2 #------------------------------------------------------------------------------
3 # $File: msdos,v 1.105 2016/03/03 18:58:14 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 # updated by Joerg Jenderek at Oct 2015
28 # https://de.wikipedia.org/wiki/Common_Object_File_Format
29 # http://www.delorie.com/djgpp/doc/coff/filhdr.html
30 # ./intel already labeled COFF type 0x14c=0514 as "80386 COFF executable"
31 #0 leshort 0x14c MS Windows COFF Intel 80386 object file
33 0 leshort 0x166 MS Windows COFF MIPS R4000 object file
35 0 leshort 0x184 MS Windows COFF Alpha object file
37 0 leshort 0x268 MS Windows COFF Motorola 68000 object file
39 0 leshort 0x1f0 MS Windows COFF PowerPC object file
41 0 leshort 0x290 MS Windows COFF PA-RISC object file
44 # Tests for various EXE types.
46 # Many of the compressed formats were extraced from IDARC 1.23 source code.
49 # All non-DOS EXE extensions have the relocation table more than 0x40 bytes into the file.
50 >0x18 leshort <0x40 MS-DOS executable
51 !:mime application/x-dosexec
52 # These traditional tests usually work but not always. When test quality support is
53 # implemented these can be turned on.
54 #>>0x18 leshort 0x1c (Borland compiler)
55 #>>0x18 leshort 0x1e (MS compiler)
57 # If the relocation table is 0x40 or more bytes into the file, it's definitely
62 >>(0x3c.l) string PE\0\0 PE
63 !:mime application/x-dosexec
64 >>>(0x3c.l+24) leshort 0x010b \b32 executable
65 >>>(0x3c.l+24) leshort 0x020b \b32+ executable
66 >>>(0x3c.l+24) leshort 0x0107 ROM image
67 >>>(0x3c.l+24) default x Unknown PE signature
69 >>>(0x3c.l+22) leshort&0x2000 >0 (DLL)
70 >>>(0x3c.l+92) leshort 1 (native)
71 >>>(0x3c.l+92) leshort 2 (GUI)
72 >>>(0x3c.l+92) leshort 3 (console)
73 >>>(0x3c.l+92) leshort 7 (POSIX)
74 >>>(0x3c.l+92) leshort 9 (Windows CE)
75 >>>(0x3c.l+92) leshort 10 (EFI application)
76 >>>(0x3c.l+92) leshort 11 (EFI boot service driver)
77 >>>(0x3c.l+92) leshort 12 (EFI runtime driver)
78 >>>(0x3c.l+92) leshort 13 (EFI ROM)
79 >>>(0x3c.l+92) leshort 14 (XBOX)
80 >>>(0x3c.l+92) leshort 15 (Windows boot application)
81 >>>(0x3c.l+92) default x (Unknown subsystem
82 >>>>&0 leshort x 0x%x)
83 >>>(0x3c.l+4) leshort 0x14c Intel 80386
84 >>>(0x3c.l+4) leshort 0x166 MIPS R4000
85 >>>(0x3c.l+4) leshort 0x168 MIPS R10000
86 >>>(0x3c.l+4) leshort 0x184 Alpha
87 >>>(0x3c.l+4) leshort 0x1a2 Hitachi SH3
88 >>>(0x3c.l+4) leshort 0x1a6 Hitachi SH4
89 >>>(0x3c.l+4) leshort 0x1c0 ARM
90 >>>(0x3c.l+4) leshort 0x1c2 ARM Thumb
91 >>>(0x3c.l+4) leshort 0x1c4 ARMv7 Thumb
92 >>>(0x3c.l+4) leshort 0x1f0 PowerPC
93 >>>(0x3c.l+4) leshort 0x200 Intel Itanium
94 >>>(0x3c.l+4) leshort 0x266 MIPS16
95 >>>(0x3c.l+4) leshort 0x268 Motorola 68000
96 >>>(0x3c.l+4) leshort 0x290 PA-RISC
97 >>>(0x3c.l+4) leshort 0x366 MIPSIV
98 >>>(0x3c.l+4) leshort 0x466 MIPS16 with FPU
99 >>>(0x3c.l+4) leshort 0xebc EFI byte code
100 >>>(0x3c.l+4) leshort 0x8664 x86-64
101 >>>(0x3c.l+4) leshort 0xc0ee MSIL
102 >>>(0x3c.l+4) default x Unknown processor type
103 >>>>&0 leshort x 0x%x
104 >>>(0x3c.l+22) leshort&0x0200 >0 (stripped to external PDB)
105 >>>(0x3c.l+22) leshort&0x1000 >0 system file
106 >>>(0x3c.l+24) leshort 0x010b
107 >>>>(0x3c.l+232) lelong >0 Mono/.Net assembly
108 >>>(0x3c.l+24) leshort 0x020b
109 >>>>(0x3c.l+248) lelong >0 Mono/.Net assembly
111 # hooray, there's a DOS extender using the PE format, with a valid PE
112 # executable inside (which just prints a message and exits if run in win)
113 >>>(8.s*16) string 32STUB \b, 32rtm DOS extender
114 >>>(8.s*16) string !32STUB \b, for MS Windows
115 >>>(0x3c.l+0xf8) string UPX0 \b, UPX compressed
116 >>>(0x3c.l+0xf8) search/0x140 PEC2 \b, PECompact2 compressed
117 >>>(0x3c.l+0xf8) search/0x140 UPX2
118 >>>>(&0x10.l+(-4)) string PK\3\4 \b, ZIP self-extracting archive (Info-Zip)
119 >>>(0x3c.l+0xf8) search/0x140 .idata
120 >>>>(&0xe.l+(-4)) string PK\3\4 \b, ZIP self-extracting archive (Info-Zip)
121 >>>>(&0xe.l+(-4)) string ZZ0 \b, ZZip self-extracting archive
122 >>>>(&0xe.l+(-4)) string ZZ1 \b, ZZip self-extracting archive
123 >>>(0x3c.l+0xf8) search/0x140 .rsrc
124 >>>>(&0x0f.l+(-4)) string a\\\4\5 \b, WinHKI self-extracting archive
125 >>>>(&0x0f.l+(-4)) string Rar! \b, RAR self-extracting archive
126 >>>>(&0x0f.l+(-4)) search/0x3000 MSCF \b, InstallShield self-extracting archive
127 >>>>(&0x0f.l+(-4)) search/32 Nullsoft \b, Nullsoft Installer self-extracting archive
128 >>>(0x3c.l+0xf8) search/0x140 .data
129 >>>>(&0x0f.l) string WEXTRACT \b, MS CAB-Installer self-extracting archive
130 >>>(0x3c.l+0xf8) search/0x140 .petite\0 \b, Petite compressed
131 >>>>(0x3c.l+0xf7) byte x
132 >>>>>(&0x104.l+(-4)) string =!sfx! \b, ACE self-extracting archive
133 >>>(0x3c.l+0xf8) search/0x140 .WISE \b, WISE installer self-extracting archive
134 >>>(0x3c.l+0xf8) search/0x140 .dz\0\0\0 \b, Dzip self-extracting archive
135 >>>&(0x3c.l+0xf8) search/0x100 _winzip_ \b, ZIP self-extracting archive (WinZip)
136 >>>&(0x3c.l+0xf8) search/0x100 SharedD \b, Microsoft Installer self-extracting archive
137 >>>0x30 string Inno \b, InnoSetup self-extracting archive
139 # Hmm, not a PE but the relocation table is too high for a traditional DOS exe,
140 # must be one of the unusual subformats.
141 >>(0x3c.l) string !PE\0\0 MS-DOS executable
142 !:mime application/x-dosexec
144 >>(0x3c.l) string NE \b, NE
145 !:mime application/x-dosexec
146 >>>(0x3c.l+0x36) byte 1 for OS/2 1.x
147 >>>(0x3c.l+0x36) byte 2 for MS Windows 3.x
148 >>>(0x3c.l+0x36) byte 3 for MS-DOS
149 >>>(0x3c.l+0x36) byte 4 for Windows 386
150 >>>(0x3c.l+0x36) byte 5 for Borland Operating System Services
151 >>>(0x3c.l+0x36) default x
152 >>>>(0x3c.l+0x36) byte x (unknown OS %x)
153 >>>(0x3c.l+0x36) byte 0x81 for MS-DOS, Phar Lap DOS extender
154 >>>(0x3c.l+0x0c) leshort&0x8003 0x8002 (DLL)
155 >>>(0x3c.l+0x0c) leshort&0x8003 0x8001 (driver)
156 >>>&(&0x24.s-1) string ARJSFX \b, ARJ self-extracting archive
157 >>>(0x3c.l+0x70) search/0x80 WinZip(R)\ Self-Extractor \b, ZIP self-extracting archive (WinZip)
159 >>(0x3c.l) string LX\0\0 \b, LX
160 !:mime application/x-dosexec
161 >>>(0x3c.l+0x0a) leshort <1 (unknown OS)
162 >>>(0x3c.l+0x0a) leshort 1 for OS/2
163 >>>(0x3c.l+0x0a) leshort 2 for MS Windows
164 >>>(0x3c.l+0x0a) leshort 3 for DOS
165 >>>(0x3c.l+0x0a) leshort >3 (unknown OS)
166 >>>(0x3c.l+0x10) lelong&0x28000 =0x8000 (DLL)
167 >>>(0x3c.l+0x10) lelong&0x20000 >0 (device driver)
168 >>>(0x3c.l+0x10) lelong&0x300 0x300 (GUI)
169 >>>(0x3c.l+0x10) lelong&0x28300 <0x300 (console)
170 >>>(0x3c.l+0x08) leshort 1 i80286
171 >>>(0x3c.l+0x08) leshort 2 i80386
172 >>>(0x3c.l+0x08) leshort 3 i80486
173 >>>(8.s*16) string emx \b, emx
175 >>>&(&0x54.l-3) string arjsfx \b, ARJ self-extracting archive
177 # MS Windows system file, supposedly a collection of LE executables
178 >>(0x3c.l) string W3 \b, W3 for MS Windows
179 !:mime application/x-dosexec
181 >>(0x3c.l) string LE\0\0 \b, LE executable
182 !:mime application/x-dosexec
183 >>>(0x3c.l+0x0a) leshort 1
184 # some DOS extenders use LE files with OS/2 header
185 >>>>0x240 search/0x100 DOS/4G for MS-DOS, DOS4GW DOS extender
186 >>>>0x240 search/0x200 WATCOM\ C/C++ for MS-DOS, DOS4GW DOS extender
187 >>>>0x440 search/0x100 CauseWay\ DOS\ Extender for MS-DOS, CauseWay DOS extender
188 >>>>0x40 search/0x40 PMODE/W for MS-DOS, PMODE/W DOS extender
189 >>>>0x40 search/0x40 STUB/32A for MS-DOS, DOS/32A DOS extender (stub)
190 >>>>0x40 search/0x80 STUB/32C for MS-DOS, DOS/32A DOS extender (configurable stub)
191 >>>>0x40 search/0x80 DOS/32A for MS-DOS, DOS/32A DOS extender (embedded)
192 # this is a wild guess; hopefully it is a specific signature
193 >>>>&0x24 lelong <0x50
194 >>>>>(&0x4c.l) string \xfc\xb8WATCOM
195 >>>>>>&0 search/8 3\xdbf\xb9 \b, 32Lite compressed
196 # another wild guess: if real OS/2 LE executables exist, they probably have higher start EIP
197 #>>>>(0x3c.l+0x1c) lelong >0x10000 for OS/2
198 # fails with DOS-Extenders.
199 >>>(0x3c.l+0x0a) leshort 2 for MS Windows
200 >>>(0x3c.l+0x0a) leshort 3 for DOS
201 >>>(0x3c.l+0x0a) leshort 4 for MS Windows (VxD)
202 >>>(&0x7c.l+0x26) string UPX \b, UPX compressed
203 >>>&(&0x54.l-3) string UNACE \b, ACE self-extracting archive
205 # looks like ASCII, probably some embedded copyright message.
206 # and definitely not NE/LE/LX/PE
207 >>0x3c lelong >0x20000000
208 >>>(4.s*512) leshort !0x014c \b, MZ for MS-DOS
209 !:mime application/x-dosexec
210 # header data too small for extended executable
213 >>>(4.s*512) leshort !0x014c
215 >>>>&(2.s-514) string !LE
216 >>>>>&-2 string !BW \b, MZ for MS-DOS
217 !:mime application/x-dosexec
218 >>>>&(2.s-514) string LE \b, LE
219 >>>>>0x240 search/0x100 DOS/4G for MS-DOS, DOS4GW DOS extender
220 # educated guess since indirection is still not capable enough for complex offset
221 # calculations (next embedded executable would be at &(&2*512+&0-2)
222 # I suspect there are only LE executables in these multi-exe files
223 >>>>&(2.s-514) string BW
224 >>>>>0x240 search/0x100 DOS/4G \b, LE for MS-DOS, DOS4GW DOS extender (embedded)
225 >>>>>0x240 search/0x100 !DOS/4G \b, BW collection for MS-DOS
227 # This sequence skips to the first COFF segment, usually .text
228 >(4.s*512) leshort 0x014c \b, COFF
229 !:mime application/x-dosexec
230 >>(8.s*16) string go32stub for MS-DOS, DJGPP go32 DOS extender
231 >>(8.s*16) string emx
232 >>>&1 string x for DOS, Win or OS/2, emx %s
233 >>&(&0x42.l-3) byte x
234 >>>&0x26 string UPX \b, UPX compressed
235 # and yet another guess: small .text, and after large .data is unusal, could be 32lite
236 >>&0x2c search/0xa0 .text
237 >>>&0x0b lelong <0x2000
238 >>>>&0 lelong >0x6000 \b, 32lite compressed
240 >(8.s*16) string $WdX \b, WDos/X DOS extender
242 # By now an executable type should have been printed out. The executable
243 # may be a self-uncompressing archive, so look for evidence of that and
246 # Some signatures below from Greg Roelofs, newt@uchicago.edu.
248 >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
249 >0xe7 string LH/2\ Self-Extract \b, %s
250 >0x1c string UC2X \b, UCEXE compressed
251 >0x1c string WWP\ \b, WWPACK compressed
252 >0x1c string RJSX \b, ARJ self-extracting archive
253 >0x1c string diet \b, diet compressed
254 >0x1c string LZ09 \b, LZEXE v0.90 compressed
255 >0x1c string LZ91 \b, LZEXE v0.91 compressed
256 >0x1c string tz \b, TinyProg compressed
257 >0x1e string Copyright\ 1989-1990\ PKWARE\ Inc. Self-extracting PKZIP archive
258 !:mime application/zip
259 # Yes, this really is "Copr", not "Corp."
260 >0x1e string PKLITE\ Copr. Self-extracting PKZIP archive
261 !:mime application/zip
262 # winarj stores a message in the stub instead of the sig in the MZ header
263 >0x20 search/0xe0 aRJsfX \b, ARJ self-extracting archive
265 >>0x23 string 2 \b, AIN 2.x compressed
266 >>0x23 string <2 \b, AIN 1.x compressed
267 >>0x23 string >2 \b, AIN 1.x compressed
268 >0x24 string LHa's\ SFX \b, LHa self-extracting archive
269 !:mime application/x-lha
270 >0x24 string LHA's\ SFX \b, LHa self-extracting archive
271 !:mime application/x-lha
272 >0x24 string \ $ARX \b, ARX self-extracting archive
273 >0x24 string \ $LHarc \b, LHarc self-extracting archive
274 >0x20 string SFX\ by\ LARC \b, LARC self-extracting archive
275 >0x40 string aPKG \b, aPackage self-extracting archive
276 >0x64 string W\ Collis\0\0 \b, Compack compressed
277 >0x7a string Windows\ self-extracting\ ZIP \b, ZIP self-extracting archive
278 >>&0xf4 search/0x140 \x0\x40\x1\x0
279 >>>(&0.l+(4)) string MSCF \b, WinHKI CAB self-extracting archive
280 >1638 string -lh5- \b, LHa self-extracting archive v2.13S
281 >0x17888 string Rar! \b, RAR self-extracting archive
283 # Skip to the end of the EXE. This will usually work fine in the PE case
284 # because the MZ image is hardcoded into the toolchain and almost certainly
285 # won't match any of these signatures.
288 >>>&0 string PK\3\4 \b, ZIP self-extracting archive
289 >>>&0 string Rar! \b, RAR self-extracting archive
290 >>>&0 string =!\x11 \b, AIN 2.x self-extracting archive
291 >>>&0 string =!\x12 \b, AIN 2.x self-extracting archive
292 >>>&0 string =!\x17 \b, AIN 1.x self-extracting archive
293 >>>&0 string =!\x18 \b, AIN 1.x self-extracting archive
294 >>>&7 search/400 **ACE** \b, ACE self-extracting archive
295 >>>&0 search/0x480 UC2SFX\ Header \b, UC2 self-extracting archive
297 # a few unknown ZIP sfxes, no idea if they are needed or if they are
298 # already captured by the generic patterns above
299 >(8.s*16) search/0x20 PKSFX \b, ZIP self-extracting archive (PKZIP)
300 # TODO: how to add this? >FileSize-34 string Windows\ Self-Installing\ Executable \b, ZIP self-extracting archive
303 # TELVOX Teleinformatica CODEC self-extractor for OS/2:
304 >49801 string \x79\xff\x80\xff\x76\xff \b, CODEC archive v3.21
305 >>49824 leshort =1 \b, 1 file
306 >>49824 leshort >1 \b, %u files
308 # added by Joerg Jenderek of http://www.freedos.org/software/?prog=kc
309 # and http://www.freedos.org/software/?prog=kpdos
310 # for FreeDOS files like KEYBOARD.SYS, KEYBRD2.SYS, KEYBRD3.SYS, *.KBD
311 0 string/b KCF FreeDOS KEYBoard Layout collection
312 # only version=0x100 found
313 >3 uleshort x \b, version 0x%x
314 # length of string containing author,info and special characters
316 #>>6 pstring x \b, name=%s
317 >>7 string >\0 \b, author=%-.14s
318 >>7 search/254 \xff \b, info=
319 #>>>&0 string x \b%-s
320 >>>&0 string x \b%-.15s
321 # for FreeDOS *.KL files
322 0 string/b KLF FreeDOS KEYBoard Layout file
323 # only version=0x100 or 0x101 found
324 >3 uleshort x \b, version 0x%x
327 >>8 string x \b, name=%-.2s
328 0 string \xffKEYB\ \ \ \0\0\0\0
329 >12 string \0\0\0\0`\004\360 MS-DOS KEYBoard Layout file
331 # .COM formats (Daniel Quinlan, quinlan@yggdrasil.com)
332 # Uncommenting only the first two lines will cover about 2/3 of COM files,
333 # but it isn't feasible to match all COM files since there must be at least
334 # two dozen different one-byte "magics".
336 0 byte 0xe9 DOS executable (COM)
337 >0x1FE leshort 0xAA55 \b, boot code
338 >6 string SFX\ of\ LHarc (%s)
340 # DOS device driver updated by Joerg Jenderek at May 2011
341 # http://maben.homeip.net/static/S100/IBM/software/DOS/DOS%20techref/CHAPTER.009
342 0 ulequad&0x07a0ffffffff 0xffffffff DOS executable (
343 >40 search/7 UPX! \bUPX compressed
344 # DOS device driver attributes
345 >4 uleshort&0x8000 0x0000 \bblock device driver
347 >4 uleshort&0x8000 0x8000 \b
348 >>4 uleshort&0x0008 0x0008 \bclock
349 # fast video output by int 29h
350 >>4 uleshort&0x0010 0x0010 \bfast
351 # standard input/output device
352 >>4 uleshort&0x0003 >0 \bstandard
353 >>>4 uleshort&0x0001 0x0001 \binput
354 >>>4 uleshort&0x0003 0x0003 \b/
355 >>>4 uleshort&0x0002 0x0002 \boutput
356 >>4 uleshort&0x8000 0x8000 \bcharacter device driver
358 # upx compressed device driver has garbage instead of real in name field of header
361 # leading/trailing nulls, zeros or non ASCII characters in 8-byte name field at offset 10 are skipped
365 >>>>>>10 ubyte !0x2A \b%c
367 >>>>>11 ubyte !0x2E \b%c
370 >>>>>>12 ubyte !0x2E \b%c
372 >>>>13 ubyte !0x2E \b%c
374 >>>>>14 ubyte !0x2E \b%c
376 >>>>>15 ubyte !0x2E \b%c
379 >>>>>>16 ubyte <0xCB \b%c
382 >>>>>>17 ubyte <0x90 \b%c
383 # some character device drivers like ASPICD.SYS, btcdrom.sys and Cr_atapi.sys contain only spaces or points in name field
384 >>>4 uleshort&0x8000 0x8000
386 # they have their real name at offset 22
387 >>>>>22 string >\0 \b%-.5s
388 >4 uleshort&0x8000 0x0000
389 # 32 bit sector addressing ( > 32 MB) for block devices
390 >>4 uleshort&0x0002 0x0002 \b,32-bit sector-
391 # support by driver functions 13h, 17h, 18h
392 >4 uleshort&0x0040 0x0040 \b,IOCTL-
393 # open, close, removable media support by driver functions 0Dh, 0Eh, 0Fh
394 >4 uleshort&0x0800 0x0800 \b,close media-
395 # output until busy support by int 10h for character device driver
396 >4 uleshort&0x8000 0x8000
397 >>4 uleshort&0x2000 0x2000 \b,until busy-
398 # direct read/write support by driver functions 03h,0Ch
399 >4 uleshort&0x4000 0x4000 \b,control strings-
400 >4 uleshort&0x8000 0x8000
401 >>4 uleshort&0x6840 >0 \bsupport
402 >4 uleshort&0x8000 0x0000
403 >>4 uleshort&0x4842 >0 \bsupport
405 # DOS driver cmd640x.sys has 0x12 instead of 0xffffffff for pointer field to next device header
406 # Too weak, matches files that only contain 0's
407 #0 ulequad&0x000007a0ffffffed 0x0000000000000000 DOS-executable (
408 #>4 uleshort&0x8000 0x8000 \bcharacter device driver
410 #>4 uleshort&0x4000 0x4000 \b,control strings-support)
412 # updated by Joerg Jenderek
413 # GRR: line below too general as it catches also
414 # rt.lib DYADISKS.PIC and many more
415 # start with assembler instruction MOV
417 # skip "AppleWorks word processor data" like ARTICLE.1 ./apple
419 # skip some unknown basic binaries like RocketRnger.SHR
421 # skip "GPG symmetrically encrypted data" ./gnu
422 # skip "PGP symmetric key encrypted data" ./pgp
423 # openpgpdefs.h: fourth byte < 14 indicate cipher algorithm type
424 >>>4 ubyte >13 DOS executable (COM, 0x8C-variant)
425 # the remaining files should be DOS *.COM executables
426 # dosshell.COM 8cc0 2ea35f07 e85211 e88a11 b80058 cd
427 # hmload.COM 8cc8 8ec0 bbc02b 89dc 83c30f c1eb04 b4
428 # UNDELETE.COM 8cca 2e8916 6503 b430 cd21 8b 2e0200 8b
429 # BOOTFIX.COM 8cca 2e8916 9603 b430 cd21 8b 2e0200 8b
430 # RAWRITE3.COM 8cca 2e8916 d602 b430 cd21 8b 2e0200 8b
431 # SHARE.COM 8cca 2e8916 d602 b430 cd21 8b 2e0200 8b
432 # validchr.COM 8cca 2e8916 9603 b430 cd21 8b 2e028b1e
433 # devload.COM 8cca 8916ad01 b430 cd21 8b2e0200 892e
434 !:mime application/x-dosexec
437 # updated by Joerg Jenderek at Oct 2008
438 0 ulelong 0xffff10eb DR-DOS executable (COM)
439 # byte 0xeb conflicts with "sequent" magic leshort 0xn2eb
440 0 ubeshort&0xeb8d >0xeb00
441 # DR-DOS STACKER.COM SCREATE.SYS missed
443 >>0x1FE leshort 0xAA55 DOS executable (COM), boot code
444 >>85 string UPX DOS executable (COM), UPX compressed
445 >>4 string \ $ARX DOS executable (COM), ARX self-extracting archive
446 >>4 string \ $LHarc DOS executable (COM), LHarc self-extracting archive
447 >>0x20e string SFX\ by\ LARC DOS executable (COM), LARC self-extracting archive
448 # updated by Joerg Jenderek at Oct 2008,2015
449 # following line is too general
451 # skip 2 linux kernels like memtest.bin with "\xb8\xc0\x07\x8e" in ./linux
452 >0 string !\xb8\xc0\x07\x8e
453 # modified by Joerg Jenderek
454 # syslinux COM32 or COM32R executable
455 >>1 lelong&0xFFFFFFFe 0x21CD4CFe COM executable (32-bit COMBOOT
456 # http://www.syslinux.org/wiki/index.php/Comboot_API
457 # Since version 5.00 c32 modules switched from the COM32 object format to ELF
458 !:mime application/x-c32-comboot-syslinux-exec
460 # http://syslinux.zytor.com/comboot.php
461 # older syslinux version ( <4 )
462 # (32-bit COMBOOT) programs *.C32 contain 32-bit code and run in flat-memory 32-bit protected mode
463 # start with assembler instructions mov eax,21cd4cffh
464 >>>1 lelong 0x21CD4CFf \b)
465 # syslinux:doc/comboot.txt
466 # A COM32R program must start with the byte sequence B8 FE 4C CD 21 (mov
467 # eax,21cd4cfeh) as a magic number.
468 # syslinux version (4.x)
469 # "COM executable (COM32R)" or "Syslinux COM32 module" by TrID
470 >>>1 lelong 0x21CD4CFe \b, relocatable)
471 # remaining are DOS COM executables starting with assembler instruction MOV
472 # like FreeDOS BANNER*.COM FINDDISK.COM GIF2RAW.COM WINCHK.COM
473 # MS-DOS SYS.COM RESTART.COM
474 # SYSLINUX.COM (version 1.40 - 2.13)
475 # GFXBOOT.COM (version 3.75)
476 # COPYBS.COM POWEROFF.COM INT18.COM
477 >>1 default x COM executable for DOS
478 !:mime application/x-dosexec
479 #!:mime application/x-ms-dos-executable
480 #!:mime application/x-msdos-program
484 >4 string \x77\x02\xcd\x20\xb9
485 >>36 string UPX! FREE-DOS executable (COM), UPX compressed
486 252 string Must\ have\ DOS\ version DR-DOS executable (COM)
487 # added by Joerg Jenderek at Oct 2008
488 # GRR search is not working
489 #34 search/2 UPX! FREE-DOS executable (COM), UPX compressed
490 34 string UPX! FREE-DOS executable (COM), UPX compressed
491 35 string UPX! FREE-DOS executable (COM), UPX compressed
492 # GRR search is not working
493 #2 search/28 \xcd\x21 COM executable for MS-DOS
495 2 string \xcd\x21 COM executable for DOS
496 #DELTREE.cOM DELTREE2.cOM
497 4 string \xcd\x21 COM executable for DOS
498 #IFMEMDSK.cOM ASSIGN.cOM COMP.cOM
499 5 string \xcd\x21 COM executable for DOS
500 #DELTMP.COm HASFAT32.cOM
502 >0 byte !0xb8 COM executable for DOS
505 >5 string !\xcd\x21 COM executable for DOS
507 13 string \xcd\x21 COM executable for DOS
509 18 string \xcd\x21 COM executable for MS-DOS
511 23 string \xcd\x21 COM executable for MS-DOS
512 #LOADFIX.cOm LOADFIX.cOm
513 30 string \xcd\x21 COM executable for MS-DOS
515 70 string \xcd\x21 COM executable for DOS
516 # many compressed/converted COMs start with a copy loop instead of a jump
517 0x6 search/0xa \xfc\x57\xf3\xa5\xc3 COM executable for MS-DOS
518 0x6 search/0xa \xfc\x57\xf3\xa4\xc3 COM executable for DOS
519 >0x18 search/0x10 \x50\xa4\xff\xd5\x73 \b, aPack compressed
520 0x3c string W\ Collis\0\0 COM executable for MS-DOS, Compack compressed
521 # FIXME: missing diet .com compression
523 # miscellaneous formats
524 0 string/b LZ MS-DOS executable (built-in)
525 #0 byte 0xf0 MS-DOS program library data
529 # <stuartc@rd.bbc.co.uk> Stuart Cunningham
530 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
531 >30 byte 9 (512B sectors)
532 >30 byte 12 (4kB sectors)
533 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
534 >30 byte 9 (512B sectors)
535 >30 byte 12 (4kB sectors)
537 # Popular applications
538 2080 string Microsoft\ Word\ 6.0\ Document %s
539 !:mime application/msword
540 2080 string Documento\ Microsoft\ Word\ 6 Spanish Microsoft Word 6 document data
541 !:mime application/msword
542 # Pawel Wiecek <coven@i17linuxb.ists.pwr.wroc.pl> (for polish Word)
543 2112 string MSWordDoc Microsoft Word document data
544 !:mime application/msword
546 0 belong 0x31be0000 Microsoft Word Document
547 !:mime application/msword
549 0 string/b PO^Q` Microsoft Word 6.0 Document
550 !:mime application/msword
552 0 string/b \376\067\0\043 Microsoft Office Document
553 !:mime application/msword
554 0 string/b \333\245-\0\0\0 Microsoft Office Document
555 !:mime application/msword
556 512 string/b \354\245\301 Microsoft Word Document
557 !:mime application/msword
560 0 string/b \xDB\xA5\x2D\x00 Microsoft WinWord 2.0 Document
561 !:mime application/msword
563 2080 string Microsoft\ Excel\ 5.0\ Worksheet %s
564 !:mime application/vnd.ms-excel
566 0 string/b \xDB\xA5\x2D\x00 Microsoft WinWord 2.0 Document
567 !:mime application/msword
569 2080 string Foglio\ di\ lavoro\ Microsoft\ Exce %s
570 !:mime application/vnd.ms-excel
572 # Pawel Wiecek <coven@i17linuxb.ists.pwr.wroc.pl> (for polish Excel)
573 2114 string Biff5 Microsoft Excel 5.0 Worksheet
574 !:mime application/vnd.ms-excel
576 2121 string Biff5 Microsoft Excel 5.0 Worksheet
577 !:mime application/vnd.ms-excel
578 0 string/b \x09\x04\x06\x00\x00\x00\x10\x00 Microsoft Excel Worksheet
579 !:mime application/vnd.ms-excel
581 0 belong 0x00001a00 Lotus 1-2-3
582 !:mime application/x-123
583 >4 belong 0x00100400 wk3 document data
584 >4 belong 0x02100400 wk4 document data
585 >4 belong 0x07800100 fm3 or fmb document data
586 >4 belong 0x07800000 fm3 or fmb document data
588 0 belong 0x00000200 Lotus 1-2-3
589 !:mime application/x-123
590 >4 belong 0x06040600 wk1 document data
591 >4 belong 0x06800200 fmt document data
592 0 string/b WordPro\0 Lotus WordPro
593 !:mime application/vnd.lotus-wordpro
594 0 string/b WordPro\r\373 Lotus WordPro
595 !:mime application/vnd.lotus-wordpro
598 # Summary: Script used by InstallScield to uninstall applications
600 # Submitted by: unknown
601 # Modified by (1): Abel Cheung <abelcheung@gmail.com> (replace useless entry)
602 0 string \x71\xa8\x00\x00\x01\x02
603 >12 string Stirling\ Technologies, InstallShield Uninstall Script
606 #0 string Nullsoft\ AVS\ Preset\ \060\056\061\032 A plug in for Winamp ms-windows Freeware media player
607 0 string/b Nullsoft\ AVS\ Preset\ Winamp plug in
609 # Windows Metafont .WMF
610 0 string/b \327\315\306\232 ms-windows metafont .wmf
611 0 string/b \002\000\011\000 ms-windows metafont .wmf
612 0 string/b \001\000\011\000 ms-windows metafont .wmf
614 #tz3 files whatever that is (MS Works files)
615 0 string/b \003\001\001\004\070\001\000\000 tz3 ms-works file
616 0 string/b \003\002\001\004\070\001\000\000 tz3 ms-works file
617 0 string/b \003\003\001\004\070\001\000\000 tz3 ms-works file
620 #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
621 0 string \211\000\077\003\005\000\063\237\127\065\027\266\151\064\005\045\101\233\021\002 PGP sig
622 0 string \211\000\077\003\005\000\063\237\127\066\027\266\151\064\005\045\101\233\021\002 PGP sig
623 0 string \211\000\077\003\005\000\063\237\127\067\027\266\151\064\005\045\101\233\021\002 PGP sig
624 0 string \211\000\077\003\005\000\063\237\127\070\027\266\151\064\005\045\101\233\021\002 PGP sig
625 0 string \211\000\077\003\005\000\063\237\127\071\027\266\151\064\005\045\101\233\021\002 PGP sig
626 0 string \211\000\225\003\005\000\062\122\207\304\100\345\042 PGP sig
628 # windows zips files .dmf
629 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
633 0 string/b \102\101\050\000\000\000\056\000\000\000\000\000\000\000 Icon for MS Windows
637 # not entirely accurate, the number of icons is part of the header
639 >0 ubyte >1 - %d icons
644 >4 ubyte !0 \b, %d colors
648 >>0 byte x MS Windows icon resource
652 >>0 byte x MS Windows icon resource
656 # Windows non-animated cursors
658 # not entirely accurate, the number of icons is part of the header
660 >0 ubyte >1 - %d icons
665 >6 uleshort x \b, hotspot @%dx
670 >>0 byte x MS Windows cursor resource
674 >>0 byte x MS Windows cursor resource
679 0 string/b PK\010\010BGI Borland font
681 # then there is a copyright notice
685 0 string/b pk\010\010BGI Borland device
687 # then there is a copyright notice
690 # Windows Recycle Bin record file (named INFO2)
691 # By Abel Cheung (abelcheung AT gmail dot com)
692 # Version 4 always has 280 bytes (0x118) per record, version 5 has 800 bytes
693 # Since Vista uses another structure, INFO2 structure probably won't change
694 # anymore. Detailed analysis in:
695 # http://www.cybersecurityinstitute.biz/downloads/INFO2.pdf
697 >12 lelong 0x00000118 Windows Recycle Bin INFO2 file (Win98 or below)
700 >12 lelong 0x00000320 Windows Recycle Bin INFO2 file (Win2k - WinXP)
703 ##### put in Either Magic/font or Magic/news
704 # Acroread or something files wrongly identified as G3 .pfm
705 # these have the form \000 \001 any? \002 \000 \000
706 # or \000 \001 any? \022 \000 \000
707 0 belong&0xffff00ff 0x00010012 PFM data
711 0 belong&0xffff00ff 0x00010002 PFM data
714 #0 string \000\001 pfm?
715 #>3 string \022\000\000Copyright\ yes
716 #>3 string \002\000\000Copyright\ yes
717 #>3 string >\0 oops, not a font file. Cancel that.
718 #it clashes with ttf files so put it lower down.
720 # From Doug Lee via a FreeBSD pr
721 9 string GERBILDOC First Choice document
722 9 string GERBILDB First Choice database
723 9 string GERBILCLIP First Choice database
724 0 string GERBIL First Choice device file
725 9 string RABBITGRAPH RabbitGraph file
726 0 string DCU1 Borland Delphi .DCU file
727 0 string =!<spell> MKS Spell hash list (old format)
728 0 string =!<spell2> MKS Spell hash list
730 #0 string AH Halo(TM) bitmapped font file
731 0 lelong 0x08086b70 TurboC BGI file
732 0 lelong 0x08084b50 TurboC Font file
734 # Debian#712046: The magic below identifies "Delphi compiled form data".
735 # An additional source of information is available at:
736 # http://www.woodmann.com/fravia/dafix_t1.htm
738 >4 pstring >\0 Delphi compiled form '%s'
740 # tests for DBase files moved, updated and merged to database
742 0 string PMCC Windows 3.x .GRP file
743 1 string RDC-meg MegaDots
744 >8 byte >0x2F version %c
745 >9 byte >0x2F \b.%c file
747 >4 lelong 0x00021401 Windows shortcut file
749 # .PIF files added by Joerg Jenderek from http://smsoft.ru/en/pifdoc.htm
750 # only for windows versions equal or greater 3.0
751 0x171 string MICROSOFT\ PIFEX\0 Windows Program Information File
752 !:mime application/x-dosexec
753 #>2 string >\0 \b, Title:%.30s
754 >0x24 string >\0 \b for %.63s
755 >0x65 string >\0 \b, directory=%.64s
756 >0xA5 string >\0 \b, parameters=%.64s
757 #>0x181 leshort x \b, offset %x
758 #>0x183 leshort x \b, offsetdata %x
759 #>0x185 leshort x \b, section length %x
760 >0x187 search/0xB55 WINDOWS\ VMM\ 4.0\0
762 >>>&-1 string <PIFMGR.DLL \b, icon=%s
763 #>>>&-1 string PIFMGR.DLL \b, icon=%s
764 >>>&-1 string >PIFMGR.DLL \b, icon=%s
766 >>>&-1 string <Terminal \b, font=%.32s
767 #>>>&-1 string =Terminal \b, font=%.32s
768 >>>&-1 string >Terminal \b, font=%.32s
770 >>>&-1 string <Lucida\ Console \b, TrueTypeFont=%.32s
771 #>>>&-1 string =Lucida\ Console \b, TrueTypeFont=%.32s
772 >>>&-1 string >Lucida\ Console \b, TrueTypeFont=%.32s
773 #>0x187 search/0xB55 WINDOWS\ 286\ 3.0\0 \b, Windows 3.X standard mode-style
774 #>0x187 search/0xB55 WINDOWS\ 386\ 3.0\0 \b, Windows 3.X enhanced mode-style
775 >0x187 search/0xB55 WINDOWS\ NT\ \ 3.1\0 \b, Windows NT-style
776 #>0x187 search/0xB55 WINDOWS\ NT\ \ 4.0\0 \b, Windows NT-style
777 >0x187 search/0xB55 CONFIG\ \ SYS\ 4.0\0 \b +CONFIG.SYS
778 #>>&06 string x \b:%s
779 >0x187 search/0xB55 AUTOEXECBAT\ 4.0\0 \b +AUTOEXEC.BAT
780 #>>&06 string x \b:%s
782 # DOS EPS Binary File Header
783 # From: Ed Sznyter <ews@Black.Market.NET>
784 0 belong 0xC5D0D3C6 DOS EPS Binary File
785 >4 long >0 Postscript starts at byte %d
786 >>8 long >0 length %d
787 >>>12 long >0 Metafile starts at byte %d
788 >>>>16 long >0 length %d
789 >>>20 long >0 TIFF starts at byte %d
790 >>>>24 long >0 length %d
792 # TNEF magic From "Joomy" <joomy@se-ed.net>
793 # Microsoft Outlook's Transport Neutral Encapsulation Format (TNEF)
794 0 leshort 0x223e9f78 TNEF
795 !:mime application/vnd.ms-tnef
797 # Norton Guide (.NG , .HLP) files added by Joerg Jenderek from source NG2HTML.C
798 # of http://www.davep.org/norton-guides/ng2h-105.tgz
799 # http://en.wikipedia.org/wiki/Norton_Guides
801 # only value 0x100 found at offset 2
802 >2 ulelong 0x00000100 Norton Guide
804 >>8 string >\0 "%-.40s"
805 #>>6 uleshort x \b, MenuCount=%u
807 >>48 string >\0 \b, %-.66s
808 >>114 string >\0 %-.66s
810 # 4DOS help (.HLP) files added by Joerg Jenderek from source TPHELP.PAS
811 # of http://www.4dos.info/
812 # pointer,HelpID[8]=4DHnnnmm
813 0 ulelong 0x48443408 4DOS help file
814 >4 string x \b, version %-4.4s
816 # old binary Microsoft (.HLP) files added by Joerg Jenderek from http://file-extension.net/seeker/file_extension_hlp
817 0 ulequad 0x3a000000024e4c MS Advisor help file
819 # HtmlHelp files (.chm)
820 0 string/b ITSF\003\000\000\000\x60\000\000\000 MS Windows HtmlHelp Data
822 # GFA-BASIC (Wolfram Kleff)
823 2 string/b GFA-BASIC3 GFA-BASIC 3 data
825 #------------------------------------------------------------------------------
826 # From Stuart Caie <kyzer@4u.net> (developer of cabextract)
827 # Microsoft Cabinet files
828 0 string/b MSCF\0\0\0\0 Microsoft Cabinet archive data
829 !:mime application/vnd.ms-cab-compressed
830 >8 lelong x \b, %u bytes
831 >28 leshort 1 \b, 1 file
832 >28 leshort >1 \b, %u files
834 # InstallShield Cabinet files
835 0 string/b ISc( InstallShield Cabinet archive data
836 >5 byte&0xf0 =0x60 version 6,
837 >5 byte&0xf0 !0x60 version 4/5,
838 >(12.l+40) lelong x %u files
840 # Windows CE package files
841 0 string/b MSCE\0\0\0\0 Microsoft WinCE install header
842 >20 lelong 0 \b, architecture-independent
843 >20 lelong 103 \b, Hitachi SH3
844 >20 lelong 104 \b, Hitachi SH4
845 >20 lelong 0xA11 \b, StrongARM
846 >20 lelong 4000 \b, MIPS R4000
847 >20 lelong 10003 \b, Hitachi SH3
848 >20 lelong 10004 \b, Hitachi SH3E
849 >20 lelong 10005 \b, Hitachi SH4
850 >20 lelong 70001 \b, ARM 7TDMI
851 >52 leshort 1 \b, 1 file
852 >52 leshort >1 \b, %u files
853 >56 leshort 1 \b, 1 registry entry
854 >56 leshort >1 \b, %u registry entries
857 # Windows Enhanced Metafile (EMF)
858 # See msdn.microsoft.com/archive/en-us/dnargdi/html/msdn_enhmeta.asp
859 # for further information.
861 >40 string \ EMF Windows Enhanced Metafile (EMF) image data
862 >>44 ulelong x version 0x%x
864 # from http://filext.com by Derek M Jones <derek@knosof.co.uk>
865 # False positive with PPT (also currently this string is too long)
866 #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
867 0 string/b \320\317\021\340\241\261\032\341 Microsoft Office Document
868 #>48 byte 0x1B Excel Document
869 #!:mime application/vnd.ms-excel
870 >546 string bjbj Microsoft Word Document
871 !:mime application/msword
872 >546 string jbjb Microsoft Word Document
873 !:mime application/msword
875 0 string/b \224\246\056 Microsoft Word Document
876 !:mime application/msword
878 512 string R\0o\0o\0t\0\ \0E\0n\0t\0r\0y Microsoft Word Document
879 !:mime application/msword
881 # From: "Nelson A. de Oliveira" <naoliv@gmail.com>
882 # Magic type for Dell's BIOS .hdr files
885 >23 string Dell %s system BIOS
887 >>48 byte x version %d.
891 >>48 string x version %.3s
893 # Type: Microsoft DirectDraw Surface
894 # URL: http://msdn.microsoft.com/library/default.asp?url=/library/en-us/directx9_c/directx/graphics/reference/DDSFileReference/ddsfileformat.asp
895 # From: Morten Hustveit <morten@debian.org>
896 0 string/b DDS\040\174\000\000\000 Microsoft DirectDraw Surface (DDS),
901 # Type: Microsoft Document Imaging Format (.mdi)
902 # URL: http://en.wikipedia.org/wiki/Microsoft_Document_Imaging_Format
903 # From: Daniele Sempione <scrows@oziosi.org>
904 0 short 0x5045 Microsoft Document Imaging Format
906 # MS eBook format (.lit)
907 0 string/b ITOLITLS Microsoft Reader eBook Data
908 >8 lelong x \b, version %u
909 !:mime application/x-ms-reader
911 # Windows CE Binary Image Data Format
912 # From: Dr. Jesus <j@hug.gs>
913 0 string/b B000FF\n Windows Embedded CE binary image
915 # Windows Imaging (WIM) Image
916 0 string/b MSWIM\000\000\000 Windows imaging (WIM) image
917 0 string/b WLPWM\000\000\000 Windows imaging (WIM) image, wimlib pipable format
919 # The second byte of these signatures is a file version; I don't know what,
920 # if anything, produced files with version numbers 0-2.
921 # From: John Elliott <johne@seasip.demon.co.uk>
922 0 string \xfc\x03\x00 Mallard BASIC program data (v1.11)
923 0 string \xfc\x04\x00 Mallard BASIC program data (v1.29+)
924 0 string \xfc\x03\x01 Mallard BASIC protected program data (v1.11)
925 0 string \xfc\x04\x01 Mallard BASIC protected program data (v1.29+)
927 0 string MIOPEN Mallard BASIC Jetsam data
928 0 string Jetsam0 Mallard BASIC Jetsam index data