#------------------------------------------------------------------------------
# $File: msdos,v 1.158 2022/09/07 11:17:31 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
!:ext bat
>1 string/cW echo\ off DOS batch file text
!:mime text/x-msdos-batch
!:ext bat
>1 string/cW rem DOS batch file text
!:mime text/x-msdos-batch
!:ext bat
>1 string/cW set\ DOS batch file text
!:mime text/x-msdos-batch
!:ext bat
# 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 extracted 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
# Windows and later versions of DOS will allow .EXEs to be named with a .COM
# extension, mostly for compatibility's sake.
# URL: https://en.wikipedia.org/wiki/Personal_NetWare#VLM
# Reference: https://mark0.net/download/triddefs_xml.7z/defs/e/exe-vlm-msg.trid.xml
!:ext exe/com/vlm
# 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)
# 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 %#x
>>(0x3c.l+22) leshort&0x2000 >0 (DLL)
>>(0x3c.l+92) leshort 1
# Native PEs include ntoskrnl.exe, hal.dll, smss.exe, autochk.exe, and all the
# drivers in Windows/System32/drivers/*.sys.
>>>(0x3c.l+22) leshort&0x2000 >0 (native)
!:ext dll/sys
>>>(0x3c.l+22) leshort&0x2000 0 (native)
!:ext exe/sys
>>(0x3c.l+92) leshort 2
>>>(0x3c.l+22) leshort&0x2000 >0 (GUI)
# These could probably be at least partially distinguished from one another by
# looking for specific exported functions.
# CPL: Control Panel item
# TLB: Type library
# OCX: OLE/ActiveX control
# ACM: Audio compression manager codec
# AX: DirectShow source filter
# IME: Input method editor
!:ext dll/cpl/tlb/ocx/acm/ax/ime
>>>(0x3c.l+22) leshort&0x2000 0 (GUI)
# Screen savers typically include code from the scrnsave.lib static library, but
# that's not guaranteed.
!:ext exe/scr
>>(0x3c.l+92) leshort 3
>>>(0x3c.l+22) leshort&0x2000 >0 (console)
!:ext dll/cpl/tlb/ocx/acm/ax/ime
>>>(0x3c.l+22) leshort&0x2000 0 (console)
!:ext exe/com
# https://docs.microsoft.com/en-us/windows/win32/debug/pe-format
>>(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 %#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 0x1a3 Hitachi SH3 DSP
>>(0x3c.l+4) leshort 0x1a8 Hitachi SH5
>>(0x3c.l+4) leshort 0x169 MIPS WCE v2
>>(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 0x1d3 Matsushita AM33
>>(0x3c.l+4) leshort 0x1f0 PowerPC
>>(0x3c.l+4) leshort 0x1f1 PowerPC with FPU
>>(0x3c.l+4) leshort 0x1f2 PowerPC (big-endian)
>>(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 0x5032 RISC-V 32-bit
>>(0x3c.l+4) leshort 0x5064 RISC-V 64-bit
>>(0x3c.l+4) leshort 0x5128 RISC-V 128-bit
>>(0x3c.l+4) leshort 0x9041 Mitsubishi M32R
>>(0x3c.l+4) leshort 0x8664 x86-64
>>(0x3c.l+4) leshort 0xaa64 Aarch64
>>(0x3c.l+4) leshort 0xc0ee MSIL
>>(0x3c.l+4) default x Unknown processor type
>>>&0 leshort x %#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
# If the relocation table is 0x40 or more bytes into the file, it's definitely
# not a DOS EXE.
>0x18 leshort >0x3f
# 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&0x8000 0x8000 (DLL or font)
# DRV: Driver
# 3GR: Grabber device driver
# CPL: Control Panel Item
# VBX: Visual Basic Extension
# FON: Bitmap font
# FOT: Font resource file
!:ext dll/drv/3gr/cpl/vbx/fon/fot
>>>(0x3c.l+0x0c) leshort&0x8000 0 (EXE)
!:ext exe/scr
>>>&(&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)
# VXD: VxD for Windows 95/98/Me
# 386: VxD for Windows 2.10, 3.0, 3.1x
# PDR: Port driver
# MPD: Miniport driver (?)
!:ext vxd/386/pdr/mpd
>>>(&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
!:ext exe/com
# 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 unusual, 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
# Summary: OS/2 LX Library and device driver (no DOS stub)
# From: Joerg Jenderek
# URL: http://en.wikipedia.org/wiki/EXE
# Reference: http://www.textfiles.com/programming/FORMATS/lxexe.txt
# https://github.com/open-watcom/open-watcom-v2/blob/master/bld/watcom/h/exeflat.h
# Note: by dll-os2-no-dos-stub.trid.xml called "OS/2 Dynamic Link Library (no DOS stub)"
# TODO: unify with DOS stub variant (MZ magic)
0 string/b LX
>2 ushort =0
>>0 use lx-executable
# no examples found for big endian variant
>2 ushort =0x0101
>>0 use \^lx-executable
0 name lx-executable
# similar looking like variant with MS-DOS stub (MZ magic): "MS-DOS executable, LX"
#>0x00 uleshort x executable,
# signature OSF_FLAT_LX_SIGNATURE~0x584C~LX OSF_FLAT_SIGNATURE~0x454C~LE
>0x00 uleshort =0x584c LX
>0x00 uleshort =0x454C LE
>0x00 uleshort x executable
#!:mime application/x-msdownload
!:mime application/x-lx-executable
# byte order: 00h~little-endian non-zero=1~big-endian
#>0x02 ubyte =0 (little-endian)
>0x02 ubyte !0 (big-endian)
# FOR DEBUGGING!
# word order: 00h~little-endian non-zero=1~big-endian
#>0x03 ubyte =0 \b, little-endian word order
#>0x03 ubyte !0 \b, big-endian word order
# cpu_type; CPU type like: 1~286 2~386 3~486 4 20h~i860 21h~Intel N11 40h~MIPS R2000,R3000 41h~MIPS R6000 42h~MIPS R4000
#>0x08 uleshort x \b, CPU %u
# os_type; target operating system like: 0~unknown 1~OS/2 2~Windows 3~DOS 4.x 4~Windows 386
#>0x0A leshort x \b, OS %u
# flags; module type flags
#>0x10 ulelong x \b, FLAGS %#8.8x
# 00000002h ~Reserved for system use
#>0x10 ulelong &0x00000002 \b, 2h reserved
# OSF_INIT_INSTANCE=00000004h ~Per-Process Library Initialization; setting this bit for EXE file is invalid
#>0x10 ulelong &0x00000004 \b, per-process library Initialization
# OSF_INTERNAL_FIXUPS_DONE=00000010h ~Internal fixups for the module have been applied
#>0x10 ulelong &0x00000010 \b, int. fixup
# OSF_EXTERNAL_FIXUPS_DONE=00000020h ~External fixups for the module have been applied
#>0x10 ulelong &0x00000020 \b, ext. fixup
# OSF_NOT_PM_COMPATIBLE=00000100h ~Incompatible with PM windowing
#>0x10 ulelong&0x00000100 =0x00000100 \b, incompatible with PM windowing
# OSF_PM_COMPATIBLE=00000200h ~Compatible with PM windowing
#>0x10 ulelong&0x00000200 =0x00000200 \b, compatible with PM windowing
# bit 17; device driver
#>0x10 ulelong&0x00020000 >0 \b, device driver
# Per-process Library Termination; setting this bit for EXE file is invalid
#>0x10 ulelong&0x40000000 =0x40000000 \b, per-process library termination
>0x0a leshort 1 for OS/2
# no example found
>0x0a leshort 3 for DOS
# http://www.ctyme.com/intr/rb-2939.htm#Table1610
# library by module type mask 00038000h (bits 15-17);
# 0h ~exectable Program module
>0x10 ulelong&0x00038000 =0x00000000 (program)
#!:ext exe
# OSF_IS_DLL=8000h ~Library module (DLL)
>0x10 ulelong&0x00038000 >0x00000000
# OSF_PHYS_DEVICE=00020000h ~device driver
>>0x10 ulelong&0x00020000 >0 (device driver)
!:ext sys
# if not device driver it is library (DLL)
>>0x10 ulelong&0x00020000 =0 (library)
!:ext dll
# bits 8-10; OSF_PM_APP=300h in flags ~Uses PM windowing API; either it is GUI or console
>0x10 ulelong&0x00000300 =0x00000300 (GUI)
>0x10 ulelong&0x00000300 !0x00000300 (console)
# CPU type
>0x08 uleshort 1 i80286
# all inspected examples
>0x08 uleshort 2 i80386
>0x08 uleshort 3 i80486
>0x08 uleshort 4 i80586
# 21h Intel "N11" or compatible
# 40h MIPS Mark I ( R2000, R3000) or compatible
# 41h MIPS Mark II ( R6000 ) or compatible
# 42h MIPS Mark III ( R4000 ) or compatible
# added by Joerg Jenderek of https://www.freedos.org/software/?prog=kc
# and https://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 %#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 %#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,Aug 2020
# URL: http://fileformats.archiveteam.org/wiki/DOS_device_driver
# Reference: http://www.delorie.com/djgpp/doc/rbinter/it/46/16.html
# https://amaus.net/static/S100/IBM/software/DOS/DOS%20techref/CHAPTER.009
0 ulequad&0x07a0ffffffff 0xffffffff
# skip OS/2 INI ./os2
>4 ubelong !0x14000000
>>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
# and IBM Token-Ring adapter IBMTOK.DOS. Why and when DOS instead SYS is used?
# PROTMAN.DOS ELNKPL.DOS
!:ext sys/dev/bin/dos
# 1 space char after "UPX compressed" to get phrase like "UPX compressed character device"
>40 search/7 UPX! \bUPX compressed
# DOS device driver attributes
>4 uleshort&0x8000 0x0000 \bblock device driver
# character device
>4 uleshort&0x8000 0x8000 \b
# 1 space char after "clock" to get phrase like "clock character device driver CLOCK$"
>>4 uleshort&0x0008 0x0008 \bclock
# fast video output by int 29h
# 1 space char after "fast" to get phrase like "fast standard input/output character device driver"
>>4 uleshort&0x0010 0x0010 \bfast
# standard input/output device
# 1 space char after "standard" to get phrase like "standard input/output character device driver"
>>4 uleshort&0x0003 >0 \bstandard
>>>4 uleshort&0x0001 0x0001 \binput
>>>4 uleshort&0x0003 0x0003 \b/
# 1 space char after "output" to get phrase like "input/output character device driver"
>>>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
# 1 space char before device driver name to get phrase like "device driver PROTMAN$"
>>>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)
>0 ulelong !0xffffffff with pointer %#x
# 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
# https://www.uwe-sieber.de/files/cfg_echo.zip
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
# 3Com EtherLink 3C501 CID\SERVER\IBMLS\IBM500D1\DLSNETDR.ZIP\ELNK.DOS
0 ulequad 0x027ac0c0ffffffff
>0 use msdos-driver
# IBM Streamer CID\SERVER\IBMLS\IBM500D1\DLSNETDR.ZIP\IBMMPC.DOS
0 ulequad 0x00228880ffffffff
>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
>>>>0 use msdos-com
# 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
0 name msdos-com
# URL: http://fileformats.archiveteam.org/wiki/DOS_executable_(.com)
>0 byte x DOS executable (
# DOS execuable with JuMP 16-bit instruction
>0 byte =0xE9
# check for probably nil padding til offset 64 of Lotus driver name
>>56 quad =0
# check for "long" alpabetical Lotus driver name like:
# Diablo "COMPAQ Text Display" "IBM Monochrome Display" "Plantronics ColorPlus"
>>>24 regex =^[A-Z][A-Za-z\040]{5,21} \bLotus driver) %s
!:mime application/x-dosexec
# like: CPQ0TD.DRV IBM0MONO.DRV (Lotus 123 10a) SDIAB4.DRV SPL0CPLS.DRV (Lotus Symphony 2)
!:ext drv
# COM with nils like MODE.COM IBMDOS.COM (pcdos 3.31 ru Compaq) RSSTUB.COM (PC-DOS 2000 de) ACCESS.COM (Lotus Symphony 1)
>>>24 default x \bCOM)
!:mime application/x-dosexec
!:ext com
# DOS excutable with JuMP 16-bit and without nil padding
>>56 quad !0
# https://wiki.syslinux.org/wiki/index.php?title=Doc/comboot
# TODO: HOWTO distinguish COMboot from pure DOS executables?
# look for unreliable Syslinux specific api call INTerrupt 22h for 16-bit COMBOOT program
>>>1 search/0xc088 \xcd\x22 \bCOM or COMBOOT 16-bit)
!:mime application/x-dosexec
# like: sbm.cbt command.com (Windows XP) UNI2ASCI.COM (FreeDOS 1.2)
!:ext com/cbt
>>>1 default x \bCOM)
!:mime application/x-dosexec
!:ext com
# DOS executable without JuMP 16-bit instruction
>0 byte !0xE9
# SCREATE.SYS https://en.wikipedia.org/wiki/Stac_Electronics
>>10 string =?STACVOL \bSCREATE.SYS)
!:mime application/x-dosexec
!:ext sys
# COM executable without JuMP 16-bit instruction and not SCREATE.SYS
>>10 string !?STACVOL \bCOM)
!:mime application/x-dosexec
!:ext 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 \ $LHarc \b, LHarc self-extracting archive
>0x20e string SFX\ by\ LARC \b, LARC self-extracting archive
# like: E30ODI.COM MADGEODI.COM UNI2ASCI.COM RECOVER.COM (DOS 2) COMMAND.COM (DOS 2)
>1 search/0xc088 \xcd\x22 \b, maybe with interrupt 22h
>0 ubelong x \b, start instruction %#8.8x
# show more instructions but not in samples like: rem.com (DJGPP)
>4 ubelong x %8.8x
# JMP 8bit
0 byte 0xeb
# byte 0xeb conflicts with magic leshort 0xn2eb of "SYMMETRY i386" handled by ./sequent
# allow forward jumps only
>1 byte >-1
# that offset must be accessible
# with hexadecimal values like: 0e 2e 50 8c 8d ba bc bd be e8 fb fc
>>(1.b+2) byte x
# if look like COM executable with x86 boot signature then this
# implies FAT volume with x86 real mode code already handled by ./filesystems
#
# No x86 boot signature implies often DOS executable
# check for unrealistic high number of FATs. Then it is an unusual disk image or often a DOS executable
# like: FIXBIOS.COM (50 bytes)
>>>16 ubyte >3
# https://www.drivedroid.io/
# skip MBR disk image drivedroid.img version 12 July 2013 by start message
>>>>2 string !DriveDroid
# ftp://old-dos.ru/OSCollect/OS/MS-DOS/Final Releases/
# skip unusual floppy image disk1.img of MS-DOS 1.25 (Corona Data Systems OEM)
# by check for characteristic message text near the beginning
>>>>>15 string !Non\040System\040disk
# "ftp://old-dos.ru/OSCollect/OS/BeOS/BeOS 4.0.rar"
# skip BeOS 4 bootfloppy.img done as "Linux kernel x86 boot executable" by ./linux
# by check for characteristic message text near the beginning
>>>>>>6 string !read\040error\015
# https://github.com/ventoy/Ventoy/releases/download/v1.0.78/ventoy-1.0.78-windows.zip
# skip ventoy 1.0.78 boot_hybrid.img
>>>>>>>24 string !\220\220\353I$\022\017
# "ftp://old-dos.ru/OSCollect/OS/MS-DOS/Final Releases/PC-DOS 1.0 (5.25).rar"
# skip unusual floppy image PCDOS100.IMG of DOS 1.0
# by check for characteristic message text near the beginning
>>>>>>>>9 string !7-May-81
# "ftp://old-dos.ru/OSCollect/OS/BeOS/BeOS 5.0 Personal (BA).rar"
# skip BeOS 5 floppy_1.44.00.ima done as "DOS/MBR boot sector" by ./filesystems
# by check for characteristic message near the beginning
>>>>>>>>>3 string !\370sdfS\270
# like: FIXBIOS.COM (50 bytes)
>>>>>>>>>>0 use msdos-com
# check for unrealistic low number of FATs. Then it is an unusual FAT disk image or often a DOS executable
# like: DEVICE.COM INSTALL.COM (GAG 4.10) WORD.COM (Word 1.15)
>>>16 ubyte =0
# if low FATs with x86 boot signature it can be unusual disk image like: boot.img (Ventoy 1.0.27) geodspms.img (Syslinux)
>>>>0x1FE leshort =0xAA55
>>>>0x1FE default x
# https://thestarman.pcministry.com/tool/hxd/dimtut.htm
# skip unusual floppy image TK-DOS11.img IBMDOS11.img of IBM DOS 1.10
# by check for characteristic bootloader names near end of boot sector
>>>>>395 string !ibmbio\040\040com
>>>>>>0 use msdos-com
# 8-bit jump with valid number of FAT implies FAT volume already handled by ./filesystems
# like: balder.img
>>>16 default x
# skip disk images with boot signature at end of 1st sector
# like: TDSK-64b.img
>>>>(11.s-2) uleshort !0xAA55
# skip unusual floppy image without boot signature like 360k-256.img (mtools 4.0.18)
# by check for characteristic file system type text for FAT (12 bit or 16 bit)
>>>>>54 string !FAT
# "ftp://old-dos.ru/OSCollect/OS/MS-DOS/Final Releases/Microsoft MS-DOS 3.31 (Compaq OEM) (3.5).rar"
# skip unusual floppy image Disk4.img without boot signature and file system type text
# by check for characteristic OEM-ID text
>>>>>>3 string !COMPAQ\040\040
# no such DOS COM executables found
>>>>>>>0 use msdos-com
# JMP 16bit
0 byte 0xe9
# 16-bit offset; for DEBUGGING!; can be negative like: USBDRIVE.COM
#>1 leshort x \b, OFFSET %d
# forward jumps
>1 leshort >-1
# that offset must be accessible
# with hexadecimal values like: 06 1e 0e 2e 60 8c 8d b4 ba be e8 fc
>>(1.s+3) byte x
# check for unrealistic high number of FATs. Then it is not a disk image and it is a DOS executable
# like: CALLVER.COM CPUCACHE.COM K437_EUR.COM SHSUCDX.COM UMBFILL.COM (183 bytes)
>>>16 ubyte >3
>>>>0 use msdos-com
# check for unrealistic low number of FATs. Then it is not a disk image and it is a DOS executable
# like: GAG.COM DRMOUSE.COM NDN.COM CPQ0TD.DRV
>>>16 ubyte =0
>>>>0 use msdos-com
# maybe disc image with valid number of FATs or DOS executable
# like: IPXODI.COM PERUSE.COM TASKID.COM
>>>16 default x
# invalid low media descriptor. Then it is not a disk image and it is a DOS executable
>>>>21 ubyte <0xE5
>>>>>0 use msdos-com
# valid media descriptor. Then it is maybe disk image or DOS executable
>>>>21 ubyte >0xE4
# invalid sectorsize not a power of 2 from 32-32768. Then it is not a disk image and it must be DOS executable
# like: LEARN.COM (Word 1.15)
>>>>>11 uleshort&0x001f !0
>>>>>>0 use msdos-com
# negative offset, must not lead into PSP
# like: BASICA.COM (PC dos 3.20) FORMAT.COM SMC8100.COM WORD.COM (word4)
# HIDSUPT1.COM USBDRIVE.COM USBSUPT1.COM USBUHCI.COM (FreeDOS USBDOS)
>1 leshort <-259
# that offset must be accessible
# add 10000h to jump at end of 64 KiB segment, add 1 for jump instruction and 2 for 16-bit offset
>>(1,s+65539) byte x
# after jump next instruction for DEBUGGING!
#>>>&-1 ubelong x \b, NEXT instruction %#8.8x
>>>0 use msdos-com
# updated by Joerg Jenderek at Oct 2008,2015,2022
# 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
# https://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
# https://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)
>>1 default x
# look for interrupt instruction like in rem.com (DJGPP) LOADER.COM (DR-DOS 7.x)
>>>3 search/118 \xCD
# FOR DEBUGGING; possible hexadecimal interupt number like: 10~BANNER.COM 13~bcdw_cl.com 15~poweroff.com (Syslinux)
# 1A~BERNDPCI.COM 20~SETENHKB.COM 21~mostly 22~gfxboot.com (Syslinux) 2F~SHUTDOWN.COM (GEMSYS)
#>>>>&0 ubyte x \b, INTERUPT %#x
# few examples with interrupt 0x13 instruction
>>>>&0 ubyte =0x13
# FOR DEBUGGING!
#>>>>>3 ubequad x \b, 2nd INSTRUCTION %#16.16llx
# skip Gpt.com Mbr.com (edk2-UDK2018 bootsector) described as "DOS/MBR boot sector" by ./filesystems
# by check for assembler instructions: mov es,ax ; mov ax,07c0h ; mov ds,ax
>>>>>3 ubequad !0x8ec0b8c0078ed88d
# few COM exectables with interrupt 0x13 instruction like: Bootable CD Wizard executables bcdw_cl.com fdemuoff.com
# http://bootcd.narod.ru/bcdw150z_en.zip
>>>>>>0 use msdos-com
# few examples with interrupt 0x16 instruction like flashimg.img
>>>>&0 ubyte =0x16
# skip Syslinux 3.71 flashimg.img done as "DOS/MBR boot sector" by ./filesystems
# by check for assembler instructions: cmp ax 0xE4E4 (magic); jnz
>>>>>8 ubelong !0x3DE4E475
# no DOS executable with interrupt 0x16 found
>>>>>>0 use msdos-com
# most examples with interrupt instruction unequal 0x13 and 0x16
>>>>&0 default x
#>>>>>&-1 ubyte x \b, INTERUPT %#x
# like: LOADER.COM SETENHKB.COM banner.com copybs.com gif2raw.com poweroff.com rem.com
>>>>>0 use msdos-com
# few COM executables without interupt instruction like RESTART.COM (DOS 7.10) REBOOT.COM
# or some EUC-KR text files or one Ulead Imaginfo thumbnail
>>>3 default x
# FOR DEBUGGING; 2nd instruction like 0x50 (RESTART.COM) 0x8e (REBOOT.COM)
# or random like: 0x0 (IMAGINFO.PE3 sky_snow) 0xb1 (euckr_.txt)
#>>>>3 ubyte x \b, 2nd INSTRUCTION %#x
# skip 1 Ulead Imaginfo thumbnail (IMAGINFO.PE3 sky_snow)
# inside SAMPLES/TEXTURES/SKY_SNOW
# from https://archive.org/download/PI3CANON/PI3CANON.iso
>>>>3 ubyte !0x0
# skip some EUC-KR text files like: euckr_falsepositive.txt
# https://bugs.astron.com/view.php?id=186
>>>>>3 ubyte !0xb1
# like: RESTART.COM (DOS 7.10) REBOOT.COM
>>>>>>0 use msdos-com
# URL: https://en.wikipedia.org/wiki/UPX
# Reference: https://github.com/upx/upx/archive/v3.96.zip/upx-3.96/
# src/stub/src/i086-dos16.com.S
# Update: Joerg Jenderek
# assembler instructions: cmp sp, offset sp_limit
0 string/b \x81\xfc
#>2 uleshort x \b, sp_limit=%#x
# assembler instructions: jump above +2; int 0x20; mov cx, offset bytes_to_copy
>4 string \x77\x02\xcd\x20\xb9
#>9 uleshort x \b, [bytes_to_copy]=%#x
# at different offsets assembler instructions: push di; jump decomp_start_n2b
>0x1e search/3 \x57\xe9
#>>&0 uleshort x \b, decomp_start_n2b=%#x
# src/stub/src/include/header.S; UPX_MAGIC_LE32
>>&2 string UPX! FREE-DOS executable (COM), UPX
!:mime application/x-dosexec
# UPX compressed *.CPI; See ./fonts
>>>&21 string =FONT compressed DOS code page font
!:ext cpx
>>>&21 string !FONT compressed
!:ext com
# compressed size?
#>>>&14 uleshort+152 x \b, %u bytes
# uncompressed len
>>>&12 uleshort x \b, uncompressed %u bytes
252 string Must\ have\ DOS\ version DR-DOS executable (COM)
!:mime application/x-dosexec
!:ext com
# 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
!:mime application/x-dosexec
!:ext com
#DELTREE.cOM DELTREE2.cOM
4 string \xcd\x21 COM executable for DOS
!:mime application/x-dosexec
!:ext com
#IFMEMDSK.cOM ASSIGN.cOM COMP.cOM
5 string \xcd\x21 COM executable for DOS
!:mime application/x-dosexec
!:ext com
#DELTMP.COm HASFAT32.cOM
7 string \xcd\x21
>0 byte !0xb8 COM executable for DOS
!:mime application/x-dosexec
!:ext com
#COMP.cOM MORE.COm
10 string \xcd\x21
>5 string !\xcd\x21 COM executable for DOS
!:mime application/x-dosexec
!:ext com
#comecho.com
13 string \xcd\x21 COM executable for DOS
!:mime application/x-dosexec
!:ext com
#HELP.COm EDIT.coM
18 string \xcd\x21
# not printable before it?
>17 byte >32
>>17 byte <126
>>17 default x COM executable for MS-DOS
!:mime application/x-dosexec
!:ext com
#NWRPLTRM.COm
23 string \xcd\x21 COM executable for MS-DOS
!:mime application/x-dosexec
!:ext com
#LOADFIX.cOm LOADFIX.cOm
30 string \xcd\x21 COM executable for MS-DOS
!:mime application/x-dosexec
!:ext com
#syslinux.com 3.11
70 string \xcd\x21 COM executable for DOS
!:mime application/x-dosexec
!:ext com
# 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
!:mime application/x-dosexec
!:ext com
0x6 search/0xa \xfc\x57\xf3\xa4\xc3 COM executable for DOS
!:mime application/x-dosexec
!:ext com
>0x18 search/0x10 \x50\xa4\xff\xd5\x73 \b, aPack compressed
0x3c string W\ Collis\0\0 COM executable for MS-DOS, Compack compressed
!:mime application/x-dosexec
!:ext com
# 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
#
# Update: Joerg Jenderek
# URL: http://fileformats.archiveteam.org/wiki/DOC
# Reference: https://web.archive.org/web/20170206041048/
# http://www.msxnet.org/word2rtf/formats/ffh-dosword5
# wIdent+dty
0 belong 0x31be0000
# skip droid skeleton like x-fmt-274-signature-id-488.doc
>128 ubyte >0 Microsoft
>>96 uleshort =0 Word
!:mime application/msword
!:apple MSWDWDBN
# DCX is used in the Unix version.
!:ext doc/dcx
>>>0x6E ulequad =0 1.0-4.0
>>>0x6E ulequad !0 5.0-6.0
>>>0x6E ulequad x (DOS) Document
# https://web.archive.org/web/20130831064118/http://msxnet.org/word2rtf/formats/write.txt
>>96 uleshort !0 Write 3.0 (Windows) Document
!:mime application/x-mswrite
!:apple MSWDWDBN
# sometimes also doc like in splitter.doc srchtest.doc
!:ext wri/doc
# wTool must be 0125400 octal
#>>4 uleshort !0xAB00 \b, wTool %o
# reserved; must be zero
#>>6 ulelong !0 \b, reserved %u
# block pointer to the block containing optional file manager information
#>>0x1C uleshort x \b, at %#x info block
# jump to File manager information block
>>(0x1C.s*128) uleshort x
# test for valid information start; maybe also 0012h
>>>&-2 uleshort =0x0014
# Document ASCIIZ name
>>>>&0x12 string x %s
# author name
>>>>>&1 string x \b, author %s
# reviser name
>>>>>>&1 string x \b, reviser %s
# keywords
>>>>>>>&1 string x \b, keywords %s
# comment
>>>>>>>>&1 string x \b, comment %s
# version number
>>>>>>>>>&1 string x \b, version %s
# date of last change MM/DD/YY
>>>>>>>>>>&1 string x \b, %-.8s
# creation date MM/DD/YY
>>>>>>>>>>&9 string x created %-.8s
# file name of print format like NORMAL.STY
>>0x1E string >0 \b, formatted by %-.66s
# count of pages in whole file for write variant; maybe some times wrong
>>96 uleshort >0 \b, %u pages
# name of the printer driver like HPLASMS
>>0x62 string >0 \b, %-.8s printer
# number of blocks used in the file; seems to be 0 for Word 4.0 and Write 3.0
>>0x6A uleshort >0 \b, %u blocks
# bit field for corrected text areas
#>>0x6C uleshort x \b, %#x bit field
# text of document; some times start with 4 non printable characters like CR LF
>>128 ubyte x \b,
>>>128 ubyte >0x1F
>>>>128 string x %s
>>>128 ubyte <0x20
>>>>129 ubyte >0x1F
>>>>>129 string x %s
>>>>129 ubyte <0x20
>>>>>130 ubyte >0x1F
>>>>>>130 string x %s
>>>>>130 ubyte <0x20
>>>>>>131 ubyte >0x1F
>>>>>>>131 string x %s
>>>>>>131 ubyte <0x20
>>>>>>>132 ubyte >0x1F
>>>>>>>>132 string x %s
>>>>>>>132 ubyte <0x20
>>>>>>>>133 ubyte >0x1F
>>>>>>>>>133 string x %s
#
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
#
0 string/b \xDB\xA5\x2D\x00 Microsoft WinWord 2.0 Document
!:mime application/msword
#
0 string/b \x09\x04\x06\x00\x00\x00\x10\x00 Microsoft Excel Worksheet
!:mime application/vnd.ms-excel
# https://www.macdisk.com/macsigen.php
!:apple XCELXLS4
!:ext xls
#
# 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 %#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 %#x
# flags
>>>>21 ubyte x \b, flags %#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 positive 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 %#x
# 2nd record for most worksheets describes cells range
>>>6 use lotus-cells
# 3rd 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
# 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
# https://www.iana.org/assignments/media-types/image/vnd.microsoft.icon
!: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 %#x
# PNG header (\x89PNG)
>(12.l) ubelong =0x89504e47
# 1 space char after "with" to get phrase "with PNG image" by magic in ./images
>>&-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 https://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
!:ext pif
#>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
# Norton Guide (.NG , .HLP) files added by Joerg Jenderek from source NG2HTML.C
# of http://www.davep.org/norton-guides/ng2h-105.tgz
# https://en.wikipedia.org/wiki/Norton_Guides
0 string NG\0\001
# only value 0x100 found at offset 2
>2 ulelong 0x00000100 Norton Guide
!:mime application/x-norton-guide
# often like NORTON.NG but some times like NC.HLP
!:ext ng/hlp
# Title[40]
>>8 string >\0 "%-.40s"
#>>6 uleshort x \b, MenuCount=%u
# szCredits[5][66]
>>48 string >\0 \b, %-.66s
>>114 string >\0 %-.66s
# URL: https://en.wikipedia.org/wiki/Norton_Commander
# Reference: http://mark0.net/download/triddefs_xml.7z/defs/m/msg-nc-eng.trid.xml
# From: Joerg Jenderek
# Note: Message file is used by executable with same main name.
# Only tested with version 5.50 (english) and 2.01 (Windows)
0 string Abort
# \0 or i
#>5 ubyte x %x
# skip ASCII Abort text by looking for error message like in NCVIEW.MSG
>6 search/7089 Non-DOS\ disk Norton Commander module message
!:mime application/x-norton-msg
!:ext msg
# URL: http://www.antonis.de/dos/dos-tuts/mpdostip/html/nwdostip.htm
# Reference: https://mark0.net/download/triddefs_xml.7z/defs/m/msg-netware-dos.trid.xml
# From: Joerg Jenderek
0 string DOS\ Client\ Message\ File: Novell DOS client message
#!:mime application/octet-stream
#!:mime application/x-novell-msg
!:ext msg
# look for second letter instead space character
>26 ubyte >0x20
# digit 1 or often main or program name like: IPXODI.COM TASKID pnwtrap DOSRqstr
>>25 ubyte !0x20 %c
>>>26 ubyte !0x20 \b%c
>>>>27 ubyte !0x20 \b%c
>>>>>28 ubyte !0x20 \b%c
>>>>>>29 ubyte !0x20 \b%c
>>>>>>>30 ubyte !0x20 \b%c
>>>>>>>>31 ubyte !0x20 \b%c
>>>>>>>>>32 ubyte !0x20 \b%c
>>>>>>>>>>33 ubyte !0x20 \b%c
>>>>>>>>>>>34 ubyte !0x20 \b%c
>>>>>>>>>>>>35 ubyte !0x20 \b%c
>>>>>>>>>>>>>36 ubyte !0x20 \b%c
# followed by string like: 0 v.10 V1.20
#
# followed by ,\040Tran
>28 search/14 ,\040Tran
# probably translated version string like: 0 v1.00
>>&0 string x \b, tran version %s
# followed by Ctrl-J Ctrl-Z
>>>&0 ubyte !0xa \b, terminated by %#2.2x
>>>>&0 ubyte x \b%2.2x
# Ctrl-Z
>0x65 ubyte !0x1A \b, at 0x65 %#x
# one
>0x66 ubyte !0x01 \b, at 0x66 %#x
# URL: https://en.wikipedia.org/wiki/NetWare
# Reference: http://mark0.net/download/triddefs_xml.7z/defs/d/dat-novell-msg.trid.xml
# ftp://ftp.iitb.ac.in/LDP/en/NLM-HOWTO/NLM-HOWTO-single.html
# From: Joerg Jenderek
0 string Novell\ Message\ Librarian\ Data\ File Novell message librarian data
#>35 string Version\ 1.00
#>49 string COPYRIGHT\ (c)\ 1985\ by\ Novell,\ Inc.
#>83 string \ \ All\ Rights\ Reserved
#!:mime application/octet-stream
#!:mime application/x-novell-msg
!:ext msg
#!:ext msg/dat
# 4DOS help (.HLP) files added by Joerg Jenderek from source TPHELP.PAS
# of https://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
!:mime application/vnd.ms-htmlhelp
!:ext chm
# 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
# URL: https://en.wikipedia.org/wiki/Windows_Desktop_Gadgets
# Reference: https://docs.microsoft.com/en-us/previous-versions/windows/desktop/sidebar/
# http://win10gadgets.com/download/273/ All_CPU_Meter1.zip/All_CPU_Meter_V4.7.3.gadget
>0x2c search/968/c gadget.xml \b, Windows Desktop Gadget
#!:mime application/vnd.ms-cab-compressed
# http://extension.nirsoft.net/gadget
!:mime application/x-windows-gadget
!:ext gadget
# 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, Packed and Go, Windows Desktop Gadget, 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://en.wikipedia.org/wiki/Microsoft_InfoPath
>>>&-1 string manifest.xsf \b, InfoPath Form Template
!:mime application/vnd.ms-cab-compressed
#!:mime application/vnd.ms-infopath
!:ext xsn
# 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
# https://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 character 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
# https://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
# URL: https://en.wikipedia.org/wiki/Microsoft_OneNote#File_format
# http://fileformats.archiveteam.org/wiki/OneNote
# Reference: https://mark0.net/download/triddefs_xml.7z/defs/o/onepkg.trid.xml
# 1st member name like: "Class Notes.one" "test-onenote.one" "Open Notebook.onetoc2" "Editor �ffnen.onetoc2"
>>>>>&0 string/c one \b, OneNote Package
!:mime application/msonenote
!:ext onepkg
>>>>>&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
# .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 %#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 %#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 %#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 %#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, %#x compression
# optional per-folder reserved area
#>8 ubequad x \b, abReserve %#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 %#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 %#x
# date stamp for file
#>10 uleshort x \b, date %#x
# time stamp for file
#>12 uleshort x \b, time %#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 %#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 %#x
0 string/b \224\246\056 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: https://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
# 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
# URL: http://fileformats.archiveteam.org/wiki/BACKUP_(MS-DOS)
# Reference: http://www.ibiblio.org/pub/micro/pc-stuff/freedos/files/dos/restore/brtecdoc.htm
# 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
#!:mime application/octet-stream
!: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
#!:mime application/octet-stream
# backup name is original filename
#!:ext doc/exe/rar/zip
#!: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.
# From: Joerg Jenderek
# URL: http://fileformats.archiveteam.org/wiki/MS-DOS_date/time
# Reference: https://docs.microsoft.com/en-us/windows/win32/api/winbase/nf-winbase-dosdatetimetofiletime
# Note: DOS date+time format is different from formats such as Unix epoch
# bit encoded; uses year values relative to 1980 and 2 second precision
0 name dos-date
# HHHHHMMMMMMSSSSS bit encoded Hour (0-23) Minute (0-59) SecondPart (*2)
#>0 uleshort x RAW TIME [%#4.4x]
# hour part
#>0 uleshort/2048 x hour [%u]
# YYYYYMMMMDDDDD bit encoded YearPart (+1980) Month (1-12) Day (1-31)
#>2 uleshort x RAW DATE [%#4.4x]
# day part
>2 uleshort&0x001F x %u
#>2 uleshort/16 x MONTH PART [%#x]
# GRR: not working
#>2 uleshort/16 &0x000F MONTH [%u]
#>2 uleshort&0x01E0 x MONTH PART [%#4.4x]
>2 uleshort&0x01E0 =0x0020 jan
>2 uleshort&0x01E0 =0x0040 feb
>2 uleshort&0x01E0 =0x0060 mar
>2 uleshort&0x01E0 =0x0080 apr
>2 uleshort&0x01E0 =0x00A0 may
>2 uleshort&0x01E0 =0x00C0 jun
>2 uleshort&0x01E0 =0x00E0 jul
>2 uleshort&0x01E0 =0x0100 aug
>2 uleshort&0x01E0 =0x0120 sep
>2 uleshort&0x01E0 =0x0140 oct
>2 uleshort&0x01E0 =0x0160 nov
>2 uleshort&0x01E0 =0x0180 dec
# year part
>2 uleshort/512 x 1980+%u
#