
# [GRR:  the original entries collide with ARC, above; replaced with combined
#  version (not tested)]
#0	byte		0x1a		RISC OS archive (spark format)
0	string		\032archive	RISC OS archive (ArcFS format)
0       string          Archive\000     RISC OS archive (ArcFS format)

# All these were taken from idarc, many could not be verified. Unfortunately,
# there were many low-quality sigs, i.e. easy to trigger false positives.
# Please notify me of any real-world fishy/ambiguous signatures and I'll try
# to get my hands on the actual archiver and see if I find something better. [JW]
# probably many can be enhanced by finding some 0-byte or control char near the start

# idarc calls this Crush/Uncompressed... *shrug*
0	string	CRUSH Crush archive data
# Squeeze It (.sqz)
0	string	HLSQZ Squeeze It archive data
# SQWEZ
0	string	SQWEZ SQWEZ archive data
# HPack (.hpk)
0	string	HPAK HPack archive data
# HAP
0	string	\x91\x33HF HAP archive data
# MD/MDCD
0	string	MDmd MDCD archive data
# LIM
0	string	LIM\x1a LIM archive data
# SAR
3	string	LH5 SAR archive data
# BSArc/BS2
0	string	\212\3SB\020\0	BSArc/BS2 archive data
# Bethesda Softworks Archive (Oblivion)
0	string	BSA\0 		BSArc archive data
>4	lelong	x		version %d
# MAR
2	string	=-ah MAR archive data
# ACB
#0	belong&0x00f800ff	0x00800000 ACB archive data
# CPZ
# TODO, this is what idarc says: 0	string	\0\0\0 CPZ archive data
# JRC
0	string	JRchive JRC archive data
# Quantum
0	string	DS\0 Quantum archive data
# ReSOF
0	string	PK\3\6 ReSOF archive data
# QuArk
0	string	7\4 QuArk archive data
# YAC
14	string	YC YAC archive data
# X1
0	string	X1 X1 archive data
0	string	XhDr X1 archive data
# CDC Codec (.dqt)
0	belong&0xffffe000	0x76ff2000 CDC Codec archive data
# AMGC
0	string	\xad6" AMGC archive data
# NuLIB
0	string	N\xc3\xb5F\xc3\xa9lx\xc3\xa5 NuLIB archive data
# PakLeo
0	string	LEOLZW PAKLeo archive data
# ChArc
0	string	SChF ChArc archive data
# PSA
0	string	PSA PSA archive data
# CrossePAC
0	string	DSIGDCC CrossePAC archive data
# Freeze
0	string	\x1f\x9f\x4a\x10\x0a Freeze archive data
# KBoom
0	string	\xc2\xa8MP\xc2\xa8 KBoom archive data
# NSQ, must go after CDC Codec
0	string	\x76\xff NSQ archive data
# DPA
0	string	Dirk\ Paehl DPA archive data
# BA
# TODO: idarc says "bytes 0-2 == bytes 3-5"
# TTComp
# URL: http://fileformats.archiveteam.org/wiki/TTComp_archive
# Update: Joerg Jenderek
# GRR: line below is too general as it matches also Panorama database "TCDB 2003-10 demo.pan", others
0	string	\0\6
# look for first keyword of Panorama database *.pan
>12	search/261	DESIGN
# skip keyword with low entropy
>12	default		x	TTComp archive, binary, 4K dictionary
# (version 5.25) labeled the above entry as "TTComp archive data"
# ESP, could this conflict with Easy Software Products' (e.g.ESP ghostscript) documentation?
0	string	ESP ESP archive data
# ZPack
0	string	\1ZPK\1 ZPack archive data
# Sky
0	string	\xbc\x40 Sky archive data
# UFA
0	string	UFA UFA archive data
# Dry
0	string	=-H2O DRY archive data
# FoxSQZ
0	string	FOXSQZ FoxSQZ archive data
# AR7
0	string	,AR7 AR7 archive data
# PPMZ
0	string	PPMZ PPMZ archive data
# MS Compress
4	string	\x88\xf0\x27 MS Compress archive data
# updated by Joerg Jenderek
>9	string	\0
>>0	string	KWAJ
>>>7	string	\321\003	MS Compress archive data
>>>>14	ulong	>0		\b, original size: %d bytes
>>>>18		ubyte	>0x65
>>>>>18		string	x       \b, was %.8s
>>>>>(10.b-4)	string	x       \b.%.3s
# MP3 (archiver, not lossy audio compression)
0	string	MP3\x1a MP3-Archiver archive data
# ZET
0	string	OZ\xc3\x9d ZET archive data
# TSComp
0	string	\x65\x5d\x13\x8c\x08\x01\x03\x00 TSComp archive data
# ARQ
0	string	gW\4\1 ARQ archive data
# Squash
3	string	OctSqu Squash archive data
# Terse
0	string	\5\1\1\0 Terse archive data
# PUCrunch
0	string	\x01\x08\x0b\x08\xef\x00\x9e\x32\x30\x36\x31 PUCrunch archive data
# UHarc
0	string	UHA UHarc archive data
# ABComp
0	string	\2AB ABComp archive data
0	string	\3AB2 ABComp archive data
# CMP
0	string	CO\0 CMP archive data
# Splint
0	string	\x93\xb9\x06 Splint archive data
# InstallShield
0	string	\x13\x5d\x65\x8c InstallShield Z archive Data
# Gather
1	string	GTH Gather archive data
# BOA
0	string	BOA BOA archive data
# RAX
0	string	ULEB\xa RAX archive data
# Xtreme
0	string	ULEB\0 Xtreme archive data
# Pack Magic
0	string	@\xc3\xa2\1\0 Pack Magic archive data
# BTS
0	belong&0xfeffffff	0x1a034465 BTS archive data
# ELI 5750
0	string	Ora\  ELI 5750 archive data
# QFC
0	string	\x1aFC\x1a QFC archive data
0	string	\x1aQF\x1a QFC archive data
# PRO-PACK
0	string	RNC PRO-PACK archive data
# 777
0	string	777 777 archive data
# LZS221
0	string	sTaC LZS221 archive data
# HPA
0	string	HPA HPA archive data
# Arhangel
0	string	LG Arhangel archive data
# EXP1, uses bzip2
0	string	0123456789012345BZh EXP1 archive data
# IMP
0	string	IMP\xa IMP archive data
# NRV
0	string	\x00\x9E\x6E\x72\x76\xFF NRV archive data
# Squish
0	string	\x73\xb2\x90\xf4 Squish archive data
# Par
0	string	PHILIPP Par archive data
0	string	PAR Par archive data
# HIT
0	string	UB HIT archive data
# SBX
0	belong&0xfffff000	0x53423000 SBX archive data
# NaShrink
0	string	NSK NaShrink archive data
# SAPCAR
0	string	#\ CAR\ archive\ header SAPCAR archive data
0	string	CAR\ 2.00RG SAPCAR archive data
# Disintegrator
0	string	DST Disintegrator archive data
# ASD
0	string	ASD ASD archive data
# InstallShield CAB
0	string	ISc( InstallShield CAB
# TOP4
0	string	T4\x1a TOP4 archive data
# BatComp left out: sig looks like COM executable
# so TODO: get real 4dos batcomp file and find sig
# BlakHole
0	string	BH\5\7 BlakHole archive data
# BIX
0	string	BIX0 BIX archive data
# ChiefLZA
0	string	ChfLZ ChiefLZA archive data
# Blink
0	string	Blink Blink archive data
# Logitech Compress
0	string	\xda\xfa Logitech Compress archive data
# ARS-Sfx (FIXME: really a SFX? then goto COM/EXE)
1	string	(C)\ STEPANYUK ARS-Sfx archive data
# AKT/AKT32
0	string	AKT32 AKT32 archive data
0	string	AKT AKT archive data
# NPack
0	string	MSTSM NPack archive data
# PFT
0	string	\0\x50\0\x14 PFT archive data
# SemOne
0	string	SEM SemOne archive data
# PPMD
0	string	\x8f\xaf\xac\x84 PPMD archive data
# FIZ
0	string	FIZ FIZ archive data
# MSXiE
0	belong&0xfffff0f0	0x4d530000 MSXiE archive data
# DeepFreezer
0	belong&0xfffffff0	0x797a3030 DeepFreezer archive data
# DC
0	string	=<DC- DC archive data
# TPac
0	string	\4TPAC\3 TPac archive data
# Ai
0	string	Ai\1\1\0 Ai archive data
0	string	Ai\1\0\0 Ai archive data
# Ai32
0	string	Ai\2\0 Ai32 archive data
0	string	Ai\2\1 Ai32 archive data
# SBC
0	string	SBC SBC archive data
# Ybs
0	string	YBS Ybs archive data
# DitPack
0	string	\x9e\0\0 DitPack archive data
# DMS
0	string	DMS! DMS archive data
# EPC
0	string	\x8f\xaf\xac\x8c EPC archive data
# VSARC
0	string	VS\x1a VSARC archive data
# PDZ
0	string	PDZ PDZ archive data
# ReDuq
0	string	rdqx ReDuq archive data
# GCA
0	string	GCAX GCA archive data
# PPMN
0	string	pN PPMN archive data
# WinImage
3	string	WINIMAGE WinImage archive data
# Compressia
0	string	CMP0CMP Compressia archive data
# UHBC
0	string	UHB UHBC archive data
# WinHKI
0	string	\x61\x5C\x04\x05 WinHKI archive data
# WWPack data file
0	string	WWP WWPack archive data
# BSN (BSA, PTS-DOS)
0	string	\xffBSG BSN archive data
1	string	\xffBSG BSN archive data
3	string	\xffBSG BSN archive data
1	string	\0\xae\2 BSN archive data
1	string	\0\xae\3 BSN archive data
1	string	\0\xae\7 BSN archive data
# AIN
0	string	\x33\x18 AIN archive data
0	string	\x33\x17 AIN archive data
# XPA32 test moved and merged with XPA by Joerg Jenderek at Sep 2015
# SZip (TODO: doesn't catch all versions)
0	string	SZ\x0a\4 SZip archive data
# XPack DiskImage
# *.XDI updated by Joerg Jenderek Sep 2015
# ftp://ftp.sac.sk/pub/sac/pack/0index.txt
# GRR: this test is still too general as it catches also text files starting with jm
0	string	jm
# only found examples with this additional characteristic 2 bytes
>2	string	\x2\x4	Xpack DiskImage archive data
#!:ext xdi
# XPack Data
# *.xpa updated by Joerg Jenderek Sep 2015
# ftp://ftp.elf.stuba.sk/pub/pc/pack/
0	string	xpa	XPA
!:ext	xpa
# XPA32
# ftp://ftp.elf.stuba.sk/pub/pc/pack/xpa32.zip
# created by XPA32.EXE version 1.0.2 for Windows
>0	string	xpa\0\1 \b32 archive data
# created by XPACK.COM version 1.67m or 1.67r with short 0x1800
>3	ubeshort	!0x0001	\bck archive data
# XPack Single Data
# changed by Joerg Jenderek Sep 2015 back to like in version 5.12
# letter 'I'+ acute accent is equivalent to \xcd
0	string	\xcd\ jm	Xpack single archive data
#!:mime	application/x-xpa-compressed
!:ext xpa

# TODO: missing due to unknown magic/magic at end of file:
#DWC
#ARG
#ZAR
#PC/3270
#InstallIt
#RKive
#RK
#XPack Diskimage

# These were inspired by idarc, but actually verified
# Dzip archiver (.dz)
0	string	DZ Dzip archive data
>2	byte	x \b, version %i
>3	byte	x \b.%i
# ZZip archiver (.zz)
0	string	ZZ\ \0\0 ZZip archive data
0	string	ZZ0 ZZip archive data
# PAQ archiver (.paq)
0	string	\xaa\x40\x5f\x77\x1f\xe5\x82\x0d PAQ archive data
0	string	PAQ PAQ archive data
>3	byte&0xf0	0x30
>>3	byte	x (v%c)
# JAR archiver (.j), this is the successor to ARJ, not Java's JAR (which is essentially ZIP)
0xe	string	\x1aJar\x1b JAR (ARJ Software, Inc.) archive data
0	string	JARCS JAR (ARJ Software, Inc.) archive data

# ARJ archiver (jason@jarthur.Claremont.EDU)
0	leshort		0xea60		ARJ archive data
!:mime	application/x-arj
>5	byte		x		\b, v%d,
>8	byte		&0x04		multi-volume,
>8	byte		&0x10		slash-switched,
>8	byte		&0x20		backup,
>34	string		x		original name: %s,
>7	byte		0		os: MS-DOS
>7	byte		1		os: PRIMOS
>7	byte		2		os: Unix
>7	byte		3		os: Amiga
>7	byte		4		os: Macintosh
>7	byte		5		os: OS/2
>7	byte		6		os: Apple ][ GS
>7	byte		7		os: Atari ST
>7	byte		8		os: NeXT
>7	byte		9		os: VAX/VMS
>3	byte		>0		%d]
# [JW] idarc says this is also possible
2	leshort		0xea60		ARJ archive data

# HA archiver (Greg Roelofs, newt@uchicago.edu)
# This is a really bad format. A file containing HAWAII will match this...
#0	string		HA		HA archive data,
#>2	leshort		=1		1 file,
#>2	leshort		>1		%hu files,
#>4	byte&0x0f	=0		first is type CPY
#>4	byte&0x0f	=1		first is type ASC
#>4	byte&0x0f	=2		first is type HSC
#>4	byte&0x0f	=0x0e		first is type DIR
#>4	byte&0x0f	=0x0f		first is type SPECIAL
# suggestion: at least identify small archives (<1024 files)
0  belong&0xffff00fc 0x48410000 HA archive data
>2	leshort		=1		1 file,
>2	leshort		>1		%u files,
>4	byte&0x0f	=0		first is type CPY
>4	byte&0x0f	=1		first is type ASC
>4	byte&0x0f	=2		first is type HSC
>4	byte&0x0f	=0x0e		first is type DIR
>4	byte&0x0f	=0x0f		first is type SPECIAL

# HPACK archiver (Peter Gutmann, pgut1@cs.aukuni.ac.nz)
0	string		HPAK		HPACK archive data

# JAM Archive volume format, by Dmitry.Kohmanyuk@UA.net
0	string		\351,\001JAM\ 		JAM archive,
>7	string		>\0			version %.4s
>0x26	byte		=0x27			-
>>0x2b	string          >\0			label %.11s,
>>0x27	lelong		x			serial %08x,
>>0x36	string		>\0			fstype %.8s

# LHARC/LHA archiver (Greg Roelofs, newt@uchicago.edu)
# Update: Joerg Jenderek
# URL: https://en.wikipedia.org/wiki/LHA_(file_format)
# Reference: http://web.archive.org/web/20021005080911/http://www.osirusoft.com/joejared/lzhformat.html
#
#	check and display information of lharc (LHa,PMarc) file
0	name				lharc-file
# check 1st character of method id like -lz4- -lh5- or -pm2-
>2	string		-
# check 5th character of method id
>>6	string		-
# check header level 0 1 2 3
>>>20	ubyte		<4
# check 2nd, 3th and 4th character of method id
>>>>3	regex		\^(lh[0-9a-ex]|lz[s2-8]|pm[012]|pc1)		\b
!:mime	application/x-lzh-compressed
# creator type "LHA "
!:apple	????LHA
# display archive type name like "LHa/LZS archive data" or "LArc archive"
>>>>>2	string		-lz		\b
!:ext	lzs
# already known  -lzs- -lz4- -lz5- with old names
>>>>>>2	string	-lzs		LHa/LZS archive data
>>>>>>3	regex	\^lz[45]	LHarc 1.x archive data
# missing -lz?- with wikipedia names
>>>>>>3	regex	\^lz[2378]	LArc archive
# display archive type name like "LHa (2.x) archive data"
>>>>>2	string		-lh		\b
# already known -lh0- -lh1- -lh2- -lh3-  -lh4- -lh5- -lh6- -lh7- -lhd- variants with old names
>>>>>>3	regex		\^lh[01]	LHarc 1.x/ARX archive data
# LHice archiver use ".ICE" as name extension instead usual one ".lzh"
# FOOBAR archiver use ".foo" as name extension instead usual one
# "Florain Orjanov's and Olga Bachetska's ARchiver" not found at the moment
>>>>>>>2	string	-lh1		\b
!:ext lha/lzh/ice
>>>>>>3	regex		\^lh[23d]	LHa 2.x? archive data
>>>>>>3	regex		\^lh[7]		LHa (2.x)/LHark archive data
>>>>>>3	regex		\^lh[456]	LHa (2.x) archive data
>>>>>>>2	string	-lh5		\b
# https://en.wikipedia.org/wiki/BIOS
# Some mainboard BIOS like Award use LHa compression. So archives with unusal extension are found like
# bios.rom , kd7_v14.bin, 1010.004, ...
!:ext lha/lzh/rom/bin
# missing -lh?- variants (Joe Jared)
>>>>>>3	regex		\^lh[89a-ce]	LHa (Joe Jared) archive
# UNLHA32 2.67a
>>>>>>2	string		-lhx		LHa (UNLHA32) archive
# lha archives with standard file name extensions ".lha" ".lzh"
>>>>>>3	regex		!\^(lh1|lh5)	\b
!:ext lha/lzh
# this should not happen if all -lh variants are described
>>>>>>2	default		x		LHa (unknown) archive
#!:ext	lha
# PMarc
>>>>>3	regex		\^pm[012]	PMarc archive data
!:ext pma
# append method id without leading and trailing minus character
>>>>>3	string		x		[%3.3s]
>>>>>>0	use	lharc-header
#
#	check and display information of lharc header
0	name				lharc-header
# header size 0x4 , 0x1b-0x61
>0	ubyte		x
# compressed data size != compressed file size
#>7	ulelong		x		\b, data size %d
# attribute: 0x2~?? 0x10~symlink|target 0x20~normal
#>19	ubyte		x		\b, 19_0x%x
# level identifier 0 1 2 3
#>20	ubyte		x		\b, level %d
# time stamp
#>15		ubelong	x		DATE 0x%8.8x
# OS ID for level 1
>20	ubyte		1
# 0x20 types find for *.rom files
>>(21.b+24)	ubyte	<0x21		\b, 0x%x OS
# ascii type like M for MSDOS
>>(21.b+24)	ubyte	>0x20		\b, '%c' OS
# OS ID for level 2
>20	ubyte		2
#>>23	ubyte		x		\b, OS ID 0x%x
>>23	ubyte		<0x21		\b, 0x%x OS
>>23	ubyte		>0x20		\b, '%c' OS
# filename only for level 0 and 1
>20	ubyte		<2
# length of filename
>>21		ubyte	>0		\b, with
# filename
>>>21		pstring	x		"%s"
#
#2	string		-lh0-		LHarc 1.x/ARX archive data [lh0]
#!:mime	application/x-lharc
2	string		-lh0-
>0	use	lharc-file
#2	string		-lh1-		LHarc 1.x/ARX archive data [lh1]
#!:mime	application/x-lharc
2	string		-lh1-
>0	use	lharc-file
# NEW -lz2- ... -lz8-
2	string		-lz2-
>0	use	lharc-file
2	string		-lz3-
>0	use	lharc-file
2	string		-lz4-
>0	use	lharc-file
2	string		-lz5-
>0	use	lharc-file
2	string		-lz7-
>0	use	lharc-file
2	string		-lz8-
>0	use	lharc-file
#	[never seen any but the last; -lh4- reported in comp.compression:]
#2	string		-lzs-		LHa/LZS archive data [lzs]
2	string		-lzs-
>0	use	lharc-file
# According to wikipedia and others such a version does not exist
#2	string		-lh\40-		LHa 2.x? archive data [lh ]
#2	string		-lhd-		LHa 2.x? archive data [lhd]
2	string		-lhd-
>0	use	lharc-file
#2	string		-lh2-		LHa 2.x? archive data [lh2]
2	string		-lh2-
>0	use	lharc-file
#2	string		-lh3-		LHa 2.x? archive data [lh3]
2	string		-lh3-
>0	use	lharc-file
#2	string		-lh4-		LHa (2.x) archive data [lh4]
2	string		-lh4-
>0	use	lharc-file
#2	string		-lh5-		LHa (2.x) archive data [lh5]
2	string		-lh5-
>0	use	lharc-file
#2	string		-lh6-		LHa (2.x) archive data [lh6]
2	string		-lh6-
>0	use	lharc-file
#2	string		-lh7-		LHa (2.x)/LHark archive data [lh7]
2	string		-lh7-
# !:mime	application/x-lha
# >20	byte		x		- header level %d
>0	use	lharc-file
# NEW -lh8- ... -lhe- , -lhx-
2	string		-lh8-
>0	use	lharc-file
2	string		-lh9-
>0	use	lharc-file
2	string		-lha-
>0	use	lharc-file
2	string		-lhb-
>0	use	lharc-file
2	string		-lhc-
>0	use	lharc-file
2	string		-lhe-
>0	use	lharc-file
2	string		-lhx-
>0	use	lharc-file
# taken from idarc [JW]
2   string      -lZ         PUT archive data
# already done by LHarc magics
# this should never happen if all sub types of LZS archive are identified
#2   string      -lz         LZS archive data
2   string      -sw1-       Swag archive data

0	name		rar-file-header
>24	byte		15		\b, v1.5
>24	byte		20		\b, v2.0
>24	byte		29		\b, v4
>15	byte		0		\b, os: MS-DOS
>15	byte		1		\b, os: OS/2
>15	byte		2		\b, os: Win32
>15	byte		3		\b, os: Unix
>15	byte		4		\b, os: Mac OS
>15	byte		5		\b, os: BeOS

0	name		rar-archive-header
>3	leshort&0x1ff	>0		\b, flags:
>>3	leshort		&0x01		ArchiveVolume
>>3	leshort		&0x02		Commented
>>3	leshort		&0x04		Locked
>>3	leshort		&0x10		NewVolumeNaming
>>3	leshort		&0x08		Solid
>>3	leshort		&0x20		Authenticated
>>3	leshort		&0x40		RecoveryRecordPresent
>>3	leshort		&0x80		EncryptedBlockHeader
>>3	leshort		&0x100		FirstVolume

# RAR (Roshal Archive) archive
0	string		Rar!\x1a\7\0		RAR archive data
!:mime	application/x-rar
!:ext	rar/cbr
# file header
>(0xc.l+9)	byte	0x74
>>(0xc.l+7)	use	rar-file-header
# subblock seems to share information with file header
>(0xc.l+9)	byte	0x7a
>>(0xc.l+7)	use	rar-file-header
>9		byte	0x73
>>7		use	rar-archive-header

0	string		Rar!\x1a\7\1\0		RAR archive data, v5
!:mime	application/x-rar
!:ext	rar

# Very old RAR archive
# http://jasonblanks.com/wp-includes/images/papers/KnowyourarchiveRAR.pdf
0	string		RE\x7e\x5e  RAR archive data (<v1.5)
!:mime	application/x-rar
!:ext	rar/cbr

# SQUISH archiver (Greg Roelofs, newt@uchicago.edu)
0	string		SQSH		squished archive data (Acorn RISCOS)

# UC2 archiver (Greg Roelofs, newt@uchicago.edu)
# [JW] see exe section for self-extracting version
0	string		UC2\x1a		UC2 archive data

# PKZIP multi-volume archive
0	string		PK\x07\x08PK\x03\x04	Zip multi-volume archive data, at least PKZIP v2.50 to extract
!:mime	application/zip
!:ext zip/cbz

# Zip archives (Greg Roelofs, c/o zip-bugs@wkuvx1.wku.edu)
0	string		PK\005\006	Zip archive data (empty)
!:mime application/zip
!:ext zip/cbz
0	string		PK\003\004

# Specialised zip formats which start with a member named 'mimetype'
# (stored uncompressed, with no 'extra field') containing the file's MIME type.
# Check for have 8-byte name, 0-byte extra field, name "mimetype", and
#  contents starting with "application/":
>26	string		\x8\0\0\0mimetypeapplication/

#  KOffice / OpenOffice & StarOffice / OpenDocument formats
#    From: Abel Cheung <abel@oaka.org>

#   KOffice (1.2 or above) formats
#    (mimetype contains "application/vnd.kde.<SUBTYPE>")
>>50	string	vnd.kde.		KOffice (>=1.2)
>>>58	string	karbon			Karbon document
>>>58	string	kchart			KChart document
>>>58	string	kformula		KFormula document
>>>58	string	kivio			Kivio document
>>>58	string	kontour			Kontour document
>>>58	string	kpresenter		KPresenter document
>>>58	string	kspread			KSpread document
>>>58	string	kword			KWord document

#   OpenOffice formats (for OpenOffice 1.x / StarOffice 6/7)
#    (mimetype contains "application/vnd.sun.xml.<SUBTYPE>")
>>50	string	vnd.sun.xml.		OpenOffice.org 1.x
>>>62	string	writer			Writer
>>>>68	byte	!0x2e			document
>>>>68	string	.template		template
>>>>68	string	.global			global document
>>>62	string	calc			Calc
>>>>66	byte	!0x2e			spreadsheet
>>>>66	string	.template		template
>>>62	string	draw			Draw
>>>>66	byte	!0x2e			document
>>>>66	string	.template		template
>>>62	string	impress			Impress
>>>>69	byte	!0x2e			presentation
>>>>69	string	.template		template
>>>62	string	math			Math document
>>>62	string	base			Database file

#   OpenDocument formats (for OpenOffice 2.x / StarOffice >= 8)
#    http://lists.oasis-open.org/archives/office/200505/msg00006.html
#    (mimetype contains "application/vnd.oasis.opendocument.<SUBTYPE>")
>>50	string	vnd.oasis.opendocument.	OpenDocument
>>>73	string	text
>>>>77	byte	!0x2d			Text
!:mime	application/vnd.oasis.opendocument.text
>>>>77	string	-template		Text Template
!:mime	application/vnd.oasis.opendocument.text-template
>>>>77	string	-web			HTML Document Template
!:mime	application/vnd.oasis.opendocument.text-web
>>>>77	string	-master			Master Document
!:mime	application/vnd.oasis.opendocument.text-master
>>>73	string	graphics
>>>>81	byte	!0x2d			Drawing
!:mime	application/vnd.oasis.opendocument.graphics
>>>>81	string	-template		Template
!:mime	application/vnd.oasis.opendocument.graphics-template
>>>73	string	presentation
>>>>85	byte	!0x2d			Presentation
!:mime	application/vnd.oasis.opendocument.presentation
>>>>85	string	-template		Template
!:mime	application/vnd.oasis.opendocument.presentation-template
>>>73	string	spreadsheet
>>>>84	byte	!0x2d			Spreadsheet
!:mime	application/vnd.oasis.opendocument.spreadsheet
>>>>84	string	-template		Template
!:mime	application/vnd.oasis.opendocument.spreadsheet-template
>>>73	string	chart
>>>>78	byte	!0x2d			Chart
!:mime	application/vnd.oasis.opendocument.chart
>>>>78	string	-template		Template
!:mime	application/vnd.oasis.opendocument.chart-template
>>>73	string	formula
>>>>80	byte	!0x2d			Formula
!:mime	application/vnd.oasis.opendocument.formula
>>>>80	string	-template		Template
!:mime	application/vnd.oasis.opendocument.formula-template
>>>73	string	database		Database
!:mime	application/vnd.oasis.opendocument.database
>>>73	string	image
>>>>78	byte	!0x2d			Image
!:mime	application/vnd.oasis.opendocument.image
>>>>78	string	-template		Template
!:mime	application/vnd.oasis.opendocument.image-template

#  EPUB (OEBPS) books using OCF (OEBPS Container Format)
#    http://www.idpf.org/ocf/ocf1.0/download/ocf10.htm, section 4.
#    From: Ralf Brown <ralf.brown@gmail.com>
>>50	string	epub+zip	EPUB document
!:mime application/epub+zip

#  Catch other ZIP-with-mimetype formats
#	In a ZIP file, the bytes immediately after a member's contents are
#	always "PK". The 2 regex rules here print the "mimetype" member's
#	contents up to the first 'P'. Luckily, most MIME types don't contain
#	any capital 'P's. This is a kludge.
#    (mimetype contains "application/<OTHER>")
>>50		string	!epub+zip
>>>50		string	!vnd.oasis.opendocument.
>>>>50		string	!vnd.sun.xml.
>>>>>50		string	!vnd.kde.
>>>>>>38	regex	[!-OQ-~]+		Zip data (MIME type "%s"?)
!:mime	application/zip
#    (mimetype contents other than "application/*")
>26		string	\x8\0\0\0mimetype
>>38		string	!application/
>>>38		regex	[!-OQ-~]+		Zip data (MIME type "%s"?)
!:mime	application/zip

# Java Jar files
>(26.s+30)	leshort	0xcafe		Java archive data (JAR)
!:mime	application/java-archive

# iOS App
>(26.s+30)	leshort	!0xcafe
>>26		string	!\x8\0\0\0mimetype
>>>30		string	Payload/
>>>>38		search/64       .app/   iOS App
!:mime application/x-ios-app


# Generic zip archives (Greg Roelofs, c/o zip-bugs@wkuvx1.wku.edu)
#   Next line excludes specialized formats:
>(26.s+30)	leshort	!0xcafe
>>26    string          !\x8\0\0\0mimetype	Zip archive data
!:mime	application/zip
>>>4	byte		0x09		\b, at least v0.9 to extract
>>>4	byte		0x0a		\b, at least v1.0 to extract
>>>4	byte		0x0b		\b, at least v1.1 to extract
>>>4	byte		0x14		\b, at least v2.0 to extract
>>>4	byte		0x15		\b, at least v2.1 to extract
>>>4	byte		0x19		\b, at least v2.5 to extract
>>>4	byte		0x1b		\b, at least v2.7 to extract
>>>4	byte		0x2d		\b, at least v4.5 to extract
>>>4	byte		0x2e		\b, at least v4.6 to extract
>>>4	byte		0x32		\b, at least v5.0 to extract
>>>4	byte		0x33		\b, at least v5.1 to extract
>>>4	byte		0x34		\b, at least v5.2 to extract
>>>4	byte		0x3d		\b, at least v6.1 to extract
>>>4	byte		0x3e		\b, at least v6.2 to extract
>>>4	byte		0x3f		\b, at least v6.3 to extract
>>>0x161	string		WINZIP		\b, WinZIP self-extracting

# StarView Metafile
# From Pierre Ducroquet <pinaraf@pinaraf.info>
0	string	VCLMTF	StarView MetaFile
>6	beshort	x	\b, version %d
>8	belong	x	\b, size %d

# Zoo archiver
20	lelong		0xfdc4a7dc	Zoo archive data
!:mime	application/x-zoo
>4	byte		>48		\b, v%c.
>>6	byte		>47		\b%c
>>>7	byte		>47		\b%c
>32	byte		>0		\b, modify: v%d
>>33	byte		x		\b.%d+
>42	lelong		0xfdc4a7dc	\b,
>>70	byte		>0		extract: v%d
>>>71	byte		x		\b.%d+

# Shell archives
10	string		#\ This\ is\ a\ shell\ archive	shell archive text
!:mime	application/octet-stream

#
# LBR. NB: May conflict with the questionable
#          "binary Computer Graphics Metafile" format.
#
0       string  \0\ \ \ \ \ \ \ \ \ \ \ \0\0    LBR archive data
#
# PMA (CP/M derivative of LHA)
# Update: Joerg Jenderek
# URL: https://en.wikipedia.org/wiki/LHA_(file_format)
#
#2       string          -pm0-           PMarc archive data [pm0]
2	string		-pm0-
>0	use	lharc-file
#2       string          -pm1-           PMarc archive data [pm1]
2	string		-pm1-
>0	use	lharc-file
#2       string          -pm2-           PMarc archive data [pm2]
2	string		-pm2-
>0	use	lharc-file
2       string          -pms-           PMarc SFX archive (CP/M, DOS)
#!:mime	application/x-foobar-exec
!:ext com
5       string          -pc1-           PopCom compressed executable (CP/M)
#!:mime	application/x-
#!:ext com

# From Rafael Laboissiere <rafael@laboissiere.net>
# The Project Revision Control System (see
# http://prcs.sourceforge.net) generates a packaged project
# file which is recognized by the following entry:
0	leshort		0xeb81	PRCS packaged project

# Microsoft cabinets
# by David Necas (Yeti) <yeti@physics.muni.cz>
#0	string	MSCF\0\0\0\0	Microsoft cabinet file data,
#>25	byte	x		v%d
#>24	byte	x		\b.%d
# MPi: All CABs have version 1.3, so this is pointless.
# Better magic in debian-additions.

# GTKtalog catalogs
# by David Necas (Yeti) <yeti@physics.muni.cz>
4	string	gtktalog\ 	GTKtalog catalog data,
>13	string	3		version 3
>>14	beshort	0x677a		(gzipped)
>>14	beshort	!0x677a		(not gzipped)
>13	string	>3		version %s

############################################################################
# Parity archive reconstruction file, the 'par' file format now used on Usenet.
0       string          PAR\0	PARity archive data
>48	leshort		=0	- Index file
>48	leshort		>0	- file number %d

# Felix von Leitner <felix-file@fefe.de>
0	string	d8:announce	BitTorrent file
!:mime	application/x-bittorrent
# Durval Menezes, <jmgthbfile at durval dot com>
0	string	d13:announce-list	BitTorrent file
!:mime	application/x-bittorrent

# Atari MSA archive - Teemu Hukkanen <tjhukkan@iki.fi>
0	beshort 0x0e0f		Atari MSA archive data
>2	beshort x		\b, %d sectors per track
>4	beshort 0		\b, 1 sided
>4	beshort 1		\b, 2 sided
>6	beshort x		\b, starting track: %d
>8	beshort x		\b, ending track: %d

# Alternate ZIP string (amc@arwen.cs.berkeley.edu)
0	string	PK00PK\003\004	Zip archive data

# ACE archive (from http://www.wotsit.org/download.asp?f=ace)
# by Stefan `Sec` Zehl <sec@42.org>
7	string		**ACE**		ACE archive data
>15	byte	>0		version %d
>16	byte	=0x00		\b, from MS-DOS
>16	byte	=0x01		\b, from OS/2
>16	byte	=0x02		\b, from Win/32
>16	byte	=0x03		\b, from Unix
>16	byte	=0x04		\b, from MacOS
>16	byte	=0x05		\b, from WinNT
>16	byte	=0x06		\b, from Primos
>16	byte	=0x07		\b, from AppleGS
>16	byte	=0x08		\b, from Atari
>16	byte	=0x09		\b, from Vax/VMS
>16	byte	=0x0A		\b, from Amiga
>16	byte	=0x0B		\b, from Next
>14	byte	x		\b, version %d to extract
>5	leshort &0x0080		\b, multiple volumes,
>>17	byte	x		\b (part %d),
>5	leshort &0x0002		\b, contains comment
>5	leshort	&0x0200		\b, sfx
>5	leshort	&0x0400		\b, small dictionary
>5	leshort	&0x0800		\b, multi-volume
>5	leshort	&0x1000		\b, contains AV-String
>>30	string	\x16*UNREGISTERED\x20VERSION*	(unregistered)
>5	leshort &0x2000		\b, with recovery record
>5	leshort &0x4000		\b, locked
>5	leshort &0x8000		\b, solid
# Date in MS-DOS format (whatever that is)
#>18	lelong	x		Created on

# sfArk : compression program for Soundfonts (sf2) by Dirk Jagdmann
# <doj@cubic.org>
0x1A	string	sfArk		sfArk compressed Soundfont
>0x15	string	2
>>0x1	string	>\0		Version %s
>>0x2A	string	>\0		: %s

# DR-DOS 7.03 Packed File *.??_
0	string	Packed\ File\ 	Personal NetWare Packed File
>12	string	x		\b, was "%.12s"

# EET archive
# From: Tilman Sauerbeck <tilman@code-monkey.de>
0	belong	0x1ee7ff00	EET archive
!:mime	application/x-eet

# rzip archives
0	string	RZIP		rzip compressed data
>4	byte	x		- version %d
>5	byte	x		\b.%d
>6	belong	x		(%d bytes)

# From: "Robert Dale" <robdale@gmail.com>
0	belong	123		dar archive,
>4	belong	x		label "%.8x
>>8	belong	x		%.8x
>>>12	beshort	x		%.4x"
>14	byte	0x54		end slice
>14	beshort	0x4e4e		multi-part
>14	beshort	0x4e53		multi-part, with -S

# Symbian installation files
#  http://www.thouky.co.uk/software/psifs/sis.html
#  http://developer.symbian.com/main/downloads/papers/SymbianOSv91/softwareinstallsis.pdf
8	lelong	0x10000419	Symbian installation file
!:mime	application/vnd.symbian.install
>4	lelong	0x1000006D	(EPOC release 3/4/5)
>4	lelong	0x10003A12	(EPOC release 6)
0	lelong	0x10201A7A	Symbian installation file (Symbian OS 9.x)
!:mime	x-epoc/x-sisx-app

# From "Nelson A. de Oliveira" <naoliv@gmail.com>
0	string	MPQ\032		MoPaQ (MPQ) archive

# From: "Nelson A. de Oliveira" <naoliv@gmail.com>
# .kgb
0	string KGB_arch		KGB Archiver file
>10	string x		with compression level %.1s

# xar (eXtensible ARchiver) archive
# xar archive format: http://code.google.com/p/xar/
# From: "David Remahl" <dremahl@apple.com>
0	string	xar!		xar archive
!:mime	application/x-xar
#>4	beshort	x		header size %d
>6	beshort	x		version %d,
#>8	quad	x		compressed TOC: %d,
#>16	quad	x		uncompressed TOC: %d,
>24	belong	0		no checksum
>24	belong	1		SHA-1 checksum
>24	belong	2		MD5 checksum

# Type: Parity Archive
# From: Daniel van Eeden <daniel_e@dds.nl>
0	string	PAR2		Parity Archive Volume Set

# Bacula volume format. (Volumes always start with a block header.)
# URL: http://bacula.org/3.0.x-manuals/en/developers/developers/Block_Header.html
# From: Adam Buchbinder <adam.buchbinder@gmail.com>
12	string	BB02		Bacula volume
>20	bedate	x		\b, started %s

# ePub is XHTML + XML inside a ZIP archive.  The first member of the
#   archive must be an uncompressed file called 'mimetype' with contents
#   'application/epub+zip'


# From: "Michael Gorny" <mgorny@gentoo.org>
# ZPAQ: http://mattmahoney.net/dc/zpaq.html
0	string	zPQ	ZPAQ stream
>3	byte	x	\b, level %d
# From: Barry Carter <carter.barry@gmail.com>
# http://encode.ru/threads/456-zpaq-updates/page32
0	string	7kSt	ZPAQ file

# BBeB ebook, unencrypted (LRF format)
# URL: http://www.sven.de/librie/Librie/LrfFormat
# From: Adam Buchbinder <adam.buchbinder@gmail.com>
0	string	L\0R\0F\0\0\0	BBeB ebook data, unencrypted
>8	beshort	x		\b, version %d
>36	byte	1		\b, front-to-back
>36	byte	16		\b, back-to-front
>42	beshort	x		\b, (%dx,
>44	beshort	x		%d)

# Symantec GHOST image by Joerg Jenderek at May 2014
# http://us.norton.com/ghost/
# http://www.garykessler.net/library/file_sigs.html
0		ubelong&0xFFFFf7f0	0xFEEF0100	Norton GHost image
# *.GHO
>2		ubyte&0x08		0x00		\b, first file
# *.GHS or *.[0-9] with cns program option
>2		ubyte&0x08		0x08		\b, split file
# part of split index interesting for *.ghs
>>4		ubyte			x		id=0x%x
# compression tag minus one equals numeric compression command line switch z[1-9]
>3		ubyte			0		\b, no compression
>3		ubyte			2		\b, fast compression (Z1)
>3		ubyte			3		\b, medium compression (Z2)
>3		ubyte			>3
>>3		ubyte			<11		\b, compression (Z%d-1)
>2		ubyte&0x08		0x00
# ~ 30 byte password field only for *.gho
>>12		ubequad			!0		\b, password protected
>>44		ubyte			!1
# 1~Image All, sector-by-sector only for *.gho
>>>10		ubyte			1		\b, sector copy
# 1~Image Boot track only for *.gho
>>>43		ubyte			1		\b, boot track
# 1~Image Disc only for *.gho implies Image Boot track and sector copy
>>44		ubyte			1		\b, disc sector copy
# optional image description only *.gho
>>0xff		string			>\0		"%-.254s"
# look for DOS sector end sequence
>0xE08	search/7776		\x55\xAA
>>&-512	indirect		x		\b; contains

# Google Chrome extensions
# https://developer.chrome.com/extensions/crx
# https://developer.chrome.com/extensions/hosting
0	string	Cr24	Google Chrome extension
!:mime	application/x-chrome-extension
>4	ulong	x	\b, version %u

# SeqBox - Sequenced container
# ext: sbx, seqbox
# Marco Pontello marcopon@gmail.com
# reference: https://github.com/MarcoPon/SeqBox
0	string	SBx	SeqBox,
>3	byte	x	version %d