xref: /freebsd/contrib/file/magic/Magdir/archive (revision a2dfb7224ec9933ee804cae54d51848dce938b6b)

#------------------------------------------------------------------------------
# $File: archive,v 1.169 2022/09/12 13:13:28 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 also handled in the C code ../../src/is_tar.c.

# POSIX tar archives
# URL: https://en.wikipedia.org/wiki/Tar_(computing)
# Reference: https://www.freebsd.org/cgi/man.cgi?query=tar&sektion=5&manpath=FreeBSD+8-current
# header mainly padded with nul bytes
500	quad		0
!:strength /2
# filename or extended attribute printable strings in range space null til umlaut ue
>0	ubeshort	>0x1F00
>>0	ubeshort	<0xFCFD
# last 4 header bytes often null but tar\0 in gtarfail2.tar gtarfail.tar-bad
# at https://sourceforge.net/projects/s-tar/files/testscripts/
>>>508	ubelong&0x8B9E8DFF	0
# nul, space or ascii digit 0-7 at start of mode
>>>>100	ubyte&0xC8	=0
>>>>>101 ubyte&0xC8	=0
# nul, space at end of check sum
>>>>>>155 ubyte&0xDF	=0
# space or ascii digit 0 at start of check sum
>>>>>>>148	ubyte&0xEF	=0x20
# FOR DEBUGGING:
#>>>>>>>>0	regex		\^[0-9]{2,4}[.](png|jpg|jpeg|tif|tiff|gif|bmp)	NAME "%s"
# check for 1st image main name with digits used for sorting
# and for name extension case insensitive like: PNG JPG JPEG TIF TIFF GIF BMP
>>>>>>>>0	regex		\^[0-9]{2,4}[.](png|jpg|jpeg|tif|tiff|gif|bmp)
#foo
>>>>>>>>>0	use	tar-cbt
# if 1st member name without digits and without used image suffix then it is a TAR archive
>>>>>>>>0	default		x
>>>>>>>>>0	use	tar-file
#	minimal check and then display tar archive information which can also be
#	embedded inside others like Android Backup, Clam AntiVirus database
0	name		tar-file
>257	string		!ustar
# header padded with nuls
>>257	ulong		=0
# GNU tar version 1.29 with non pax format option without refusing
# creates misleading V7 header for Long path, Multi-volume, Volume type
>>>156	ubyte		0x4c		GNU tar archive
!:mime	application/x-gtar
!:ext	tar/gtar
>>>156	ubyte		0x4d		GNU tar archive
!:mime	application/x-gtar
!:ext	tar/gtar
>>>156	ubyte		0x56		GNU tar archive
!:mime	application/x-gtar
!:ext	tar/gtar
>>>156	default		x		tar archive (V7)
!:mime	application/x-tar
!:ext	tar
# other stuff in padding
# some implementations add new fields to the blank area at the end of the header record
# created for example by DOS TAR 3.20g 1994 Tim V.Shapore with -j option
>>257	ulong		!0		tar archive (old)
!:mime	application/x-tar
!:ext	tar
# magic in newer, GNU, posix variants
>257	string		=ustar
# 2 last char of magic and UStar version because string expression does not work
# 2 space characters followed by a null for GNU variant
>>261	ubelong		=0x72202000	POSIX tar archive (GNU)
!:mime	application/x-gtar
!:ext	tar/gtar
# UStar version with ASCII "00"
>>261	ubelong		0x72003030	POSIX
# gLOBAL and ExTENSION type only found in POSIX.1-2001 format
>>>156	ubyte		0x67		\b.1-2001
>>>156	ubyte		0x78		\b.1-2001
>>>156	ubyte		x		tar archive
!:mime	application/x-ustar
!:ext	tar/ustar
# version with 2 binary nuls embedded in Android Backup like com.android.settings.ab
>>261	ubelong		0x72000000	tar archive (ustar)
!:mime	application/x-ustar
!:ext	tar/ustar
# not seen ustar variant with garbish version
>>261	default		x		tar archive (unknown ustar)
!:mime	application/x-ustar
!:ext	tar/ustar
# type flag of 1st tar archive member
#>156	ubyte		x		\b, %c-type
>156	ubyte		x
>>156	ubyte		0		\b, file
>>156	ubyte		0x30		\b, file
>>156	ubyte		0x31		\b, hard link
>>156	ubyte		0x32		\b, symlink
>>156	ubyte		0x33		\b, char device
>>156	ubyte		0x34		\b, block device
>>156	ubyte		0x35		\b, directory
>>156	ubyte		0x36		\b, fifo
>>156	ubyte		0x37		\b, reserved
>>156	ubyte		0x4c		\b, long path
>>156	ubyte		0x4d		\b, multi volume
>>156	ubyte		0x56		\b, volume
>>156	ubyte		0x67		\b, global
>>156	ubyte		0x78		\b, extension
>>156	default		x		\b, type
>>>156	ubyte		x		'%c'
# name[100]
>0	string		>\0		%-.60s
# mode mainly stored as an octal number in ASCII null or space terminated
>100	string		>\0		\b, mode %-.7s
# user id mainly as octal numbers in ASCII null or space terminated
>108	string		>\0		\b, uid %-.7s
# group id mainly as octal numbers in ASCII null or space terminated
>116	string		>\0		\b, gid %-.7s
# size mainly as octal number in ASCII
>124	ubyte		<0x38
>>124	string		>\0		\b, size %-.12s
# coding indicated by setting the high-order bit of the leftmost byte
>124	ubyte		>0xEF		\b, size 0x
>>124	ubyte		!0xff		\b%2.2x
>>125	ubyte		!0xff		\b%2.2x
>>126	ubyte		!0xff		\b%2.2x
>>127	ubyte		!0xff		\b%2.2x
>>128	ubyte		!0xff		\b%2.2x
>>129	ubyte		!0xff		\b%2.2x
>>130	ubyte		!0xff		\b%2.2x
>>131	ubyte		!0xff		\b%2.2x
>>132	ubyte		!0xff		\b%2.2x
>>133	ubyte		!0xff		\b%2.2x
>>134	ubyte		!0xff		\b%2.2x
>>135	ubyte		!0xff		\b%2.2x
# seconds since 0:0:0 1 jan 1970 UTC as octal number mainly in ASCII null or space terminated
>136	string		>\0		\b, seconds %-.11s
# header checksum stored as an octal number in ASCII null or space terminated
#>148	string		x		\b, cksum %.7s
# linkname[100]
>157	string		>\0		\b, linkname %-.40s
# additional fields for ustar
>257	string		=ustar
# owner user name null terminated
>>265	string		>\0		\b, user %-.32s
# group name null terminated
>>297	string		>\0		\b, group %-.32s
# device major minor if not zero
>>329	ubequad&0xCFCFCFCFcFcFcFdf	!0
>>>329	string		x		\b, devmaj %-.7s
>>337	ubequad&0xCFCFCFCFcFcFcFdf	!0
>>>337	string		x		\b, devmin %-.7s
# prefix[155]
>>345	string		>\0		\b, prefix %-.155s
# old non ustar/POSIX tar
>257	string		!ustar
>>508	string		=tar\0
# padding[255] in old star
>>>257	string		>\0		\b, padding: %-.40s
>>508	default		x
# padding[255] in old tar sometimes comment field
>>>257	string		>\0		\b, comment: %-.40s
# Summary:	Comic Book Archive *.CBT with TAR format
# URL:		https://en.wikipedia.org/wiki/Comic_book_archive
#		http://fileformats.archiveteam.org/wiki/Comic_Book_Archive
# Note:		there exist also RAR, ZIP, ACE and 7Z packed variants
0	name		tar-cbt
>0	string		x		Comic Book archive, tar archive
#!:mime	application/x-tar
!:mime	application/vnd.comicbook
#!:mime	application/vnd.comicbook+tar
!:ext	cbt
# name[100] probably like: 19.jpg 0001.png 0002.png
# or maybe like ComicInfo.xml
>0	string		>\0		\b, 1st image %-.60s

# Incremental snapshot gnu-tar format from:
# https://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)
!:mime	application/x-cpio
0	string		070701		ASCII cpio archive (SVR4 with no CRC)
!:mime	application/x-cpio
0	string		070702		ASCII cpio archive (SVR4 with CRC)
!:mime	application/x-cpio

#
# 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".
#
# Update: Joerg Jenderek
# URL: https://en.wikipedia.org/wiki/Deb_(file_format)
0	string		=!<arch>\ndebian
# https://manpages.debian.org/testing/dpkg/dpkg-split.1.en.html
>14	string		-split	part of multipart Debian package
!:mime	application/vnd.debian.binary-package
# udeb is used for stripped down deb file
!:ext	deb/udeb
>14	string		-binary	Debian binary package
!:mime	application/vnd.debian.binary-package
# For ipk packager see also https://en.wikipedia.org/wiki/Opkg
!:ext	deb/udeb/ipk
# This should not happen
>14	default		x	Unknown Debian package
# NL terminated version; for most Debian cases this is 2.0 or 2.1 for split
>68	string		>\0		(format %s)
#>68	string		!2.0\n
#>>68	string		x		(format %.3s)
>68	string		=2.0\n
# 2nd archive name=control archive name like control.tar.gz or control.tar.xz
>>72	string		>\0		\b, with %.14s
# look for 3rd archive name=data archive name like data.tar.{gz,xz,bz2,lzma}
>>0	search/0x93e4f	data.tar.	\b, data compression
# the above line only works if FILE_BYTES_MAX in ../../src/file.h is raised
# for example like libreoffice-dev-doc_1%3a5.2.7-1+rpi1+deb9u3_all.deb
>>>&0	string		x		%.2s
# skip space (0x20 BSD) and slash (0x2f System V) character marking end of name
>>>&2	ubyte		!0x20
>>>>&-1	ubyte		!0x2f
# display 3rd character of file name extension like 2 of bz2 or m of lzma
>>>>>&-1	ubyte	x		\b%c
>>>>>>&0	ubyte	!0x20
>>>>>>>&-1	ubyte	!0x2f
# display 4th character of file name extension like a of lzma
>>>>>>>>&-1	ubyte	x		\b%c
# split debian package case
>68	string		=2.1\n
# dpkg-1.18.25/dpkg-split/info.c
# NL terminated ASCII package name like ckermit
>>&0	string		x		\b, %s
# NL terminated package version like 302-5.3
>>>&1	string		x		%s
# NL terminated MD5 checksum
>>>>&1	string		x		\b, MD5 %s
# NL terminated original package length
>>>>>&1	string		x		\b, unsplitted size %s
# NL terminated part length
>>>>>>&1	string	x		\b, part length %s
# NL terminated package part like n/m
>>>>>>>&1	string	x		\b, part %s
# NL terminated package architecture like armhf since dpkg 1.16.1 or later
>>>>>>>>&1	string	x		\b, %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

#
# BSD/SVR2-and-later portable archive formats.
#
# Update: Joerg Jenderek
# URL:		http://fileformats.archiveteam.org/wiki/AR
# Reference:	https://www.unix.com/man-page/opensolaris/3HEAD/ar.h/
# Note:		Mach-O universal binary in ./cafebabe is dependent
# TODO:		unify current ar archive, MIPS archive, Debian package
#		distinguish BSD, SVR; 32, 64 bit; HP from other 32-bit SVR;
#		*.ar packages from *.a libraries. handle empty archive
0	string		=!<arch>\n		current ar archive
# print first and possibly second ar_name[16] for debugging purpose
#>8			string	x	\b, 1st "%.16s"
#>68			string	x	\b, 2nd "%.16s"
!:mime	application/x-archive
# a in most case for libraries; lib for Microsoft libraries; ar else cases
!:ext	a/lib/ar
>8	string		__.SYMDEF	random library
# first member with long marked name __.SYMDEF SORTED implies BSD library
>68	string		__.SYMDEF\ SORTED	random library
# Reference: https://parisc.wiki.kernel.org/images-parisc/b/b2/Rad_11_0_32.pdf
# "archive file" entry moved from ./hp
# LST header system_id 0210h~PA-RISC 1.1,... identifies the target architecture
# LST header a_magic 0619h~relocatable library
>68	belong 		0x020b0619	- PA-RISC1.0 relocatable library
>68	belong	 	0x02100619	- PA-RISC1.1 relocatable library
>68	belong 		0x02110619	- PA-RISC1.2 relocatable library
>68	belong 		0x02140619	- PA-RISC2.0 relocatable library
#EOF for common ar archives

#
# "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

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

# 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
# skip DOS 2.0 backup id file, sequence 6 with many nils like BACKUPID_xx6.@@@ handled by ./msdos
>>8	quad		!0
>>>0	use	ttcomp
# variant ASCII, 4K dictionary (strength=48=50-2). With strength=49 wrong order! WHY?
0	string	\1\6
# TODO:
# skip VAX-order 68k Blit mpx/mux executable (strength=50) handled by ./blit
!:strength	-2
>0	use	ttcomp
0	string	\0\5
# skip some DOS 2.0 backup id file, sequence 5 with many nils like BACKUPID_075.@@@ handled by ./msdos
>8	quad	!0
>>0	use	ttcomp
0	string	\1\5
# TODO:
# variant ASCII, 2K dictionary (strength=48=50-2). With strength=49 wrong order! WHY?
# skip ctab data (strength=50) handled by ./ibm6000
# skip locale data table (strength=50) handled by ./digital
!:strength	-2
>0	use	ttcomp
0	string	\0\4
# skip many Maple help database *.hdb with version tag handled by ./maple
>1028	string	!version
# skip veclib maple.hdb by looking for Mable keyword
>>4	search/1091	Maple\040
#>4	search/34090	Maple\040
>>4	default		x
# skip DOS 2.0-3.2 backed up sequence 4 with many nils like LOTUS5.RAR handled by ./msdos
# skip xBASE Compound Index file *.CDX with many nils
>>>0x54	quad		!0
>>>>0	use	ttcomp
0	string	\1\4
# TODO:
# skip Commodore PET BASIC 4.0 program *.prg
# variant ASCII, 1K dictionary (strength=48=50-2). With strength=49 wrong order! WHY?
# skip shared library (strength=50) handled by ./ibm6000
!:strength	-2
>0	use	ttcomp
#	display information of TTComp archive
0	name	ttcomp
# (version 5.25) labeled the entry as "TTComp archive data"
>0	ubyte	x	TTComp archive data
!:mime	application/x-compress-ttcomp
# PBACKSCR.PI1
!:ext	$xe/$ts/pi1/__d
# compression type: 0~binary compression 1~ASCII compression
>0	ubyte	0	\b, binary
>0	ubyte	1	\b, ASCII
# size of the dictionary:  4~1024 bytes 5~2048 bytes 6~4096 bytes
>1	ubyte	4	\b, 1K
>1	ubyte	5	\b, 2K
>1	ubyte	6	\b, 4K
>1	ubyte	x	dictionary
#	https://mark0.net/forum/index.php?topic=848
# last 3 bytes probably have only 8 possible bit sequences
# xxxxxxxx 0000000x 11111111	____FFh
# xxxxxxxx 10000000 01111111	__807Fh
# 0xxxxxxx 11000000 00111111	__C03Fh
# 00xxxxxx 11100000 00011111	__E01Fh
# 000xxxxx 11110000 00001111	__F00Fh
# 0000xxxx 11111000 00000111	__F807h
# 00000xxx 11111100 00000011	__FC03h
# 000000xx 11111110 00000001	__FE01h
# but for quickgif.__d 0A7DD4h
#>-3	ubyte		x	\b, last 3 bytes 0x%2.2x
#>-2	ubeshort	x	\b%4.4x
# From:		Joerg Jenderek
# URL:		https://en.wikipedia.org/wiki/Disk_Copy
# reference:	http://nulib.com/library/FTN.e00005.htm
0x52	ubeshort	0x0100
# test for disk image size equal or above 400k
>0x40	ubelong		>409599
# test also for disk image size equal or below 1440k to skip
# windows7en.mbr UNICODE.DAT
#>>0x40	ubelong		<1474561
# test now for "low" disk image size equal or below 64 MiB to skip
# windows7en.mbr (B441BBAAh) UNICODE.DAT (0400AF05h)
>>0x40	ubelong		<0x04000001
# To skip Flags$StringJoiner.class with size 00106A61h test also for valid disk image sizes
# 00064000 for  400k GCR disks	dc42-400k-gcr.trid.xml
# 000c8000 for  800k GCR disks	dc42-800k-gcr.trid.xml
# 000b4000 for  720k MFM disks	dc42-720k-mfm.trid.xml
# 00168000 for 1440k MFM disks	dc42-1440k-mfm.trid.xml
#	https://lisaem.sunder.net/LisaProjectDocs.txt
# 00500000	05M	available
# 00A00000	10M	available
# 01800000	24M	possible
# 02000000	32M	uncertain
# 04000000	64M	uncertain
>>>0x40	ubelong&0xf8003fFF	0
# skip samples with invalid disk name length like:
# 181 (biosmd80.rom) 202 (Flags$StringJoiner.class) 90 (UNICODE.DAT)
>>>>0x0	ubyte			<64
>>>>>0	use			dc42-floppy
#	display information of Apple DiskCopy 4.2 floppy image
0	name		dc42-floppy
# disk name length; maximal 63
#>0	ubyte	    	x	DISK NAME LENGTH %u
# ASCII image pascal (maximal 63 bytes) name padded with NULs like:
# "Microsoft Mail" "Disquette 2" "IIe Installer Disk"
# "-lisaem.sunder.net hd-" (dc42-lisaem.trid.xml) "-not a Macintosh disk" (dc42-nonmac.trid.xml)
>00	pstring/B	x	Apple DiskCopy 4.2 image %s
#!:mime	application/octet-stream
!:mime	application/x-dc42-floppy-image
!:apple	dCpydImg
# probably also img like: "Utilitaires 2.img" "Installation 7.img"
!:ext	image/dc42/img
# data size in bytes like: 409600 737280 819200 1474560
>0x40	ubelong		x	\b, %u bytes
# for debugging purpose size in hexadecimal
#>0x40	ubelong		x	(%#8.8x)
# tag size in bytes like: 0 (often) 2580h (PUID fmt/625) 4B00h (Microsoft Mail.image)
>0x44	ubelong		>0	\b, %#x tag size
# data checksum
#>0x48	ubelong		x	\b, %#x checksum
# tag checksum
#>0x4c	ubelong		x	\b, %#x tag checksum
# disk encoding like: 0 1 2 3 (PUID: fmt/625)
>0x50	ubyte		0	\b, GCR CLV ssdd (400k)
>0x50	ubyte		1	\b, GCR CLV dsdd (800k)
>0x50	ubyte		2	\b, MFM CAV dsdd (720k)
>0x50	ubyte		3	\b, MFM CAV dshd (1440k)
>0x50	ubyte		>3	\b, %#x encoding
# format byte like: 12h (Lisa 400K) 24h (400K Macintosh) 96h (800K Apple II disk)
# 2 (Mac 400k "Disquette Installation 13.image")
# 22h (double-sided MFM or Mac 800k "Disco 12.image" "IIe Installer Disk.image")
>0x51	ubyte		x	\b, %#x format
#>0x54	ubequad		x	\b, data %#16.16llx
# 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
# Update: Joerg Jenderek
# URL: http://fileformats.archiveteam.org/wiki/MS-DOS_installation_compression
# Reference: https://hwiegman.home.xs4all.nl/fileformats/compress/szdd_kwaj_format.html
# Note: use correct version of extracting tool like EXPAND, UNPACK, DECOMP or 7Z
4	string	\x88\xf0\x27
#		KWAJ variant
>0	string	KWAJ		MS Compress archive data, KWAJ variant
!:mime	application/x-ms-compress-kwaj
# extension not working in version 5.32
# magic/Magdir/archive, 284: Warning: EXTENSION type ` ??_' has bad char '?'
# file: line 284: Bad magic entry '   ??_'
!:ext	??_
# compression method (0-4)
>>8	uleshort	x	\b, %u method
# offset of compressed data
>>10	uleshort	x	\b, %#x offset
#>>(10.s)	uleshort	x
#>>>&-6		string	x	\b, TEST extension %-.3s
# header flags to mark header extensions
>>12	uleshort	>0	\b, %#x flags
# 4 bytes: decompressed length of file
>>12	uleshort	&0x01
>>>14	ulelong		x	\b, original size: %u bytes
# 2 bytes: unknown purpose
# 2 bytes: length of unknown data + mentioned bytes
# 1-9 bytes: null-terminated file name
# 1-4 bytes: null-terminated file extension
>>12	uleshort	&0x08
>>>12	uleshort				^0x01
>>>>12		uleshort			^0x02
>>>>>12			uleshort		^0x04
>>>>>>12			uleshort	^0x10
>>>>>>>14				string	x	\b, %-.8s
>>>>>>12			uleshort	&0x10
>>>>>>>14				string	x	\b, %-.8s
>>>>>>>>&1				string	x	\b.%-.3s
>>>>>12			uleshort		&0x04
>>>>>>12			uleshort	^0x10
>>>>>>>(14.s)			uleshort	x
>>>>>>>>&14				string	x	\b, %-.8s
>>>>>>12			uleshort	&0x10
>>>>>>>(14.s)			uleshort	x
>>>>>>>>&14				string	x	\b, %-.8s
>>>>>>>>>&1				string	x	\b.%-.3s
>>>>12		uleshort			&0x02
>>>>>12			uleshort		^0x04
>>>>>>12			uleshort	^0x10
>>>>>>>16				string	x	\b, %-.8s
>>>>>>12			uleshort	&0x10
>>>>>>>16				string	x	\b, %-.8s
>>>>>>>>&1				string	x	\b.%-.3s
>>>>>12			uleshort		&0x04
>>>>>>12			uleshort	^0x10
>>>>>>>(16.s)			uleshort	x
>>>>>>>>&16				string	x	\b, %-.8s
>>>>>>12			uleshort	&0x10
>>>>>>>(16.s)			uleshort	x
>>>>>>>&16				string	x	%-.8s
>>>>>>>>&1				string	x	\b.%-.3s
>>>12	uleshort				&0x01
>>>>12		uleshort			^0x02
>>>>>12			uleshort		^0x04
>>>>>>12			uleshort	^0x10
>>>>>>>18				string	x	\b, %-.8s
>>>>>>12			uleshort	&0x10
>>>>>>>18				string	x	\b, %-.8s
>>>>>>>>&1				string	x	\b.%-.3s
>>>>>12			uleshort		&0x04
>>>>>>12			uleshort	^0x10
>>>>>>>(18.s)			uleshort	x
>>>>>>>>&18				string	x	\b, %-.8s
>>>>>>12			uleshort	&0x10
>>>>>>>(18.s)			uleshort	x
>>>>>>>>&18				string	x	\b, %-.8s
>>>>>>>>>&1				string	x	\b.%-.3s
>>>>12		uleshort			&0x02
>>>>>12			uleshort		^0x04
>>>>>>12			uleshort	^0x10
>>>>>>>20				string	x	\b, %-.8s
>>>>>>12			uleshort	&0x10
>>>>>>>20				string	x	\b, %-.8s
>>>>>>>>&1				string	x	\b.%-.3s
>>>>>12			uleshort		&0x04
>>>>>>12			uleshort	^0x10
>>>>>>>(20.s)			uleshort	x
>>>>>>>>&20				string	x	\b, %-.8s
>>>>>>12			uleshort	&0x10
>>>>>>>(20.s)			uleshort	x
>>>>>>>>&20				string	x	\b, %-.8s
>>>>>>>>>&1				string	x	\b.%-.3s
# 2 bytes: length of data + mentioned bytes
#
#		SZDD variant Haruhiko Okumura's LZSS or 7z type MsLZ
# URL:		http://fileformats.archiveteam.org/wiki/MS-DOS_installation_compression
# Reference:	http://www.cabextract.org.uk/libmspack/doc/szdd_kwaj_format.html
#		http://mark0.net/download/triddefs_xml.7z/defs/s/szdd.trid.xml
# Note:		called "Microsoft SZDD compressed (Haruhiko Okumura's LZSS)" by TrID
#		verfied by 7-Zip `7z l -tMsLZ -slt *.??_` as MsLZ
#		`deark -l -m lzss_oku -d2 setup-1-41.bin` as "LZSS.C by Haruhiko Okumura"
>0	string	SZDD		MS Compress archive data, SZDD variant
# 2nd part of signature
#>>4	ubelong	0x88F02733	\b, SIGNATURE OK
!:mime	application/x-ms-compress-szdd
!:ext	??_
# The character missing from the end of the filename (0=unknown)
>>9	string	>\0		\b, %-.1s is last character of original name
# https://www.betaarchive.com/forum/viewtopic.php?t=26161
# Compression mode: "A" (0x41) found but sometimes "B" in Windows 3.1 builds 026 and 034e
>>8	string	!A		\b, %-.1s method
>>10	ulelong	>0		\b, original size: %u bytes
# Summary:	InstallShield archive with SZDD compressed
# URL:		https://community.flexera.com/t5/InstallShield-Knowledge-Base/InstallShield-Redistributable-Files/ta-p/5647
# From:		Joerg Jenderek
1	search/48/bs	SZDD\x88\xF0\x27\x33	InstallShield archive
#!:mime	application/octet-stream
!:mime	application/x-installshield-compress-szdd
!:ext	ibt
# name of compressed archive member like: setup.dl_ _setup7int.dl_ _setup2k.dl_ _igdi.dl_ cabinet.dl_
>0	string	x		%s
# name of uncompressed archive member like: setup.dll _Setup.dll IGdi.dll CABINET.DLL
>>&1	string	x		(%s)
# probably version like: 9.0.0.333 9.1.0.429 11.50.0.42618
>>>&1	string	x		\b, version %s
# SZDD member length like: 168048 169333 181842
>>>>&1	string	x		\b, %s bytes
# MS Compress archive data
#>&0	string		SZDD	\b, SIGNATURE FOUND
>&0	indirect	x
#		QBasic SZDD variant
3	string	\x88\xf0\x27
>0	string	SZ\x20		MS Compress archive data, QBasic variant
!:mime	application/x-ms-compress-sz
!:ext	??$
>>8	ulelong	>0		\b, original size: %u bytes

# Summary:	CAZIP compressed file
# From:		Joerg Jenderek
# URL:		http://fileformats.archiveteam.org/wiki/CAZIP
# Reference:	http://mark0.net/download/triddefs_xml.7z/defs/c/caz.trid.xml
# Note:		Format is distinct from CAZIPXP compressed
0	string	\x0D\x0A\x1ACAZIP	CAZIP compressed file
#!:mime	application/octet-stream
!:mime	application/x-compress-cazip
# like: BLINKER.WR_ CLIPDEFS._ CAOSETUP.EX_ CLIPPER.EX_ FILEIO.C_
!:ext	??_/?_/_

# Summary:	FTCOMP compressed archive
# From:		Joerg Jenderek
# URL:		http://fileformats.archiveteam.org/wiki/FTCOMP
# Reference:    http://mark0.net/download/triddefs_xml.7z/defs/a/ark-ftcomp.trid.xml
# Note:		called by TrID "FTCOMP compressed archive"
#		extracted by `unpack seahelp.hl_`
24	string/b	FTCOMP		FTCOMP compressed archive
#!:mime	application/octet-stream
!:mime	application/x-compress-ftcomp
!:ext	??_/??@/dll/drv/pk2/
# probably A596FDFF magic at the beginning
>0	ubelong		!0xA596FDFF	\b, at beginning %#x
# probably original file name with directory like: \OS2\unpack.exe \SYSTEM\8514.DRV MAHJONGG.EXE
>41	string		x		"%s"

# 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\ 2.00 SAPCAR archive data
0	string	CAR\ 2.01 SAPCAR archive data
#!:mime	application/octet-stream
!:mime	application/vnd.sar
!:ext	sar
# Disintegrator
0	string	DST Disintegrator archive data
# ASD
0	string	ASD ASD archive data
# InstallShield CAB
# Update:	Joerg Jenderek at Nov 2021
# URL:		https://en.wikipedia.org/wiki/InstallShield
# Reference:	https://github.com/twogood/unshield/blob/master/lib/cabfile.h
# Note:		Not compatible with Microsoft CAB files
# http://mark0.net/download/triddefs_xml.7z/defs/a/ark-cab-ishield.trid.xml
# CAB_SIGNATURE 0x28635349
0	string	ISc( InstallShield
#!:mime		application/octet-stream
!:mime		application/x-installshield
# http://mark0.net/download/triddefs_xml.7z/defs/a/ark-cab-ishield-hdr.trid.xml
>16	ulelong	!0	setup header
# like: _SYS1.HDR _USER1.HDR data1.hdr
!:ext	hdr
>16	ulelong	=0	CAB
# like: _SYS1.CAB _USER1.CAB DATA1.CAB  data2.cab
!:ext	cab
# https://github.com/twogood/unshield/blob/master/lib/helper.c
# version like:	0x1005201 0x100600c 0x1007000 0x1009500
#		0x2000578 0x20005dc 0x2000640 0x40007d0 0x4000834
>4	ulelong	x	\b, version %#x
# volume_info like: 0
>8	ulelong	!0	\b, volume_info %#x
# cab_descriptor_offset like: 0x200
>12	ulelong	!0x200	\b, offset %#x
#>0x200	ubequad	x	\b, at 0x200 %#16.16llx
# cab_descriptor_size like: 0 (*.cab) BD5 C8B DA5 E2A E36 116C 251D 4DA9 56F0 5CC2 6E4B 777D 779E 1F7C2
>16	ulelong	!0	\b, descriptor size %#x
# 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)
# Update: Joerg Jenderek
# URL: http://speeddemosarchive.com/dzip/
# reference: http://speeddemosarchive.com/dzip/dz29src.zip/main.c
# GRR: line below is too general as it matches also ASCII texts like Doszip commander help dz.txt
0	string	DZ
# latest version is 2.9 dated 7 may 2003
>2	byte	<4 Dzip archive data
!:mime	application/x-dzip
!:ext	dz
>>2	byte	x \b, version %i
>>3	byte	x \b.%i
>>4	ulelong	x \b, offset %#x
>>8	ulelong	x \b, %u files
# 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)
# Update:	Joerg Jenderek
# URL:		http://fileformats.archiveteam.org/wiki/JAR_(ARJ_Software)
# reference:	http://mark0.net/download/triddefs_xml.7z/defs/a/ark-jar.trid.xml
#		https://www.sac.sk/download/pack/jar102x.exe/TECHNOTE.DOC
# Note:		called "JAR compressed archive" by TrID
0xe	string	\x1aJar\x1b JAR (ARJ Software, Inc.) archive data
#!:mime	application/octet-stream
!:mime	application/x-compress-j
>0	ulelong	x		\b, CRC32 %#x
# standard suffix is ".j"; for multi volumes following order j01 j02 ... j99 100 ... 990
!:ext	j/j01/j02
# URL:		http://fileformats.archiveteam.org/wiki/JARCS
# reference:	http://mark0.net/download/triddefs_xml.7z/defs/a/ark-jarcs.trid.xml
# Note:		called "JARCS compressed archive" by TrID
0	string	JARCS JAR (ARJ Software, Inc.) archive data
#!:mime	application/octet-stream
!:mime	application/x-compress-jar
!:ext	jar

# ARJ archiver (jason@jarthur.Claremont.EDU)
# URL:		http://fileformats.archiveteam.org/wiki/ARJ
# reference:	http://mark0.net/download/triddefs_xml.7z/defs/a/ark-arj.trid.xml
#		https://github.com/FarGroup/FarManager/
#		blob/master/plugins/multiarc/arc.doc/arj.txt
# Note:		called "ARJ compressed archive" by TrID and
#		"ARJ File Format" by DROID via PUID fmt/610
#		verified by `7z l -tarj PHRACK1.ARJ` and
#		`arj.exe l TEST-hk9.ARJ`
0	leshort		0xea60
# skip DROID fmt-610-signature-id-946.arj by check for valid file type of main header
>0xA	ubyte		2
>>0	use		arj-archive
0	name		arj-archive
>0	leshort		x		ARJ archive
!:mime	application/x-arj
# look for terminating 0-character of filename
>0x26	search/1024	\0
# file name extension is normally .arj but not for parts of multi volume
#>>&-5	string		x		extension %.4s
>>&-5	string/c	.arj		data
!:ext	arj
>>&-5	default		x
# for multi volume first name is archive.arj then following parts archive.a01 archive.a02 ...
>>>8	byte		&0x04		data
!:ext	a01/a02
# for SFX first name is archive.exe then following parts archive.e01 archive.e02 ...
>>>8	byte		^0x04		data, SFX multi-volume
!:ext	e01/e02
# basic header size like: 0x002b 0x002c 0x04e0 0x04e3 0x04e7
#>2	uleshort	x		basic header size %#4.4x
# next fragment content like: 0x0a200a003a8fc713 0x524a000010bb3471 0x524a0000c73c70f9
#>(2.s)	ubequad		x		NEXT FRAGMENT CONTENT %#16.16llx
# first_hdr_size; seems to be same as basic header size
#>2	uleshort	x		1st header size %#x
# archiver version number like: 3 4 6 11 102
>5	byte		x		\b, v%d
# minimum archiver version to extract like: 1
>6	ubyte		!1		\b, minimum %u to extract
# FOR DEBUGGING
#>8	byte		x		\b, FLAGS %#x
# GARBLED_FLAG1; garble with password; g switch
>8	byte		&0x01		\b, password-protected
# encryption version: 0~old  1~old 2~new 3~reserved 4~40 bit key GOST
>>0x20	ubyte		x		(v%u)
#>8	byte		&0x02		\b, secured
# ANSIPAGE_FLAG; indicates ANSI codepage used by ARJ32; hy switch
>8	byte		&0x02		\b, ANSI codepage
# VOLUME_FLAG indicates presence of succeeding volume; but apparently not for SFX
>8	byte		&0x04		\b, multi-volume
#>8	byte		&0x08		\b, file-offset
# ARJPROT_FLAG; build with data protection record; hk switch
>8	byte		&0x08		\b, recoverable
# arj protection factor; maximal 10; switch hky -> factor=y+1
>>0x22	byte		x		(factor %u)
>8	byte		&0x10		\b, slash-switched
# BACKUP_FLAG; obsolete
>8	byte		&0x20		\b, backup
# SECURED_FLAG;
>8	byte		&0x40		\b, secured,
# ALTNAME_FLAG; indicates dual-name archive
>8	byte		&0x80		\b, dual-name
# security version; 0~old 2~current
>9	ubyte		!0
>>9	ubyte		!2		\b, security version %u
# file type; 2 in main header; 0~binary 1~7-bitText 2~comment 3~directory 4~VolumeLabel 5=ChapterLabel
>0xA	ubyte		!2		\b, file type %u
# date+time when original archive was created in MS-DOS format via ./msdos
>0xC	ulelong		x		\b, created
>0xC	use		dos-date
# or date and time by new internal function
#>0xE	lemsdosdate	x		%s
#>0xC	lemsdostime	x		%s
# FOR DEBUGGING
#>0x12	uleshort	x		RAW DATE %#4.4x
#>0x10	uleshort	x		RAW TIME %#4.4x
# date+time when archive was last modified; sometimes nil or
# maybe wrong like in HP4DRVR.ARJ
#>0x10	ulelong		>0		\b, modified
#>>0x10	use		dos-date
# or date and time by new internal function
#>>0x12	lemsdosdate	x		%s
#>>0x10	lemsdostime	x		%s
# archive size (currently used only for secured archives); MAYBE?
#>0x14	ulelong		!0		\b, file size %u
# security envelope file position; MAYBE?
#>0x18	ulelong		!0		\b, at %#x security envelope
# filespec position in filename; WHAT IS THAT?
#>0x1C	uleshort	>0		\b, filespec position %#x
# length in bytes of security envelope data like: 2CAh 301h 364h 471h
>0x1E	uleshort	!0		\b, security envelope length %#x
# last chapter like: 0 1
>0x21	ubyte		!0		\b, last chapter %u
# filename (null-terminated string); sometimes at 0x26 when 4 bytes for extra data
>34	byte		x		\b, original name:
# with extras data
>34	byte		<0x0B
>>38	string		x		%s
# without extras data
>34	byte		>0x0A
>>34	string		x		%s
# host OS: 0~MSDOS ... 11~WIN32
>7	byte		0		\b, os: MS-DOS
>7	byte		1		\b, os: PRIMOS
>7	byte		2		\b, os: Unix
>7	byte		3		\b, os: Amiga
>7	byte		4		\b, os: Macintosh
>7	byte		5		\b, os: OS/2
>7	byte		6		\b, os: Apple ][ GS
>7	byte		7		\b, os: Atari ST
>7	byte		8		\b, os: NeXT
>7	byte		9		\b, os: VAX/VMS
>7	byte		10		\b, os: WIN95
>7	byte		11		\b, os: WIN32
# [JW] idarc says this is also possible
2	leshort		0xea60		ARJ archive data
#2	leshort		0xea60
#>2	use		arj-archive

# 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: https://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 unusual 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_%#x
# level identifier 0 1 2 3
#>20	ubyte		x		\b, level %d
# time stamp
#>15		ubelong	x		DATE %#8.8x
# OS ID for level 1
>20	ubyte		1
# 0x20 types find for *.rom files
>>(21.b+24)	ubyte	<0x21		\b, %#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 %#x
>>23	ubyte		<0x21		\b, %#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
# https://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
!:strength +1
0	string		PK\003\004
!:strength +1

# 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>")
# URL:		https://en.wikipedia.org/wiki/OpenOffice.org_XML
# reference:	http://fileformats.archiveteam.org/wiki/OpenOffice.org_XML
>>50	string	vnd.sun.xml.		OpenOffice.org 1.x
>>>62	string	writer			Writer
>>>>68	byte	!0x2e			document
!:mime	application/vnd.sun.xml.writer
!:ext	sxw
>>>>68	string	.template		template
!:mime	application/vnd.sun.xml.writer.template
!:ext	stw
>>>>68	string	.web			Web template
!:mime	application/vnd.sun.xml.writer.web
!:ext	stw
>>>>68	string	.global			global document
!:mime	application/vnd.sun.xml.writer.global
!:ext	sxg
>>>62	string	calc			Calc
>>>>66	byte	!0x2e			spreadsheet
!:mime	application/vnd.sun.xml.calc
!:ext	sxc
>>>>66	string	.template		template
!:mime	application/vnd.sun.xml.calc.template
!:ext	stc
>>>62	string	draw			Draw
>>>>66	byte	!0x2e			document
!:mime	application/vnd.sun.xml.draw
!:ext	sxd
>>>>66	string	.template		template
!:mime	application/vnd.sun.xml.draw.template
!:ext	std
>>>62	string	impress			Impress
>>>>69	byte	!0x2e			presentation
!:mime	application/vnd.sun.xml.impress
!:ext	sxi
>>>>69	string	.template		template
!:mime	application/vnd.sun.xml.impress.template
!:ext	sti
>>>62	string	math			Math document
!:mime	application/vnd.sun.xml.math
!:ext	sxm
>>>62	string	base			Database file
!:mime	application/vnd.sun.xml.base
!:ext	sdb

# URL:	https://wiki.openoffice.org/wiki/Documentation/DevGuide/Extensions/File_Format
# From:	Joerg Jenderek
# Note:	only few OXT samples are detected here by mimetype member
#	is used by OpenOffice and LibreOffice and probably also NeoOffice
#	verified by `unzip -Zv *.oxt` or `7z l -slt *.oxt`
>>50	string	vnd.openofficeorg.		OpenOffice
>>>68	string	extension			\b/LibreOffice Extension
# http://extension.nirsoft.net/oxt
!:mime	application/vnd.openofficeorg.extension
# like: Gallery-Puzzle.2.1.0.1.oxt
!:ext	oxt

#   OpenDocument formats (for OpenOffice 2.x / StarOffice >= 8)
#   URL: http://fileformats.archiveteam.org/wiki/OpenDocument
#    https://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
!:ext	odt
>>>>77	string	-template		Text Template
!:mime	application/vnd.oasis.opendocument.text-template
!:ext	ott
>>>>77	string	-web			HTML Document Template
!:mime	application/vnd.oasis.opendocument.text-web
!:ext	oth
>>>>77	string	-master			Master Document
!:mime	application/vnd.oasis.opendocument.text-master
!:ext	odm
>>>73	string	graphics
>>>>81	byte	!0x2d			Drawing
!:mime	application/vnd.oasis.opendocument.graphics
!:ext	odg
>>>>81	string	-template		Drawing Template
!:mime	application/vnd.oasis.opendocument.graphics-template
!:ext	otg
>>>73	string	presentation
>>>>85	byte	!0x2d			Presentation
!:mime	application/vnd.oasis.opendocument.presentation
!:ext	odp
>>>>85	string	-template		Presentation Template
!:mime	application/vnd.oasis.opendocument.presentation-template
!:ext	otp
>>>73	string	spreadsheet
>>>>84	byte	!0x2d			Spreadsheet
!:mime	application/vnd.oasis.opendocument.spreadsheet
!:ext	ods
>>>>84	string	-template		Spreadsheet Template
!:mime	application/vnd.oasis.opendocument.spreadsheet-template
!:ext	ots
>>>73	string	chart
>>>>78	byte	!0x2d			Chart
!:mime	application/vnd.oasis.opendocument.chart
!:ext	odc
>>>>78	string	-template		Chart Template
!:mime	application/vnd.oasis.opendocument.chart-template
!:ext	otc
>>>73	string	formula
>>>>80	byte	!0x2d			Formula
!:mime	application/vnd.oasis.opendocument.formula
!:ext	odf
>>>>80	string	-template		Formula Template
!:mime	application/vnd.oasis.opendocument.formula-template
!:ext	otf
# https://www.loc.gov/preservation/digital/formats/fdd/fdd000441.shtml
>>>73	string	database		Database
!:mime	application/vnd.oasis.opendocument.database
!:ext	odb
# Valid for LibreOffice Base 6.0.1.1 at least
>>>73	string	base 			Database
# https://bugs.documentfoundation.org/show_bug.cgi?id=45854
!:mime	application/vnd.oasis.opendocument.database
#!:mime	application/vnd.oasis.opendocument.base
!:ext	odb
>>>73	string	image
>>>>78	byte	!0x2d			Image
!:mime	application/vnd.oasis.opendocument.image
!:ext	odi
>>>>78	string	-template		Image Template
!:mime	application/vnd.oasis.opendocument.image-template
!:ext	oti

#  EPUB (OEBPS) books using OCF (OEBPS Container Format)
#    https://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

# From:	Joerg Jenderek
# URL:	http://en.wikipedia.org/wiki/CorelDRAW
# NOTE:	version; til 2 WL-based; from 3 til 13 by ./riff; from 14 zip based
>>50	string	x-vnd.corel.	 Corel
>>>62	string	draw.document+zip	Draw drawing, version 14-16
!:mime	application/x-vnd.corel.draw.document+zip
!:ext	cdr
>>>62	string	draw.template+zip	Draw template, version 14-16
!:mime	application/x-vnd.corel.draw.template+zip
!:ext	cdrt
>>>62	string	zcf.draw.document+zip	Draw drawing, version 17-22
!:mime	application/x-vnd.corel.zcf.draw.document+zip
!:ext	cdr
>>>62	string	zcf.draw.template+zip	Draw template, version 17-22
!:mime	application/x-vnd.corel.zcf.draw.template+zip
!:ext	cdt/cdrt
# URL:	http://product.corel.com/help/CorelDRAW/540240626/Main/EN/Doc/CorelDRAW-Other-file-formats.html
>>>62	string	zcf.pattern+zip		Draw pattern, version 22
!:mime	application/x-vnd.corel.zcf.pattern+zip
!:ext	pat
# URL:		https://en.wikipedia.org/wiki/Corel_Designer
# Reference:	http://fileformats.archiveteam.org/wiki/Corel_Designer
# Note:		called by TrID "Corel DESIGN graphics"
>>>62	string	designer.document+zip		DESIGNER graphics, version 14-16
!:mime	application/x-vnd.corel.designer.document+zip
!:ext	des
>>>62	string	zcf.designer.document+zip	DESIGNER graphics, version 17-21
!:mime	application/x-vnd.corel.zcf.designer.document+zip
!:ext	des
# URL:	http://product.corel.com/help/CorelDRAW/540223850/Main/EN/Documentation/
#	CorelDRAW-Corel-Symbol-Library-CSL.html
>>>62	string	symbol.library+zip		Symbol Library, version 6-16.3
!:mime	application/x-vnd.corel.symbol.library+zip
!:ext	csl
>>>62	string	zcf.symbol.library+zip		Symbol Library, version 17-22
!:mime	application/x-vnd.corel.zcf.symbol.library+zip
!:ext	csl

#  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		default	x			Zip data
>>>38		regex	[!-OQ-~]+		(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

# Dup, see above.
#>30	search/100/b application/epub+zip	EPUB document
#!:mime application/epub+zip

# Generic zip archives (Greg Roelofs, c/o zip-bugs@wkuvx1.wku.edu)
#   Next line excludes specialized formats:
>(26.s+30)	leshort	!0xcafe
>>30	search/100/b !application/epub+zip
>>>26    string          !\x8\0\0\0mimetype	Zip archive data
!:mime	application/zip
>>>>4	beshort		x			\b, at least
>>>>4	use		zipversion
>>>>4	beshort		x			to extract
>>>>8	beshort		x			\b, compression method=
>>>>8	use		zipcompression
>>>>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
!:ext	torrent
# Durval Menezes, <jmgthbfile at durval dot com>
0	string	d13:announce-list	BitTorrent file
!:mime	application/x-bittorrent
!:ext	torrent
0	string	d7:comment	BitTorrent file
!:mime	application/x-bittorrent
!:ext	torrent
0	string	d4:info		BitTorrent file
!:mime	application/x-bittorrent
!:ext	torrent

# Atari MSA archive - Teemu Hukkanen <tjhukkan@iki.fi>
# URL:		http://fileformats.archiveteam.org/wiki/MSA_(Magic_Shadow_Archiver)
# Reference:	http://info-coach.fr/atari/documents/_mydoc/FD_Image_File_Format.pdf
#		http://mark0.net/download/triddefs_xml.7z/defs/m/msa.trid.xml
# Update:	Joerg Jenderek
# Note:		called by TrID "Atari MSA Disk Image" and verified by
#		command like `deark -l -m msa -d2 PDATS578.msa` as " Atari ST floppy disk image"
# GRR: line below is too general as it matches setup.skin
0	beshort 0x0e0f
# skip foo setup.skin with unrealistic high number 52255 of sides by check for valid "low" value
>4	ubeshort <2		Atari MSA archive data
#!:mime	application/octet-stream
!:mime	application/x-atari-msa
!:ext	msa
# sectors per track like: 9 10
>>2	beshort x		\b, %d sectors per track
# sides (0 or 1; add 1 to this to get correct number of sides)
>>4	beshort 0		\b, 1 sided
>>4	beshort 1		\b, 2 sided
# starting track like: 0
>>6	beshort x		\b, starting track: %d
# ending track like: 39 79 80 81
>>8	beshort x		\b, ending track: %d
# tracks content
#>>10	ubequad x		\b, track content %#16.16llx

# Alternate ZIP string (amc@arwen.cs.berkeley.edu)
0	string	PK00PK\003\004	Zip archive data
!:mime	application/zip
!:ext zip/cbz

# ACE archive (from http://www.wotsit.org/download.asp?f=ace)
# by Stefan `Sec` Zehl <sec@42.org>
7	string		**ACE**		ACE archive data
!:mime	application/x-ace-compressed
!:ext	ace
>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 *.??_
# Reference: http://www.antonis.de/dos/dos-tuts/mpdostip/html/nwdostip.htm
# Note:	unpacked by PNUNPACK.EXE
0	string	Packed\ File\
# by looking for Control-Z skip ASCII text starting with Packed File
>0x18	ubyte	0x1a		Personal NetWare Packed File
!:mime	application/x-novell-compress
!:ext	??_
>>12	string	x		\b, was "%.12s"
# 1 or 2
#>>0x19	ubyte	x		\b, at 0x19 %u
>>0x1b	ulelong	x		with %u bytes

# 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:		Joerg Jenderek
# URL:		https://help.foxitsoftware.com/kb/install-fzip-file.php
# reference:	http://mark0.net/download/triddefs_xml.7z/
#		defs/f/fzip.trid.xml
# Note: unknown compression; No "PK" zip magic; normally in directory like
#	"%APPDATA%\Foxit Software\Addon\Foxit Reader\Install"
0	ubequad	0x2506781901010000	Foxit add-on/update
!:mime	application/x-fzip
!:ext	fzip

# 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
#  https://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
# URL: https://en.wikipedia.org/wiki/Xar_(archiver)
# xar archive format: https://code.google.com/p/xar/
# From: "David Remahl" <dremahl@apple.com>
# Update: Joerg Jenderek
# TODO: lzma compression; X509Data for pkg and xip
# Note: verified by `xar --dump-header -f FullBundleUpdate.xar` or
# 7z t -txar Xcode_10.2_beta_4.xip`
0	string	xar!		xar archive
!:mime	application/x-xar
# pkg for Mac OSX installer package like FullBundleUpdate.pkg
# xip for signed Apple software like Xcode_10.2_beta_4.xip
!:ext	xar/pkg/xip
# always 28 in older archives
>4	ubeshort >28		\b, header size %u
# currently there exit only version 1 since about 2014
>6	ubeshort >1		version %u,
>8	ubequad	x		compressed TOC: %llu,
#>16	ubequad	x		uncompressed TOC: %llu,
# cksum_alg 0-2 in older and also 3-4 in newer
>24	belong	0		no checksum
>24	belong	1		SHA-1 checksum
>24	belong	2		MD5 checksum
>24	belong	3		SHA-256 checksum
>24	belong	4		SHA-512 checksum
>24	belong	>4		unknown %#x checksum
#>24	belong	>4		checksum
#			For no compression jump 0 bytes
>24	belong	0
>>0		ubyte	x
# jump more bytes forward by header size
>>>&(4.S)	ubyte	x
# jump more bytes forward by compressed table of contents size
#>>>>&(8.Q)	ubequad	x	\b, heap data %#llx
>>>>&(8.Q)	ubyte	x
# look for data by ./compress after message with 1 space at end
>>>>>&-3	indirect x	\b, contains
#			For SHA-1 jump 20 minus 2 bytes
>24	belong	1
>>18		ubyte	x
# jump more bytes forward by header size
>>>&(4.S)	ubyte	x
# jump more bytes forward by compressed table of contents size
>>>>&(8.Q)	ubyte	x
# data compressed by gzip, bzip, lzma or none
>>>>>&-1	indirect x	\b, contains
#			For SHA-256 jump 32 minus 2 bytes
>24	belong	3
>>30		ubyte	x
# jump more bytes forward by header size
>>>&(4.S)	ubyte	x
# jump more bytes forward by compressed table of contents size
>>>>&(8.Q)	ubyte	x
>>>>>&-1	indirect x	\b, contains
#			For SHA-512 jump 64 minus 2 bytes
>24	belong	4
>>62		ubyte	x
# jump more bytes forward by header size
>>>&(4.S)	ubyte	x
# jump more bytes forward by compressed table of contents size
>>>>&(8.Q)	ubyte	x
>>>>>&-1	indirect x	\b, contains

# 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: https://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>
# https://encode.ru/threads/456-zpaq-updates/page32
0	string	7kSt	ZPAQ file

# BBeB ebook, unencrypted (LRF format)
# URL: https://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
# https://us.norton.com/ghost/
# https://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=%#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

# LyNX archive
56	string	USE\040LYNX\040TO\040DISSOLVE\040THIS\040FILE	 LyNX archive

# From: Joerg Jenderek
# URL: https://www.acronis.com/
# Reference: https://en.wikipedia.org/wiki/TIB_(file_format)
# Note: only tested with True Image 2013 Build 5962 and 2019 Build 14110
0	ubequad		0xce24b9a220000000	Acronis True Image backup
!:mime	application/x-acronis-tib
!:ext	tib
# 01000000
#>20	ubelong		x			\b, at 20 %#x
# 20000000
#>28	ubelong		x			\b, at 28 %#x
# strings like "Generic- SD/MMC 1.00" "Unknown Disk" "Msft Virtual Disk 1.0"
# ???
# strings like "\Device\0000011e" "\Device\0000015a"
#>0	search/0x6852300/cs	\\Device\\
#>>&-1	pstring		x			\b, %s
# "\Device\HarddiskVolume30" "\Device\HarddiskVolume39"
#>>>&1	search/180/cs	\\Device\\
#>>>>&-1	pstring		x			\b, %s
#>>>>>&0	search/29/cs	\0\0\xc8\0
# disk label
#>>>>>>&10	lestring16	x		\b, disk label %11.11s
#>>>>>>&9	plestring16	x		\b, disk label "%11.11s"
#>>>>>>&10	ubequad	x			%16.16llx


# Gentoo XPAK binary package
# by Michal Gorny <mgorny@gentoo.org>
# https://gitweb.gentoo.org/proj/portage.git/tree/man/xpak.5
-4	string	STOP
>-16	string	XPAKSTOP	Gentoo binary package (XPAK)

# From:		Joerg Jenderek
# URL:		https://kodi.wiki/view/TexturePacker
# Reference:	https://mirrors.kodi.tv/releases/source/17.3-Krypton.tar.gz
# /xbmc-Krypton/xbmc/guilib/XBTF.h
# /xbmc-Krypton/xbmc/guilib/XBTF.cpp
0	string	XBTF
# skip ASCII text by looking for terminating \0 of path
>264	ubyte	0		XBMC texture package
!:mime	application/x-xbmc-xbt
!:ext	xbt
# XBTF_VERSION 2
>>4	string	!2		\b, version %-.1s
# nofFiles /xbmc-Krypton/xbmc/guilib/XBTFReader.cpp
>>5	ulelong	x		\b, %u file
# plural s
>>5	ulelong	>1		\bs
# path[CXBTFFile[MaximumPathLength=256]
>>9	string	x		\b, 1st %s

# ALZIP archive
# by Hyungjun Park <hyungjun.park@worksmobile.com>, Hajin Jang <hajin_jang@worksmobile.com>
# http://kippler.com/win/unalz/
# https://salsa.debian.org/l10n-korean-team/unalz
0	string	ALZ\001		ALZ archive data
!:ext   alz

# https://cf-aldn.altools.co.kr/setup/EGG_Specification.zip
0	string	EGGA		EGG archive data,
!:ext   egg
>5	byte	x		version %u
>4	byte	x		\b.%u
>>0x0E	ulelong	=0x08E28222
>>0x0E	ulelong	=0x24F5A262	\b, split
>>0x0E	ulelong	=0x24E5A060	\b, solid
>>0x0E	default	x		\b, unknown

# PAQ9A archive
# URL: http://mattmahoney.net/dc/#paq9a
# Note: Line 1186 of paq9a.cpp gives the magic bytes
0	string	pQ9\001		PAQ9A archive

# From wof (wof@stachelkaktus.net)
0	string	Unison\ archive\ format	Unison archive format