| blob | 716e266dcb3ec0c019329244adc4fa9ad26cfd01 |
2 #------------------------------------------------------------------------------
3 # $File: msdos,v 1.75 2011/08/08 08:56:17 christos Exp $
4 # msdos: file(1) magic for MS-DOS files
5 #
7 # .BAT files (Daniel Quinlan, quinlan@yggdrasil.com)
8 # updated by Joerg Jenderek at Oct 2008,Apr 2011
9 0 string/t @
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
24 100 search/0xffff say
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
28 #>4 ledate x stamp %s
29 0 leshort 0x166 MS Windows COFF MIPS R4000 object file
30 #>4 ledate x stamp %s
31 0 leshort 0x184 MS Windows COFF Alpha object file
32 #>4 ledate x stamp %s
33 0 leshort 0x268 MS Windows COFF Motorola 68000 object file
34 #>4 ledate x stamp %s
35 0 leshort 0x1f0 MS Windows COFF PowerPC object file
36 #>4 ledate x stamp %s
37 0 leshort 0x290 MS Windows COFF PA-RISC object file
38 #>4 ledate x stamp %s
40 # Tests for various EXE types.
41 #
42 # Many of the compressed formats were extraced from IDARC 1.23 source code.
43 #
44 0 string MZ
45 !:mime application/x-dosexec
46 # All non-DOS EXE extensions have the relocation table more than 0x40 bytes into the file.
47 >0x18 leshort <0x40 MS-DOS executable
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
54 # not a DOS EXE.
55 >0x18 leshort >0x3f
57 # Maybe it's a PE?
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
63 >>>>&0 leshort x 0x%x
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 0x1f0 PowerPC
87 >>>(0x3c.l+4) leshort 0x200 Intel Itanium
88 >>>(0x3c.l+4) leshort 0x266 MIPS16
89 >>>(0x3c.l+4) leshort 0x268 Motorola 68000
90 >>>(0x3c.l+4) leshort 0x290 PA-RISC
91 >>>(0x3c.l+4) leshort 0x366 MIPSIV
92 >>>(0x3c.l+4) leshort 0x466 MIPS16 with FPU
93 >>>(0x3c.l+4) leshort 0xebc EFI byte code
94 >>>(0x3c.l+4) leshort 0x8664 x86-64
95 >>>(0x3c.l+4) leshort 0xc0ee MSIL
96 >>>(0x3c.l+4) default x Unknown processor type
97 >>>>&0 leshort x 0x%x
98 >>>(0x3c.l+22) leshort&0x0200 >0 (stripped to external PDB)
99 >>>(0x3c.l+22) leshort&0x1000 >0 system file
100 >>>(0x3c.l+24) leshort 0x010b
101 >>>>(0x3c.l+232) lelong >0 Mono/.Net assembly
102 >>>(0x3c.l+24) leshort 0x020b
103 >>>>(0x3c.l+248) lelong >0 Mono/.Net assembly
105 # hooray, there's a DOS extender using the PE format, with a valid PE
106 # executable inside (which just prints a message and exits if run in win)
107 >>>(8.s*16) string 32STUB \b, 32rtm DOS extender
108 >>>(8.s*16) string !32STUB \b, for MS Windows
109 >>>(0x3c.l+0xf8) string UPX0 \b, UPX compressed
110 >>>(0x3c.l+0xf8) search/0x140 PEC2 \b, PECompact2 compressed
111 >>>(0x3c.l+0xf8) search/0x140 UPX2
112 >>>>(&0x10.l+(-4)) string PK\3\4 \b, ZIP self-extracting archive (Info-Zip)
113 >>>(0x3c.l+0xf8) search/0x140 .idata
114 >>>>(&0xe.l+(-4)) string PK\3\4 \b, ZIP self-extracting archive (Info-Zip)
115 >>>>(&0xe.l+(-4)) string ZZ0 \b, ZZip self-extracting archive
116 >>>>(&0xe.l+(-4)) string ZZ1 \b, ZZip self-extracting archive
117 >>>(0x3c.l+0xf8) search/0x140 .rsrc
118 >>>>(&0x0f.l+(-4)) string a\\\4\5 \b, WinHKI self-extracting archive
119 >>>>(&0x0f.l+(-4)) string Rar! \b, RAR self-extracting archive
120 >>>>(&0x0f.l+(-4)) search/0x3000 MSCF \b, InstallShield self-extracting archive
121 >>>>(&0x0f.l+(-4)) search/32 Nullsoft \b, Nullsoft Installer self-extracting archive
122 >>>(0x3c.l+0xf8) search/0x140 .data
123 >>>>(&0x0f.l) string WEXTRACT \b, MS CAB-Installer self-extracting archive
124 >>>(0x3c.l+0xf8) search/0x140 .petite\0 \b, Petite compressed
125 >>>>(0x3c.l+0xf7) byte x
126 >>>>>(&0x104.l+(-4)) string =!sfx! \b, ACE self-extracting archive
127 >>>(0x3c.l+0xf8) search/0x140 .WISE \b, WISE installer self-extracting archive
128 >>>(0x3c.l+0xf8) search/0x140 .dz\0\0\0 \b, Dzip self-extracting archive
129 >>>&(0x3c.l+0xf8) search/0x100 _winzip_ \b, ZIP self-extracting archive (WinZip)
130 >>>&(0x3c.l+0xf8) search/0x100 SharedD \b, Microsoft Installer self-extracting archive
131 >>>0x30 string Inno \b, InnoSetup self-extracting archive
133 # Hmm, not a PE but the relocation table is too high for a traditional DOS exe,
134 # must be one of the unusual subformats.
135 >>(0x3c.l) string !PE\0\0 MS-DOS executable
137 >>(0x3c.l) string NE \b, NE
138 >>>(0x3c.l+0x36) byte 1 for OS/2 1.x
139 >>>(0x3c.l+0x36) byte 2 for MS Windows 3.x
140 >>>(0x3c.l+0x36) byte 3 for MS-DOS
141 >>>(0x3c.l+0x36) byte 4 for Windows 386
142 >>>(0x3c.l+0x36) byte 5 for Borland Operating System Services
143 >>>(0x3c.l+0x36) default x
144 >>>>(0x3c.l+0x36) byte x (unknown OS %x)
145 >>>(0x3c.l+0x36) byte 0x81 for MS-DOS, Phar Lap DOS extender
146 >>>(0x3c.l+0x0c) leshort&0x8003 0x8002 (DLL)
147 >>>(0x3c.l+0x0c) leshort&0x8003 0x8001 (driver)
148 >>>&(&0x24.s-1) string ARJSFX \b, ARJ self-extracting archive
149 >>>(0x3c.l+0x70) search/0x80 WinZip(R)\ Self-Extractor \b, ZIP self-extracting archive (WinZip)
151 >>(0x3c.l) string LX\0\0 \b, LX
152 >>>(0x3c.l+0x0a) leshort <1 (unknown OS)
153 >>>(0x3c.l+0x0a) leshort 1 for OS/2
154 >>>(0x3c.l+0x0a) leshort 2 for MS Windows
155 >>>(0x3c.l+0x0a) leshort 3 for DOS
156 >>>(0x3c.l+0x0a) leshort >3 (unknown OS)
157 >>>(0x3c.l+0x10) lelong&0x28000 =0x8000 (DLL)
158 >>>(0x3c.l+0x10) lelong&0x20000 >0 (device driver)
159 >>>(0x3c.l+0x10) lelong&0x300 0x300 (GUI)
160 >>>(0x3c.l+0x10) lelong&0x28300 <0x300 (console)
161 >>>(0x3c.l+0x08) leshort 1 i80286
162 >>>(0x3c.l+0x08) leshort 2 i80386
163 >>>(0x3c.l+0x08) leshort 3 i80486
164 >>>(8.s*16) string emx \b, emx
165 >>>>&1 string x %s
166 >>>&(&0x54.l-3) string arjsfx \b, ARJ self-extracting archive
168 # MS Windows system file, supposedly a collection of LE executables
169 >>(0x3c.l) string W3 \b, W3 for MS Windows
171 >>(0x3c.l) string LE\0\0 \b, LE executable
172 >>>(0x3c.l+0x0a) leshort 1
173 # some DOS extenders use LE files with OS/2 header
174 >>>>0x240 search/0x100 DOS/4G for MS-DOS, DOS4GW DOS extender
175 >>>>0x240 search/0x200 WATCOM\ C/C++ for MS-DOS, DOS4GW DOS extender
176 >>>>0x440 search/0x100 CauseWay\ DOS\ Extender for MS-DOS, CauseWay DOS extender
177 >>>>0x40 search/0x40 PMODE/W for MS-DOS, PMODE/W DOS extender
178 >>>>0x40 search/0x40 STUB/32A for MS-DOS, DOS/32A DOS extender (stub)
179 >>>>0x40 search/0x80 STUB/32C for MS-DOS, DOS/32A DOS extender (configurable stub)
180 >>>>0x40 search/0x80 DOS/32A for MS-DOS, DOS/32A DOS extender (embedded)
181 # this is a wild guess; hopefully it is a specific signature
182 >>>>&0x24 lelong <0x50
183 >>>>>(&0x4c.l) string \xfc\xb8WATCOM
184 >>>>>>&0 search/8 3\xdbf\xb9 \b, 32Lite compressed
185 # another wild guess: if real OS/2 LE executables exist, they probably have higher start EIP
186 #>>>>(0x3c.l+0x1c) lelong >0x10000 for OS/2
187 # fails with DOS-Extenders.
188 >>>(0x3c.l+0x0a) leshort 2 for MS Windows
189 >>>(0x3c.l+0x0a) leshort 3 for DOS
190 >>>(0x3c.l+0x0a) leshort 4 for MS Windows (VxD)
191 >>>(&0x7c.l+0x26) string UPX \b, UPX compressed
192 >>>&(&0x54.l-3) string UNACE \b, ACE self-extracting archive
194 # looks like ASCII, probably some embedded copyright message.
195 # and definitely not NE/LE/LX/PE
196 >>0x3c lelong >0x20000000
197 >>>(4.s*512) leshort !0x014c \b, MZ for MS-DOS
198 # header data too small for extended executable
199 >2 long !0
200 >>0x18 leshort <0x40
201 >>>(4.s*512) leshort !0x014c
203 >>>>&(2.s-514) string !LE
204 >>>>>&-2 string !BW \b, MZ for MS-DOS
205 >>>>&(2.s-514) string LE \b, LE
206 >>>>>0x240 search/0x100 DOS/4G for MS-DOS, DOS4GW DOS extender
207 # educated guess since indirection is still not capable enough for complex offset
208 # calculations (next embedded executable would be at &(&2*512+&0-2)
209 # I suspect there are only LE executables in these multi-exe files
210 >>>>&(2.s-514) string BW
211 >>>>>0x240 search/0x100 DOS/4G ,\b LE for MS-DOS, DOS4GW DOS extender (embedded)
212 >>>>>0x240 search/0x100 !DOS/4G ,\b BW collection for MS-DOS
214 # This sequence skips to the first COFF segment, usually .text
215 >(4.s*512) leshort 0x014c \b, COFF
216 >>(8.s*16) string go32stub for MS-DOS, DJGPP go32 DOS extender
217 >>(8.s*16) string emx
218 >>>&1 string x for DOS, Win or OS/2, emx %s
219 >>&(&0x42.l-3) byte x
220 >>>&0x26 string UPX \b, UPX compressed
221 # and yet another guess: small .text, and after large .data is unusal, could be 32lite
222 >>&0x2c search/0xa0 .text
223 >>>&0x0b lelong <0x2000
224 >>>>&0 lelong >0x6000 \b, 32lite compressed
226 >(8.s*16) string $WdX \b, WDos/X DOS extender
228 # By now an executable type should have been printed out. The executable
229 # may be a self-uncompressing archive, so look for evidence of that and
230 # print it out.
231 #
232 # Some signatures below from Greg Roelofs, newt@uchicago.edu.
233 #
234 >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
235 >0xe7 string LH/2\ Self-Extract \b, %s
236 >0x1c string UC2X \b, UCEXE compressed
237 >0x1c string WWP\ \b, WWPACK compressed
238 >0x1c string RJSX \b, ARJ self-extracting archive
239 >0x1c string diet \b, diet compressed
240 >0x1c string LZ09 \b, LZEXE v0.90 compressed
241 >0x1c string LZ91 \b, LZEXE v0.91 compressed
242 >0x1c string tz \b, TinyProg compressed
243 >0x1e string Copyright\ 1989-1990\ PKWARE\ Inc. Self-extracting PKZIP archive
244 !:mime application/zip
245 # Yes, this really is "Copr", not "Corp."
246 >0x1e string PKLITE\ Copr. Self-extracting PKZIP archive
247 !:mime application/zip
248 # winarj stores a message in the stub instead of the sig in the MZ header
249 >0x20 search/0xe0 aRJsfX \b, ARJ self-extracting archive
250 >0x20 string AIN
251 >>0x23 string 2 \b, AIN 2.x compressed
252 >>0x23 string <2 \b, AIN 1.x compressed
253 >>0x23 string >2 \b, AIN 1.x compressed
254 >0x24 string LHa's\ SFX \b, LHa self-extracting archive
255 !:mime application/x-lha
256 >0x24 string LHA's\ SFX \b, LHa self-extracting archive
257 !:mime application/x-lha
258 >0x24 string \ $ARX \b, ARX self-extracting archive
259 >0x24 string \ $LHarc \b, LHarc self-extracting archive
260 >0x20 string SFX\ by\ LARC \b, LARC self-extracting archive
261 >0x40 string aPKG \b, aPackage self-extracting archive
262 >0x64 string W\ Collis\0\0 \b, Compack compressed
263 >0x7a string Windows\ self-extracting\ ZIP \b, ZIP self-extracting archive
264 >>&0xf4 search/0x140 \x0\x40\x1\x0
265 >>>(&0.l+(4)) string MSCF \b, WinHKI CAB self-extracting archive
266 >1638 string -lh5- \b, LHa self-extracting archive v2.13S
267 >0x17888 string Rar! \b, RAR self-extracting archive
269 # Skip to the end of the EXE. This will usually work fine in the PE case
270 # because the MZ image is hardcoded into the toolchain and almost certainly
271 # won't match any of these signatures.
272 >(4.s*512) long x
273 >>&(2.s-517) byte x
274 >>>&0 string PK\3\4 \b, ZIP self-extracting archive
275 >>>&0 string Rar! \b, RAR self-extracting archive
276 >>>&0 string =!\x11 \b, AIN 2.x self-extracting archive
277 >>>&0 string =!\x12 \b, AIN 2.x self-extracting archive
278 >>>&0 string =!\x17 \b, AIN 1.x self-extracting archive
279 >>>&0 string =!\x18 \b, AIN 1.x self-extracting archive
280 >>>&7 search/400 **ACE** \b, ACE self-extracting archive
281 >>>&0 search/0x480 UC2SFX\ Header \b, UC2 self-extracting archive
283 # a few unknown ZIP sfxes, no idea if they are needed or if they are
284 # already captured by the generic patterns above
285 >(8.s*16) search/0x20 PKSFX \b, ZIP self-extracting archive (PKZIP)
286 # TODO: how to add this? >FileSize-34 string Windows\ Self-Installing\ Executable \b, ZIP self-extracting archive
287 #
289 # TELVOX Teleinformatica CODEC self-extractor for OS/2:
290 >49801 string \x79\xff\x80\xff\x76\xff \b, CODEC archive v3.21
291 >>49824 leshort =1 \b, 1 file
292 >>49824 leshort >1 \b, %u files
294 # added by Joerg Jenderek of http://www.freedos.org/software/?prog=kc
295 # and http://www.freedos.org/software/?prog=kpdos
296 # for FreeDOS files like KEYBOARD.SYS, KEYBRD2.SYS, KEYBRD3.SYS, *.KBD
297 0 string KCF FreeDOS KEYBoard Layout collection
298 # only version=0x100 found
299 >3 uleshort x \b, version 0x%x
300 # length of string containing author,info and special characters
301 >6 ubyte >0
302 #>>6 pstring x \b, name=%s
303 >>7 string >\0 \b, author=%-.14s
304 >>7 search/254 \xff \b, info=
305 #>>>&0 string x \b%-s
306 >>>&0 string x \b%-.15s
307 # for FreeDOS *.KL files
308 0 string KLF FreeDOS KEYBoard Layout file
309 # only version=0x100 or 0x101 found
310 >3 uleshort x \b, version 0x%x
311 # stringlength
312 >5 ubyte >0
313 >>8 string x \b, name=%-.2s
314 0 string \xffKEYB\ \ \ \0\0\0\0
315 >12 string \0\0\0\0`\x04\360 MS-DOS KEYBoard Layout file
317 # .COM formats (Daniel Quinlan, quinlan@yggdrasil.com)
318 # Uncommenting only the first two lines will cover about 2/3 of COM files,
319 # but it isn't feasible to match all COM files since there must be at least
320 # two dozen different one-byte "magics".
321 # test too generic ?
322 0 byte 0xe9 DOS executable (COM)
323 >0x1FE leshort 0xAA55 \b, boot code
324 >6 string SFX\ of\ LHarc (%s)
326 # DOS device driver updated by Joerg Jenderek at May 2011
327 # http://maben.homeip.net/static/S100/IBM/software/DOS/DOS%20techref/CHAPTER.009
328 0 ulequad&0x07a0ffffffff 0xffffffff DOS executable (
329 >40 search/7 UPX! \bUPX compressed
330 # DOS device driver attributes
331 >4 uleshort&0x8000 0x0000 \bblock device driver
332 # character device
333 >4 uleshort&0x8000 0x8000 \b
334 >>4 uleshort&0x0008 0x0008 \bclock
335 # fast video output by int 29h
336 >>4 uleshort&0x0010 0x0010 \bfast
337 # standard input/output device
338 >>4 uleshort&0x0003 >0 \bstandard
339 >>>4 uleshort&0x0001 0x0001 \binput
340 >>>4 uleshort&0x0003 0x0003 \b/
341 >>>4 uleshort&0x0002 0x0002 \boutput
342 >>4 uleshort&0x8000 0x8000 \bcharacter device driver
343 >0 ubyte x
344 # upx compressed device driver has garbage instead of real in name field of header
345 >>40 search/7 UPX!
346 >>40 default x
347 # leading/trailing nulls, zeros or non ASCII characters in 8-byte name field at offset 10 are skipped
348 >>>12 ubyte >0x27 \b
349 >>>>10 ubyte >0x20
350 >>>>>10 ubyte !0x2E
351 >>>>>>10 ubyte !0x2A \b%c
352 >>>>11 ubyte >0x20
353 >>>>>11 ubyte !0x2E \b%c
354 >>>>12 ubyte >0x20
355 >>>>>12 ubyte !0x39
356 >>>>>>12 ubyte !0x2E \b%c
357 >>>13 ubyte >0x20
358 >>>>13 ubyte !0x2E \b%c
359 >>>>14 ubyte >0x20
360 >>>>>14 ubyte !0x2E \b%c
361 >>>>15 ubyte >0x20
362 >>>>>15 ubyte !0x2E \b%c
363 >>>>16 ubyte >0x20
364 >>>>>16 ubyte !0x2E
365 >>>>>>16 ubyte <0xCB \b%c
366 >>>>17 ubyte >0x20
367 >>>>>17 ubyte !0x2E
368 >>>>>>17 ubyte <0x90 \b%c
369 # some character device drivers like ASPICD.SYS, btcdrom.sys and Cr_atapi.sys contain only spaces or points in name field
370 >>>4 uleshort&0x8000 0x8000
371 >>>>12 ubyte <0x2F
372 # they have their real name at offset 22
373 >>>>>22 string >\0 \b%-.5s
374 >4 uleshort&0x8000 0x0000
375 # 32 bit sector adressing ( > 32 MB) for block devices
376 >>4 uleshort&0x0002 0x0002 \b,32-bit sector-
377 # support by driver functions 13h, 17h, 18h
378 >4 uleshort&0x0040 0x0040 \b,IOCTL-
379 # open, close, removable media support by driver functions 0Dh, 0Eh, 0Fh
380 >4 uleshort&0x0800 0x0800 \b,close media-
381 # output until busy support by int 10h for character device driver
382 >4 uleshort&0x8000 0x8000
383 >>4 uleshort&0x2000 0x2000 \b,until busy-
384 # direct read/write support by driver functions 03h,0Ch
385 >4 uleshort&0x4000 0x4000 \b,control strings-
386 >4 uleshort&0x8000 0x8000
387 >>4 uleshort&0x6840 >0 \bsupport
388 >4 uleshort&0x8000 0x0000
389 >>4 uleshort&0x4842 >0 \bsupport
390 >0 ubyte x \b)
391 # DOS driver cmd640x.sys has 0x12 instead of 0xffffffff for pointer field to next device header
392 # Too weak, matches files that only contain 0's
393 #0 ulequad&0x000007a0ffffffed 0x0000000000000000 DOS-executable (
394 #>4 uleshort&0x8000 0x8000 \bcharacter device driver
395 #>>10 string x %-.8s
396 #>4 uleshort&0x4000 0x4000 \b,control strings-support)
398 # test too generic ?
399 0 byte 0x8c DOS executable (COM)
400 # updated by Joerg Jenderek at Oct 2008
401 0 ulelong 0xffff10eb DR-DOS executable (COM)
402 # byte 0xeb conflicts with "sequent" magic leshort 0xn2eb
403 0 ubeshort&0xeb8d >0xeb00
404 # DR-DOS STACKER.COM SCREATE.SYS missed
405 >0 byte 0xeb DOS executable (COM)
406 >>0x1FE leshort 0xAA55 \b, boot code
407 >>85 string UPX \b, UPX compressed
408 >>4 string \ $ARX \b, ARX self-extracting archive
409 >>4 string \ $LHarc \b, LHarc self-extracting archive
410 >>0x20e string SFX\ by\ LARC \b, LARC self-extracting archive
411 # updated by Joerg Jenderek at Oct 2008
412 #0 byte 0xb8 COM executable
413 0 uleshort&0x80ff 0x00b8
414 # modified by Joerg Jenderek
415 >1 lelong !0x21cd4cff COM executable for DOS
416 # http://syslinux.zytor.com/comboot.php
417 # (32-bit COMBOOT) programs *.C32 contain 32-bit code and run in flat-memory 32-bit protected mode
418 # start with assembler instructions mov eax,21cd4cffh
419 0 uleshort&0xc0ff 0xc0b8
420 >1 lelong 0x21cd4cff COM executable (32-bit COMBOOT)
421 # syslinux:doc/comboot.txt
422 # A COM32R program must start with the byte sequence B8 FE 4C CD 21 (mov
423 # eax,21cd4cfeh) as a magic number.
424 0 string \xb8\xfe\x4c\xcd\x21 COM executable (COM32R)
425 # start with assembler instructions mov eax,21cd4cfeh
426 0 uleshort&0xc0ff 0xc0b8
427 >1 lelong 0x21cd4cfe COM executable (32-bit COMBOOT, relocatable)
428 0 string \x81\xfc
429 >4 string \x77\x02\xcd\x20\xb9
430 >>36 string UPX! FREE-DOS executable (COM), UPX compressed
431 252 string Must\ have\ DOS\ version DR-DOS executable (COM)
432 # added by Joerg Jenderek at Oct 2008
433 # GRR search is not working
434 #34 search/2 UPX! FREE-DOS executable (COM), UPX compressed
435 34 string UPX! FREE-DOS executable (COM), UPX compressed
436 35 string UPX! FREE-DOS executable (COM), UPX compressed
437 # GRR search is not working
438 #2 search/28 \xcd\x21 COM executable for MS-DOS
439 #WHICHFAT.cOM
440 2 string \xcd\x21 COM executable for DOS
441 #DELTREE.cOM DELTREE2.cOM
442 4 string \xcd\x21 COM executable for DOS
443 #IFMEMDSK.cOM ASSIGN.cOM COMP.cOM
444 5 string \xcd\x21 COM executable for DOS
445 #DELTMP.COm HASFAT32.cOM
446 7 string \xcd\x21
447 >0 byte !0xb8 COM executable for DOS
448 #COMP.cOM MORE.COm
449 10 string \xcd\x21
450 >5 string !\xcd\x21 COM executable for DOS
451 #comecho.com
452 13 string \xcd\x21 COM executable for DOS
453 #HELP.COm EDIT.coM
454 18 string \xcd\x21 COM executable for MS-DOS
455 #NWRPLTRM.COm
456 23 string \xcd\x21 COM executable for MS-DOS
457 #LOADFIX.cOm LOADFIX.cOm
458 30 string \xcd\x21 COM executable for MS-DOS
459 #syslinux.com 3.11
460 70 string \xcd\x21 COM executable for DOS
461 # many compressed/converted COMs start with a copy loop instead of a jump
462 0x6 search/0xa \xfc\x57\xf3\xa5\xc3 COM executable for MS-DOS
463 0x6 search/0xa \xfc\x57\xf3\xa4\xc3 COM executable for DOS
464 >0x18 search/0x10 \x50\xa4\xff\xd5\x73 \b, aPack compressed
465 0x3c string W\ Collis\0\0 COM executable for MS-DOS, Compack compressed
466 # FIXME: missing diet .com compression
468 # miscellaneous formats
469 0 string LZ MS-DOS executable (built-in)
470 #0 byte 0xf0 MS-DOS program library data
471 #
473 # AAF files:
474 # <stuartc@rd.bbc.co.uk> Stuart Cunningham
475 0 string \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
476 >30 byte 9 (512B sectors)
477 >30 byte 12 (4kB sectors)
478 0 string \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
479 >30 byte 9 (512B sectors)
480 >30 byte 12 (4kB sectors)
482 # Popular applications
483 2080 string Microsoft\ Word\ 6.0\ Document %s
484 !:mime application/msword
485 2080 string Documento\ Microsoft\ Word\ 6 Spanish Microsoft Word 6 document data
486 !:mime application/msword
487 # Pawel Wiecek <coven@i17linuxb.ists.pwr.wroc.pl> (for polish Word)
488 2112 string MSWordDoc Microsoft Word document data
489 !:mime application/msword
490 #
491 0 belong 0x31be0000 Microsoft Word Document
492 !:mime application/msword
493 #
494 0 string PO^Q` Microsoft Word 6.0 Document
495 !:mime application/msword
496 #
497 0 string \376\067\0\043 Microsoft Office Document
498 !:mime application/msword
499 0 string \333\245-\0\0\0 Microsoft Office Document
500 !:mime application/msword
501 512 string \354\245\301 Microsoft Word Document
502 !:mime application/msword
503 #
504 2080 string Microsoft\ Excel\ 5.0\ Worksheet %s
505 !:mime application/vnd.ms-excel
507 2080 string Foglio\ di\ lavoro\ Microsoft\ Exce %s
508 !:mime application/vnd.ms-excel
509 #
510 # Pawel Wiecek <coven@i17linuxb.ists.pwr.wroc.pl> (for polish Excel)
511 2114 string Biff5 Microsoft Excel 5.0 Worksheet
512 !:mime application/vnd.ms-excel
513 # Italian MS-Excel
514 2121 string Biff5 Microsoft Excel 5.0 Worksheet
515 !:mime application/vnd.ms-excel
516 0 string \x09\x04\x06\x00\x00\x00\x10\x00 Microsoft Excel Worksheet
517 !:mime application/vnd.ms-excel
518 #
519 0 belong 0x00001a00 Lotus 1-2-3
520 !:mime application/x-123
521 >4 belong 0x00100400 wk3 document data
522 >4 belong 0x02100400 wk4 document data
523 >4 belong 0x07800100 fm3 or fmb document data
524 >4 belong 0x07800000 fm3 or fmb document data
525 #
526 0 belong 0x00000200 Lotus 1-2-3
527 !:mime application/x-123
528 >4 belong 0x06040600 wk1 document data
529 >4 belong 0x06800200 fmt document data
530 0 string WordPro\0 Lotus WordPro
531 !:mime application/vnd.lotus-wordpro
532 0 string WordPro\r\373 Lotus WordPro
533 !:mime application/vnd.lotus-wordpro
536 # Summary: Script used by InstallScield to uninstall applications
537 # Extension: .isu
538 # Submitted by: unknown
539 # Modified by (1): Abel Cheung <abelcheung@gmail.com> (replace useless entry)
540 0 string \x71\xa8\x00\x00\x01\x02
541 >12 string Stirling\ Technologies, InstallShield Uninstall Script
543 # Winamp .avs
544 #0 string Nullsoft\ AVS\ Preset\ \060\056\061\032 A plug in for Winamp ms-windows Freeware media player
545 0 string Nullsoft\ AVS\ Preset\ Winamp plug in
547 # Windows Metafont .WMF
548 0 string \327\315\306\232 ms-windows metafont .wmf
549 0 string \002\000\011\000 ms-windows metafont .wmf
550 0 string \001\000\011\000 ms-windows metafont .wmf
552 #tz3 files whatever that is (MS Works files)
553 0 string \003\001\001\004\070\001\000\000 tz3 ms-works file
554 0 string \003\002\001\004\070\001\000\000 tz3 ms-works file
555 0 string \003\003\001\004\070\001\000\000 tz3 ms-works file
557 # PGP sig files .sig
558 #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
559 0 string \211\000\077\003\005\000\063\237\127\065\027\266\151\064\005\045\101\233\021\002 PGP sig
560 0 string \211\000\077\003\005\000\063\237\127\066\027\266\151\064\005\045\101\233\021\002 PGP sig
561 0 string \211\000\077\003\005\000\063\237\127\067\027\266\151\064\005\045\101\233\021\002 PGP sig
562 0 string \211\000\077\003\005\000\063\237\127\070\027\266\151\064\005\045\101\233\021\002 PGP sig
563 0 string \211\000\077\003\005\000\063\237\127\071\027\266\151\064\005\045\101\233\021\002 PGP sig
564 0 string \211\000\225\003\005\000\062\122\207\304\100\345\042 PGP sig
566 # windows zips files .dmf
567 0 string MDIF\032\000\010\000\000\000\372\046\100\175\001\000\001\036\001\000 MS Windows special zipped file
570 #ico files
571 0 string \102\101\050\000\000\000\056\000\000\000\000\000\000\000 Icon for MS Windows
573 # Windows icons (Ian Springer <ips@fpk.hp.com>)
574 0 string \000\000\001\000 MS Windows icon resource
575 !:mime image/x-icon
576 >4 byte 1 - 1 icon
577 >4 byte >1 - %d icons
578 >>6 byte >0 \b, %dx
579 >>>7 byte >0 \b%d
580 >>8 byte 0 \b, 256-colors
581 >>8 byte >0 \b, %d-colors
584 # .chr files
585 0 string PK\010\010BGI Borland font
586 >4 string >\0 %s
587 # then there is a copyright notice
590 # .bgi files
591 0 string pk\010\010BGI Borland device
592 >4 string >\0 %s
593 # then there is a copyright notice
596 # Windows Recycle Bin record file (named INFO2)
597 # By Abel Cheung (abelcheung AT gmail dot com)
598 # Version 4 always has 280 bytes (0x118) per record, version 5 has 800 bytes
599 # Since Vista uses another structure, INFO2 structure probably won't change
600 # anymore. Detailed analysis in:
601 # http://www.cybersecurityinstitute.biz/downloads/INFO2.pdf
602 0 lelong 0x00000004
603 >12 lelong 0x00000118 Windows Recycle Bin INFO2 file (Win98 or below)
605 0 lelong 0x00000005
606 >12 lelong 0x00000320 Windows Recycle Bin INFO2 file (Win2k - WinXP)
609 ##### put in Either Magic/font or Magic/news
610 # Acroread or something files wrongly identified as G3 .pfm
611 # these have the form \000 \001 any? \002 \000 \000
612 # or \000 \001 any? \022 \000 \000
613 0 belong&0xffff00ff 0x00010012 PFM data
614 >4 string \000\000
615 >6 string >\060 - %s
617 0 belong&0xffff00ff 0x00010002 PFM data
618 >4 string \000\000
619 >6 string >\060 - %s
620 #0 string \000\001 pfm?
621 #>3 string \022\000\000Copyright\ yes
622 #>3 string \002\000\000Copyright\ yes
623 #>3 string >\0 oops, not a font file. Cancel that.
624 #it clashes with ttf files so put it lower down.
626 # From Doug Lee via a FreeBSD pr
627 9 string GERBILDOC First Choice document
628 9 string GERBILDB First Choice database
629 9 string GERBILCLIP First Choice database
630 0 string GERBIL First Choice device file
631 9 string RABBITGRAPH RabbitGraph file
632 0 string DCU1 Borland Delphi .DCU file
633 0 string =!<spell> MKS Spell hash list (old format)
634 0 string =!<spell2> MKS Spell hash list
635 # Too simple - MPi
636 #0 string AH Halo(TM) bitmapped font file
637 0 lelong 0x08086b70 TurboC BGI file
638 0 lelong 0x08084b50 TurboC Font file
640 # WARNING: below line conflicts with Infocom game data Z-machine 3
641 0 byte 0x03
642 >0x02 byte <0x13 DBase 3 data file
643 >>0x04 lelong 0 (no records)
644 >>0x04 lelong >0 (%ld records)
645 0 byte 0x83
646 >0x02 byte <0x13 DBase 3 data file with memo(s)
647 >>0x04 lelong 0 (no records)
648 >>0x04 lelong >0 (%ld records)
649 0 leshort 0x0006 DBase 3 index file
650 0 string PMCC Windows 3.x .GRP file
651 1 string RDC-meg MegaDots
652 >8 byte >0x2F version %c
653 >9 byte >0x2F \b.%c file
654 0 lelong 0x4C
655 >4 lelong 0x00021401 Windows shortcut file
657 # .PIF files added by Joerg Jenderek from http://smsoft.ru/en/pifdoc.htm
658 # only for windows versions equal or greater 3.0
659 0x171 string MICROSOFT\ PIFEX\0 Windows Program Information File
660 !:mime application/x-dosexec
661 #>2 string >\0 \b, Title:%.30s
662 >0x24 string >\0 \b for %.63s
663 >0x65 string >\0 \b, directory=%.64s
664 >0xA5 string >\0 \b, parameters=%.64s
665 #>0x181 leshort x \b, offset %x
666 #>0x183 leshort x \b, offsetdata %x
667 #>0x185 leshort x \b, section length %x
668 >0x187 search/0xB55 WINDOWS\ VMM\ 4.0\0
669 >>&0x5e ubyte >0
670 >>>&-1 string <PIFMGR.DLL \b, icon=%s
671 #>>>&-1 string PIFMGR.DLL \b, icon=%s
672 >>>&-1 string >PIFMGR.DLL \b, icon=%s
673 >>&0xF0 ubyte >0
674 >>>&-1 string <Terminal \b, font=%.32s
675 #>>>&-1 string =Terminal \b, font=%.32s
676 >>>&-1 string >Terminal \b, font=%.32s
677 >>&0x110 ubyte >0
678 >>>&-1 string <Lucida\ Console \b, TrueTypeFont=%.32s
679 #>>>&-1 string =Lucida\ Console \b, TrueTypeFont=%.32s
680 >>>&-1 string >Lucida\ Console \b, TrueTypeFont=%.32s
681 #>0x187 search/0xB55 WINDOWS\ 286\ 3.0\0 \b, Windows 3.X standard mode-style
682 #>0x187 search/0xB55 WINDOWS\ 386\ 3.0\0 \b, Windows 3.X enhanced mode-style
683 >0x187 search/0xB55 WINDOWS\ NT\ \ 3.1\0 \b, Windows NT-style
684 #>0x187 search/0xB55 WINDOWS\ NT\ \ 4.0\0 \b, Windows NT-style
685 >0x187 search/0xB55 CONFIG\ \ SYS\ 4.0\0 \b +CONFIG.SYS
686 #>>&06 string x \b:%s
687 >0x187 search/0xB55 AUTOEXECBAT\ 4.0\0 \b +AUTOEXEC.BAT
688 #>>&06 string x \b:%s
690 # DOS EPS Binary File Header
691 # From: Ed Sznyter <ews@Black.Market.NET>
692 0 belong 0xC5D0D3C6 DOS EPS Binary File
693 >4 long >0 Postscript starts at byte %d
694 >>8 long >0 length %d
695 >>>12 long >0 Metafile starts at byte %d
696 >>>>16 long >0 length %d
697 >>>20 long >0 TIFF starts at byte %d
698 >>>>24 long >0 length %d
700 # TNEF magic From "Joomy" <joomy@se-ed.net>
701 # Microsoft Outlook's Transport Neutral Encapsulation Format (TNEF)
702 0 leshort 0x223e9f78 TNEF
703 !:mime application/vnd.ms-tnef
705 # HtmlHelp files (.chm)
706 0 string ITSF\003\000\000\000\x60\000\000\000\001\000\000\000 MS Windows HtmlHelp Data
708 # GFA-BASIC (Wolfram Kleff)
709 2 string GFA-BASIC3 GFA-BASIC 3 data
711 #------------------------------------------------------------------------------
712 # From Stuart Caie <kyzer@4u.net> (developer of cabextract)
713 # Microsoft Cabinet files
714 0 string MSCF\0\0\0\0 Microsoft Cabinet archive data
715 !:mime application/vnd.ms-cab-compressed
716 >8 lelong x \b, %u bytes
717 >28 leshort 1 \b, 1 file
718 >28 leshort >1 \b, %u files
720 # InstallShield Cabinet files
721 0 string ISc( InstallShield Cabinet archive data
722 >5 byte&0xf0 =0x60 version 6,
723 >5 byte&0xf0 !0x60 version 4/5,
724 >(12.l+40) lelong x %u files
726 # Windows CE package files
727 0 string MSCE\0\0\0\0 Microsoft WinCE install header
728 >20 lelong 0 \b, architecture-independent
729 >20 lelong 103 \b, Hitachi SH3
730 >20 lelong 104 \b, Hitachi SH4
731 >20 lelong 0xA11 \b, StrongARM
732 >20 lelong 4000 \b, MIPS R4000
733 >20 lelong 10003 \b, Hitachi SH3
734 >20 lelong 10004 \b, Hitachi SH3E
735 >20 lelong 10005 \b, Hitachi SH4
736 >20 lelong 70001 \b, ARM 7TDMI
737 >52 leshort 1 \b, 1 file
738 >52 leshort >1 \b, %u files
739 >56 leshort 1 \b, 1 registry entry
740 >56 leshort >1 \b, %u registry entries
743 # Windows Enhanced Metafile (EMF)
744 # See msdn.microsoft.com/archive/en-us/dnargdi/html/msdn_enhmeta.asp
745 # for further information.
746 0 ulelong 1
747 >40 string \ EMF Windows Enhanced Metafile (EMF) image data
748 >>44 ulelong x version 0x%x
750 # From: Alex Beregszaszi <alex@fsn.hu>
751 0 string COWD VMWare3
752 >4 byte 3 disk image
753 >>32 lelong x (%d/
754 >>36 lelong x \b%d/
755 >>40 lelong x \b%d)
756 >4 byte 2 undoable disk image
757 >>32 string >\0 (%s)
759 0 string VMDK VMware4 disk image
760 0 string KDMV VMware4 disk image
762 #--------------------------------------------------------------------
763 # Qemu Emulator Images
764 # Lines written by Friedrich Schwittay (f.schwittay@yousable.de)
765 # Updated by Adam Buchbinder (adam.buchbinder@gmail.com)
766 # Made by reading sources, reading documentation, and doing trial and error
767 # on existing QCOW files
768 0 string QFI\xFB QEMU QCOW Image
770 # Uncomment the following line to display Magic (only used for debugging
771 # this magic number)
772 #>0 string x , Magic: %s
774 # There are currently 2 Versions: "1" and "2".
775 # http://www.gnome.org/~markmc/qcow-image-format-version-1.html
776 >4 belong 1 (v1)
778 # Using the existence of the Backing File Offset to determine whether
779 # to read Backing File Information
780 >>12 belong >0 \b, has backing file (
781 # Note that this isn't a null-terminated string; the length is actually
782 # (16.L). Assuming a null-terminated string happens to work usually, but it
783 # may spew junk until it reaches a \0 in some cases.
784 >>>(12.L) string >\0 \bpath %s
786 # Modification time of the Backing File
787 # Really useful if you want to know if your backing
788 # file is still usable together with this image
789 >>>>20 bedate >0 \b, mtime %s)
790 >>>>20 default x \b)
792 # Size is stored in bytes in a big-endian u64.
793 >>24 bequad x \b, %lld bytes
795 # 1 for AES encryption, 0 for none.
796 >>36 belong 1 \b, AES-encrypted
798 # http://www.gnome.org/~markmc/qcow-image-format.html
799 >4 belong 2 (v2)
800 # Using the existence of the Backing File Offset to determine whether
801 # to read Backing File Information
802 >>8 bequad >0 \b, has backing file
803 # Note that this isn't a null-terminated string; the length is actually
804 # (16.L). Assuming a null-terminated string happens to work usually, but it
805 # may spew junk until it reaches a \0 in some cases. Also, since there's no
806 # .Q modifier, we just use the bottom four bytes as an offset. Note that if
807 # the file is over 4G, and the backing file path is stored after the first 4G,
808 # the wrong filename will be printed. (This should be (8.Q), when that syntax
809 # is introduced.)
810 >>>(12.L) string >\0 (path %s)
811 >>24 bequad x \b, %lld bytes
812 >>32 belong 1 \b, AES-encrypted
814 >4 default x (unknown version)
816 0 string QEVM QEMU suspend to disk image
818 0 string Bochs\ Virtual\ HD\ Image Bochs disk image,
819 >32 string x type %s,
820 >48 string x subtype %s
822 0 lelong 0x02468ace Bochs Sparse disk image
824 # from http://filext.com by Derek M Jones <derek@knosof.co.uk>
825 # False positive with PPT (also currently this string is too long)
826 #0 string \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
827 0 string \320\317\021\340\241\261\032\341 Microsoft Office Document
828 #>48 byte 0x1B Excel Document
829 #!:mime application/vnd.ms-excel
830 >546 string bjbj Microsoft Word Document
831 !:mime application/msword
832 >546 string jbjb Microsoft Word Document
833 !:mime application/msword
835 0 string \224\246\056 Microsoft Word Document
836 !:mime application/msword
838 512 string R\0o\0o\0t\0\ \0E\0n\0t\0r\0y Microsoft Word Document
839 !:mime application/msword
841 # From: "Nelson A. de Oliveira" <naoliv@gmail.com>
842 # Magic type for Dell's BIOS .hdr files
843 # Dell's .hdr
844 0 string $RBU
845 >23 string Dell %s system BIOS
846 >5 byte 2
847 >>48 byte x version %d.
848 >>49 byte x \b%d.
849 >>50 byte x \b%d
850 >5 byte <2
851 >>48 string x version %.3s
853 # Type: Microsoft DirectDraw Surface
854 # URL: http://msdn.microsoft.com/library/default.asp?url=/library/en-us/directx9_c/directx/graphics/reference/DDSFileReference/ddsfileformat.asp
855 # From: Morten Hustveit <morten@debian.org>
856 0 string DDS\040\174\000\000\000 Microsoft DirectDraw Surface (DDS),
857 >16 lelong >0 %hd x
858 >12 lelong >0 %hd,
859 >84 string x %.4s
861 # Type: Microsoft Document Imaging Format (.mdi)
862 # URL: http://en.wikipedia.org/wiki/Microsoft_Document_Imaging_Format
863 # From: Daniele Sempione <scrows@oziosi.org>
864 0 short 0x5045 Microsoft Document Imaging Format
866 # MS eBook format (.lit)
867 0 string ITOLITLS Microsoft Reader eBook Data
868 >8 lelong x \b, version %u
869 !:mime application/x-ms-reader
871 # Windows CE Binary Image Data Format
872 # From: Dr. Jesus <j@hug.gs>
873 0 string B000FF\n Windows Embedded CE binary image
875 # Windows Imaging (WIM) Image
876 0 string MSWIM\000\000\000 Windows imaging (WIM) image