2 #------------------------------------------------------------------------------
3 # $File: msdos,v 1.92 2014/03/14 18:47:29 christos Exp $
4 # msdos: file(1) magic for MS-DOS files
7 # .BAT files (Daniel Quinlan, quinlan@yggdrasil.com)
8 # updated by Joerg Jenderek at Oct 2008,Apr 2011
10 >1 string/cW \ echo\ off DOS batch file text
11 !:mime text/x-msdos-batch
12 >1 string/cW echo\ off DOS batch file text
13 !:mime text/x-msdos-batch
14 >1 string/cW rem DOS batch file text
15 !:mime text/x-msdos-batch
16 >1 string/cW set\ DOS batch file text
17 !:mime text/x-msdos-batch
20 # OS/2 batch files are REXX. the second regex is a bit generic, oh well
21 # the matched commands seem to be common in REXX and uncommon elsewhere
22 100 search/0xffff rxfuncadd
23 >100 regex/c =^[\ \t]{0,10}call[\ \t]{1,10}rxfunc OS/2 REXX batch file text
25 >100 regex/c =^[\ \t]{0,10}say\ ['"] OS/2 REXX batch file text
27 0 leshort 0x14c MS Windows COFF Intel 80386 object file
29 0 leshort 0x166 MS Windows COFF MIPS R4000 object file
31 0 leshort 0x184 MS Windows COFF Alpha object file
33 0 leshort 0x268 MS Windows COFF Motorola 68000 object file
35 0 leshort 0x1f0 MS Windows COFF PowerPC object file
37 0 leshort 0x290 MS Windows COFF PA-RISC object file
40 # Tests for various EXE types.
42 # Many of the compressed formats were extraced from IDARC 1.23 source code.
45 # All non-DOS EXE extensions have the relocation table more than 0x40 bytes into the file.
46 >0x18 leshort <0x40 MS-DOS executable
47 !:mime application/x-dosexec
48 # These traditional tests usually work but not always. When test quality support is
49 # implemented these can be turned on.
50 #>>0x18 leshort 0x1c (Borland compiler)
51 #>>0x18 leshort 0x1e (MS compiler)
53 # If the relocation table is 0x40 or more bytes into the file, it's definitely
58 >>(0x3c.l) string PE\0\0 PE
59 >>>(0x3c.l+24) leshort 0x010b \b32 executable
60 >>>(0x3c.l+24) leshort 0x020b \b32+ executable
61 >>>(0x3c.l+24) leshort 0x0107 ROM image
62 >>>(0x3c.l+24) default x Unknown PE signature
64 >>>(0x3c.l+22) leshort&0x2000 >0 (DLL)
65 >>>(0x3c.l+92) leshort 1 (native)
66 >>>(0x3c.l+92) leshort 2 (GUI)
67 >>>(0x3c.l+92) leshort 3 (console)
68 >>>(0x3c.l+92) leshort 7 (POSIX)
69 >>>(0x3c.l+92) leshort 9 (Windows CE)
70 >>>(0x3c.l+92) leshort 10 (EFI application)
71 >>>(0x3c.l+92) leshort 11 (EFI boot service driver)
72 >>>(0x3c.l+92) leshort 12 (EFI runtime driver)
73 >>>(0x3c.l+92) leshort 13 (EFI ROM)
74 >>>(0x3c.l+92) leshort 14 (XBOX)
75 >>>(0x3c.l+92) leshort 15 (Windows boot application)
76 >>>(0x3c.l+92) default x (Unknown subsystem
77 >>>>&0 leshort x 0x%x)
78 >>>(0x3c.l+4) leshort 0x14c Intel 80386
79 >>>(0x3c.l+4) leshort 0x166 MIPS R4000
80 >>>(0x3c.l+4) leshort 0x168 MIPS R10000
81 >>>(0x3c.l+4) leshort 0x184 Alpha
82 >>>(0x3c.l+4) leshort 0x1a2 Hitachi SH3
83 >>>(0x3c.l+4) leshort 0x1a6 Hitachi SH4
84 >>>(0x3c.l+4) leshort 0x1c0 ARM
85 >>>(0x3c.l+4) leshort 0x1c2 ARM Thumb
86 >>>(0x3c.l+4) leshort 0x1c4 ARMv7 Thumb
87 >>>(0x3c.l+4) leshort 0x1f0 PowerPC
88 >>>(0x3c.l+4) leshort 0x200 Intel Itanium
89 >>>(0x3c.l+4) leshort 0x266 MIPS16
90 >>>(0x3c.l+4) leshort 0x268 Motorola 68000
91 >>>(0x3c.l+4) leshort 0x290 PA-RISC
92 >>>(0x3c.l+4) leshort 0x366 MIPSIV
93 >>>(0x3c.l+4) leshort 0x466 MIPS16 with FPU
94 >>>(0x3c.l+4) leshort 0xebc EFI byte code
95 >>>(0x3c.l+4) leshort 0x8664 x86-64
96 >>>(0x3c.l+4) leshort 0xc0ee MSIL
97 >>>(0x3c.l+4) default x Unknown processor type
99 >>>(0x3c.l+22) leshort&0x0200 >0 (stripped to external PDB)
100 >>>(0x3c.l+22) leshort&0x1000 >0 system file
101 >>>(0x3c.l+24) leshort 0x010b
102 >>>>(0x3c.l+232) lelong >0 Mono/.Net assembly
103 >>>(0x3c.l+24) leshort 0x020b
104 >>>>(0x3c.l+248) lelong >0 Mono/.Net assembly
106 # hooray, there's a DOS extender using the PE format, with a valid PE
107 # executable inside (which just prints a message and exits if run in win)
108 >>>(8.s*16) string 32STUB \b, 32rtm DOS extender
109 >>>(8.s*16) string !32STUB \b, for MS Windows
110 >>>(0x3c.l+0xf8) string UPX0 \b, UPX compressed
111 >>>(0x3c.l+0xf8) search/0x140 PEC2 \b, PECompact2 compressed
112 >>>(0x3c.l+0xf8) search/0x140 UPX2
113 >>>>(&0x10.l+(-4)) string PK\3\4 \b, ZIP self-extracting archive (Info-Zip)
114 >>>(0x3c.l+0xf8) search/0x140 .idata
115 >>>>(&0xe.l+(-4)) string PK\3\4 \b, ZIP self-extracting archive (Info-Zip)
116 >>>>(&0xe.l+(-4)) string ZZ0 \b, ZZip self-extracting archive
117 >>>>(&0xe.l+(-4)) string ZZ1 \b, ZZip self-extracting archive
118 >>>(0x3c.l+0xf8) search/0x140 .rsrc
119 >>>>(&0x0f.l+(-4)) string a\\\4\5 \b, WinHKI self-extracting archive
120 >>>>(&0x0f.l+(-4)) string Rar! \b, RAR self-extracting archive
121 >>>>(&0x0f.l+(-4)) search/0x3000 MSCF \b, InstallShield self-extracting archive
122 >>>>(&0x0f.l+(-4)) search/32 Nullsoft \b, Nullsoft Installer self-extracting archive
123 >>>(0x3c.l+0xf8) search/0x140 .data
124 >>>>(&0x0f.l) string WEXTRACT \b, MS CAB-Installer self-extracting archive
125 >>>(0x3c.l+0xf8) search/0x140 .petite\0 \b, Petite compressed
126 >>>>(0x3c.l+0xf7) byte x
127 >>>>>(&0x104.l+(-4)) string =!sfx! \b, ACE self-extracting archive
128 >>>(0x3c.l+0xf8) search/0x140 .WISE \b, WISE installer self-extracting archive
129 >>>(0x3c.l+0xf8) search/0x140 .dz\0\0\0 \b, Dzip self-extracting archive
130 >>>&(0x3c.l+0xf8) search/0x100 _winzip_ \b, ZIP self-extracting archive (WinZip)
131 >>>&(0x3c.l+0xf8) search/0x100 SharedD \b, Microsoft Installer self-extracting archive
132 >>>0x30 string Inno \b, InnoSetup self-extracting archive
134 # Hmm, not a PE but the relocation table is too high for a traditional DOS exe,
135 # must be one of the unusual subformats.
136 >>(0x3c.l) string !PE\0\0 MS-DOS executable
138 >>(0x3c.l) string NE \b, NE
139 >>>(0x3c.l+0x36) byte 1 for OS/2 1.x
140 >>>(0x3c.l+0x36) byte 2 for MS Windows 3.x
141 >>>(0x3c.l+0x36) byte 3 for MS-DOS
142 >>>(0x3c.l+0x36) byte 4 for Windows 386
143 >>>(0x3c.l+0x36) byte 5 for Borland Operating System Services
144 >>>(0x3c.l+0x36) default x
145 >>>>(0x3c.l+0x36) byte x (unknown OS %x)
146 >>>(0x3c.l+0x36) byte 0x81 for MS-DOS, Phar Lap DOS extender
147 >>>(0x3c.l+0x0c) leshort&0x8003 0x8002 (DLL)
148 >>>(0x3c.l+0x0c) leshort&0x8003 0x8001 (driver)
149 >>>&(&0x24.s-1) string ARJSFX \b, ARJ self-extracting archive
150 >>>(0x3c.l+0x70) search/0x80 WinZip(R)\ Self-Extractor \b, ZIP self-extracting archive (WinZip)
152 >>(0x3c.l) string LX\0\0 \b, LX
153 >>>(0x3c.l+0x0a) leshort <1 (unknown OS)
154 >>>(0x3c.l+0x0a) leshort 1 for OS/2
155 >>>(0x3c.l+0x0a) leshort 2 for MS Windows
156 >>>(0x3c.l+0x0a) leshort 3 for DOS
157 >>>(0x3c.l+0x0a) leshort >3 (unknown OS)
158 >>>(0x3c.l+0x10) lelong&0x28000 =0x8000 (DLL)
159 >>>(0x3c.l+0x10) lelong&0x20000 >0 (device driver)
160 >>>(0x3c.l+0x10) lelong&0x300 0x300 (GUI)
161 >>>(0x3c.l+0x10) lelong&0x28300 <0x300 (console)
162 >>>(0x3c.l+0x08) leshort 1 i80286
163 >>>(0x3c.l+0x08) leshort 2 i80386
164 >>>(0x3c.l+0x08) leshort 3 i80486
165 >>>(8.s*16) string emx \b, emx
167 >>>&(&0x54.l-3) string arjsfx \b, ARJ self-extracting archive
169 # MS Windows system file, supposedly a collection of LE executables
170 >>(0x3c.l) string W3 \b, W3 for MS Windows
172 >>(0x3c.l) string LE\0\0 \b, LE executable
173 >>>(0x3c.l+0x0a) leshort 1
174 # some DOS extenders use LE files with OS/2 header
175 >>>>0x240 search/0x100 DOS/4G for MS-DOS, DOS4GW DOS extender
176 >>>>0x240 search/0x200 WATCOM\ C/C++ for MS-DOS, DOS4GW DOS extender
177 >>>>0x440 search/0x100 CauseWay\ DOS\ Extender for MS-DOS, CauseWay DOS extender
178 >>>>0x40 search/0x40 PMODE/W for MS-DOS, PMODE/W DOS extender
179 >>>>0x40 search/0x40 STUB/32A for MS-DOS, DOS/32A DOS extender (stub)
180 >>>>0x40 search/0x80 STUB/32C for MS-DOS, DOS/32A DOS extender (configurable stub)
181 >>>>0x40 search/0x80 DOS/32A for MS-DOS, DOS/32A DOS extender (embedded)
182 # this is a wild guess; hopefully it is a specific signature
183 >>>>&0x24 lelong <0x50
184 >>>>>(&0x4c.l) string \xfc\xb8WATCOM
185 >>>>>>&0 search/8 3\xdbf\xb9 \b, 32Lite compressed
186 # another wild guess: if real OS/2 LE executables exist, they probably have higher start EIP
187 #>>>>(0x3c.l+0x1c) lelong >0x10000 for OS/2
188 # fails with DOS-Extenders.
189 >>>(0x3c.l+0x0a) leshort 2 for MS Windows
190 >>>(0x3c.l+0x0a) leshort 3 for DOS
191 >>>(0x3c.l+0x0a) leshort 4 for MS Windows (VxD)
192 >>>(&0x7c.l+0x26) string UPX \b, UPX compressed
193 >>>&(&0x54.l-3) string UNACE \b, ACE self-extracting archive
195 # looks like ASCII, probably some embedded copyright message.
196 # and definitely not NE/LE/LX/PE
197 >>0x3c lelong >0x20000000
198 >>>(4.s*512) leshort !0x014c \b, MZ for MS-DOS
199 # header data too small for extended executable
202 >>>(4.s*512) leshort !0x014c
204 >>>>&(2.s-514) string !LE
205 >>>>>&-2 string !BW \b, MZ for MS-DOS
206 >>>>&(2.s-514) string LE \b, LE
207 >>>>>0x240 search/0x100 DOS/4G for MS-DOS, DOS4GW DOS extender
208 # educated guess since indirection is still not capable enough for complex offset
209 # calculations (next embedded executable would be at &(&2*512+&0-2)
210 # I suspect there are only LE executables in these multi-exe files
211 >>>>&(2.s-514) string BW
212 >>>>>0x240 search/0x100 DOS/4G \b, LE for MS-DOS, DOS4GW DOS extender (embedded)
213 >>>>>0x240 search/0x100 !DOS/4G \b, BW collection for MS-DOS
215 # This sequence skips to the first COFF segment, usually .text
216 >(4.s*512) leshort 0x014c \b, COFF
217 >>(8.s*16) string go32stub for MS-DOS, DJGPP go32 DOS extender
218 >>(8.s*16) string emx
219 >>>&1 string x for DOS, Win or OS/2, emx %s
220 >>&(&0x42.l-3) byte x
221 >>>&0x26 string UPX \b, UPX compressed
222 # and yet another guess: small .text, and after large .data is unusal, could be 32lite
223 >>&0x2c search/0xa0 .text
224 >>>&0x0b lelong <0x2000
225 >>>>&0 lelong >0x6000 \b, 32lite compressed
227 >(8.s*16) string $WdX \b, WDos/X DOS extender
229 # By now an executable type should have been printed out. The executable
230 # may be a self-uncompressing archive, so look for evidence of that and
233 # Some signatures below from Greg Roelofs, newt@uchicago.edu.
235 >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
236 >0xe7 string LH/2\ Self-Extract \b, %s
237 >0x1c string UC2X \b, UCEXE compressed
238 >0x1c string WWP\ \b, WWPACK compressed
239 >0x1c string RJSX \b, ARJ self-extracting archive
240 >0x1c string diet \b, diet compressed
241 >0x1c string LZ09 \b, LZEXE v0.90 compressed
242 >0x1c string LZ91 \b, LZEXE v0.91 compressed
243 >0x1c string tz \b, TinyProg compressed
244 >0x1e string Copyright\ 1989-1990\ PKWARE\ Inc. Self-extracting PKZIP archive
245 !:mime application/zip
246 # Yes, this really is "Copr", not "Corp."
247 >0x1e string PKLITE\ Copr. Self-extracting PKZIP archive
248 !:mime application/zip
249 # winarj stores a message in the stub instead of the sig in the MZ header
250 >0x20 search/0xe0 aRJsfX \b, ARJ self-extracting archive
252 >>0x23 string 2 \b, AIN 2.x compressed
253 >>0x23 string <2 \b, AIN 1.x compressed
254 >>0x23 string >2 \b, AIN 1.x compressed
255 >0x24 string LHa's\ SFX \b, LHa self-extracting archive
256 !:mime application/x-lha
257 >0x24 string LHA's\ SFX \b, LHa self-extracting archive
258 !:mime application/x-lha
259 >0x24 string \ $ARX \b, ARX self-extracting archive
260 >0x24 string \ $LHarc \b, LHarc self-extracting archive
261 >0x20 string SFX\ by\ LARC \b, LARC self-extracting archive
262 >0x40 string aPKG \b, aPackage self-extracting archive
263 >0x64 string W\ Collis\0\0 \b, Compack compressed
264 >0x7a string Windows\ self-extracting\ ZIP \b, ZIP self-extracting archive
265 >>&0xf4 search/0x140 \x0\x40\x1\x0
266 >>>(&0.l+(4)) string MSCF \b, WinHKI CAB self-extracting archive
267 >1638 string -lh5- \b, LHa self-extracting archive v2.13S
268 >0x17888 string Rar! \b, RAR self-extracting archive
270 # Skip to the end of the EXE. This will usually work fine in the PE case
271 # because the MZ image is hardcoded into the toolchain and almost certainly
272 # won't match any of these signatures.
275 >>>&0 string PK\3\4 \b, ZIP self-extracting archive
276 >>>&0 string Rar! \b, RAR self-extracting archive
277 >>>&0 string =!\x11 \b, AIN 2.x self-extracting archive
278 >>>&0 string =!\x12 \b, AIN 2.x self-extracting archive
279 >>>&0 string =!\x17 \b, AIN 1.x self-extracting archive
280 >>>&0 string =!\x18 \b, AIN 1.x self-extracting archive
281 >>>&7 search/400 **ACE** \b, ACE self-extracting archive
282 >>>&0 search/0x480 UC2SFX\ Header \b, UC2 self-extracting archive
284 # a few unknown ZIP sfxes, no idea if they are needed or if they are
285 # already captured by the generic patterns above
286 >(8.s*16) search/0x20 PKSFX \b, ZIP self-extracting archive (PKZIP)
287 # TODO: how to add this? >FileSize-34 string Windows\ Self-Installing\ Executable \b, ZIP self-extracting archive
290 # TELVOX Teleinformatica CODEC self-extractor for OS/2:
291 >49801 string \x79\xff\x80\xff\x76\xff \b, CODEC archive v3.21
292 >>49824 leshort =1 \b, 1 file
293 >>49824 leshort >1 \b, %u files
295 # added by Joerg Jenderek of http://www.freedos.org/software/?prog=kc
296 # and http://www.freedos.org/software/?prog=kpdos
297 # for FreeDOS files like KEYBOARD.SYS, KEYBRD2.SYS, KEYBRD3.SYS, *.KBD
298 0 string/b KCF FreeDOS KEYBoard Layout collection
299 # only version=0x100 found
300 >3 uleshort x \b, version 0x%x
301 # length of string containing author,info and special characters
303 #>>6 pstring x \b, name=%s
304 >>7 string >\0 \b, author=%-.14s
305 >>7 search/254 \xff \b, info=
306 #>>>&0 string x \b%-s
307 >>>&0 string x \b%-.15s
308 # for FreeDOS *.KL files
309 0 string/b KLF FreeDOS KEYBoard Layout file
310 # only version=0x100 or 0x101 found
311 >3 uleshort x \b, version 0x%x
314 >>8 string x \b, name=%-.2s
315 0 string \xffKEYB\ \ \ \0\0\0\0
316 >12 string \0\0\0\0`\004\360 MS-DOS KEYBoard Layout file
318 # .COM formats (Daniel Quinlan, quinlan@yggdrasil.com)
319 # Uncommenting only the first two lines will cover about 2/3 of COM files,
320 # but it isn't feasible to match all COM files since there must be at least
321 # two dozen different one-byte "magics".
323 0 byte 0xe9 DOS executable (COM)
324 >0x1FE leshort 0xAA55 \b, boot code
325 >6 string SFX\ of\ LHarc (%s)
327 # DOS device driver updated by Joerg Jenderek at May 2011
328 # http://maben.homeip.net/static/S100/IBM/software/DOS/DOS%20techref/CHAPTER.009
329 0 ulequad&0x07a0ffffffff 0xffffffff DOS executable (
330 >40 search/7 UPX! \bUPX compressed
331 # DOS device driver attributes
332 >4 uleshort&0x8000 0x0000 \bblock device driver
334 >4 uleshort&0x8000 0x8000 \b
335 >>4 uleshort&0x0008 0x0008 \bclock
336 # fast video output by int 29h
337 >>4 uleshort&0x0010 0x0010 \bfast
338 # standard input/output device
339 >>4 uleshort&0x0003 >0 \bstandard
340 >>>4 uleshort&0x0001 0x0001 \binput
341 >>>4 uleshort&0x0003 0x0003 \b/
342 >>>4 uleshort&0x0002 0x0002 \boutput
343 >>4 uleshort&0x8000 0x8000 \bcharacter device driver
345 # upx compressed device driver has garbage instead of real in name field of header
348 # leading/trailing nulls, zeros or non ASCII characters in 8-byte name field at offset 10 are skipped
352 >>>>>>10 ubyte !0x2A \b%c
354 >>>>>11 ubyte !0x2E \b%c
357 >>>>>>12 ubyte !0x2E \b%c
359 >>>>13 ubyte !0x2E \b%c
361 >>>>>14 ubyte !0x2E \b%c
363 >>>>>15 ubyte !0x2E \b%c
366 >>>>>>16 ubyte <0xCB \b%c
369 >>>>>>17 ubyte <0x90 \b%c
370 # some character device drivers like ASPICD.SYS, btcdrom.sys and Cr_atapi.sys contain only spaces or points in name field
371 >>>4 uleshort&0x8000 0x8000
373 # they have their real name at offset 22
374 >>>>>22 string >\0 \b%-.5s
375 >4 uleshort&0x8000 0x0000
376 # 32 bit sector adressing ( > 32 MB) for block devices
377 >>4 uleshort&0x0002 0x0002 \b,32-bit sector-
378 # support by driver functions 13h, 17h, 18h
379 >4 uleshort&0x0040 0x0040 \b,IOCTL-
380 # open, close, removable media support by driver functions 0Dh, 0Eh, 0Fh
381 >4 uleshort&0x0800 0x0800 \b,close media-
382 # output until busy support by int 10h for character device driver
383 >4 uleshort&0x8000 0x8000
384 >>4 uleshort&0x2000 0x2000 \b,until busy-
385 # direct read/write support by driver functions 03h,0Ch
386 >4 uleshort&0x4000 0x4000 \b,control strings-
387 >4 uleshort&0x8000 0x8000
388 >>4 uleshort&0x6840 >0 \bsupport
389 >4 uleshort&0x8000 0x0000
390 >>4 uleshort&0x4842 >0 \bsupport
392 # DOS driver cmd640x.sys has 0x12 instead of 0xffffffff for pointer field to next device header
393 # Too weak, matches files that only contain 0's
394 #0 ulequad&0x000007a0ffffffed 0x0000000000000000 DOS-executable (
395 #>4 uleshort&0x8000 0x8000 \bcharacter device driver
397 #>4 uleshort&0x4000 0x4000 \b,control strings-support)
400 0 byte 0x8c DOS executable (COM)
401 # updated by Joerg Jenderek at Oct 2008
402 0 ulelong 0xffff10eb DR-DOS executable (COM)
403 # byte 0xeb conflicts with "sequent" magic leshort 0xn2eb
404 0 ubeshort&0xeb8d >0xeb00
405 # DR-DOS STACKER.COM SCREATE.SYS missed
407 >>0x1FE leshort 0xAA55 DOS executable (COM), boot code
408 >>85 string UPX DOS executable (COM), UPX compressed
409 >>4 string \ $ARX DOS executable (COM), ARX self-extracting archive
410 >>4 string \ $LHarc DOS executable (COM), LHarc self-extracting archive
411 >>0x20e string SFX\ by\ LARC DOS executable (COM), LARC self-extracting archive
412 # updated by Joerg Jenderek at Oct 2008
413 #0 byte 0xb8 COM executable
414 0 uleshort&0x80ff 0x00b8
415 # modified by Joerg Jenderek
416 >1 lelong !0x21cd4cff COM executable for DOS
417 # http://syslinux.zytor.com/comboot.php
418 # (32-bit COMBOOT) programs *.C32 contain 32-bit code and run in flat-memory 32-bit protected mode
419 # start with assembler instructions mov eax,21cd4cffh
420 0 uleshort&0xc0ff 0xc0b8
421 >1 lelong 0x21cd4cff COM executable (32-bit COMBOOT)
422 # syslinux:doc/comboot.txt
423 # A COM32R program must start with the byte sequence B8 FE 4C CD 21 (mov
424 # eax,21cd4cfeh) as a magic number.
425 0 string/b \xb8\xfe\x4c\xcd\x21 COM executable (COM32R)
426 # start with assembler instructions mov eax,21cd4cfeh
427 0 uleshort&0xc0ff 0xc0b8
428 >1 lelong 0x21cd4cfe COM executable (32-bit COMBOOT, relocatable)
430 >4 string \x77\x02\xcd\x20\xb9
431 >>36 string UPX! FREE-DOS executable (COM), UPX compressed
432 252 string Must\ have\ DOS\ version DR-DOS executable (COM)
433 # added by Joerg Jenderek at Oct 2008
434 # GRR search is not working
435 #34 search/2 UPX! FREE-DOS executable (COM), UPX compressed
436 34 string UPX! FREE-DOS executable (COM), UPX compressed
437 35 string UPX! FREE-DOS executable (COM), UPX compressed
438 # GRR search is not working
439 #2 search/28 \xcd\x21 COM executable for MS-DOS
441 2 string \xcd\x21 COM executable for DOS
442 #DELTREE.cOM DELTREE2.cOM
443 4 string \xcd\x21 COM executable for DOS
444 #IFMEMDSK.cOM ASSIGN.cOM COMP.cOM
445 5 string \xcd\x21 COM executable for DOS
446 #DELTMP.COm HASFAT32.cOM
448 >0 byte !0xb8 COM executable for DOS
451 >5 string !\xcd\x21 COM executable for DOS
453 13 string \xcd\x21 COM executable for DOS
455 18 string \xcd\x21 COM executable for MS-DOS
457 23 string \xcd\x21 COM executable for MS-DOS
458 #LOADFIX.cOm LOADFIX.cOm
459 30 string \xcd\x21 COM executable for MS-DOS
461 70 string \xcd\x21 COM executable for DOS
462 # many compressed/converted COMs start with a copy loop instead of a jump
463 0x6 search/0xa \xfc\x57\xf3\xa5\xc3 COM executable for MS-DOS
464 0x6 search/0xa \xfc\x57\xf3\xa4\xc3 COM executable for DOS
465 >0x18 search/0x10 \x50\xa4\xff\xd5\x73 \b, aPack compressed
466 0x3c string W\ Collis\0\0 COM executable for MS-DOS, Compack compressed
467 # FIXME: missing diet .com compression
469 # miscellaneous formats
470 0 string/b LZ MS-DOS executable (built-in)
471 #0 byte 0xf0 MS-DOS program library data
475 # <stuartc@rd.bbc.co.uk> Stuart Cunningham
476 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
477 >30 byte 9 (512B sectors)
478 >30 byte 12 (4kB sectors)
479 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
480 >30 byte 9 (512B sectors)
481 >30 byte 12 (4kB sectors)
483 # Popular applications
484 2080 string Microsoft\ Word\ 6.0\ Document %s
485 !:mime application/msword
486 2080 string Documento\ Microsoft\ Word\ 6 Spanish Microsoft Word 6 document data
487 !:mime application/msword
488 # Pawel Wiecek <coven@i17linuxb.ists.pwr.wroc.pl> (for polish Word)
489 2112 string MSWordDoc Microsoft Word document data
490 !:mime application/msword
492 0 belong 0x31be0000 Microsoft Word Document
493 !:mime application/msword
495 0 string/b PO^Q` Microsoft Word 6.0 Document
496 !:mime application/msword
498 0 string/b \376\067\0\043 Microsoft Office Document
499 !:mime application/msword
500 0 string/b \333\245-\0\0\0 Microsoft Office Document
501 !:mime application/msword
502 512 string/b \354\245\301 Microsoft Word Document
503 !:mime application/msword
506 0 string/b \xDB\xA5\x2D\x00 Microsoft WinWord 2.0 Document
507 !:mime application/msword
509 2080 string Microsoft\ Excel\ 5.0\ Worksheet %s
510 !:mime application/vnd.ms-excel
512 0 string/b \xDB\xA5\x2D\x00 Microsoft WinWord 2.0 Document
513 !:mime application/msword
515 2080 string Foglio\ di\ lavoro\ Microsoft\ Exce %s
516 !:mime application/vnd.ms-excel
518 # Pawel Wiecek <coven@i17linuxb.ists.pwr.wroc.pl> (for polish Excel)
519 2114 string Biff5 Microsoft Excel 5.0 Worksheet
520 !:mime application/vnd.ms-excel
522 2121 string Biff5 Microsoft Excel 5.0 Worksheet
523 !:mime application/vnd.ms-excel
524 0 string/b \x09\x04\x06\x00\x00\x00\x10\x00 Microsoft Excel Worksheet
525 !:mime application/vnd.ms-excel
527 0 belong 0x00001a00 Lotus 1-2-3
528 !:mime application/x-123
529 >4 belong 0x00100400 wk3 document data
530 >4 belong 0x02100400 wk4 document data
531 >4 belong 0x07800100 fm3 or fmb document data
532 >4 belong 0x07800000 fm3 or fmb document data
534 0 belong 0x00000200 Lotus 1-2-3
535 !:mime application/x-123
536 >4 belong 0x06040600 wk1 document data
537 >4 belong 0x06800200 fmt document data
538 0 string/b WordPro\0 Lotus WordPro
539 !:mime application/vnd.lotus-wordpro
540 0 string/b WordPro\r\373 Lotus WordPro
541 !:mime application/vnd.lotus-wordpro
544 # Summary: Script used by InstallScield to uninstall applications
546 # Submitted by: unknown
547 # Modified by (1): Abel Cheung <abelcheung@gmail.com> (replace useless entry)
548 0 string \x71\xa8\x00\x00\x01\x02
549 >12 string Stirling\ Technologies, InstallShield Uninstall Script
552 #0 string Nullsoft\ AVS\ Preset\ \060\056\061\032 A plug in for Winamp ms-windows Freeware media player
553 0 string/b Nullsoft\ AVS\ Preset\ Winamp plug in
555 # Windows Metafont .WMF
556 0 string/b \327\315\306\232 ms-windows metafont .wmf
557 0 string/b \002\000\011\000 ms-windows metafont .wmf
558 0 string/b \001\000\011\000 ms-windows metafont .wmf
560 #tz3 files whatever that is (MS Works files)
561 0 string/b \003\001\001\004\070\001\000\000 tz3 ms-works file
562 0 string/b \003\002\001\004\070\001\000\000 tz3 ms-works file
563 0 string/b \003\003\001\004\070\001\000\000 tz3 ms-works file
566 #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
567 0 string \211\000\077\003\005\000\063\237\127\065\027\266\151\064\005\045\101\233\021\002 PGP sig
568 0 string \211\000\077\003\005\000\063\237\127\066\027\266\151\064\005\045\101\233\021\002 PGP sig
569 0 string \211\000\077\003\005\000\063\237\127\067\027\266\151\064\005\045\101\233\021\002 PGP sig
570 0 string \211\000\077\003\005\000\063\237\127\070\027\266\151\064\005\045\101\233\021\002 PGP sig
571 0 string \211\000\077\003\005\000\063\237\127\071\027\266\151\064\005\045\101\233\021\002 PGP sig
572 0 string \211\000\225\003\005\000\062\122\207\304\100\345\042 PGP sig
574 # windows zips files .dmf
575 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
579 0 string/b \102\101\050\000\000\000\056\000\000\000\000\000\000\000 Icon for MS Windows
583 # not entirely accurate, the number of icons is part of the header
585 >0 ubyte >1 - %d icons
590 >4 ubyte !0 \b, %d colors
595 >>0 byte x MS Windows icon resource
599 >>0 byte x MS Windows icon resource
603 # Windows non-animated cursors
605 # not entirely accurate, the number of icons is part of the header
607 >0 ubyte >1 - %d icons
612 >6 uleshort x \b, hotspot @%dx
617 >>0 byte x MS Windows cursor resource
621 >>0 byte x MS Windows cursor resource
626 0 string/b PK\010\010BGI Borland font
628 # then there is a copyright notice
632 0 string/b pk\010\010BGI Borland device
634 # then there is a copyright notice
637 # Windows Recycle Bin record file (named INFO2)
638 # By Abel Cheung (abelcheung AT gmail dot com)
639 # Version 4 always has 280 bytes (0x118) per record, version 5 has 800 bytes
640 # Since Vista uses another structure, INFO2 structure probably won't change
641 # anymore. Detailed analysis in:
642 # http://www.cybersecurityinstitute.biz/downloads/INFO2.pdf
644 >12 lelong 0x00000118 Windows Recycle Bin INFO2 file (Win98 or below)
647 >12 lelong 0x00000320 Windows Recycle Bin INFO2 file (Win2k - WinXP)
650 ##### put in Either Magic/font or Magic/news
651 # Acroread or something files wrongly identified as G3 .pfm
652 # these have the form \000 \001 any? \002 \000 \000
653 # or \000 \001 any? \022 \000 \000
654 0 belong&0xffff00ff 0x00010012 PFM data
658 0 belong&0xffff00ff 0x00010002 PFM data
661 #0 string \000\001 pfm?
662 #>3 string \022\000\000Copyright\ yes
663 #>3 string \002\000\000Copyright\ yes
664 #>3 string >\0 oops, not a font file. Cancel that.
665 #it clashes with ttf files so put it lower down.
667 # From Doug Lee via a FreeBSD pr
668 9 string GERBILDOC First Choice document
669 9 string GERBILDB First Choice database
670 9 string GERBILCLIP First Choice database
671 0 string GERBIL First Choice device file
672 9 string RABBITGRAPH RabbitGraph file
673 0 string DCU1 Borland Delphi .DCU file
674 0 string =!<spell> MKS Spell hash list (old format)
675 0 string =!<spell2> MKS Spell hash list
677 #0 string AH Halo(TM) bitmapped font file
678 0 lelong 0x08086b70 TurboC BGI file
679 0 lelong 0x08084b50 TurboC Font file
681 # Debian#712046: The magic below identifies "Delphi compiled form data".
682 # An additional source of information is available at:
683 # http://www.woodmann.com/fravia/dafix_t1.htm
685 >4 pstring >\0 Delphi compiled form '%s'
687 # tests for DBase files moved, updated and merged to database
689 0 string PMCC Windows 3.x .GRP file
690 1 string RDC-meg MegaDots
691 >8 byte >0x2F version %c
692 >9 byte >0x2F \b.%c file
694 >4 lelong 0x00021401 Windows shortcut file
696 # .PIF files added by Joerg Jenderek from http://smsoft.ru/en/pifdoc.htm
697 # only for windows versions equal or greater 3.0
698 0x171 string MICROSOFT\ PIFEX\0 Windows Program Information File
699 !:mime application/x-dosexec
700 #>2 string >\0 \b, Title:%.30s
701 >0x24 string >\0 \b for %.63s
702 >0x65 string >\0 \b, directory=%.64s
703 >0xA5 string >\0 \b, parameters=%.64s
704 #>0x181 leshort x \b, offset %x
705 #>0x183 leshort x \b, offsetdata %x
706 #>0x185 leshort x \b, section length %x
707 >0x187 search/0xB55 WINDOWS\ VMM\ 4.0\0
709 >>>&-1 string <PIFMGR.DLL \b, icon=%s
710 #>>>&-1 string PIFMGR.DLL \b, icon=%s
711 >>>&-1 string >PIFMGR.DLL \b, icon=%s
713 >>>&-1 string <Terminal \b, font=%.32s
714 #>>>&-1 string =Terminal \b, font=%.32s
715 >>>&-1 string >Terminal \b, font=%.32s
717 >>>&-1 string <Lucida\ Console \b, TrueTypeFont=%.32s
718 #>>>&-1 string =Lucida\ Console \b, TrueTypeFont=%.32s
719 >>>&-1 string >Lucida\ Console \b, TrueTypeFont=%.32s
720 #>0x187 search/0xB55 WINDOWS\ 286\ 3.0\0 \b, Windows 3.X standard mode-style
721 #>0x187 search/0xB55 WINDOWS\ 386\ 3.0\0 \b, Windows 3.X enhanced mode-style
722 >0x187 search/0xB55 WINDOWS\ NT\ \ 3.1\0 \b, Windows NT-style
723 #>0x187 search/0xB55 WINDOWS\ NT\ \ 4.0\0 \b, Windows NT-style
724 >0x187 search/0xB55 CONFIG\ \ SYS\ 4.0\0 \b +CONFIG.SYS
725 #>>&06 string x \b:%s
726 >0x187 search/0xB55 AUTOEXECBAT\ 4.0\0 \b +AUTOEXEC.BAT
727 #>>&06 string x \b:%s
729 # DOS EPS Binary File Header
730 # From: Ed Sznyter <ews@Black.Market.NET>
731 0 belong 0xC5D0D3C6 DOS EPS Binary File
732 >4 long >0 Postscript starts at byte %d
733 >>8 long >0 length %d
734 >>>12 long >0 Metafile starts at byte %d
735 >>>>16 long >0 length %d
736 >>>20 long >0 TIFF starts at byte %d
737 >>>>24 long >0 length %d
739 # TNEF magic From "Joomy" <joomy@se-ed.net>
740 # Microsoft Outlook's Transport Neutral Encapsulation Format (TNEF)
741 0 leshort 0x223e9f78 TNEF
742 !:mime application/vnd.ms-tnef
744 # 4DOS help (.HLP) files added by Joerg Jenderek from source TPHELP.PAS
745 # of http://www.4dos.info/
746 # pointer,HelpID[8]=4DHnnnmm
747 0 ulelong 0x48443408 4DOS help file
748 >4 string x \b, version %-4.4s
750 # old binary Microsoft (.HLP) files added by Joerg Jenderek from http://file-extension.net/seeker/file_extension_hlp
751 0 ulequad 0x3a000000024e4c MS Advisor help file
753 # HtmlHelp files (.chm)
754 0 string/b ITSF\003\000\000\000\x60\000\000\000\001\000\000\000 MS Windows HtmlHelp Data
756 # GFA-BASIC (Wolfram Kleff)
757 2 string/b GFA-BASIC3 GFA-BASIC 3 data
759 #------------------------------------------------------------------------------
760 # From Stuart Caie <kyzer@4u.net> (developer of cabextract)
761 # Microsoft Cabinet files
762 0 string/b MSCF\0\0\0\0 Microsoft Cabinet archive data
763 !:mime application/vnd.ms-cab-compressed
764 >8 lelong x \b, %u bytes
765 >28 leshort 1 \b, 1 file
766 >28 leshort >1 \b, %u files
768 # InstallShield Cabinet files
769 0 string/b ISc( InstallShield Cabinet archive data
770 >5 byte&0xf0 =0x60 version 6,
771 >5 byte&0xf0 !0x60 version 4/5,
772 >(12.l+40) lelong x %u files
774 # Windows CE package files
775 0 string/b MSCE\0\0\0\0 Microsoft WinCE install header
776 >20 lelong 0 \b, architecture-independent
777 >20 lelong 103 \b, Hitachi SH3
778 >20 lelong 104 \b, Hitachi SH4
779 >20 lelong 0xA11 \b, StrongARM
780 >20 lelong 4000 \b, MIPS R4000
781 >20 lelong 10003 \b, Hitachi SH3
782 >20 lelong 10004 \b, Hitachi SH3E
783 >20 lelong 10005 \b, Hitachi SH4
784 >20 lelong 70001 \b, ARM 7TDMI
785 >52 leshort 1 \b, 1 file
786 >52 leshort >1 \b, %u files
787 >56 leshort 1 \b, 1 registry entry
788 >56 leshort >1 \b, %u registry entries
791 # Windows Enhanced Metafile (EMF)
792 # See msdn.microsoft.com/archive/en-us/dnargdi/html/msdn_enhmeta.asp
793 # for further information.
795 >40 string \ EMF Windows Enhanced Metafile (EMF) image data
796 >>44 ulelong x version 0x%x
798 # From: Alex Beregszaszi <alex@fsn.hu>
799 0 string/b COWD VMWare3
804 >4 byte 2 undoable disk image
807 0 string/b VMDK VMware4 disk image
808 0 string/b KDMV VMware4 disk image
810 #--------------------------------------------------------------------
811 # Qemu Emulator Images
812 # Lines written by Friedrich Schwittay (f.schwittay@yousable.de)
813 # Updated by Adam Buchbinder (adam.buchbinder@gmail.com)
814 # Made by reading sources, reading documentation, and doing trial and error
815 # on existing QCOW files
816 0 string/b QFI\xFB QEMU QCOW Image
818 # Uncomment the following line to display Magic (only used for debugging
820 #>0 string/b x , Magic: %s
822 # There are currently 2 Versions: "1" and "2".
823 # http://www.gnome.org/~markmc/qcow-image-format-version-1.html
826 # Using the existence of the Backing File Offset to determine whether
827 # to read Backing File Information
828 >>12 belong >0 \b, has backing file (
829 # Note that this isn't a null-terminated string; the length is actually
830 # (16.L). Assuming a null-terminated string happens to work usually, but it
831 # may spew junk until it reaches a \0 in some cases.
832 >>>(12.L) string >\0 \bpath %s
834 # Modification time of the Backing File
835 # Really useful if you want to know if your backing
836 # file is still usable together with this image
837 >>>>20 bedate >0 \b, mtime %s)
840 # Size is stored in bytes in a big-endian u64.
841 >>24 bequad x \b, %lld bytes
843 # 1 for AES encryption, 0 for none.
844 >>36 belong 1 \b, AES-encrypted
846 # http://www.gnome.org/~markmc/qcow-image-format.html
848 # Using the existence of the Backing File Offset to determine whether
849 # to read Backing File Information
850 >>8 bequad >0 \b, has backing file
851 # Note that this isn't a null-terminated string; the length is actually
852 # (16.L). Assuming a null-terminated string happens to work usually, but it
853 # may spew junk until it reaches a \0 in some cases. Also, since there's no
854 # .Q modifier, we just use the bottom four bytes as an offset. Note that if
855 # the file is over 4G, and the backing file path is stored after the first 4G,
856 # the wrong filename will be printed. (This should be (8.Q), when that syntax
858 >>>(12.L) string >\0 (path %s)
859 >>24 bequad x \b, %lld bytes
860 >>32 belong 1 \b, AES-encrypted
863 # Using the existence of the Backing File Offset to determine whether
864 # to read Backing File Information
865 >>8 bequad >0 \b, has backing file
866 # Note that this isn't a null-terminated string; the length is actually
867 # (16.L). Assuming a null-terminated string happens to work usually, but it
868 # may spew junk until it reaches a \0 in some cases. Also, since there's no
869 # .Q modifier, we just use the bottom four bytes as an offset. Note that if
870 # the file is over 4G, and the backing file path is stored after the first 4G,
871 # the wrong filename will be printed. (This should be (8.Q), when that syntax
873 >>>(12.L) string >\0 (path %s)
874 >>24 bequad x \b, %lld bytes
875 >>32 belong 1 \b, AES-encrypted
877 >4 default x (unknown version)
879 0 string/b QEVM QEMU suspend to disk image
882 # http://wiki.qemu.org/Features/QED/Specification
883 0 string/b QED\0 QEMU QED Image
886 64 string/b \x7f\x10\xda\xbe VDI Image
887 >68 string/b \x01\x00\x01\x00 version 1.1
889 >368 lequad x \b, %lld bytes
891 0 string/b Bochs\ Virtual\ HD\ Image Bochs disk image,
892 >32 string x type %s,
893 >48 string x subtype %s
895 0 lelong 0x02468ace Bochs Sparse disk image
897 # from http://filext.com by Derek M Jones <derek@knosof.co.uk>
898 # False positive with PPT (also currently this string is too long)
899 #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
900 0 string/b \320\317\021\340\241\261\032\341 Microsoft Office Document
901 #>48 byte 0x1B Excel Document
902 #!:mime application/vnd.ms-excel
903 >546 string bjbj Microsoft Word Document
904 !:mime application/msword
905 >546 string jbjb Microsoft Word Document
906 !:mime application/msword
908 0 string/b \224\246\056 Microsoft Word Document
909 !:mime application/msword
911 512 string R\0o\0o\0t\0\ \0E\0n\0t\0r\0y Microsoft Word Document
912 !:mime application/msword
914 # From: "Nelson A. de Oliveira" <naoliv@gmail.com>
915 # Magic type for Dell's BIOS .hdr files
918 >23 string Dell %s system BIOS
920 >>48 byte x version %d.
924 >>48 string x version %.3s
926 # Type: Microsoft DirectDraw Surface
927 # URL: http://msdn.microsoft.com/library/default.asp?url=/library/en-us/directx9_c/directx/graphics/reference/DDSFileReference/ddsfileformat.asp
928 # From: Morten Hustveit <morten@debian.org>
929 0 string/b DDS\040\174\000\000\000 Microsoft DirectDraw Surface (DDS),
934 # Type: Microsoft Document Imaging Format (.mdi)
935 # URL: http://en.wikipedia.org/wiki/Microsoft_Document_Imaging_Format
936 # From: Daniele Sempione <scrows@oziosi.org>
937 0 short 0x5045 Microsoft Document Imaging Format
939 # MS eBook format (.lit)
940 0 string/b ITOLITLS Microsoft Reader eBook Data
941 >8 lelong x \b, version %u
942 !:mime application/x-ms-reader
944 # Windows CE Binary Image Data Format
945 # From: Dr. Jesus <j@hug.gs>
946 0 string/b B000FF\n Windows Embedded CE binary image
948 # Windows Imaging (WIM) Image
949 0 string/b MSWIM\000\000\000 Windows imaging (WIM) image
951 # The second byte of these signatures is a file version; I don't know what,
952 # if anything, produced files with version numbers 0-2.
953 # From: John Elliott <johne@seasip.demon.co.uk>
954 0 string \xfc\x03\x00 Mallard BASIC program data (v1.11)
955 0 string \xfc\x04\x00 Mallard BASIC program data (v1.29+)
956 0 string \xfc\x03\x01 Mallard BASIC protected program data (v1.11)
957 0 string \xfc\x04\x01 Mallard BASIC protected program data (v1.29+)
959 0 string MIOPEN Mallard BASIC Jetsam data
960 0 string Jetsam0 Mallard BASIC Jetsam index data