file/magic/Magdir/msdos

#------------------------------------------------------------------------------
# $File: msdos,v 1.124 2018/07/10 04:05:50 christos Exp $
# msdos:  file(1) magic for MS-DOS files
#

# .BAT files (Daniel Quinlan, quinlan@yggdrasil.com)
# updated by Joerg Jenderek at Oct 2008,Apr 2011
0	string/t	@
>1	string/cW	\ echo\ off	DOS batch file text
!:mime	text/x-msdos-batch
>1	string/cW	echo\ off	DOS batch file text
!:mime	text/x-msdos-batch
>1	string/cW	rem		DOS batch file text
!:mime	text/x-msdos-batch
>1	string/cW	set\ 		DOS batch file text
!:mime	text/x-msdos-batch


# OS/2 batch files are REXX. the second regex is a bit generic, oh well
# the matched commands seem to be common in REXX and uncommon elsewhere
100	search/0xffff   rxfuncadd
>100	regex/c =^[\ \t]{0,10}call[\ \t]{1,10}rxfunc	OS/2 REXX batch file text
100	search/0xffff   say
>100	regex/c =^[\ \t]{0,10}say\ ['"]			OS/2 REXX batch file text

# updated by Joerg Jenderek at Oct 2015
# https://de.wikipedia.org/wiki/Common_Object_File_Format
# http://www.delorie.com/djgpp/doc/coff/filhdr.html
# ./intel already labeled COFF type 0x14c=0514 as "80386 COFF executable"
#0	leshort		0x14c	MS Windows COFF Intel 80386 object file
#>4	ledate		x	stamp %s
0	leshort		0x166	MS Windows COFF MIPS R4000 object file
#>4	ledate		x	stamp %s
0	leshort		0x184	MS Windows COFF Alpha object file
#>4	ledate		x	stamp %s
0	leshort		0x268	MS Windows COFF Motorola 68000 object file
#>4	ledate		x	stamp %s
0	leshort		0x1f0	MS Windows COFF PowerPC object file
#>4	ledate		x	stamp %s
0	leshort		0x290	MS Windows COFF PA-RISC object file
#>4	ledate		x	stamp %s

# Tests for various EXE types.
#
# Many of the compressed formats were extraced from IDARC 1.23 source code.
#
0	string/b	MZ
# All non-DOS EXE extensions have the relocation table more than 0x40 bytes into the file.
>0x18	leshort <0x40 MS-DOS executable
!:mime	application/x-dosexec
# These traditional tests usually work but not always.  When test quality support is
# implemented these can be turned on.
#>>0x18	leshort	0x1c	(Borland compiler)
#>>0x18	leshort	0x1e	(MS compiler)

# If the relocation table is 0x40 or more bytes into the file, it's definitely
# not a DOS EXE.
>0x18  leshort >0x3f

# Maybe it's a PE?
>>(0x3c.l) string PE\0\0 PE
!:mime	application/x-dosexec
>>>(0x3c.l+24)	leshort		0x010b	\b32 executable
>>>(0x3c.l+24)	leshort		0x020b	\b32+ executable
>>>(0x3c.l+24)	leshort		0x0107	ROM image
>>>(0x3c.l+24)	default		x	Unknown PE signature
>>>>&0 		leshort		x	0x%x
>>>(0x3c.l+22)	leshort&0x2000	>0	(DLL)
>>>(0x3c.l+92)	leshort		1	(native)
>>>(0x3c.l+92)	leshort		2	(GUI)
>>>(0x3c.l+92)	leshort		3	(console)
>>>(0x3c.l+92)	leshort		7	(POSIX)
>>>(0x3c.l+92)	leshort		9	(Windows CE)
>>>(0x3c.l+92)	leshort		10	(EFI application)
>>>(0x3c.l+92)	leshort		11	(EFI boot service driver)
>>>(0x3c.l+92)	leshort		12	(EFI runtime driver)
>>>(0x3c.l+92)	leshort		13	(EFI ROM)
>>>(0x3c.l+92)	leshort		14	(XBOX)
>>>(0x3c.l+92)	leshort		15	(Windows boot application)
>>>(0x3c.l+92)	default		x	(Unknown subsystem
>>>>&0		leshort		x	0x%x)
>>>(0x3c.l+4)	leshort		0x14c	Intel 80386
>>>(0x3c.l+4)	leshort		0x166	MIPS R4000
>>>(0x3c.l+4)	leshort		0x168	MIPS R10000
>>>(0x3c.l+4)	leshort		0x184	Alpha
>>>(0x3c.l+4)	leshort		0x1a2	Hitachi SH3
>>>(0x3c.l+4)	leshort		0x1a6	Hitachi SH4
>>>(0x3c.l+4)	leshort		0x1c0	ARM
>>>(0x3c.l+4)	leshort		0x1c2	ARM Thumb
>>>(0x3c.l+4)	leshort		0x1c4	ARMv7 Thumb
>>>(0x3c.l+4)	leshort		0x1f0	PowerPC
>>>(0x3c.l+4)	leshort		0x200	Intel Itanium
>>>(0x3c.l+4)	leshort		0x266	MIPS16
>>>(0x3c.l+4)	leshort		0x268	Motorola 68000
>>>(0x3c.l+4)	leshort		0x290	PA-RISC
>>>(0x3c.l+4)	leshort		0x366	MIPSIV
>>>(0x3c.l+4)	leshort		0x466	MIPS16 with FPU
>>>(0x3c.l+4)	leshort		0xebc	EFI byte code
>>>(0x3c.l+4)	leshort		0x8664	x86-64
>>>(0x3c.l+4)	leshort		0xc0ee	MSIL
>>>(0x3c.l+4)	default		x	Unknown processor type
>>>>&0		leshort		x	0x%x
>>>(0x3c.l+22)	leshort&0x0200	>0	(stripped to external PDB)
>>>(0x3c.l+22)	leshort&0x1000	>0	system file
>>>(0x3c.l+24)	leshort		0x010b
>>>>(0x3c.l+232) lelong	>0	Mono/.Net assembly
>>>(0x3c.l+24)	leshort		0x020b
>>>>(0x3c.l+248) lelong	>0	Mono/.Net assembly

# hooray, there's a DOS extender using the PE format, with a valid PE
# executable inside (which just prints a message and exits if run in win)
>>>(8.s*16)		string		32STUB	\b, 32rtm DOS extender
>>>(8.s*16)		string		!32STUB	\b, for MS Windows
>>>(0x3c.l+0xf8)	string		UPX0 \b, UPX compressed
>>>(0x3c.l+0xf8)	search/0x140	PEC2 \b, PECompact2 compressed
>>>(0x3c.l+0xf8)	search/0x140	UPX2
>>>>(&0x10.l+(-4))	string		PK\3\4 \b, ZIP self-extracting archive (Info-Zip)
>>>(0x3c.l+0xf8)	search/0x140	.idata
>>>>(&0xe.l+(-4))	string		PK\3\4 \b, ZIP self-extracting archive (Info-Zip)
>>>>(&0xe.l+(-4))	string		ZZ0 \b, ZZip self-extracting archive
>>>>(&0xe.l+(-4))	string		ZZ1 \b, ZZip self-extracting archive
>>>(0x3c.l+0xf8)	search/0x140	.rsrc
>>>>(&0x0f.l+(-4))	string		a\\\4\5 \b, WinHKI self-extracting archive
>>>>(&0x0f.l+(-4))	string		Rar! \b, RAR self-extracting archive
>>>>(&0x0f.l+(-4))	search/0x3000	MSCF \b, InstallShield self-extracting archive
>>>>(&0x0f.l+(-4))	search/32	Nullsoft \b, Nullsoft Installer self-extracting archive
>>>(0x3c.l+0xf8)	search/0x140	.data
>>>>(&0x0f.l)		string		WEXTRACT \b, MS CAB-Installer self-extracting archive
>>>(0x3c.l+0xf8)	search/0x140	.petite\0 \b, Petite compressed
>>>>(0x3c.l+0xf7)	byte		x
>>>>>(&0x104.l+(-4))	string		=!sfx! \b, ACE self-extracting archive
>>>(0x3c.l+0xf8)	search/0x140	.WISE \b, WISE installer self-extracting archive
>>>(0x3c.l+0xf8)	search/0x140	.dz\0\0\0 \b, Dzip self-extracting archive
>>>&(0x3c.l+0xf8)	search/0x100	_winzip_ \b, ZIP self-extracting archive (WinZip)
>>>&(0x3c.l+0xf8)	search/0x100	SharedD \b, Microsoft Installer self-extracting archive
>>>0x30			string		Inno \b, InnoSetup self-extracting archive

# Hmm, not a PE but the relocation table is too high for a traditional DOS exe,
# must be one of the unusual subformats.
>>(0x3c.l) string !PE\0\0 MS-DOS executable
!:mime	application/x-dosexec

>>(0x3c.l)		string		NE \b, NE
!:mime	application/x-dosexec
>>>(0x3c.l+0x36)	byte		1 for OS/2 1.x
>>>(0x3c.l+0x36)	byte		2 for MS Windows 3.x
>>>(0x3c.l+0x36)	byte		3 for MS-DOS
>>>(0x3c.l+0x36)	byte		4 for Windows 386
>>>(0x3c.l+0x36)	byte		5 for Borland Operating System Services
>>>(0x3c.l+0x36)	default		x
>>>>(0x3c.l+0x36)	byte		x (unknown OS %x)
>>>(0x3c.l+0x36)	byte		0x81 for MS-DOS, Phar Lap DOS extender
>>>(0x3c.l+0x0c)	leshort&0x8003	0x8002 (DLL)
>>>(0x3c.l+0x0c)	leshort&0x8003	0x8001 (driver)
>>>&(&0x24.s-1)		string		ARJSFX \b, ARJ self-extracting archive
>>>(0x3c.l+0x70)	search/0x80	WinZip(R)\ Self-Extractor \b, ZIP self-extracting archive (WinZip)

>>(0x3c.l)		string		LX\0\0 \b, LX
!:mime	application/x-dosexec
>>>(0x3c.l+0x0a)	leshort		<1 (unknown OS)
>>>(0x3c.l+0x0a)	leshort		1 for OS/2
>>>(0x3c.l+0x0a)	leshort		2 for MS Windows
>>>(0x3c.l+0x0a)	leshort		3 for DOS
>>>(0x3c.l+0x0a)	leshort		>3 (unknown OS)
>>>(0x3c.l+0x10)	lelong&0x28000	=0x8000 (DLL)
>>>(0x3c.l+0x10)	lelong&0x20000	>0 (device driver)
>>>(0x3c.l+0x10)	lelong&0x300	0x300 (GUI)
>>>(0x3c.l+0x10)	lelong&0x28300	<0x300 (console)
>>>(0x3c.l+0x08)	leshort		1 i80286
>>>(0x3c.l+0x08)	leshort		2 i80386
>>>(0x3c.l+0x08)	leshort		3 i80486
>>>(8.s*16)		string		emx \b, emx
>>>>&1			string		x %s
>>>&(&0x54.l-3)		string		arjsfx \b, ARJ self-extracting archive

# MS Windows system file, supposedly a collection of LE executables
>>(0x3c.l)		string		W3 \b, W3 for MS Windows
!:mime	application/x-dosexec

>>(0x3c.l)		string		LE\0\0 \b, LE executable
!:mime	application/x-dosexec
>>>(0x3c.l+0x0a)	leshort		1
# some DOS extenders use LE files with OS/2 header
>>>>0x240		search/0x100	DOS/4G for MS-DOS, DOS4GW DOS extender
>>>>0x240		search/0x200	WATCOM\ C/C++ for MS-DOS, DOS4GW DOS extender
>>>>0x440		search/0x100	CauseWay\ DOS\ Extender for MS-DOS, CauseWay DOS extender
>>>>0x40		search/0x40	PMODE/W for MS-DOS, PMODE/W DOS extender
>>>>0x40		search/0x40	STUB/32A for MS-DOS, DOS/32A DOS extender (stub)
>>>>0x40		search/0x80	STUB/32C for MS-DOS, DOS/32A DOS extender (configurable stub)
>>>>0x40		search/0x80	DOS/32A for MS-DOS, DOS/32A DOS extender (embedded)
# this is a wild guess; hopefully it is a specific signature
>>>>&0x24		lelong		<0x50
>>>>>(&0x4c.l)		string		\xfc\xb8WATCOM
>>>>>>&0		search/8	3\xdbf\xb9 \b, 32Lite compressed
# another wild guess: if real OS/2 LE executables exist, they probably have higher start EIP
#>>>>(0x3c.l+0x1c)	lelong		>0x10000 for OS/2
# fails with DOS-Extenders.
>>>(0x3c.l+0x0a)	leshort		2 for MS Windows
>>>(0x3c.l+0x0a)	leshort		3 for DOS
>>>(0x3c.l+0x0a)	leshort		4 for MS Windows (VxD)
>>>(&0x7c.l+0x26)	string		UPX \b, UPX compressed
>>>&(&0x54.l-3)		string		UNACE \b, ACE self-extracting archive

# looks like ASCII, probably some embedded copyright message.
# and definitely not NE/LE/LX/PE
>>0x3c		lelong	>0x20000000
>>>(4.s*512)	leshort !0x014c \b, MZ for MS-DOS
!:mime	application/x-dosexec
# header data too small for extended executable
>2		long	!0
>>0x18		leshort <0x40
>>>(4.s*512)	leshort !0x014c

>>>>&(2.s-514)	string	!LE
>>>>>&-2	string	!BW \b, MZ for MS-DOS
!:mime	application/x-dosexec
>>>>&(2.s-514)	string	LE \b, LE
>>>>>0x240	search/0x100	DOS/4G for MS-DOS, DOS4GW DOS extender
# educated guess since indirection is still not capable enough for complex offset
# calculations (next embedded executable would be at &(&2*512+&0-2)
# I suspect there are only LE executables in these multi-exe files
>>>>&(2.s-514)	string	BW
>>>>>0x240	search/0x100	DOS/4G	\b, LE for MS-DOS, DOS4GW DOS extender (embedded)
>>>>>0x240	search/0x100	!DOS/4G	\b, BW collection for MS-DOS

# This sequence skips to the first COFF segment, usually .text
>(4.s*512)	leshort		0x014c \b, COFF
!:mime	application/x-dosexec
>>(8.s*16)	string		go32stub for MS-DOS, DJGPP go32 DOS extender
>>(8.s*16)	string		emx
>>>&1		string		x for DOS, Win or OS/2, emx %s
>>&(&0x42.l-3)	byte		x
>>>&0x26	string		UPX \b, UPX compressed
# and yet another guess: small .text, and after large .data is unusal, could be 32lite
>>&0x2c		search/0xa0	.text
>>>&0x0b	lelong		<0x2000
>>>>&0		lelong		>0x6000 \b, 32lite compressed

>(8.s*16) string $WdX \b, WDos/X DOS extender

# By now an executable type should have been printed out.  The executable
# may be a self-uncompressing archive, so look for evidence of that and
# print it out.
#
# Some signatures below from Greg Roelofs, newt@uchicago.edu.
#
>0x35	string	\x8e\xc0\xb9\x08\x00\xf3\xa5\x4a\x75\xeb\x8e\xc3\x8e\xd8\x33\xff\xbe\x30\x00\x05 \b, aPack compressed
>0xe7	string	LH/2\ 	Self-Extract \b, %s
>0x1c	string	UC2X	\b, UCEXE compressed
>0x1c	string	WWP\ 	\b, WWPACK compressed
>0x1c	string	RJSX 	\b, ARJ self-extracting archive
>0x1c	string	diet 	\b, diet compressed
>0x1c	string	LZ09 	\b, LZEXE v0.90 compressed
>0x1c	string	LZ91 	\b, LZEXE v0.91 compressed
>0x1c	string	tz 	\b, TinyProg compressed
>0x1e	string	Copyright\ 1989-1990\ PKWARE\ Inc.	Self-extracting PKZIP archive
!:mime	application/zip
# Yes, this really is "Copr", not "Corp."
>0x1e	string	PKLITE\ Copr.	Self-extracting PKZIP archive
!:mime	application/zip
# winarj stores a message in the stub instead of the sig in the MZ header
>0x20	search/0xe0	aRJsfX \b, ARJ self-extracting archive
>0x20	string AIN
>>0x23	string 2	\b, AIN 2.x compressed
>>0x23	string <2	\b, AIN 1.x compressed
>>0x23	string >2	\b, AIN 1.x compressed
>0x24	string	LHa's\ SFX \b, LHa self-extracting archive
!:mime	application/x-lha
>0x24	string	LHA's\ SFX \b, LHa self-extracting archive
!:mime	application/x-lha
>0x24	string	\ $ARX \b, ARX self-extracting archive
>0x24	string	\ $LHarc \b, LHarc self-extracting archive
>0x20	string	SFX\ by\ LARC \b, LARC self-extracting archive
>0x40	string aPKG \b, aPackage self-extracting archive
>0x64	string	W\ Collis\0\0 \b, Compack compressed
>0x7a	string		Windows\ self-extracting\ ZIP	\b, ZIP self-extracting archive
>>&0xf4 search/0x140 \x0\x40\x1\x0
>>>(&0.l+(4)) string MSCF \b, WinHKI CAB self-extracting archive
>1638	string	-lh5- \b, LHa self-extracting archive v2.13S
>0x17888 string Rar! \b, RAR self-extracting archive

# Skip to the end of the EXE.  This will usually work fine in the PE case
# because the MZ image is hardcoded into the toolchain and almost certainly
# won't match any of these signatures.
>(4.s*512)	long	x
>>&(2.s-517)	byte	x
>>>&0	string		PK\3\4 \b, ZIP self-extracting archive
>>>&0	string		Rar! \b, RAR self-extracting archive
>>>&0	string		=!\x11 \b, AIN 2.x self-extracting archive
>>>&0	string		=!\x12 \b, AIN 2.x self-extracting archive
>>>&0	string		=!\x17 \b, AIN 1.x self-extracting archive
>>>&0	string		=!\x18 \b, AIN 1.x self-extracting archive
>>>&7	search/400	**ACE** \b, ACE self-extracting archive
>>>&0	search/0x480	UC2SFX\ Header \b, UC2 self-extracting archive

# a few unknown ZIP sfxes, no idea if they are needed or if they are
# already captured by the generic patterns above
>(8.s*16)	search/0x20	PKSFX \b, ZIP self-extracting archive (PKZIP)
# TODO: how to add this? >FileSize-34 string Windows\ Self-Installing\ Executable \b, ZIP self-extracting archive
#

# TELVOX Teleinformatica CODEC self-extractor for OS/2:
>49801	string	\x79\xff\x80\xff\x76\xff	\b, CODEC archive v3.21
>>49824 leshort		=1			\b, 1 file
>>49824 leshort		>1			\b, %u files

# added by Joerg Jenderek of http://www.freedos.org/software/?prog=kc
# and http://www.freedos.org/software/?prog=kpdos
# for FreeDOS files like KEYBOARD.SYS, KEYBRD2.SYS, KEYBRD3.SYS, *.KBD
0	string/b	KCF		FreeDOS KEYBoard Layout collection
# only version=0x100 found
>3	uleshort	x		\b, version 0x%x
# length of string containing author,info and special characters
>6	ubyte		>0
#>>6	pstring		x		\b, name=%s
>>7	string		>\0		\b, author=%-.14s
>>7	search/254	\xff		\b, info=
#>>>&0	string		x		\b%-s
>>>&0	string		x		\b%-.15s
# for FreeDOS *.KL files
0	string/b	KLF		FreeDOS KEYBoard Layout file
# only version=0x100 or 0x101 found
>3	uleshort	x		\b, version 0x%x
# stringlength
>5	ubyte		>0
>>8	string		x		\b, name=%-.2s
0	string	\xffKEYB\ \ \ \0\0\0\0
>12	string	\0\0\0\0`\004\360	MS-DOS KEYBoard Layout file

# DOS device driver updated by Joerg Jenderek at May 2011,Mar 2017
# https://amaus.net/static/S100/IBM/software/DOS/DOS%20techref/CHAPTER.009
0	ulequad&0x07a0ffffffff		0xffffffff
>0	use				msdos-driver
0       name    			msdos-driver		DOS executable (
#!:mime	application/octet-stream
!:mime	application/x-dosdriver
# also found FreeDOS print driver SPOOL.DEV and disc compression driver STACLOAD.BIN
!:ext	sys/dev/bin
>40	search/7			UPX!			\bUPX compressed
# DOS device driver attributes
>4	uleshort&0x8000			0x0000			\bblock device driver
# character device
>4	uleshort&0x8000			0x8000			\b
>>4	uleshort&0x0008			0x0008			\bclock
# fast video output by int 29h
>>4	uleshort&0x0010			0x0010			\bfast
# standard input/output device
>>4	uleshort&0x0003			>0			\bstandard
>>>4	uleshort&0x0001			0x0001			\binput
>>>4	uleshort&0x0003			0x0003			\b/
>>>4	uleshort&0x0002			0x0002			\boutput
>>4	uleshort&0x8000			0x8000			\bcharacter device driver
>0	ubyte				x
# upx compressed device driver has garbage instead of real in name field of header
>>40	search/7			UPX!
>>40	default				x
# leading/trailing nulls, zeros or non ASCII characters in 8-byte name field at offset 10 are skipped
>>>12		ubyte			>0x2E			\b
>>>>10		ubyte			>0x20
>>>>>10		ubyte			!0x2E
>>>>>>10	ubyte			!0x2A			\b%c
>>>>11		ubyte			>0x20
>>>>>11		ubyte			!0x2E			\b%c
>>>>12		ubyte			>0x20
>>>>>12		ubyte			!0x39
>>>>>>12	ubyte			!0x2E			\b%c
>>>13		ubyte			>0x20
>>>>13		ubyte			!0x2E			\b%c
>>>>14		ubyte			>0x20
>>>>>14		ubyte			!0x2E			\b%c
>>>>15		ubyte			>0x20
>>>>>15		ubyte			!0x2E			\b%c
>>>>16		ubyte			>0x20
>>>>>16		ubyte			!0x2E
>>>>>>16	ubyte			<0xCB			\b%c
>>>>17		ubyte			>0x20
>>>>>17		ubyte			!0x2E
>>>>>>17	ubyte			<0x90			\b%c
# some character device drivers like ASPICD.SYS, btcdrom.sys and Cr_atapi.sys contain only spaces or points in name field
>>>12		ubyte			<0x2F
# they have their real name at offset 22
# also block device drivers like DUMBDRV.SYS
>>>>22		string			>\056			%-.6s
>4	uleshort&0x8000			0x0000
# 32 bit sector addressing ( > 32 MB) for block devices
>>4	uleshort&0x0002			0x0002			\b,32-bit sector-
# support by driver functions 13h, 17h, 18h
>4	uleshort&0x0040			0x0040			\b,IOCTL-
# open, close, removable media support by driver functions 0Dh, 0Eh, 0Fh
>4	uleshort&0x0800			0x0800			\b,close media-
# output until busy support by int 10h for character device driver
>4	uleshort&0x8000			0x8000
>>4	uleshort&0x2000			0x2000			\b,until busy-
# direct read/write support by driver functions 03h,0Ch
>4	uleshort&0x4000			0x4000			\b,control strings-
>4	uleshort&0x8000			0x8000
>>4	uleshort&0x6840			>0			\bsupport
>4	uleshort&0x8000			0x0000
>>4	uleshort&0x4842			>0			\bsupport
>0	ubyte				x			\b)
# DOS driver cmd640x.sys has 0x12 instead of 0xffffffff for pointer field to next device header
0	ulequad				0x0513c00000000012
>0	use				msdos-driver
# DOS drivers DC2975.SYS, DUMBDRV.SYS, ECHO.SYS has also none 0xffffffff for pointer field
0	ulequad				0x32f28000ffff0016
>0	use				msdos-driver
0	ulequad				0x007f00000000ffff
>0	use				msdos-driver
0	ulequad				0x001600000000ffff
>0	use				msdos-driver
# DOS drivers LS120.SYS, MKELS120.SYS use reserved bits of attribute field
0	ulequad				0x0bf708c2ffffffff
>0	use				msdos-driver
0	ulequad				0x07bd08c2ffffffff
>0	use				msdos-driver

# updated by Joerg Jenderek
# GRR: line below too general as it catches also
# rt.lib DYADISKS.PIC and many more
# start with assembler instruction MOV
0	ubyte		0x8c
# skip "AppleWorks word processor data" like ARTICLE.1 ./apple
>4	string			!O====
# skip some unknown basic binaries like RocketRnger.SHR
>>5	string			!MAIN
# skip "GPG symmetrically encrypted data" ./gnu
# skip "PGP symmetric key encrypted data" ./pgp
# openpgpdefs.h: fourth byte < 14 indicate cipher algorithm type
>>>4	ubyte			>13	DOS executable (COM, 0x8C-variant)
# the remaining files should be DOS *.COM executables
# dosshell.COM	8cc0 2ea35f07 e85211 e88a11 b80058 cd
# hmload.COM	8cc8 8ec0 bbc02b 89dc 83c30f c1eb04 b4
# UNDELETE.COM	8cca 2e8916 6503 b430 cd21 8b 2e0200 8b
# BOOTFIX.COM	8cca 2e8916 9603 b430 cd21 8b 2e0200 8b
# RAWRITE3.COM	8cca 2e8916 d602 b430 cd21 8b 2e0200 8b
# SHARE.COM	8cca 2e8916 d602 b430 cd21 8b 2e0200 8b
# validchr.COM	8cca 2e8916 9603 b430 cd21 8b 2e028b1e
# devload.COM	8cca 8916ad01 b430 cd21 8b2e0200 892e
!:mime	application/x-dosexec
!:ext com

# updated by Joerg Jenderek at Oct 2008
0	ulelong		0xffff10eb	DR-DOS executable (COM)
# byte 0xeb conflicts with "sequent" magic leshort 0xn2eb
0	ubeshort&0xeb8d	>0xeb00
# DR-DOS STACKER.COM SCREATE.SYS missed

0       name    msdos-com
>0  byte        x               DOS executable (COM)
>6	string		SFX\ of\ LHarc	\b, %s
>0x1FE leshort	0xAA55		    \b, boot code
>85	string		UPX		        \b, UPX compressed
>4	string		\ $ARX		    \b, ARX self-extracting archive
>4	string		\ $LHarc	    \b, LHarc self-extracting archive
>0x20e string	SFX\ by\ LARC	\b, LARC self-extracting archive

# JMP 8bit
0	        byte	0xeb
# allow forward jumps only
>1          byte    >-1
# that offset must be accessible
>>(1.b+2)   byte    x
>>>0        use msdos-com

# JMP 16bit
0           byte    0xe9
# forward jumps
>1          short   >-1
# that offset must be accessible
>>(1.s+3)   byte    x
>>>0        use msdos-com
# negative offset, must not lead into PSP
>1          short   <-259
# that offset must be accessible
>>(1,s+65539)   byte    x
>>>0        use msdos-com

# updated by Joerg Jenderek at Oct 2008,2015
# following line is too general
0	ubyte		0xb8
# skip 2 linux kernels like memtest.bin with "\xb8\xc0\x07\x8e" in ./linux
>0	string		!\xb8\xc0\x07\x8e
# modified by Joerg Jenderek
# syslinux COM32 or COM32R executable
>>1	lelong&0xFFFFFFFe 0x21CD4CFe	COM executable (32-bit COMBOOT
# http://www.syslinux.org/wiki/index.php/Comboot_API
# Since version 5.00 c32 modules switched from the COM32 object format to ELF
!:mime	application/x-c32-comboot-syslinux-exec
!:ext c32
# http://syslinux.zytor.com/comboot.php
# older syslinux version ( <4 )
# (32-bit COMBOOT) programs *.C32 contain 32-bit code and run in flat-memory 32-bit protected mode
# start with assembler instructions mov eax,21cd4cffh
>>>1	lelong		0x21CD4CFf	\b)
# syslinux:doc/comboot.txt
# A COM32R program must start with the byte sequence B8 FE 4C CD 21 (mov
# eax,21cd4cfeh) as a magic number.
# syslinux version (4.x)
# "COM executable (COM32R)" or "Syslinux COM32 module" by TrID
>>>1	lelong		0x21CD4CFe	\b, relocatable)
# remaining are DOS COM executables starting with assembler instruction MOV
# like FreeDOS BANNER*.COM FINDDISK.COM GIF2RAW.COM WINCHK.COM
# MS-DOS SYS.COM RESTART.COM
# SYSLINUX.COM (version 1.40 - 2.13)
# GFXBOOT.COM (version 3.75)
# COPYBS.COM POWEROFF.COM INT18.COM
>>1	default	x			COM executable for DOS
!:mime	application/x-dosexec
#!:mime	application/x-ms-dos-executable
#!:mime	application/x-msdos-program
!:ext com

0	string/b	\x81\xfc
>4	string	\x77\x02\xcd\x20\xb9
>>36	string	UPX!			FREE-DOS executable (COM), UPX compressed
252	string Must\ have\ DOS\ version DR-DOS executable (COM)
# added by Joerg Jenderek at Oct 2008
# GRR search is not working
#34	search/2	UPX!		FREE-DOS executable (COM), UPX compressed
34	string	UPX!			FREE-DOS executable (COM), UPX compressed
35	string	UPX!			FREE-DOS executable (COM), UPX compressed
# GRR search is not working
#2	search/28	\xcd\x21	COM executable for MS-DOS
#WHICHFAT.cOM
2	string	\xcd\x21		COM executable for DOS
#DELTREE.cOM DELTREE2.cOM
4	string	\xcd\x21		COM executable for DOS
#IFMEMDSK.cOM ASSIGN.cOM COMP.cOM
5	string	\xcd\x21		COM executable for DOS
#DELTMP.COm HASFAT32.cOM
7	string	\xcd\x21
>0	byte	!0xb8			COM executable for DOS
#COMP.cOM MORE.COm
10	string	\xcd\x21
>5	string	!\xcd\x21		COM executable for DOS
#comecho.com
13	string	\xcd\x21		COM executable for DOS
#HELP.COm EDIT.coM
18	string	\xcd\x21		COM executable for MS-DOS
#NWRPLTRM.COm
23	string	\xcd\x21		COM executable for MS-DOS
#LOADFIX.cOm LOADFIX.cOm
30	string	\xcd\x21		COM executable for MS-DOS
#syslinux.com 3.11
70	string	\xcd\x21		COM executable for DOS
# many compressed/converted COMs start with a copy loop instead of a jump
0x6	search/0xa	\xfc\x57\xf3\xa5\xc3	COM executable for MS-DOS
0x6	search/0xa	\xfc\x57\xf3\xa4\xc3	COM executable for DOS
>0x18	search/0x10	\x50\xa4\xff\xd5\x73	\b, aPack compressed
0x3c	string		W\ Collis\0\0		COM executable for MS-DOS, Compack compressed
# FIXME: missing diet .com compression

# miscellaneous formats
0	string/b	LZ		MS-DOS executable (built-in)
#0	byte		0xf0		MS-DOS program library data
#

# AAF files:
# <stuartc@rd.bbc.co.uk> Stuart Cunningham
0	string/b	\320\317\021\340\241\261\032\341AAFB\015\000OM\006\016\053\064\001\001\001\377			AAF legacy file using MS Structured Storage
>30	byte	9		(512B sectors)
>30	byte	12		(4kB sectors)
0	string/b	\320\317\021\340\241\261\032\341\001\002\001\015\000\002\000\000\006\016\053\064\003\002\001\001			AAF file using MS Structured Storage
>30	byte	9		(512B sectors)
>30	byte	12		(4kB sectors)

# Popular applications
2080	string	Microsoft\ Word\ 6.0\ Document	%s
!:mime	application/msword
2080	string	Documento\ Microsoft\ Word\ 6 Spanish Microsoft Word 6 document data
!:mime	application/msword
# Pawel Wiecek <coven@i17linuxb.ists.pwr.wroc.pl> (for polish Word)
2112	string	MSWordDoc			Microsoft Word document data
!:mime	application/msword
#
0	belong	0x31be0000			Microsoft Word Document
!:mime	application/msword
#
0	string/b	PO^Q`				Microsoft Word 6.0 Document
!:mime	application/msword
#
4   long        0
>0  belong      0xfe320000      Microsoft Word for Macintosh 1.0
!:mime	application/msword
!:ext   mcw
>0  belong      0xfe340000      Microsoft Word for Macintosh 3.0
!:mime	application/msword
!:ext   mcw
>0  belong      0xfe37001c      Microsoft Word for Macintosh 4.0
!:mime	application/msword
!:ext   mcw
>0  belong      0xfe370023      Microsoft Word for Macintosh 5.0
!:mime	application/msword
!:ext   mcw

0	string/b	\333\245-\0\0\0			Microsoft Word 2.0 Document
!:mime	application/msword
!:ext   doc
# Note: seems already recognized as "OLE 2 Compound Document" in ./ole2compounddocs
#512	string/b	\354\245\301			Microsoft Word Document
#!:mime	application/msword

#
0	string/b	\xDB\xA5\x2D\x00		Microsoft WinWord 2.0 Document
!:mime application/msword
#
2080	string	Microsoft\ Excel\ 5.0\ Worksheet	%s
!:mime	application/vnd.ms-excel
#
0	string/b	\xDB\xA5\x2D\x00		Microsoft WinWord 2.0 Document
!:mime application/msword

2080	string	Foglio\ di\ lavoro\ Microsoft\ Exce	%s
!:mime	application/vnd.ms-excel
#
# Pawel Wiecek <coven@i17linuxb.ists.pwr.wroc.pl> (for polish Excel)
2114	string	Biff5		Microsoft Excel 5.0 Worksheet
!:mime	application/vnd.ms-excel
# Italian MS-Excel
2121	string	Biff5		Microsoft Excel 5.0 Worksheet
!:mime	application/vnd.ms-excel
0	string/b	\x09\x04\x06\x00\x00\x00\x10\x00	Microsoft Excel Worksheet
!:mime	application/vnd.ms-excel
#
# Update: Joerg Jenderek
# URL: https://en.wikipedia.org/wiki/Lotus_1-2-3
# Reference: http://www.aboutvb.de/bas/formate/pdf/wk3.pdf
# Note: newer Lotus versions >2 use longer BOF record
# record type (BeginningOfFile=0000h) + length (001Ah)
0	belong	0x00001a00
# reserved should be 0h but 8c0dh for TUTMAC.WK3, 5h for SAMPADNS.WK3, 1h for a_readme.wk3, 1eh for K&G86.WK3
#>18	uleshort&0x73E0	0
# Lotus Multi Byte Character Set (LMBCS=1-31)
>20	ubyte		>0
>>20	ubyte		<32	Lotus 1-2-3
#!:mime	application/x-123
!:mime	application/vnd.lotus-1-2-3
!:apple	????L123
# (version 5.26) labeled the entry as "Lotus 1-2-3 wk3 document data"
>>>4	uleshort	0x1000	WorKsheet, version 3
!:ext	wk3
# (version 5.26) labeled the entry as "Lotus 1-2-3 wk4 document data"
>>>4	uleshort	0x1002	WorKsheet, version 4
# also worksheet template 4 (.wt4)
!:ext	wk4/wt4
# no example or documentation for wk5
#>>4	uleshort	0x????	WorKsheet, version 4
#!:ext	wk5
# only MacrotoScript.123 example
>>>4	uleshort	0x1003	WorKsheet, version 97
# also worksheet template Smartmaster (.12M)?
!:ext	123
# only Set_Y2K.123 example
>>>4	uleshort	0x1005	WorKsheet, version 9.8 Millennium
!:ext	123
# no example for this version
>>>4	uleshort	0x8001	FoRMatting data
!:ext	frm
# (version 5.26) labeled the entry as "Lotus 1-2-3 fm3 or fmb document data"
# TrID labeles the entry as "Formatting Data for Lotus 1-2-3 worksheet"
>>>4	uleshort	0x8007	ForMatting data, version 3
!:ext	fm3
>>>4	default		x	unknown
# file revision sub code 0004h for worksheets
>>>>6	uleshort	=0x0004	worksheet
!:ext	wXX
>>>>6	uleshort	!0x0004	formatting data
!:ext	fXX
# main revision number
>>>>4	uleshort	x	\b, revision 0x%x
>>>6	uleshort	=0x0004	\b, cell range
# active cellcoord range (start row, page,column ; end row, page, column)
# start values normally 0~1st sheet A1
>>>>8	ulelong		!0
>>>>>10	ubyte		>0	\b%d*
>>>>>8	uleshort	x	\b%d,
>>>>>11	ubyte		x	\b%d-
# end page mostly 0
>>>>14	ubyte		>0	\b%d*
# end raw, column normally not 0
>>>>12	uleshort	x	\b%d,
>>>>15	ubyte		x	\b%d
# Lotus Multi Byte Character Set (1~cp850,2~cp851,...,16~japan,...,31~??)
>>>>20	ubyte		>1	\b, character set 0x%x
# flags
>>>>21	ubyte		x	\b, flags 0x%x
>>>6	uleshort	!0x0004
# record type (FONTNAME=00AEh)
>>>>30	search/29	\0\xAE
# variable length m (2) + entries (1) + ?? (1) + LCMBS string (n)
>>>>>&4	string		>\0	\b, 1st font "%s"
#
# Update: Joerg Jenderek
# URL: http://fileformats.archiveteam.org/wiki/Lotus_1-2-3
# Reference: http://www.schnarff.com/file-formats/lotus-1-2-3/WSFF2.TXT
# Note: Used by both old Lotus 1-2-3 and Lotus Symphony (DOS) til version 2.x
# record type (BeginningOfFile=0000h) + length (0002h)
0	belong	0x00000200
# GRR: line above is too general as it catches also MS Windows CURsor
# to display MS Windows cursor (strength=70) before Lotus 1-2-3 (strength=70-1)
!:strength -1
# skip Windows cursors with image height <256 and keep Lotus with low opcode 0001-0083h
>7	ubyte		0
# skip Windows cursors with image width 256 and keep Lotus with positiv opcode
>>6	ubyte		>0	Lotus
# !:mime	application/x-123
!:mime	application/vnd.lotus-1-2-3
!:apple	????L123
# revision number (0404h = 123 1A, 0405h = Lotus Symphony , 0406h = 123 2.x wk1 , 8006h = fmt , ...)
# undocumented; (version 5.26) labeled the configurations as "Lotus 1-2-3"
>>>4	uleshort	0x0007	1-2-3 CoNFiguration, version 2.x (PGRAPH.CNF)
!:ext	cnf
>>>4	uleshort	0x0C05	1-2-3 CoNFiguration, version 2.4J
!:ext	cnf
>>>4	uleshort	0x0801	1-2-3 CoNFiguration, version 1-2.1
!:ext	cnf
>>>4	uleshort	0x0802	Symphony CoNFiguration
!:ext	cnf
>>>4	uleshort	0x0804	1-2-3 CoNFiguration, version 2.2
!:ext	cnf
>>>4	uleshort	0x080A	1-2-3 CoNFiguration, version 2.3-2.4
!:ext	cnf
>>>4	uleshort	0x1402	1-2-3 CoNFiguration, version 3.x
!:ext	cnf
>>>4	uleshort	0x1450	1-2-3 CoNFiguration, version 4.x
!:ext	cnf
# (version 5.26) labeled the entry as "Lotus 123"
# TrID labeles the entry as "Lotus 123 Worksheet (generic)"
>>>4	uleshort	0x0404	1-2-3 WorKSheet, version 1
# extension "wks" also for Microsoft Works document
!:ext	wks
# (version 5.26) labeled the entry as "Lotus 123"
# TrID labeles the entry as "Lotus 123 Worksheet (generic)"
>>>4	uleshort	0x0405	Symphony WoRksheet, version 1.0
!:ext	wrk/wr1
# (version 5.26) labeled the entry as "Lotus 1-2-3 wk1 document data"
# TrID labeles the entry as "Lotus 123 Worksheet (V2)"
>>>4	uleshort	0x0406	1-2-3/Symphony worksheet, version 2
# Symphony (.wr1)
!:ext	wk1/wr1
# no example for this japan version
>>>4	uleshort	0x0600	1-2-3 WorKsheet, version 1.xJ
!:ext	wj1
# no example or documentation for wk2
#>>>4	uleshort	0x????	1-2-3 WorKsheet, version 2
#!:ext	wk2
# undocumented japan version
>>>4	uleshort	0x0602	1-2-3 worksheet, version 2.4J
!:ext	wj3
# (version 5.26) labeled the entry as "Lotus 1-2-3 fmt document data"
>>>4	uleshort	0x8006	1-2-3 ForMaTting data, version 2.x
# japan version 2.4J (fj3)
!:ext	fmt/fj3
# no example for this version
>>>4	uleshort	0x8007	1-2-3 FoRMatting data, version 2.0
!:ext	frm
# (version 5.26) labeled the entry as "Lotus 1-2-3"
>>>4	default		x	unknown worksheet or configuration
!:ext	cnf
>>>>4	uleshort	x	\b, revision 0x%x
# 2nd record for most worksheets describes cells range
>>>6		use	lotus-cells
# 3nd record for most japan worksheets describes cells range
>>>(8.s+10)	use	lotus-cells
#	check and then display Lotus worksheet cells range
0	name		lotus-cells
# look for type (RANGE=0006h) + length (0008h) at record begin
>0	ubelong	0x06000800	\b, cell range
# cell range (start column, row, end column, row) start values normally 0,0~A1 cell
>>4	ulong		!0
>>>4	uleshort	x	\b%d,
>>>6	uleshort	x	\b%d-
# end of cell range
>>8	uleshort	x	\b%d,
>>10	uleshort	x	\b%d
# EndOfLotus123
0	string/b		WordPro\0	Lotus WordPro
!:mime	application/vnd.lotus-wordpro
0	string/b		WordPro\r\373	Lotus WordPro
!:mime	application/vnd.lotus-wordpro


# Summary: Script used by InstallScield to uninstall applications
# Extension: .isu
# Submitted by: unknown
# Modified by (1): Abel Cheung <abelcheung@gmail.com> (replace useless entry)
0		string		\x71\xa8\x00\x00\x01\x02
>12		string		Stirling\ Technologies,		InstallShield Uninstall Script

# Winamp .avs
#0	string	Nullsoft\ AVS\ Preset\ \060\056\061\032 A plug in for Winamp ms-windows Freeware media player
0	string/b	Nullsoft\ AVS\ Preset\ 	Winamp plug in

# Windows Metafile .WMF
0	string/b	\327\315\306\232	Windows metafile
!:mime	image/wmf
!:ext	wmf
0	string/b	\002\000\011\000	Windows metafile
!:mime	image/wmf
!:ext	wmf
0	string/b	\001\000\011\000	Windows metafile
!:mime	image/wmf
!:ext	wmf

#tz3 files whatever that is (MS Works files)
0	string/b	\003\001\001\004\070\001\000\000	tz3 ms-works file
0	string/b	\003\002\001\004\070\001\000\000	tz3 ms-works file
0	string/b	\003\003\001\004\070\001\000\000	tz3 ms-works file

# PGP sig files .sig
#0 string \211\000\077\003\005\000\063\237\127 065 to  \027\266\151\064\005\045\101\233\021\002 PGP sig
0 string \211\000\077\003\005\000\063\237\127\065\027\266\151\064\005\045\101\233\021\002 PGP sig
0 string \211\000\077\003\005\000\063\237\127\066\027\266\151\064\005\045\101\233\021\002 PGP sig
0 string \211\000\077\003\005\000\063\237\127\067\027\266\151\064\005\045\101\233\021\002 PGP sig
0 string \211\000\077\003\005\000\063\237\127\070\027\266\151\064\005\045\101\233\021\002 PGP sig
0 string \211\000\077\003\005\000\063\237\127\071\027\266\151\064\005\045\101\233\021\002 PGP sig
0 string \211\000\225\003\005\000\062\122\207\304\100\345\042 PGP sig

# windows zips files .dmf
0	string/b	MDIF\032\000\010\000\000\000\372\046\100\175\001\000\001\036\001\000 MS Windows special zipped file


#ico files
0	string/b	\102\101\050\000\000\000\056\000\000\000\000\000\000\000	Icon for MS Windows

# Windows icons
# Update: Joerg Jenderek
# URL: https://en.wikipedia.org/wiki/CUR_(file_format)
# Note: similar to Windows CURsor. container for BMP (only DIB part) or PNG
0   belong  0x00000100
>9  byte    0
>>0 byte    x
>>0 use     cur-ico-dir
>9  ubyte   0xff
>>0 byte    x
>>0 use     cur-ico-dir
#	displays number of icons and information for icon or cursor
0	name		cur-ico-dir
# skip some Lotus 1-2-3 worksheets, CYCLE.PIC and keep Windows cursors with
# 1st data offset = dir header size + n * dir entry size = 6 + n * 10h = ?6h
>18		ulelong		&0x00000006
# skip remaining worksheets, because valid only for DIB image (40) or PNG image (\x89PNG)
>>(18.l)	ulelong		x		MS Windows
>>>0		ubelong		0x00000100	icon resource
#!:mime		image/vnd.microsoft.icon
!:mime		image/x-icon
!:ext		ico
>>>>4 		uleshort	x		- %d icon
# plural s
>>>>4 		uleshort	>1		\bs
# 1st icon
>>>>0x06	use		ico-entry
# 2nd icon
>>>>4 		uleshort	>1
>>>>>0x16	use		ico-entry
>>>0		ubelong		0x00000200	cursor resource
#!:mime		image/x-cur
!:mime		image/x-win-bitmap
!:ext		cur
>>>>4 		uleshort	x		- %d icon
>>>>4 		uleshort	>1		\bs
# 1st cursor
>>>>0x06	use		cur-entry
#>>>>0x16	use		cur-entry
#	display information of one cursor entry
0	name		cur-entry
>0	use		cur-ico-entry
>4	uleshort	x	\b, hotspot @%dx
>6	uleshort	x	\b%d
#	display information of one icon entry
0	name		ico-entry
>0			use	cur-ico-entry
# normally 0 1 but also found 14
>4	uleshort	>1	\b, %d planes
# normally 0 1 but also found some 3, 4, some 6, 8, 24, many 32, two 256
>6	uleshort	>1	\b, %d bits/pixel
#	display shared information of cursor or icon entry
0		name		cur-ico-entry
>0		byte		=0		\b, 256x
>0		byte		!0		\b, %dx
>1		byte        	=0		\b256
>1		byte        	!0		\b%d
# number of colors in palette
>2		ubyte		!0		\b, %d colors
# reserved 0 FFh
#>3		ubyte        	x		\b, reserved %x
#>8		ulelong		x		\b, image size %d
# offset of PNG or DIB image
#>12		ulelong		x		\b, offset 0x%x
# PNG header (\x89PNG)
>(12.l)		ubelong		=0x89504e47
>>&-4		indirect	x	\b with
# DIB image
>(12.l)		ubelong		!0x89504e47
#>>&-4		use     	dib-image

# Windows non-animated cursors
# Update: Joerg Jenderek
# URL: https://en.wikipedia.org/wiki/CUR_(file_format)
# Note: similar to Windows ICOn. container for BMP ( only DIB part)
# GRR: line below is too general as it catches also Lotus 1-2-3 files
0   belong  0x00000200
>9  byte    0
>>0 use     cur-ico-dir
>9  ubyte   0xff
>>0 use     cur-ico-dir

# .chr files
0	string/b	PK\010\010BGI	Borland font
>4	string	>\0	%s
# then there is a copyright notice


# .bgi files
0	string/b	pk\010\010BGI	Borland device
>4	string	>\0	%s
# then there is a copyright notice


# Windows Recycle Bin record file (named INFO2)
# By Abel Cheung (abelcheung AT gmail dot com)
# Version 4 always has 280 bytes (0x118) per record, version 5 has 800 bytes
# Since Vista uses another structure, INFO2 structure probably won't change
# anymore. Detailed analysis in:
# http://www.cybersecurityinstitute.biz/downloads/INFO2.pdf
0	lelong		0x00000004
>12	lelong		0x00000118	Windows Recycle Bin INFO2 file (Win98 or below)

0	lelong		0x00000005
>12	lelong		0x00000320	Windows Recycle Bin INFO2 file (Win2k - WinXP)

# From Doug Lee via a FreeBSD pr
9	string		GERBILDOC	First Choice document
9	string		GERBILDB	First Choice database
9	string		GERBILCLIP	First Choice database
0	string		GERBIL		First Choice device file
9	string		RABBITGRAPH	RabbitGraph file
0	string		DCU1		Borland Delphi .DCU file
0	string		=!<spell>	MKS Spell hash list (old format)
0	string		=!<spell2>	MKS Spell hash list
# Too simple - MPi
#0	string		AH		Halo(TM) bitmapped font file
0	lelong		0x08086b70	TurboC BGI file
0	lelong		0x08084b50	TurboC Font file

# Debian#712046: The magic below identifies "Delphi compiled form data".
# An additional source of information is available at:
# http://www.woodmann.com/fravia/dafix_t1.htm
0	string		TPF0
>4	pstring		>\0		Delphi compiled form '%s'

# tests for DBase files moved, updated and merged to database

0	string		PMCC		Windows 3.x .GRP file
1	string		RDC-meg		MegaDots
>8	byte		>0x2F		version %c
>9	byte		>0x2F		\b.%c file
0	lelong		0x4C
>4	lelong		0x00021401	Windows shortcut file

# .PIF files added by Joerg Jenderek from http://smsoft.ru/en/pifdoc.htm
# only for windows versions equal or greater 3.0
0x171	string	MICROSOFT\ PIFEX\0	Windows Program Information File
!:mime	application/x-dosexec
#>2	string	 	>\0		\b, Title:%.30s
>0x24	string		>\0		\b for %.63s
>0x65	string		>\0		\b, directory=%.64s
>0xA5	string		>\0		\b, parameters=%.64s
#>0x181	leshort	x	\b, offset %x
#>0x183	leshort	x	\b, offsetdata %x
#>0x185	leshort	x	\b, section length %x
>0x187	search/0xB55	WINDOWS\ VMM\ 4.0\0
>>&0x5e		ubyte	>0
>>>&-1		string	<PIFMGR.DLL		\b, icon=%s
#>>>&-1		string	PIFMGR.DLL		\b, icon=%s
>>>&-1		string	>PIFMGR.DLL		\b, icon=%s
>>&0xF0		ubyte	>0
>>>&-1		string	<Terminal		\b, font=%.32s
#>>>&-1		string	=Terminal		\b, font=%.32s
>>>&-1		string	>Terminal		\b, font=%.32s
>>&0x110	ubyte	>0
>>>&-1		string	<Lucida\ Console	\b, TrueTypeFont=%.32s
#>>>&-1		string	=Lucida\ Console	\b, TrueTypeFont=%.32s
>>>&-1		string	>Lucida\ Console	\b, TrueTypeFont=%.32s
#>0x187	search/0xB55	WINDOWS\ 286\ 3.0\0	\b, Windows 3.X standard mode-style
#>0x187	search/0xB55	WINDOWS\ 386\ 3.0\0	\b, Windows 3.X enhanced mode-style
>0x187	search/0xB55	WINDOWS\ NT\ \ 3.1\0	\b, Windows NT-style
#>0x187	search/0xB55	WINDOWS\ NT\ \ 4.0\0	\b, Windows NT-style
>0x187	search/0xB55	CONFIG\ \ SYS\ 4.0\0	\b +CONFIG.SYS
#>>&06		string	x			\b:%s
>0x187	search/0xB55	AUTOEXECBAT\ 4.0\0	\b +AUTOEXEC.BAT
#>>&06		string	x			\b:%s

# DOS EPS Binary File Header
# From: Ed Sznyter <ews@Black.Market.NET>
0	belong		0xC5D0D3C6	DOS EPS Binary File
!:mime	image/x-eps
>4	long		>0		Postscript starts at byte %d
>>8	long		>0		length %d
>>>12	long		>0		Metafile starts at byte %d
>>>>16	long		>0		length %d
>>>20	long		>0		TIFF starts at byte %d
>>>>24	long		>0		length %d

# TNEF magic From "Joomy" <joomy@se-ed.net>
# Microsoft Outlook's Transport Neutral Encapsulation Format (TNEF)
0	lelong		0x223e9f78	TNEF
!:mime	application/vnd.ms-tnef

# Norton Guide (.NG , .HLP) files added by Joerg Jenderek from source NG2HTML.C
# of http://www.davep.org/norton-guides/ng2h-105.tgz
# http://en.wikipedia.org/wiki/Norton_Guides
0	string		NG\0\001
# only value 0x100 found at offset 2
>2	ulelong		0x00000100	Norton Guide
# Title[40]
>>8	string		>\0		"%-.40s"
#>>6	uleshort	x		\b, MenuCount=%u
# szCredits[5][66]
>>48	string		>\0		\b, %-.66s
>>114	string		>\0		%-.66s

# 4DOS help (.HLP) files added by Joerg Jenderek from source TPHELP.PAS
# of http://www.4dos.info/
# pointer,HelpID[8]=4DHnnnmm
0	ulelong	0x48443408		4DOS help file
>4	string	x			\b, version %-4.4s

# old binary Microsoft (.HLP) files added by Joerg Jenderek from http://file-extension.net/seeker/file_extension_hlp
0	ulequad	0x3a000000024e4c	MS Advisor help file

# HtmlHelp files (.chm)
0	string/b	ITSF\003\000\000\000\x60\000\000\000	MS Windows HtmlHelp Data

# GFA-BASIC (Wolfram Kleff)
2	string/b	GFA-BASIC3	GFA-BASIC 3 data

#------------------------------------------------------------------------------
# From Stuart Caie <kyzer@4u.net> (developer of cabextract)
# Update: Joerg Jenderek
# URL: https://en.wikipedia.org/wiki/Cabinet_(file_format)
# Reference: https://msdn.microsoft.com/en-us/library/bb267310.aspx
# Note: verified by `7z l *.cab`
# Microsoft Cabinet files
0	string/b	MSCF\0\0\0\0	Microsoft Cabinet archive data
#
# https://support.microsoft.com/en-us/help/973559/frequently-asked-questions-about-the-microsoft-support-diagnostic-tool
# CAB with *.{diagcfg,diagpkg} is used by Microsoft Support Diagnostic Tool MSDT.EXE
# because some archive does not have *.diag* as 1st or 2nd archive member like
# O15CTRRemove.diagcab or AzureStorageAnalyticsLogs_global.DiagCab
# brute looking after header for filenames with diagcfg or diagpkg extension in CFFILE section
>0x2c	search/980/c	.diag		\b, Diagnostic
!:mime	application/vnd.ms-cab-compressed
!:ext	diagcab
# http://fileformats.archiveteam.org/wiki/PUZ
# Microsoft Publisher version about 2003 has a "Pack and Go" feature that
# bundles a Publisher document *PNG.pub with all links into a CAB
>0x2c	search/300/c	png.pub\0		\b, Publisher Packed and Go
!:mime	application/vnd.ms-cab-compressed
!:ext	puz
# ppz variant with Microsoft PowerPoint Viewer ppview32.exe to play PowerPoint presentation
>0x2c	search/17/c	ppview32.exe\0		\b, PowerPoint Viewer Packed and Go
!:mime	application/vnd.ms-powerpoint
#!:mime	application/mspowerpoint
!:ext	ppz
# http://www.incredimail.com/
# IncrediMail CAB contains an initialisation file "content.ini" like in im2.ims
>0x2c	search/3369/c	content.ini\0	\b, IncrediMail
!:mime	application/x-incredimail
# member Flavor.htm implies IncrediMail ecard like in tell_a_friend.imf
>>0x2c	search/83/c	Flavor.htm\0	ecard
!:ext	imf
# member Macromedia Flash data *.swf implies IncrediMail skin like in im2.ims
>>0x2c	search/211/c	.swf\0		skin
!:ext	ims
# member anim.im3 implies IncrediMail animation like in letter_fold.ima 
>>0x2c	search/92/c	anim.im3\0	animation
!:ext	ima
# other IncrediMail cab archive
>>0x2c	default		x
>>>0x2c	search/116/c	thumb		ecard, image, notifier or skin
!:ext	imf/imi/imn/ims
# http://file-extension.net/seeker/file_extension_ime
>>>0x2c	default		x		emoticons or sound
!:ext	ime/imw
# no Diagnostic and IncrediMail
>0x2c	default		x
# look for 1st member name
>>(16.l+16)	ubyte	x
# https://en.wikipedia.org/wiki/SNP_file_format
>>>&-1	string/c 	_accrpt_.snp	\b, Access report snapshot
!:mime	application/msaccess
!:ext	snp
# https://www.cabextract.org.uk/wince_cab_format/
# extension of DOS 8+3 name with ".000" of 1st archive member name implies Windows CE installer
>>>&7	string 		=.000		\b, WinCE install
!:mime	application/vnd.ms-cab-compressed
!:ext	cab

# http://support.microsoft.com/kb/934307/en-US
# All inspected MSU contain a file with name WSUSSCAN.cab
# that is called "Windows Update meta data" by Microsoft
>>>&-1	string/c 	wsusscan.cab	\b, Microsoft Standalone Update
!:mime	application/vnd.ms-cab-compressed
!:ext	msu
>>>&-1	default		x
# look at point charcter of 1st archive member name for file name extension
>>>>&-1	search/255 	.
# http://www.pptfaq.com/FAQ00164_What_is_a_PPZ_file-.htm
# PPZ were created using Pack & Go feature of PowerPoint versions 97 - 2002
# packs optional files, a PowerPoint presentation *.ppt with optional PLAYLIST.LST to CAB
>>>>>&0	string/c	ppt\0		\b, PowerPoint Packed and Go
!:mime	application/vnd.ms-powerpoint
#!:mime	application/mspowerpoint
!:ext	ppz
# https://msdn.microsoft.com/en-us/library/windows/desktop/bb773190(v=vs.85).aspx
# first member *.theme implies Windows 7 Theme Pack like in CommunityShowcaseAqua3.themepack
# or Windows 8 Desktop Theme Pack like in PanoramicGlaciers.deskthemepack
>>>>>&0	string/c	theme		\b, Windows
!:mime	application/x-windows-themepack
# http://www.drewkeller.com/content/using-theme-both-windows-7-and-windows-8
# 1st member Panoramic.theme or Panoramas.theme implies Windows 8-10 Theme Pack
# with MTSM=RJSPBS in [MasterThemeSelector] inside *.theme
>>>>>>(16.l+16)	string	=Panoram	8
!:ext	deskthemepack
>>>>>>(16.l+16)	string	!Panoram	7 or 8
!:ext	themepack/deskthemepack
>>>>>>(16.l+16)	ubyte	x		Theme Pack
>>>>>&0	default		x
# look for null terminator of 1st member name
>>>>>>&0	search/255 	\0
# 2nd member name WSUSSCAN.cab like in Microsoft-Windows-MediaFeaturePack-OOB-Package.msu
>>>>>>>&16	string/c 	wsusscan.cab	\b, Microsoft Standalone Update
!:mime	application/vnd.ms-cab-compressed
!:ext	msu
>>>>>>>&16	default	x
# archive with more then one file need some output in version 5.32 to avoid error message like
# Magdir/msdos, 1138: Warning: Current entry does not yet have a description for adding a MIME type
# Magdir/msdos, 1139: Warning: Current entry does not yet have a description for adding a EXTENSION type
# file: could not find any valid magic files!
>>>>>>>>28	uleshort	>1	\b, many
!:mime	application/vnd.ms-cab-compressed
!:ext	cab
# remaining archives with just one file
>>>>>>>>28	uleshort	=1
# neither extra bytes nor cab chain implies Windows 2000,XP setup files in directory i386
>>>>>>>>>30	uleshort	=0x0000	\b, Windows 2000/XP setup
# cut of last char of source extension and add underscore to generate extension
# TERMCAP._ ... FXSCOUNT.H_ ... L3CODECA.AC_ ... NPDRMV2.ZI_
!:mime	application/vnd.ms-cab-compressed
!:ext	_/?_/??_
# archive need some output like "single" in version 5.32 to avoid error messages
>>>>>>>>>30	uleshort	!0x0000	\b, single
!:mime	application/vnd.ms-cab-compressed
!:ext	cab
# TODO: additional extensions like
# .xsn	InfoPath Dynamic Form
# .xtp	InfoPath Template Part
# .lvf	Logitech Video Effects Face Accessory
>8	ulelong		x		\b, %u bytes
>28	uleshort		1		\b, 1 file
>28	uleshort		>1		\b, %u files
# Reserved fields, set to zero
#>4	belong		!0		\b, reserved1 %x
#>12	belong		!0		\b, reserved2 %x
# offset of the first CFFILE entry coffFiles: minimal 2Ch
>16	ulelong		x		\b, at 0x%x
>(16.l)	use		cab-file
# at least also 2nd member
>28	uleshort		>1
>>(16.l+16)	ubyte	x
>>>&0	search/255 	\0
# second member info
>>>>&0	use		cab-file
#>20	belong		!0		\b, reserved %x
# Cabinet file format version. Currently, versionMajor = 1 and versionMinor = 3
>24	ubeshort	!0x0301		\b version 0x%x
# number of CFFOLDER entries
>26	uleshort	>1		\b, %u cffolders
# cabinet file option indicators 1~PREVIOUS, 2~NEXT, 4~reserved fields
# only found for flags 0 1 2 3 4 not 7
>30	uleshort	>0		\b, flags 0x%x
# Cabinet files have a 16-bit cabinet setID field that is designed for application use.
# default is zero, however, the -i option of cabarc can be used to set this field
>32	uleshort	>0		\b, ID %u
# iCabinet is number of this cabinet file in a set, where 0 for the first cabinet
#>34	uleshort	x		\b, iCabinet %u
# add one for display because humans start numbering by 1 and also fit to name of disk szDisk*
>34	uleshort+1	x		\b, number %u
>30	uleshort	&0x0004		\b, extra bytes
# cbCFHeader optional size of per-cabinet reserved area 14h 1800h
>>36	uleshort	>0		%u in head
# cbCFFolder is optional size of per-folder reserved area
>>38	ubyte		>0		%u in folder
# cbCFData is optional size of per-datablock reserved area
>>39	ubyte		>0		%u in data block
# optional per-cabinet reserved area abReserve[cbCFHeader]
>>36	uleshort	>0
# 1st CFFOLDER after reserved area in header
>>>(36.s+40)	use			cab-folder
# no reserved area in header
>30	uleshort	^0x0004
# no previous and next cab archive
>>30	uleshort		=0x0000
>>>36	use				cab-folder
# only previous cab archive
>>30	uleshort		=0x0001	\b, previous
>>>36	use				cab-anchor
# only next cab archive
>>30	uleshort		=0x0002	\b, next
>>>36	use				cab-anchor
# previous+next cab archive
# can not use sub routine cab-anchor to display previous and next cabinet together
#>>>36	use				cab-anchor
#>>>>&0	use				cab-anchor
>>30	uleshort		=0x0003	\b, previous
>>>36	string		x		%s
# optional name of previous disk szDisk*
>>>>&1	string		x		disk %s
>>>>>&1	string		x		\b, next %s
# optional name of previous disk szDisk*
>>>>>>&1	string		x	disk %s
>>>>>>>&1	use			cab-folder
#	display filename and disk name of previous or next cabinet
0       name    			cab-anchor
# optional name of previous/next cabinet file szCabinet*[255]
>&0	string		x		%s
# optional name of previous/next disk szDisk*[255]
>>&1	string		x		disk %s
#	display folder structure CFFOLDER information like compression of cabinet
0       name    			cab-folder
# offset of the CFDATA block in this folder
#>0	ulelong		x		\b, coffCabStart 0x%x
# number of CFDATA blocks in folder
>4	uleshort	x		\b, %u datablock
# plural s
>4	uleshort	>1		\bs
# compression typeCompress: 0~None 1~MSZIP 0x1503~LZX:21 0x1003~LZX:16 0x0f03~LZX:15
>6	uleshort	x		\b, 0x%x compression
# optional per-folder reserved area
#>8	ubequad		x		\b, abReserve 0x%llx
#	display member structure CFFILE information like member name of cabinet
0       name    			cab-file
# cbFile is uncompressed size of file in bytes 
#>0	ulelong		x		\b, cbFile %u
# uoffFolderStart is uncompressed offset of file in folder
#>4	ulelong		>0		\b, uoffFolderStart 0x%x
# iFolder is index into the CFFOLDER area. 0 indicates first folder in cabinet
# define ifoldCONTINUED_FROM_PREV      (0xFFFD)
# define ifoldCONTINUED_TO_NEXT        (0xFFFE)
# define ifoldCONTINUED_PREV_AND_NEXT  (0xFFFF)
>8	uleshort	>0		\b, iFolder 0x%x
# date stamp for file
#>10	uleshort	x		\b, date 0x%x
# time stamp for file
#>12	uleshort	x		\b, time 0x%x
# attribs is attribute flags for file
# define  _A_RDONLY       (0x01)  file is read-only
# define  _A_HIDDEN       (0x02)  file is hidden
# define  _A_SYSTEM       (0x04)  file is a system file
# define  _A_ARCH         (0x20)  file modified since last backup
# example http://sebastien.kirche.free.fr/pebuilder_plugins/depends.cab
# define  _A_EXEC         (0x40)  run after extraction
# define  _A_NAME_IS_UTF  (0x80)  szName[] contains UTF
# define  UNKNOWN       (0x0100)  undocumented or accident
#>14	uleshort	x		\b, attribs 0x%x
>14	uleshort	>0		+
>>14	uleshort	&0x0001		\bR
>>14	uleshort	&0x0002		\bH
>>14	uleshort	&0x0004		\bS
>>14	uleshort	&0x0020		\bA
>>14	uleshort	&0x0040		\bX
>>14	uleshort	&0x0080		\bUtf
# unknown 0x0100 flag found on one XP_CD:\I386\DRIVER.CAB
>>14	uleshort	&0x0100		\b?
# szName is name of archive member
>16	string		x		"%s"
# next archive member name if more files
#>>&17	string		>\0		\b, NEXT NAME %-.50s

# InstallShield Cabinet files
0	string/b	ISc(		InstallShield Cabinet archive data
>5	byte&0xf0	=0x60		version 6,
>5	byte&0xf0	!0x60		version 4/5,
>(12.l+40)	lelong	x		%u files

# Windows CE package files
0	string/b	MSCE\0\0\0\0	Microsoft WinCE install header
>20	lelong		0		\b, architecture-independent
>20	lelong		103		\b, Hitachi SH3
>20	lelong		104		\b, Hitachi SH4
>20	lelong		0xA11		\b, StrongARM
>20	lelong		4000		\b, MIPS R4000
>20	lelong		10003		\b, Hitachi SH3
>20	lelong		10004		\b, Hitachi SH3E
>20	lelong		10005		\b, Hitachi SH4
>20	lelong		70001		\b, ARM 7TDMI
>52	leshort		1		\b, 1 file
>52	leshort		>1		\b, %u files
>56	leshort		1		\b, 1 registry entry
>56	leshort		>1		\b, %u registry entries


# Windows Enhanced Metafile (EMF)
# See msdn.microsoft.com/archive/en-us/dnargdi/html/msdn_enhmeta.asp
# for further information.
0	ulelong 1
>40	string	\ EMF		Windows Enhanced Metafile (EMF) image data
>>44	ulelong x		version 0x%x


0	string/b	\224\246\056		Microsoft Word Document
!:mime	application/msword

512	string	R\0o\0o\0t\0\ \0E\0n\0t\0r\0y	Microsoft Word Document
!:mime	application/msword

# From: "Nelson A. de Oliveira" <naoliv@gmail.com>
# Magic type for Dell's BIOS .hdr files
# Dell's .hdr
0	string/b $RBU
>23	string Dell			%s system BIOS
>5	byte   2
>>48	byte   x			version %d.
>>49	byte   x			\b%d.
>>50	byte   x			\b%d
>5	byte   <2
>>48	string x			version %.3s

# Type: Microsoft Document Imaging Format (.mdi)
# URL:	http://en.wikipedia.org/wiki/Microsoft_Document_Imaging_Format
# From: Daniele Sempione <scrows@oziosi.org>
# Too weak (EP)
#0	short	0x5045			Microsoft Document Imaging Format

# MS eBook format (.lit)
0	string/b	ITOLITLS		Microsoft Reader eBook Data
>8	lelong	x			\b, version %u
!:mime					application/x-ms-reader

# Windows CE Binary Image Data Format
# From: Dr. Jesus <j@hug.gs>
0	string/b	B000FF\n	Windows Embedded CE binary image

# Windows Imaging (WIM) Image
0	string/b	MSWIM\000\000\000	Windows imaging (WIM) image
0	string/b	WLPWM\000\000\000	Windows imaging (WIM) image, wimlib pipable format

# The second byte of these signatures is a file version; I don't know what,
# if anything, produced files with version numbers 0-2.
# From: John Elliott <johne@seasip.demon.co.uk>
0	string	\xfc\x03\x00	Mallard BASIC program data (v1.11)
0	string	\xfc\x04\x00	Mallard BASIC program data (v1.29+)
0	string	\xfc\x03\x01	Mallard BASIC protected program data (v1.11)
0	string	\xfc\x04\x01	Mallard BASIC protected program data (v1.29+)

0	string	MIOPEN		Mallard BASIC Jetsam data
0	string	Jetsam0		Mallard BASIC Jetsam index data

# DOS backup 2.0 to 3.2

# backupid.@@@

# plausibility check for date
0x3	ushort	>1979
>0x5	ubyte-1 <31
>>0x6	ubyte-1 <12
# actually 121 nul bytes
>>>0x7	string	\0\0\0\0\0\0\0\0
>>>>0x1 ubyte	x	DOS 2.0 backup id file, sequence %d
!:ext @@@
>>>>0x0 ubyte	0xff	\b, last disk

# backed up file

# skip some AppleWorks word like Tomahawk.Awp, WIN98SE-DE.vhd
# by looking for trailing nul of maximal file name string
0x52	ubyte	0	
# test for flag byte: FFh~complete file, 00h~split file
# FFh -127 =	-1 -127 =	-128
# 00h -127 =	 0 -127 =	-127
>0	byte-127	<-126
# plausibility check for file name length
>>0x53	ubyte-1	<78	
# looking for terminating nul of file name string
>>>(0x53.b+4)	ubyte	0	
# looking if last char of string is valid DOS file name
>>>>(0x53.b+3)	ubyte	>0x1F	
# actually 44 nul bytes
# but sometimes garbage according to Ralf Quint. So can not be used as test
#>0x54	string	\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0
# first char of full file name is DOS (5Ch) or UNIX (2Fh) path separator
# only DOS variant found. UNIX variant according to V32SLASH.TXT in archive PD0315.EXE 
>>>>>5	ubyte&0x8C	0x0C	
# ./msdos (version 5.30) labeled the entry as
# "DOS 2.0 backed up file %s, split file, sequence %d" or
# "DOS 2.0 backed up file %s, complete file"
>>>>>>0	ubyte	x	DOS 2.0-3.2 backed up
#>>>>>>0	ubyte	0xff	complete
>>>>>>0	ubyte	0
>>>>>>>1 uleshort	x	sequence %d of
# full file name with path but without drive letter and colon stored from 0x05 til 0x52
>>>>>>0x5	string	x	file %s
# backup name is original filename
#!:ext	*
# magic/Magdir/msdos, 1169: Warning: EXTENSION type `     *' has bad char '*'
# file: line 1169: Bad magic entry '  *'
# after header original file content
>>>>>>128	indirect x	\b; 


# DOS backup 3.3 to 5.x

# CONTROL.nnn files
0	string	\x8bBACKUP\x20
# actually 128 nul bytes
>0xa	string	\0\0\0\0\0\0\0\0
>>0x9	ubyte	x	DOS 3.3 backup control file, sequence %d
>>0x8a	ubyte	0xff	\b, last disk

# NB: The BACKUP.nnn files consist of the files backed up,
# concatenated.