file/magic/Magdir/msdos

#------------------------------------------------------------------------------
# $File: msdos,v 1.92 2014/03/14 18:47:29 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

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
>>>(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

>>(0x3c.l)		string		NE \b, NE
>>>(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
>>>(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

>>(0x3c.l)		string		LE\0\0 \b, LE executable
>>>(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
# 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
>>>>&(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
>>(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

# .COM formats (Daniel Quinlan, quinlan@yggdrasil.com)
# Uncommenting only the first two lines will cover about 2/3 of COM files,
# but it isn't feasible to match all COM files since there must be at least
# two dozen different one-byte "magics".
# test too generic ?
0	byte		0xe9		DOS executable (COM)
>0x1FE leshort		0xAA55		\b, boot code
>6	string		SFX\ of\ LHarc	(%s)

# DOS device driver updated by Joerg Jenderek at May 2011
# http://maben.homeip.net/static/S100/IBM/software/DOS/DOS%20techref/CHAPTER.009
0	ulequad&0x07a0ffffffff		0xffffffff		DOS executable (
>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			>0x27			\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
>>>4		uleshort&0x8000		0x8000			
>>>>12		ubyte			<0x2F			
# they have their real name at offset 22
>>>>>22		string			>\0			\b%-.5s
>4	uleshort&0x8000			0x0000			
# 32 bit sector adressing ( > 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 
# Too weak, matches files that only contain 0's
#0	ulequad&0x000007a0ffffffed	0x0000000000000000	DOS-executable (
#>4	uleshort&0x8000			0x8000			\bcharacter device driver
#>>10	string				x			%-.8s
#>4	uleshort&0x4000			0x4000			\b,control strings-support)

# test too generic ?
0	byte		0x8c		DOS executable (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	byte		0xeb
>>0x1FE leshort		0xAA55		DOS executable (COM), boot code
>>85	string		UPX		DOS executable (COM), UPX compressed
>>4	string		\ $ARX		DOS executable (COM), ARX self-extracting archive
>>4	string		\ $LHarc	DOS executable (COM), LHarc self-extracting archive
>>0x20e string		SFX\ by\ LARC	DOS executable (COM), LARC self-extracting archive
# updated by Joerg Jenderek at Oct 2008
#0	byte		0xb8		COM executable
0	uleshort&0x80ff	0x00b8		
# modified by Joerg Jenderek
>1	lelong		!0x21cd4cff	COM executable for DOS
# http://syslinux.zytor.com/comboot.php
# (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
0	uleshort&0xc0ff	0xc0b8		
>1	lelong		0x21cd4cff	COM executable (32-bit COMBOOT)
# 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.
0       string/b	\xb8\xfe\x4c\xcd\x21	COM executable (COM32R)
# start with assembler instructions mov eax,21cd4cfeh
0	uleshort&0xc0ff	0xc0b8		
>1	lelong		0x21cd4cfe	COM executable (32-bit COMBOOT, relocatable)
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
#
0	string/b	\376\067\0\043			Microsoft Office Document
!:mime	application/msword
0	string/b	\333\245-\0\0\0			Microsoft Office Document
!:mime	application/msword
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
#
0	belong	0x00001a00	Lotus 1-2-3
!:mime	application/x-123
>4	belong	0x00100400	wk3 document data
>4	belong	0x02100400	wk4 document data
>4	belong	0x07800100	fm3 or fmb document data
>4	belong	0x07800000	fm3 or fmb document data
#
0	belong	0x00000200	Lotus 1-2-3
!:mime	application/x-123
>4	belong	0x06040600	wk1 document data
>4	belong	0x06800200	fmt document data
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 Metafont .WMF
0	string/b	\327\315\306\232	ms-windows metafont .wmf
0	string/b	\002\000\011\000	ms-windows metafont .wmf
0	string/b	\001\000\011\000	ms-windows metafont .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
0   name    ico-dir
# not entirely accurate, the number of icons is part of the header
>0  byte    1   - 1 icon
>0  ubyte   >1  - %d icons
>2  byte    0   \b, 256x
>2  byte    !0  \b, %dx
>3  byte    0   \b256
>3  byte    !0  \b%d
>4  ubyte   !0  \b, %d colors

0   belong  0x00000100

>9  byte    0
>>0 byte    x           MS Windows icon resource
!:mime	image/x-icon
>>4 use     ico-dir
>9  ubyte   0xff
>>0 byte    x           MS Windows icon resource
!:mime	image/x-icon
>>4 use     ico-dir

# Windows non-animated cursors
0   name    cur-dir
# not entirely accurate, the number of icons is part of the header
>0  byte        1   - 1 icon
>0  ubyte       >1  - %d icons
>2  byte        0   \b, 256x
>2  byte        !0  \b, %dx
>3  byte        0   \b256
>3  byte        !0  \b%d
>6  uleshort    x   \b, hotspot @%dx
>8  uleshort    x   \b%d

0   belong  0x00000200
>9  byte    0
>>0 byte    x           MS Windows cursor resource
!:mime image/x-cur
>>4 use     cur-dir
>9  ubyte   0xff
>>0 byte    x           MS Windows cursor resource
!:mime image/x-cur
>>4 use     cur-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)


##### put in Either Magic/font or Magic/news
# Acroread or something	 files wrongly identified as G3	 .pfm
# these have the form \000 \001 any? \002 \000 \000
# or \000 \001 any? \022 \000 \000
0	belong&0xffff00ff	0x00010012	PFM data
>4	string			\000\000
>6	string			>\060		- %s

0	belong&0xffff00ff	0x00010002	PFM data
>4	string			\000\000
>6	string			>\060		- %s
#0	string	\000\001 pfm?
#>3	string	\022\000\000Copyright\	yes
#>3	string	\002\000\000Copyright\	yes
#>3	string	>\0	oops, not a font file. Cancel that.
#it clashes with ttf files so put it lower down.

# 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
>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	leshort		0x223e9f78	TNEF
!:mime	application/vnd.ms-tnef

# 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\001\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)
# Microsoft Cabinet files
0	string/b	MSCF\0\0\0\0	Microsoft Cabinet archive data
!:mime application/vnd.ms-cab-compressed
>8	lelong		x		\b, %u bytes
>28	leshort		1		\b, 1 file
>28	leshort		>1		\b, %u files

# 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

# From: Alex Beregszaszi <alex@fsn.hu>
0	string/b	COWD		VMWare3
>4	byte	3		disk image
>>32	lelong	x		(%d/
>>36	lelong	x		\b%d/
>>40	lelong	x		\b%d)
>4	byte	2		undoable disk image
>>32	string	>\0		(%s)

0	string/b	VMDK		 VMware4 disk image
0	string/b	KDMV		 VMware4 disk image

#--------------------------------------------------------------------
# Qemu Emulator Images
# Lines written by Friedrich Schwittay (f.schwittay@yousable.de)
# Updated by Adam Buchbinder (adam.buchbinder@gmail.com)
# Made by reading sources, reading documentation, and doing trial and error
# on existing QCOW files
0	string/b	QFI\xFB	QEMU QCOW Image

# Uncomment the following line to display Magic (only used for debugging
# this magic number)
#>0	string/b	x	, Magic: %s

# There are currently 2 Versions: "1" and "2".
# http://www.gnome.org/~markmc/qcow-image-format-version-1.html
>4	belong	1	(v1)

# Using the existence of the Backing File Offset to determine whether
# to read Backing File Information
>>12	belong	 >0	 \b, has backing file (
# Note that this isn't a null-terminated string; the length is actually
# (16.L). Assuming a null-terminated string happens to work usually, but it
# may spew junk until it reaches a \0 in some cases.
>>>(12.L)	 string >\0	\bpath %s

# Modification time of the Backing File
# Really useful if you want to know if your backing
# file is still usable together with this image
>>>>20	bedate >0	\b, mtime %s)
>>>>20	default x	\b)

# Size is stored in bytes in a big-endian u64.
>>24	bequad	x	 \b, %lld bytes

# 1 for AES encryption, 0 for none.
>>36	belong	1	\b, AES-encrypted

# http://www.gnome.org/~markmc/qcow-image-format.html
>4	belong	2	(v2)
# Using the existence of the Backing File Offset to determine whether
# to read Backing File Information
>>8	bequad  >0	 \b, has backing file
# Note that this isn't a null-terminated string; the length is actually
# (16.L). Assuming a null-terminated string happens to work usually, but it
# may spew junk until it reaches a \0 in some cases. Also, since there's no
# .Q modifier, we just use the bottom four bytes as an offset. Note that if
# the file is over 4G, and the backing file path is stored after the first 4G,
# the wrong filename will be printed. (This should be (8.Q), when that syntax
# is introduced.)
>>>(12.L)	 string >\0	(path %s)
>>24	bequad	x	\b, %lld bytes
>>32	belong	1	\b, AES-encrypted

>4	belong	3	(v3)
# Using the existence of the Backing File Offset to determine whether
# to read Backing File Information
>>8	bequad  >0	 \b, has backing file
# Note that this isn't a null-terminated string; the length is actually
# (16.L). Assuming a null-terminated string happens to work usually, but it
# may spew junk until it reaches a \0 in some cases. Also, since there's no
# .Q modifier, we just use the bottom four bytes as an offset. Note that if
# the file is over 4G, and the backing file path is stored after the first 4G,
# the wrong filename will be printed. (This should be (8.Q), when that syntax
# is introduced.)
>>>(12.L)	 string >\0	(path %s)
>>24	bequad	x	\b, %lld bytes
>>32	belong	1	\b, AES-encrypted

>4	default x	(unknown version)

0	string/b	QEVM		QEMU suspend to disk image

# QEMU QED Image
# http://wiki.qemu.org/Features/QED/Specification
0	string/b	QED\0		QEMU QED Image

# VDI Image
64	string/b	\x7f\x10\xda\xbe	VDI Image
>68	string/b	\x01\x00\x01\x00	version 1.1
>0	string		>\0			(%s)
>368	lequad		x			 \b, %lld bytes

0	string/b	Bochs\ Virtual\ HD\ Image	Bochs disk image,
>32	string	x				type %s,
>48	string	x				subtype %s

0	lelong	0x02468ace			Bochs Sparse disk image

# from http://filext.com by Derek M Jones <derek@knosof.co.uk>
# False positive with PPT (also currently this string is too long)
#0	string/b	\xD0\xCF\x11\xE0\xA1\xB1\x1A\xE1\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x3E\x00\x03\x00\xFE\xFF\x09\x00\x06	Microsoft Installer
0	string/b	\320\317\021\340\241\261\032\341	Microsoft Office Document
#>48	byte	0x1B					Excel Document
#!:mime application/vnd.ms-excel
>546	string	bjbj			Microsoft Word Document
!:mime	application/msword
>546	string	jbjb			Microsoft Word Document
!:mime	application/msword

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 DirectDraw Surface
# URL:	http://msdn.microsoft.com/library/default.asp?url=/library/en-us/directx9_c/directx/graphics/reference/DDSFileReference/ddsfileformat.asp
# From: Morten Hustveit <morten@debian.org>
0	string/b	DDS\040\174\000\000\000 Microsoft DirectDraw Surface (DDS),
>16	lelong	>0			%hd x
>12	lelong	>0			%hd,
>84	string	x			%.4s

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

# 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