2 #------------------------------------------------------------------------------
3 # $File: msdos,v 1.128 2019/04/19 00:42:27 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
13 >1 string/cW echo\ off DOS batch file text
14 !:mime text/x-msdos-batch
16 >1 string/cW rem DOS batch file text
17 !:mime text/x-msdos-batch
19 >1 string/cW set\ DOS batch file text
20 !:mime text/x-msdos-batch
24 # OS/2 batch files are REXX. the second regex is a bit generic, oh well
25 # the matched commands seem to be common in REXX and uncommon elsewhere
26 100 search/0xffff rxfuncadd
27 >100 regex/c =^[\ \t]{0,10}call[\ \t]{1,10}rxfunc OS/2 REXX batch file text
29 >100 regex/c =^[\ \t]{0,10}say\ ['"] OS/2 REXX batch file text
31 # updated by Joerg Jenderek at Oct 2015
32 # https://de.wikipedia.org/wiki/Common_Object_File_Format
33 # http://www.delorie.com/djgpp/doc/coff/filhdr.html
34 # ./intel already labeled COFF type 0x14c=0514 as "80386 COFF executable"
35 #0 leshort 0x14c MS Windows COFF Intel 80386 object file
37 0 leshort 0x166 MS Windows COFF MIPS R4000 object file
39 0 leshort 0x184 MS Windows COFF Alpha object file
41 0 leshort 0x268 MS Windows COFF Motorola 68000 object file
43 0 leshort 0x1f0 MS Windows COFF PowerPC object file
45 0 leshort 0x290 MS Windows COFF PA-RISC object file
48 # Tests for various EXE types.
50 # Many of the compressed formats were extraced from IDARC 1.23 source code.
53 # All non-DOS EXE extensions have the relocation table more than 0x40 bytes into the file.
54 >0x18 leshort <0x40 MS-DOS executable
55 !:mime application/x-dosexec
56 # Windows and later versions of DOS will allow .EXEs to be named with a .COM
57 # extension, mostly for compatibility's sake.
59 # These traditional tests usually work but not always. When test quality support is
60 # implemented these can be turned on.
61 #>>0x18 leshort 0x1c (Borland compiler)
62 #>>0x18 leshort 0x1e (MS compiler)
64 # If the relocation table is 0x40 or more bytes into the file, it's definitely
69 >>(0x3c.l) string PE\0\0 PE
70 !:mime application/x-dosexec
71 >>>(0x3c.l+24) leshort 0x010b \b32 executable
72 >>>(0x3c.l+24) leshort 0x020b \b32+ executable
73 >>>(0x3c.l+24) leshort 0x0107 ROM image
74 >>>(0x3c.l+24) default x Unknown PE signature
76 >>>(0x3c.l+22) leshort&0x2000 >0 (DLL)
77 >>>(0x3c.l+92) leshort 1
78 # Native PEs include ntoskrnl.exe, hal.dll, smss.exe, autochk.exe, and all the
79 # drivers in Windows/System32/drivers/*.sys.
80 >>>>(0x3c.l+22) leshort&0x2000 >0 (native)
82 >>>>(0x3c.l+22) leshort&0x2000 0 (native)
84 >>>(0x3c.l+92) leshort 2
85 >>>>(0x3c.l+22) leshort&0x2000 >0 (GUI)
86 # These could probably be at least partially distinguished from one another by
87 # looking for specific exported functions.
88 # CPL: Control Panel item
90 # OCX: OLE/ActiveX control
91 # ACM: Audio compression manager codec
92 # AX: DirectShow source filter
93 # IME: Input method editor
94 !:ext dll/cpl/tlb/ocx/acm/ax/ime
95 >>>>(0x3c.l+22) leshort&0x2000 0 (GUI)
96 # Screen savers typically include code from the scrnsave.lib static library, but
97 # that's not guaranteed.
99 >>>(0x3c.l+92) leshort 3
100 >>>>(0x3c.l+22) leshort&0x2000 >0 (console)
101 !:ext dll/cpl/tlb/ocx/acm/ax/ime
102 >>>>(0x3c.l+22) leshort&0x2000 0 (console)
104 >>>(0x3c.l+92) leshort 7 (POSIX)
105 >>>(0x3c.l+92) leshort 9 (Windows CE)
106 >>>(0x3c.l+92) leshort 10 (EFI application)
107 >>>(0x3c.l+92) leshort 11 (EFI boot service driver)
108 >>>(0x3c.l+92) leshort 12 (EFI runtime driver)
109 >>>(0x3c.l+92) leshort 13 (EFI ROM)
110 >>>(0x3c.l+92) leshort 14 (XBOX)
111 >>>(0x3c.l+92) leshort 15 (Windows boot application)
112 >>>(0x3c.l+92) default x (Unknown subsystem
113 >>>>&0 leshort x 0x%x)
114 >>>(0x3c.l+4) leshort 0x14c Intel 80386
115 >>>(0x3c.l+4) leshort 0x166 MIPS R4000
116 >>>(0x3c.l+4) leshort 0x168 MIPS R10000
117 >>>(0x3c.l+4) leshort 0x184 Alpha
118 >>>(0x3c.l+4) leshort 0x1a2 Hitachi SH3
119 >>>(0x3c.l+4) leshort 0x1a6 Hitachi SH4
120 >>>(0x3c.l+4) leshort 0x1c0 ARM
121 >>>(0x3c.l+4) leshort 0x1c2 ARM Thumb
122 >>>(0x3c.l+4) leshort 0x1c4 ARMv7 Thumb
123 >>>(0x3c.l+4) leshort 0x1f0 PowerPC
124 >>>(0x3c.l+4) leshort 0x200 Intel Itanium
125 >>>(0x3c.l+4) leshort 0x266 MIPS16
126 >>>(0x3c.l+4) leshort 0x268 Motorola 68000
127 >>>(0x3c.l+4) leshort 0x290 PA-RISC
128 >>>(0x3c.l+4) leshort 0x366 MIPSIV
129 >>>(0x3c.l+4) leshort 0x466 MIPS16 with FPU
130 >>>(0x3c.l+4) leshort 0xebc EFI byte code
131 >>>(0x3c.l+4) leshort 0x8664 x86-64
132 >>>(0x3c.l+4) leshort 0xc0ee MSIL
133 >>>(0x3c.l+4) default x Unknown processor type
134 >>>>&0 leshort x 0x%x
135 >>>(0x3c.l+22) leshort&0x0200 >0 (stripped to external PDB)
136 >>>(0x3c.l+22) leshort&0x1000 >0 system file
137 >>>(0x3c.l+24) leshort 0x010b
138 >>>>(0x3c.l+232) lelong >0 Mono/.Net assembly
139 >>>(0x3c.l+24) leshort 0x020b
140 >>>>(0x3c.l+248) lelong >0 Mono/.Net assembly
142 # hooray, there's a DOS extender using the PE format, with a valid PE
143 # executable inside (which just prints a message and exits if run in win)
144 >>>(8.s*16) string 32STUB \b, 32rtm DOS extender
145 >>>(8.s*16) string !32STUB \b, for MS Windows
146 >>>(0x3c.l+0xf8) string UPX0 \b, UPX compressed
147 >>>(0x3c.l+0xf8) search/0x140 PEC2 \b, PECompact2 compressed
148 >>>(0x3c.l+0xf8) search/0x140 UPX2
149 >>>>(&0x10.l+(-4)) string PK\3\4 \b, ZIP self-extracting archive (Info-Zip)
150 >>>(0x3c.l+0xf8) search/0x140 .idata
151 >>>>(&0xe.l+(-4)) string PK\3\4 \b, ZIP self-extracting archive (Info-Zip)
152 >>>>(&0xe.l+(-4)) string ZZ0 \b, ZZip self-extracting archive
153 >>>>(&0xe.l+(-4)) string ZZ1 \b, ZZip self-extracting archive
154 >>>(0x3c.l+0xf8) search/0x140 .rsrc
155 >>>>(&0x0f.l+(-4)) string a\\\4\5 \b, WinHKI self-extracting archive
156 >>>>(&0x0f.l+(-4)) string Rar! \b, RAR self-extracting archive
157 >>>>(&0x0f.l+(-4)) search/0x3000 MSCF \b, InstallShield self-extracting archive
158 >>>>(&0x0f.l+(-4)) search/32 Nullsoft \b, Nullsoft Installer self-extracting archive
159 >>>(0x3c.l+0xf8) search/0x140 .data
160 >>>>(&0x0f.l) string WEXTRACT \b, MS CAB-Installer self-extracting archive
161 >>>(0x3c.l+0xf8) search/0x140 .petite\0 \b, Petite compressed
162 >>>>(0x3c.l+0xf7) byte x
163 >>>>>(&0x104.l+(-4)) string =!sfx! \b, ACE self-extracting archive
164 >>>(0x3c.l+0xf8) search/0x140 .WISE \b, WISE installer self-extracting archive
165 >>>(0x3c.l+0xf8) search/0x140 .dz\0\0\0 \b, Dzip self-extracting archive
166 >>>&(0x3c.l+0xf8) search/0x100 _winzip_ \b, ZIP self-extracting archive (WinZip)
167 >>>&(0x3c.l+0xf8) search/0x100 SharedD \b, Microsoft Installer self-extracting archive
168 >>>0x30 string Inno \b, InnoSetup self-extracting archive
170 # Hmm, not a PE but the relocation table is too high for a traditional DOS exe,
171 # must be one of the unusual subformats.
172 >>(0x3c.l) string !PE\0\0 MS-DOS executable
173 !:mime application/x-dosexec
175 >>(0x3c.l) string NE \b, NE
176 !:mime application/x-dosexec
177 >>>(0x3c.l+0x36) byte 1 for OS/2 1.x
178 >>>(0x3c.l+0x36) byte 2 for MS Windows 3.x
179 >>>(0x3c.l+0x36) byte 3 for MS-DOS
180 >>>(0x3c.l+0x36) byte 4 for Windows 386
181 >>>(0x3c.l+0x36) byte 5 for Borland Operating System Services
182 >>>(0x3c.l+0x36) default x
183 >>>>(0x3c.l+0x36) byte x (unknown OS %x)
184 >>>(0x3c.l+0x36) byte 0x81 for MS-DOS, Phar Lap DOS extender
185 >>>(0x3c.l+0x0c) leshort&0x8000 0x8000 (DLL or font)
187 # 3GR: Grabber device driver
188 # CPL: Control Panel Item
189 # VBX: Visual Basic Extension
191 # FOT: Font resource file
192 !:ext dll/drv/3gr/cpl/vbx/fon/fot
193 >>>(0x3c.l+0x0c) leshort&0x8000 0 (EXE)
195 >>>&(&0x24.s-1) string ARJSFX \b, ARJ self-extracting archive
196 >>>(0x3c.l+0x70) search/0x80 WinZip(R)\ Self-Extractor \b, ZIP self-extracting archive (WinZip)
198 >>(0x3c.l) string LX\0\0 \b, LX
199 !:mime application/x-dosexec
200 >>>(0x3c.l+0x0a) leshort <1 (unknown OS)
201 >>>(0x3c.l+0x0a) leshort 1 for OS/2
202 >>>(0x3c.l+0x0a) leshort 2 for MS Windows
203 >>>(0x3c.l+0x0a) leshort 3 for DOS
204 >>>(0x3c.l+0x0a) leshort >3 (unknown OS)
205 >>>(0x3c.l+0x10) lelong&0x28000 =0x8000 (DLL)
206 >>>(0x3c.l+0x10) lelong&0x20000 >0 (device driver)
207 >>>(0x3c.l+0x10) lelong&0x300 0x300 (GUI)
208 >>>(0x3c.l+0x10) lelong&0x28300 <0x300 (console)
209 >>>(0x3c.l+0x08) leshort 1 i80286
210 >>>(0x3c.l+0x08) leshort 2 i80386
211 >>>(0x3c.l+0x08) leshort 3 i80486
212 >>>(8.s*16) string emx \b, emx
214 >>>&(&0x54.l-3) string arjsfx \b, ARJ self-extracting archive
216 # MS Windows system file, supposedly a collection of LE executables
217 >>(0x3c.l) string W3 \b, W3 for MS Windows
218 !:mime application/x-dosexec
220 >>(0x3c.l) string LE\0\0 \b, LE executable
221 !:mime application/x-dosexec
222 >>>(0x3c.l+0x0a) leshort 1
223 # some DOS extenders use LE files with OS/2 header
224 >>>>0x240 search/0x100 DOS/4G for MS-DOS, DOS4GW DOS extender
225 >>>>0x240 search/0x200 WATCOM\ C/C++ for MS-DOS, DOS4GW DOS extender
226 >>>>0x440 search/0x100 CauseWay\ DOS\ Extender for MS-DOS, CauseWay DOS extender
227 >>>>0x40 search/0x40 PMODE/W for MS-DOS, PMODE/W DOS extender
228 >>>>0x40 search/0x40 STUB/32A for MS-DOS, DOS/32A DOS extender (stub)
229 >>>>0x40 search/0x80 STUB/32C for MS-DOS, DOS/32A DOS extender (configurable stub)
230 >>>>0x40 search/0x80 DOS/32A for MS-DOS, DOS/32A DOS extender (embedded)
231 # this is a wild guess; hopefully it is a specific signature
232 >>>>&0x24 lelong <0x50
233 >>>>>(&0x4c.l) string \xfc\xb8WATCOM
234 >>>>>>&0 search/8 3\xdbf\xb9 \b, 32Lite compressed
235 # another wild guess: if real OS/2 LE executables exist, they probably have higher start EIP
236 #>>>>(0x3c.l+0x1c) lelong >0x10000 for OS/2
237 # fails with DOS-Extenders.
238 >>>(0x3c.l+0x0a) leshort 2 for MS Windows
239 >>>(0x3c.l+0x0a) leshort 3 for DOS
240 >>>(0x3c.l+0x0a) leshort 4 for MS Windows (VxD)
241 # VXD: VxD for Windows 95/98/Me
242 # 386: VxD for Windows 2.10, 3.0, 3.1x
244 # MPD: Miniport driver (?)
245 !:ext vxd/386/pdr/mpd
246 >>>(&0x7c.l+0x26) string UPX \b, UPX compressed
247 >>>&(&0x54.l-3) string UNACE \b, ACE self-extracting archive
249 # looks like ASCII, probably some embedded copyright message.
250 # and definitely not NE/LE/LX/PE
251 >>0x3c lelong >0x20000000
252 >>>(4.s*512) leshort !0x014c \b, MZ for MS-DOS
253 !:mime application/x-dosexec
255 # header data too small for extended executable
258 >>>(4.s*512) leshort !0x014c
260 >>>>&(2.s-514) string !LE
261 >>>>>&-2 string !BW \b, MZ for MS-DOS
262 !:mime application/x-dosexec
263 >>>>&(2.s-514) string LE \b, LE
264 >>>>>0x240 search/0x100 DOS/4G for MS-DOS, DOS4GW DOS extender
265 # educated guess since indirection is still not capable enough for complex offset
266 # calculations (next embedded executable would be at &(&2*512+&0-2)
267 # I suspect there are only LE executables in these multi-exe files
268 >>>>&(2.s-514) string BW
269 >>>>>0x240 search/0x100 DOS/4G \b, LE for MS-DOS, DOS4GW DOS extender (embedded)
270 >>>>>0x240 search/0x100 !DOS/4G \b, BW collection for MS-DOS
272 # This sequence skips to the first COFF segment, usually .text
273 >(4.s*512) leshort 0x014c \b, COFF
274 !:mime application/x-dosexec
275 >>(8.s*16) string go32stub for MS-DOS, DJGPP go32 DOS extender
276 >>(8.s*16) string emx
277 >>>&1 string x for DOS, Win or OS/2, emx %s
278 >>&(&0x42.l-3) byte x
279 >>>&0x26 string UPX \b, UPX compressed
280 # and yet another guess: small .text, and after large .data is unusal, could be 32lite
281 >>&0x2c search/0xa0 .text
282 >>>&0x0b lelong <0x2000
283 >>>>&0 lelong >0x6000 \b, 32lite compressed
285 >(8.s*16) string $WdX \b, WDos/X DOS extender
287 # By now an executable type should have been printed out. The executable
288 # may be a self-uncompressing archive, so look for evidence of that and
291 # Some signatures below from Greg Roelofs, newt@uchicago.edu.
293 >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
294 >0xe7 string LH/2\ Self-Extract \b, %s
295 >0x1c string UC2X \b, UCEXE compressed
296 >0x1c string WWP\ \b, WWPACK compressed
297 >0x1c string RJSX \b, ARJ self-extracting archive
298 >0x1c string diet \b, diet compressed
299 >0x1c string LZ09 \b, LZEXE v0.90 compressed
300 >0x1c string LZ91 \b, LZEXE v0.91 compressed
301 >0x1c string tz \b, TinyProg compressed
302 >0x1e string Copyright\ 1989-1990\ PKWARE\ Inc. Self-extracting PKZIP archive
303 !:mime application/zip
304 # Yes, this really is "Copr", not "Corp."
305 >0x1e string PKLITE\ Copr. Self-extracting PKZIP archive
306 !:mime application/zip
307 # winarj stores a message in the stub instead of the sig in the MZ header
308 >0x20 search/0xe0 aRJsfX \b, ARJ self-extracting archive
310 >>0x23 string 2 \b, AIN 2.x compressed
311 >>0x23 string <2 \b, AIN 1.x compressed
312 >>0x23 string >2 \b, AIN 1.x compressed
313 >0x24 string LHa's\ SFX \b, LHa self-extracting archive
314 !:mime application/x-lha
315 >0x24 string LHA's\ SFX \b, LHa self-extracting archive
316 !:mime application/x-lha
317 >0x24 string \ $ARX \b, ARX self-extracting archive
318 >0x24 string \ $LHarc \b, LHarc self-extracting archive
319 >0x20 string SFX\ by\ LARC \b, LARC self-extracting archive
320 >0x40 string aPKG \b, aPackage self-extracting archive
321 >0x64 string W\ Collis\0\0 \b, Compack compressed
322 >0x7a string Windows\ self-extracting\ ZIP \b, ZIP self-extracting archive
323 >>&0xf4 search/0x140 \x0\x40\x1\x0
324 >>>(&0.l+(4)) string MSCF \b, WinHKI CAB self-extracting archive
325 >1638 string -lh5- \b, LHa self-extracting archive v2.13S
326 >0x17888 string Rar! \b, RAR self-extracting archive
328 # Skip to the end of the EXE. This will usually work fine in the PE case
329 # because the MZ image is hardcoded into the toolchain and almost certainly
330 # won't match any of these signatures.
333 >>>&0 string PK\3\4 \b, ZIP self-extracting archive
334 >>>&0 string Rar! \b, RAR self-extracting archive
335 >>>&0 string =!\x11 \b, AIN 2.x self-extracting archive
336 >>>&0 string =!\x12 \b, AIN 2.x self-extracting archive
337 >>>&0 string =!\x17 \b, AIN 1.x self-extracting archive
338 >>>&0 string =!\x18 \b, AIN 1.x self-extracting archive
339 >>>&7 search/400 **ACE** \b, ACE self-extracting archive
340 >>>&0 search/0x480 UC2SFX\ Header \b, UC2 self-extracting archive
342 # a few unknown ZIP sfxes, no idea if they are needed or if they are
343 # already captured by the generic patterns above
344 >(8.s*16) search/0x20 PKSFX \b, ZIP self-extracting archive (PKZIP)
345 # TODO: how to add this? >FileSize-34 string Windows\ Self-Installing\ Executable \b, ZIP self-extracting archive
348 # TELVOX Teleinformatica CODEC self-extractor for OS/2:
349 >49801 string \x79\xff\x80\xff\x76\xff \b, CODEC archive v3.21
350 >>49824 leshort =1 \b, 1 file
351 >>49824 leshort >1 \b, %u files
353 # added by Joerg Jenderek of https://www.freedos.org/software/?prog=kc
354 # and https://www.freedos.org/software/?prog=kpdos
355 # for FreeDOS files like KEYBOARD.SYS, KEYBRD2.SYS, KEYBRD3.SYS, *.KBD
356 0 string/b KCF FreeDOS KEYBoard Layout collection
357 # only version=0x100 found
358 >3 uleshort x \b, version 0x%x
359 # length of string containing author,info and special characters
361 #>>6 pstring x \b, name=%s
362 >>7 string >\0 \b, author=%-.14s
363 >>7 search/254 \xff \b, info=
364 #>>>&0 string x \b%-s
365 >>>&0 string x \b%-.15s
366 # for FreeDOS *.KL files
367 0 string/b KLF FreeDOS KEYBoard Layout file
368 # only version=0x100 or 0x101 found
369 >3 uleshort x \b, version 0x%x
372 >>8 string x \b, name=%-.2s
373 0 string \xffKEYB\ \ \ \0\0\0\0
374 >12 string \0\0\0\0`\004\360 MS-DOS KEYBoard Layout file
376 # DOS device driver updated by Joerg Jenderek at May 2011,Mar 2017
377 # https://amaus.net/static/S100/IBM/software/DOS/DOS%20techref/CHAPTER.009
378 0 ulequad&0x07a0ffffffff 0xffffffff
380 0 name msdos-driver DOS executable (
381 #!:mime application/octet-stream
382 !:mime application/x-dosdriver
383 # also found FreeDOS print driver SPOOL.DEV and disc compression driver STACLOAD.BIN
385 >40 search/7 UPX! \bUPX compressed
386 # DOS device driver attributes
387 >4 uleshort&0x8000 0x0000 \bblock device driver
389 >4 uleshort&0x8000 0x8000 \b
390 >>4 uleshort&0x0008 0x0008 \bclock
391 # fast video output by int 29h
392 >>4 uleshort&0x0010 0x0010 \bfast
393 # standard input/output device
394 >>4 uleshort&0x0003 >0 \bstandard
395 >>>4 uleshort&0x0001 0x0001 \binput
396 >>>4 uleshort&0x0003 0x0003 \b/
397 >>>4 uleshort&0x0002 0x0002 \boutput
398 >>4 uleshort&0x8000 0x8000 \bcharacter device driver
400 # upx compressed device driver has garbage instead of real in name field of header
403 # leading/trailing nulls, zeros or non ASCII characters in 8-byte name field at offset 10 are skipped
407 >>>>>>10 ubyte !0x2A \b%c
409 >>>>>11 ubyte !0x2E \b%c
412 >>>>>>12 ubyte !0x2E \b%c
414 >>>>13 ubyte !0x2E \b%c
416 >>>>>14 ubyte !0x2E \b%c
418 >>>>>15 ubyte !0x2E \b%c
421 >>>>>>16 ubyte <0xCB \b%c
424 >>>>>>17 ubyte <0x90 \b%c
425 # some character device drivers like ASPICD.SYS, btcdrom.sys and Cr_atapi.sys contain only spaces or points in name field
427 # they have their real name at offset 22
428 # also block device drivers like DUMBDRV.SYS
429 >>>>22 string >\056 %-.6s
430 >4 uleshort&0x8000 0x0000
431 # 32 bit sector addressing ( > 32 MB) for block devices
432 >>4 uleshort&0x0002 0x0002 \b,32-bit sector-
433 # support by driver functions 13h, 17h, 18h
434 >4 uleshort&0x0040 0x0040 \b,IOCTL-
435 # open, close, removable media support by driver functions 0Dh, 0Eh, 0Fh
436 >4 uleshort&0x0800 0x0800 \b,close media-
437 # output until busy support by int 10h for character device driver
438 >4 uleshort&0x8000 0x8000
439 >>4 uleshort&0x2000 0x2000 \b,until busy-
440 # direct read/write support by driver functions 03h,0Ch
441 >4 uleshort&0x4000 0x4000 \b,control strings-
442 >4 uleshort&0x8000 0x8000
443 >>4 uleshort&0x6840 >0 \bsupport
444 >4 uleshort&0x8000 0x0000
445 >>4 uleshort&0x4842 >0 \bsupport
447 # DOS driver cmd640x.sys has 0x12 instead of 0xffffffff for pointer field to next device header
448 0 ulequad 0x0513c00000000012
450 # DOS drivers DC2975.SYS, DUMBDRV.SYS, ECHO.SYS has also none 0xffffffff for pointer field
451 0 ulequad 0x32f28000ffff0016
453 0 ulequad 0x007f00000000ffff
455 0 ulequad 0x001600000000ffff
457 # DOS drivers LS120.SYS, MKELS120.SYS use reserved bits of attribute field
458 0 ulequad 0x0bf708c2ffffffff
460 0 ulequad 0x07bd08c2ffffffff
463 # updated by Joerg Jenderek
464 # GRR: line below too general as it catches also
465 # rt.lib DYADISKS.PIC and many more
466 # start with assembler instruction MOV
468 # skip "AppleWorks word processor data" like ARTICLE.1 ./apple
470 # skip some unknown basic binaries like RocketRnger.SHR
472 # skip "GPG symmetrically encrypted data" ./gnu
473 # skip "PGP symmetric key encrypted data" ./pgp
474 # openpgpdefs.h: fourth byte < 14 indicate cipher algorithm type
475 >>>4 ubyte >13 DOS executable (COM, 0x8C-variant)
476 # the remaining files should be DOS *.COM executables
477 # dosshell.COM 8cc0 2ea35f07 e85211 e88a11 b80058 cd
478 # hmload.COM 8cc8 8ec0 bbc02b 89dc 83c30f c1eb04 b4
479 # UNDELETE.COM 8cca 2e8916 6503 b430 cd21 8b 2e0200 8b
480 # BOOTFIX.COM 8cca 2e8916 9603 b430 cd21 8b 2e0200 8b
481 # RAWRITE3.COM 8cca 2e8916 d602 b430 cd21 8b 2e0200 8b
482 # SHARE.COM 8cca 2e8916 d602 b430 cd21 8b 2e0200 8b
483 # validchr.COM 8cca 2e8916 9603 b430 cd21 8b 2e028b1e
484 # devload.COM 8cca 8916ad01 b430 cd21 8b2e0200 892e
485 !:mime application/x-dosexec
488 # updated by Joerg Jenderek at Oct 2008
489 0 ulelong 0xffff10eb DR-DOS executable (COM)
490 # byte 0xeb conflicts with "sequent" magic leshort 0xn2eb
491 0 ubeshort&0xeb8d >0xeb00
492 # DR-DOS STACKER.COM SCREATE.SYS missed
495 >0 byte x DOS executable (COM)
496 !:mime application/x-dosexec
498 >6 string SFX\ of\ LHarc \b, %s
499 >0x1FE leshort 0xAA55 \b, boot code
500 >85 string UPX \b, UPX compressed
501 >4 string \ $ARX \b, ARX self-extracting archive
502 >4 string \ $LHarc \b, LHarc self-extracting archive
503 >0x20e string SFX\ by\ LARC \b, LARC self-extracting archive
507 # allow forward jumps only
509 # that offset must be accessible
517 # that offset must be accessible
520 # negative offset, must not lead into PSP
522 # that offset must be accessible
526 # updated by Joerg Jenderek at Oct 2008,2015
527 # following line is too general
529 # skip 2 linux kernels like memtest.bin with "\xb8\xc0\x07\x8e" in ./linux
530 >0 string !\xb8\xc0\x07\x8e
531 # modified by Joerg Jenderek
532 # syslinux COM32 or COM32R executable
533 >>1 lelong&0xFFFFFFFe 0x21CD4CFe COM executable (32-bit COMBOOT
534 # https://www.syslinux.org/wiki/index.php/Comboot_API
535 # Since version 5.00 c32 modules switched from the COM32 object format to ELF
536 !:mime application/x-c32-comboot-syslinux-exec
538 # https://syslinux.zytor.com/comboot.php
539 # older syslinux version ( <4 )
540 # (32-bit COMBOOT) programs *.C32 contain 32-bit code and run in flat-memory 32-bit protected mode
541 # start with assembler instructions mov eax,21cd4cffh
542 >>>1 lelong 0x21CD4CFf \b)
543 # syslinux:doc/comboot.txt
544 # A COM32R program must start with the byte sequence B8 FE 4C CD 21 (mov
545 # eax,21cd4cfeh) as a magic number.
546 # syslinux version (4.x)
547 # "COM executable (COM32R)" or "Syslinux COM32 module" by TrID
548 >>>1 lelong 0x21CD4CFe \b, relocatable)
549 # remaining are DOS COM executables starting with assembler instruction MOV
550 # like FreeDOS BANNER*.COM FINDDISK.COM GIF2RAW.COM WINCHK.COM
551 # MS-DOS SYS.COM RESTART.COM
552 # SYSLINUX.COM (version 1.40 - 2.13)
553 # GFXBOOT.COM (version 3.75)
554 # COPYBS.COM POWEROFF.COM INT18.COM
555 >>1 default x COM executable for DOS
556 !:mime application/x-dosexec
557 #!:mime application/x-ms-dos-executable
558 #!:mime application/x-msdos-program
562 >4 string \x77\x02\xcd\x20\xb9
563 >>36 string UPX! FREE-DOS executable (COM), UPX compressed
564 !:mime application/x-dosexec
566 252 string Must\ have\ DOS\ version DR-DOS executable (COM)
567 !:mime application/x-dosexec
569 # added by Joerg Jenderek at Oct 2008
570 # GRR search is not working
571 #34 search/2 UPX! FREE-DOS executable (COM), UPX compressed
572 34 string UPX! FREE-DOS executable (COM), UPX compressed
573 !:mime application/x-dosexec
575 35 string UPX! FREE-DOS executable (COM), UPX compressed
576 !:mime application/x-dosexec
578 # GRR search is not working
579 #2 search/28 \xcd\x21 COM executable for MS-DOS
581 2 string \xcd\x21 COM executable for DOS
582 !:mime application/x-dosexec
584 #DELTREE.cOM DELTREE2.cOM
585 4 string \xcd\x21 COM executable for DOS
586 !:mime application/x-dosexec
588 #IFMEMDSK.cOM ASSIGN.cOM COMP.cOM
589 5 string \xcd\x21 COM executable for DOS
590 !:mime application/x-dosexec
592 #DELTMP.COm HASFAT32.cOM
594 >0 byte !0xb8 COM executable for DOS
595 !:mime application/x-dosexec
599 >5 string !\xcd\x21 COM executable for DOS
600 !:mime application/x-dosexec
603 13 string \xcd\x21 COM executable for DOS
604 !:mime application/x-dosexec
607 18 string \xcd\x21 COM executable for MS-DOS
608 !:mime application/x-dosexec
611 23 string \xcd\x21 COM executable for MS-DOS
612 !:mime application/x-dosexec
614 #LOADFIX.cOm LOADFIX.cOm
615 30 string \xcd\x21 COM executable for MS-DOS
616 !:mime application/x-dosexec
619 70 string \xcd\x21 COM executable for DOS
620 !:mime application/x-dosexec
622 # many compressed/converted COMs start with a copy loop instead of a jump
623 0x6 search/0xa \xfc\x57\xf3\xa5\xc3 COM executable for MS-DOS
624 !:mime application/x-dosexec
626 0x6 search/0xa \xfc\x57\xf3\xa4\xc3 COM executable for DOS
627 !:mime application/x-dosexec
629 >0x18 search/0x10 \x50\xa4\xff\xd5\x73 \b, aPack compressed
630 0x3c string W\ Collis\0\0 COM executable for MS-DOS, Compack compressed
631 !:mime application/x-dosexec
633 # FIXME: missing diet .com compression
635 # miscellaneous formats
636 0 string/b LZ MS-DOS executable (built-in)
637 #0 byte 0xf0 MS-DOS program library data
641 # <stuartc@rd.bbc.co.uk> Stuart Cunningham
642 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
643 >30 byte 9 (512B sectors)
644 >30 byte 12 (4kB sectors)
645 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
646 >30 byte 9 (512B sectors)
647 >30 byte 12 (4kB sectors)
649 # Popular applications
650 2080 string Microsoft\ Word\ 6.0\ Document %s
651 !:mime application/msword
652 2080 string Documento\ Microsoft\ Word\ 6 Spanish Microsoft Word 6 document data
653 !:mime application/msword
654 # Pawel Wiecek <coven@i17linuxb.ists.pwr.wroc.pl> (for polish Word)
655 2112 string MSWordDoc Microsoft Word document data
656 !:mime application/msword
658 0 belong 0x31be0000 Microsoft Word Document
659 !:mime application/msword
661 0 string/b PO^Q` Microsoft Word 6.0 Document
662 !:mime application/msword
665 >0 belong 0xfe320000 Microsoft Word for Macintosh 1.0
666 !:mime application/msword
668 >0 belong 0xfe340000 Microsoft Word for Macintosh 3.0
669 !:mime application/msword
671 >0 belong 0xfe37001c Microsoft Word for Macintosh 4.0
672 !:mime application/msword
674 >0 belong 0xfe370023 Microsoft Word for Macintosh 5.0
675 !:mime application/msword
678 0 string/b \333\245-\0\0\0 Microsoft Word 2.0 Document
679 !:mime application/msword
681 # Note: seems already recognized as "OLE 2 Compound Document" in ./ole2compounddocs
682 #512 string/b \354\245\301 Microsoft Word Document
683 #!:mime application/msword
686 0 string/b \xDB\xA5\x2D\x00 Microsoft WinWord 2.0 Document
687 !:mime application/msword
689 2080 string Microsoft\ Excel\ 5.0\ Worksheet %s
690 !:mime application/vnd.ms-excel
692 0 string/b \xDB\xA5\x2D\x00 Microsoft WinWord 2.0 Document
693 !:mime application/msword
695 2080 string Foglio\ di\ lavoro\ Microsoft\ Exce %s
696 !:mime application/vnd.ms-excel
698 # Pawel Wiecek <coven@i17linuxb.ists.pwr.wroc.pl> (for polish Excel)
699 2114 string Biff5 Microsoft Excel 5.0 Worksheet
700 !:mime application/vnd.ms-excel
702 2121 string Biff5 Microsoft Excel 5.0 Worksheet
703 !:mime application/vnd.ms-excel
704 0 string/b \x09\x04\x06\x00\x00\x00\x10\x00 Microsoft Excel Worksheet
705 !:mime application/vnd.ms-excel
707 # Update: Joerg Jenderek
708 # URL: https://en.wikipedia.org/wiki/Lotus_1-2-3
709 # Reference: http://www.aboutvb.de/bas/formate/pdf/wk3.pdf
710 # Note: newer Lotus versions >2 use longer BOF record
711 # record type (BeginningOfFile=0000h) + length (001Ah)
713 # reserved should be 0h but 8c0dh for TUTMAC.WK3, 5h for SAMPADNS.WK3, 1h for a_readme.wk3, 1eh for K&G86.WK3
714 #>18 uleshort&0x73E0 0
715 # Lotus Multi Byte Character Set (LMBCS=1-31)
717 >>20 ubyte <32 Lotus 1-2-3
718 #!:mime application/x-123
719 !:mime application/vnd.lotus-1-2-3
721 # (version 5.26) labeled the entry as "Lotus 1-2-3 wk3 document data"
722 >>>4 uleshort 0x1000 WorKsheet, version 3
724 # (version 5.26) labeled the entry as "Lotus 1-2-3 wk4 document data"
725 >>>4 uleshort 0x1002 WorKsheet, version 4
726 # also worksheet template 4 (.wt4)
728 # no example or documentation for wk5
729 #>>4 uleshort 0x???? WorKsheet, version 4
731 # only MacrotoScript.123 example
732 >>>4 uleshort 0x1003 WorKsheet, version 97
733 # also worksheet template Smartmaster (.12M)?
735 # only Set_Y2K.123 example
736 >>>4 uleshort 0x1005 WorKsheet, version 9.8 Millennium
738 # no example for this version
739 >>>4 uleshort 0x8001 FoRMatting data
741 # (version 5.26) labeled the entry as "Lotus 1-2-3 fm3 or fmb document data"
742 # TrID labeles the entry as "Formatting Data for Lotus 1-2-3 worksheet"
743 >>>4 uleshort 0x8007 ForMatting data, version 3
745 >>>4 default x unknown
746 # file revision sub code 0004h for worksheets
747 >>>>6 uleshort =0x0004 worksheet
749 >>>>6 uleshort !0x0004 formatting data
751 # main revision number
752 >>>>4 uleshort x \b, revision 0x%x
753 >>>6 uleshort =0x0004 \b, cell range
754 # active cellcoord range (start row, page,column ; end row, page, column)
755 # start values normally 0~1st sheet A1
757 >>>>>10 ubyte >0 \b%d*
758 >>>>>8 uleshort x \b%d,
759 >>>>>11 ubyte x \b%d-
761 >>>>14 ubyte >0 \b%d*
762 # end raw, column normally not 0
763 >>>>12 uleshort x \b%d,
765 # Lotus Multi Byte Character Set (1~cp850,2~cp851,...,16~japan,...,31~??)
766 >>>>20 ubyte >1 \b, character set 0x%x
768 >>>>21 ubyte x \b, flags 0x%x
769 >>>6 uleshort !0x0004
770 # record type (FONTNAME=00AEh)
771 >>>>30 search/29 \0\xAE
772 # variable length m (2) + entries (1) + ?? (1) + LCMBS string (n)
773 >>>>>&4 string >\0 \b, 1st font "%s"
775 # Update: Joerg Jenderek
776 # URL: http://fileformats.archiveteam.org/wiki/Lotus_1-2-3
777 # Reference: http://www.schnarff.com/file-formats/lotus-1-2-3/WSFF2.TXT
778 # Note: Used by both old Lotus 1-2-3 and Lotus Symphony (DOS) til version 2.x
779 # record type (BeginningOfFile=0000h) + length (0002h)
781 # GRR: line above is too general as it catches also MS Windows CURsor
782 # to display MS Windows cursor (strength=70) before Lotus 1-2-3 (strength=70-1)
784 # skip Windows cursors with image height <256 and keep Lotus with low opcode 0001-0083h
786 # skip Windows cursors with image width 256 and keep Lotus with positiv opcode
788 # !:mime application/x-123
789 !:mime application/vnd.lotus-1-2-3
791 # revision number (0404h = 123 1A, 0405h = Lotus Symphony , 0406h = 123 2.x wk1 , 8006h = fmt , ...)
792 # undocumented; (version 5.26) labeled the configurations as "Lotus 1-2-3"
793 >>>4 uleshort 0x0007 1-2-3 CoNFiguration, version 2.x (PGRAPH.CNF)
795 >>>4 uleshort 0x0C05 1-2-3 CoNFiguration, version 2.4J
797 >>>4 uleshort 0x0801 1-2-3 CoNFiguration, version 1-2.1
799 >>>4 uleshort 0x0802 Symphony CoNFiguration
801 >>>4 uleshort 0x0804 1-2-3 CoNFiguration, version 2.2
803 >>>4 uleshort 0x080A 1-2-3 CoNFiguration, version 2.3-2.4
805 >>>4 uleshort 0x1402 1-2-3 CoNFiguration, version 3.x
807 >>>4 uleshort 0x1450 1-2-3 CoNFiguration, version 4.x
809 # (version 5.26) labeled the entry as "Lotus 123"
810 # TrID labeles the entry as "Lotus 123 Worksheet (generic)"
811 >>>4 uleshort 0x0404 1-2-3 WorKSheet, version 1
812 # extension "wks" also for Microsoft Works document
814 # (version 5.26) labeled the entry as "Lotus 123"
815 # TrID labeles the entry as "Lotus 123 Worksheet (generic)"
816 >>>4 uleshort 0x0405 Symphony WoRksheet, version 1.0
818 # (version 5.26) labeled the entry as "Lotus 1-2-3 wk1 document data"
819 # TrID labeles the entry as "Lotus 123 Worksheet (V2)"
820 >>>4 uleshort 0x0406 1-2-3/Symphony worksheet, version 2
823 # no example for this japan version
824 >>>4 uleshort 0x0600 1-2-3 WorKsheet, version 1.xJ
826 # no example or documentation for wk2
827 #>>>4 uleshort 0x???? 1-2-3 WorKsheet, version 2
829 # undocumented japan version
830 >>>4 uleshort 0x0602 1-2-3 worksheet, version 2.4J
832 # (version 5.26) labeled the entry as "Lotus 1-2-3 fmt document data"
833 >>>4 uleshort 0x8006 1-2-3 ForMaTting data, version 2.x
834 # japan version 2.4J (fj3)
836 # no example for this version
837 >>>4 uleshort 0x8007 1-2-3 FoRMatting data, version 2.0
839 # (version 5.26) labeled the entry as "Lotus 1-2-3"
840 >>>4 default x unknown worksheet or configuration
842 >>>>4 uleshort x \b, revision 0x%x
843 # 2nd record for most worksheets describes cells range
845 # 3nd record for most japan worksheets describes cells range
846 >>>(8.s+10) use lotus-cells
847 # check and then display Lotus worksheet cells range
849 # look for type (RANGE=0006h) + length (0008h) at record begin
850 >0 ubelong 0x06000800 \b, cell range
851 # cell range (start column, row, end column, row) start values normally 0,0~A1 cell
853 >>>4 uleshort x \b%d,
854 >>>6 uleshort x \b%d-
859 0 string/b WordPro\0 Lotus WordPro
860 !:mime application/vnd.lotus-wordpro
861 0 string/b WordPro\r\373 Lotus WordPro
862 !:mime application/vnd.lotus-wordpro
865 # Summary: Script used by InstallScield to uninstall applications
867 # Submitted by: unknown
868 # Modified by (1): Abel Cheung <abelcheung@gmail.com> (replace useless entry)
869 0 string \x71\xa8\x00\x00\x01\x02
870 >12 string Stirling\ Technologies, InstallShield Uninstall Script
873 #0 string Nullsoft\ AVS\ Preset\ \060\056\061\032 A plug in for Winamp ms-windows Freeware media player
874 0 string/b Nullsoft\ AVS\ Preset\ Winamp plug in
876 # Windows Metafile .WMF
877 0 string/b \327\315\306\232 Windows metafile
880 0 string/b \002\000\011\000 Windows metafile
883 0 string/b \001\000\011\000 Windows metafile
887 #tz3 files whatever that is (MS Works files)
888 0 string/b \003\001\001\004\070\001\000\000 tz3 ms-works file
889 0 string/b \003\002\001\004\070\001\000\000 tz3 ms-works file
890 0 string/b \003\003\001\004\070\001\000\000 tz3 ms-works file
893 #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
894 0 string \211\000\077\003\005\000\063\237\127\065\027\266\151\064\005\045\101\233\021\002 PGP sig
895 0 string \211\000\077\003\005\000\063\237\127\066\027\266\151\064\005\045\101\233\021\002 PGP sig
896 0 string \211\000\077\003\005\000\063\237\127\067\027\266\151\064\005\045\101\233\021\002 PGP sig
897 0 string \211\000\077\003\005\000\063\237\127\070\027\266\151\064\005\045\101\233\021\002 PGP sig
898 0 string \211\000\077\003\005\000\063\237\127\071\027\266\151\064\005\045\101\233\021\002 PGP sig
899 0 string \211\000\225\003\005\000\062\122\207\304\100\345\042 PGP sig
901 # windows zips files .dmf
902 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
906 0 string/b \102\101\050\000\000\000\056\000\000\000\000\000\000\000 Icon for MS Windows
909 # Update: Joerg Jenderek
910 # URL: https://en.wikipedia.org/wiki/CUR_(file_format)
911 # Note: similar to Windows CURsor. container for BMP (only DIB part) or PNG
919 # displays number of icons and information for icon or cursor
921 # skip some Lotus 1-2-3 worksheets, CYCLE.PIC and keep Windows cursors with
922 # 1st data offset = dir header size + n * dir entry size = 6 + n * 10h = ?6h
923 >18 ulelong &0x00000006
924 # skip remaining worksheets, because valid only for DIB image (40) or PNG image (\x89PNG)
925 >>(18.l) ulelong x MS Windows
926 >>>0 ubelong 0x00000100 icon resource
927 # https://www.iana.org/assignments/media-types/image/vnd.microsoft.icon
928 !:mime image/vnd.microsoft.icon
931 >>>>4 uleshort x - %d icon
933 >>>>4 uleshort >1 \bs
935 >>>>0x06 use ico-entry
938 >>>>>0x16 use ico-entry
939 >>>0 ubelong 0x00000200 cursor resource
941 !:mime image/x-win-bitmap
943 >>>>4 uleshort x - %d icon
944 >>>>4 uleshort >1 \bs
946 >>>>0x06 use cur-entry
947 #>>>>0x16 use cur-entry
948 # display information of one cursor entry
951 >4 uleshort x \b, hotspot @%dx
953 # display information of one icon entry
956 # normally 0 1 but also found 14
957 >4 uleshort >1 \b, %d planes
958 # normally 0 1 but also found some 3, 4, some 6, 8, 24, many 32, two 256
959 >6 uleshort >1 \b, %d bits/pixel
960 # display shared information of cursor or icon entry
966 # number of colors in palette
967 >2 ubyte !0 \b, %d colors
969 #>3 ubyte x \b, reserved %x
970 #>8 ulelong x \b, image size %d
971 # offset of PNG or DIB image
972 #>12 ulelong x \b, offset 0x%x
973 # PNG header (\x89PNG)
974 >(12.l) ubelong =0x89504e47
975 # 1 space char after "with" to get phrase "with PNG image" by magic in ./images
976 >>&-4 indirect x \b with
978 >(12.l) ubelong !0x89504e47
981 # Windows non-animated cursors
982 # Update: Joerg Jenderek
983 # URL: https://en.wikipedia.org/wiki/CUR_(file_format)
984 # Note: similar to Windows ICOn. container for BMP ( only DIB part)
985 # GRR: line below is too general as it catches also Lotus 1-2-3 files
993 0 string/b PK\010\010BGI Borland font
995 # then there is a copyright notice
999 0 string/b pk\010\010BGI Borland device
1001 # then there is a copyright notice
1004 # Windows Recycle Bin record file (named INFO2)
1005 # By Abel Cheung (abelcheung AT gmail dot com)
1006 # Version 4 always has 280 bytes (0x118) per record, version 5 has 800 bytes
1007 # Since Vista uses another structure, INFO2 structure probably won't change
1008 # anymore. Detailed analysis in:
1009 # http://www.cybersecurityinstitute.biz/downloads/INFO2.pdf
1011 >12 lelong 0x00000118 Windows Recycle Bin INFO2 file (Win98 or below)
1014 >12 lelong 0x00000320 Windows Recycle Bin INFO2 file (Win2k - WinXP)
1016 # From Doug Lee via a FreeBSD pr
1017 9 string GERBILDOC First Choice document
1018 9 string GERBILDB First Choice database
1019 9 string GERBILCLIP First Choice database
1020 0 string GERBIL First Choice device file
1021 9 string RABBITGRAPH RabbitGraph file
1022 0 string DCU1 Borland Delphi .DCU file
1023 0 string =!<spell> MKS Spell hash list (old format)
1024 0 string =!<spell2> MKS Spell hash list
1026 #0 string AH Halo(TM) bitmapped font file
1027 0 lelong 0x08086b70 TurboC BGI file
1028 0 lelong 0x08084b50 TurboC Font file
1030 # Debian#712046: The magic below identifies "Delphi compiled form data".
1031 # An additional source of information is available at:
1032 # http://www.woodmann.com/fravia/dafix_t1.htm
1034 >4 pstring >\0 Delphi compiled form '%s'
1036 # tests for DBase files moved, updated and merged to database
1038 0 string PMCC Windows 3.x .GRP file
1039 1 string RDC-meg MegaDots
1040 >8 byte >0x2F version %c
1041 >9 byte >0x2F \b.%c file
1043 >4 lelong 0x00021401 Windows shortcut file
1045 # .PIF files added by Joerg Jenderek from https://smsoft.ru/en/pifdoc.htm
1046 # only for windows versions equal or greater 3.0
1047 0x171 string MICROSOFT\ PIFEX\0 Windows Program Information File
1048 !:mime application/x-dosexec
1050 #>2 string >\0 \b, Title:%.30s
1051 >0x24 string >\0 \b for %.63s
1052 >0x65 string >\0 \b, directory=%.64s
1053 >0xA5 string >\0 \b, parameters=%.64s
1054 #>0x181 leshort x \b, offset %x
1055 #>0x183 leshort x \b, offsetdata %x
1056 #>0x185 leshort x \b, section length %x
1057 >0x187 search/0xB55 WINDOWS\ VMM\ 4.0\0
1059 >>>&-1 string <PIFMGR.DLL \b, icon=%s
1060 #>>>&-1 string PIFMGR.DLL \b, icon=%s
1061 >>>&-1 string >PIFMGR.DLL \b, icon=%s
1063 >>>&-1 string <Terminal \b, font=%.32s
1064 #>>>&-1 string =Terminal \b, font=%.32s
1065 >>>&-1 string >Terminal \b, font=%.32s
1067 >>>&-1 string <Lucida\ Console \b, TrueTypeFont=%.32s
1068 #>>>&-1 string =Lucida\ Console \b, TrueTypeFont=%.32s
1069 >>>&-1 string >Lucida\ Console \b, TrueTypeFont=%.32s
1070 #>0x187 search/0xB55 WINDOWS\ 286\ 3.0\0 \b, Windows 3.X standard mode-style
1071 #>0x187 search/0xB55 WINDOWS\ 386\ 3.0\0 \b, Windows 3.X enhanced mode-style
1072 >0x187 search/0xB55 WINDOWS\ NT\ \ 3.1\0 \b, Windows NT-style
1073 #>0x187 search/0xB55 WINDOWS\ NT\ \ 4.0\0 \b, Windows NT-style
1074 >0x187 search/0xB55 CONFIG\ \ SYS\ 4.0\0 \b +CONFIG.SYS
1075 #>>&06 string x \b:%s
1076 >0x187 search/0xB55 AUTOEXECBAT\ 4.0\0 \b +AUTOEXEC.BAT
1077 #>>&06 string x \b:%s
1079 # DOS EPS Binary File Header
1080 # From: Ed Sznyter <ews@Black.Market.NET>
1081 0 belong 0xC5D0D3C6 DOS EPS Binary File
1083 >4 long >0 Postscript starts at byte %d
1084 >>8 long >0 length %d
1085 >>>12 long >0 Metafile starts at byte %d
1086 >>>>16 long >0 length %d
1087 >>>20 long >0 TIFF starts at byte %d
1088 >>>>24 long >0 length %d
1090 # TNEF magic From "Joomy" <joomy@se-ed.net>
1091 # Microsoft Outlook's Transport Neutral Encapsulation Format (TNEF)
1092 0 lelong 0x223e9f78 TNEF
1093 !:mime application/vnd.ms-tnef
1095 # Norton Guide (.NG , .HLP) files added by Joerg Jenderek from source NG2HTML.C
1096 # of http://www.davep.org/norton-guides/ng2h-105.tgz
1097 # https://en.wikipedia.org/wiki/Norton_Guides
1099 # only value 0x100 found at offset 2
1100 >2 ulelong 0x00000100 Norton Guide
1102 >>8 string >\0 "%-.40s"
1103 #>>6 uleshort x \b, MenuCount=%u
1105 >>48 string >\0 \b, %-.66s
1106 >>114 string >\0 %-.66s
1108 # 4DOS help (.HLP) files added by Joerg Jenderek from source TPHELP.PAS
1109 # of https://www.4dos.info/
1110 # pointer,HelpID[8]=4DHnnnmm
1111 0 ulelong 0x48443408 4DOS help file
1112 >4 string x \b, version %-4.4s
1114 # old binary Microsoft (.HLP) files added by Joerg Jenderek from http://file-extension.net/seeker/file_extension_hlp
1115 0 ulequad 0x3a000000024e4c MS Advisor help file
1117 # HtmlHelp files (.chm)
1118 0 string/b ITSF\003\000\000\000\x60\000\000\000 MS Windows HtmlHelp Data
1120 # GFA-BASIC (Wolfram Kleff)
1121 2 string/b GFA-BASIC3 GFA-BASIC 3 data
1123 #------------------------------------------------------------------------------
1124 # From Stuart Caie <kyzer@4u.net> (developer of cabextract)
1125 # Update: Joerg Jenderek
1126 # URL: https://en.wikipedia.org/wiki/Cabinet_(file_format)
1127 # Reference: https://msdn.microsoft.com/en-us/library/bb267310.aspx
1128 # Note: verified by `7z l *.cab`
1129 # Microsoft Cabinet files
1130 0 string/b MSCF\0\0\0\0 Microsoft Cabinet archive data
1132 # https://support.microsoft.com/en-us/help/973559/frequently-asked-questions-about-the-microsoft-support-diagnostic-tool
1133 # CAB with *.{diagcfg,diagpkg} is used by Microsoft Support Diagnostic Tool MSDT.EXE
1134 # because some archive does not have *.diag* as 1st or 2nd archive member like
1135 # O15CTRRemove.diagcab or AzureStorageAnalyticsLogs_global.DiagCab
1136 # brute looking after header for filenames with diagcfg or diagpkg extension in CFFILE section
1137 >0x2c search/980/c .diag \b, Diagnostic
1138 !:mime application/vnd.ms-cab-compressed
1140 # http://fileformats.archiveteam.org/wiki/PUZ
1141 # Microsoft Publisher version about 2003 has a "Pack and Go" feature that
1142 # bundles a Publisher document *PNG.pub with all links into a CAB
1143 >0x2c search/300/c png.pub\0 \b, Publisher Packed and Go
1144 !:mime application/vnd.ms-cab-compressed
1146 # ppz variant with Microsoft PowerPoint Viewer ppview32.exe to play PowerPoint presentation
1147 >0x2c search/17/c ppview32.exe\0 \b, PowerPoint Viewer Packed and Go
1148 !:mime application/vnd.ms-powerpoint
1149 #!:mime application/mspowerpoint
1151 # http://www.incredimail.com/
1152 # IncrediMail CAB contains an initialisation file "content.ini" like in im2.ims
1153 >0x2c search/3369/c content.ini\0 \b, IncrediMail
1154 !:mime application/x-incredimail
1155 # member Flavor.htm implies IncrediMail ecard like in tell_a_friend.imf
1156 >>0x2c search/83/c Flavor.htm\0 ecard
1158 # member Macromedia Flash data *.swf implies IncrediMail skin like in im2.ims
1159 >>0x2c search/211/c .swf\0 skin
1161 # member anim.im3 implies IncrediMail animation like in letter_fold.ima
1162 >>0x2c search/92/c anim.im3\0 animation
1164 # other IncrediMail cab archive
1166 >>>0x2c search/116/c thumb ecard, image, notifier or skin
1167 !:ext imf/imi/imn/ims
1168 # http://file-extension.net/seeker/file_extension_ime
1169 >>>0x2c default x emoticons or sound
1171 # no Diagnostic and IncrediMail
1173 # look for 1st member name
1175 # https://en.wikipedia.org/wiki/SNP_file_format
1176 >>>&-1 string/c _accrpt_.snp \b, Access report snapshot
1177 !:mime application/msaccess
1179 # https://www.cabextract.org.uk/wince_cab_format/
1180 # extension of DOS 8+3 name with ".000" of 1st archive member name implies Windows CE installer
1181 >>>&7 string =.000 \b, WinCE install
1182 !:mime application/vnd.ms-cab-compressed
1185 # https://support.microsoft.com/kb/934307/en-US
1186 # All inspected MSU contain a file with name WSUSSCAN.cab
1187 # that is called "Windows Update meta data" by Microsoft
1188 >>>&-1 string/c wsusscan.cab \b, Microsoft Standalone Update
1189 !:mime application/vnd.ms-cab-compressed
1192 # look at point charcter of 1st archive member name for file name extension
1193 >>>>&-1 search/255 .
1194 # http://www.pptfaq.com/FAQ00164_What_is_a_PPZ_file-.htm
1195 # PPZ were created using Pack & Go feature of PowerPoint versions 97 - 2002
1196 # packs optional files, a PowerPoint presentation *.ppt with optional PLAYLIST.LST to CAB
1197 >>>>>&0 string/c ppt\0 \b, PowerPoint Packed and Go
1198 !:mime application/vnd.ms-powerpoint
1199 #!:mime application/mspowerpoint
1201 # https://msdn.microsoft.com/en-us/library/windows/desktop/bb773190(v=vs.85).aspx
1202 # first member *.theme implies Windows 7 Theme Pack like in CommunityShowcaseAqua3.themepack
1203 # or Windows 8 Desktop Theme Pack like in PanoramicGlaciers.deskthemepack
1204 >>>>>&0 string/c theme \b, Windows
1205 !:mime application/x-windows-themepack
1206 # https://www.drewkeller.com/content/using-theme-both-windows-7-and-windows-8
1207 # 1st member Panoramic.theme or Panoramas.theme implies Windows 8-10 Theme Pack
1208 # with MTSM=RJSPBS in [MasterThemeSelector] inside *.theme
1209 >>>>>>(16.l+16) string =Panoram 8
1211 >>>>>>(16.l+16) string !Panoram 7 or 8
1212 !:ext themepack/deskthemepack
1213 >>>>>>(16.l+16) ubyte x Theme Pack
1215 # look for null terminator of 1st member name
1216 >>>>>>&0 search/255 \0
1217 # 2nd member name WSUSSCAN.cab like in Microsoft-Windows-MediaFeaturePack-OOB-Package.msu
1218 >>>>>>>&16 string/c wsusscan.cab \b, Microsoft Standalone Update
1219 !:mime application/vnd.ms-cab-compressed
1221 >>>>>>>&16 default x
1222 # archive with more then one file need some output in version 5.32 to avoid error message like
1223 # Magdir/msdos, 1138: Warning: Current entry does not yet have a description for adding a MIME type
1224 # Magdir/msdos, 1139: Warning: Current entry does not yet have a description for adding a EXTENSION type
1225 # file: could not find any valid magic files!
1226 >>>>>>>>28 uleshort >1 \b, many
1227 !:mime application/vnd.ms-cab-compressed
1229 # remaining archives with just one file
1230 >>>>>>>>28 uleshort =1
1231 # neither extra bytes nor cab chain implies Windows 2000,XP setup files in directory i386
1232 >>>>>>>>>30 uleshort =0x0000 \b, Windows 2000/XP setup
1233 # cut of last char of source extension and add underscore to generate extension
1234 # TERMCAP._ ... FXSCOUNT.H_ ... L3CODECA.AC_ ... NPDRMV2.ZI_
1235 !:mime application/vnd.ms-cab-compressed
1237 # archive need some output like "single" in version 5.32 to avoid error messages
1238 >>>>>>>>>30 uleshort !0x0000 \b, single
1239 !:mime application/vnd.ms-cab-compressed
1241 # TODO: additional extensions like
1242 # .xsn InfoPath Dynamic Form
1243 # .xtp InfoPath Template Part
1244 # .lvf Logitech Video Effects Face Accessory
1245 >8 ulelong x \b, %u bytes
1246 >28 uleshort 1 \b, 1 file
1247 >28 uleshort >1 \b, %u files
1248 # Reserved fields, set to zero
1249 #>4 belong !0 \b, reserved1 %x
1250 #>12 belong !0 \b, reserved2 %x
1251 # offset of the first CFFILE entry coffFiles: minimal 2Ch
1252 >16 ulelong x \b, at 0x%x
1253 >(16.l) use cab-file
1254 # at least also 2nd member
1258 # second member info
1260 #>20 belong !0 \b, reserved %x
1261 # Cabinet file format version. Currently, versionMajor = 1 and versionMinor = 3
1262 >24 ubeshort !0x0301 \b version 0x%x
1263 # number of CFFOLDER entries
1264 >26 uleshort >1 \b, %u cffolders
1265 # cabinet file option indicators 1~PREVIOUS, 2~NEXT, 4~reserved fields
1266 # only found for flags 0 1 2 3 4 not 7
1267 >30 uleshort >0 \b, flags 0x%x
1268 # Cabinet files have a 16-bit cabinet setID field that is designed for application use.
1269 # default is zero, however, the -i option of cabarc can be used to set this field
1270 >32 uleshort >0 \b, ID %u
1271 # iCabinet is number of this cabinet file in a set, where 0 for the first cabinet
1272 #>34 uleshort x \b, iCabinet %u
1273 # add one for display because humans start numbering by 1 and also fit to name of disk szDisk*
1274 >34 uleshort+1 x \b, number %u
1275 >30 uleshort &0x0004 \b, extra bytes
1276 # cbCFHeader optional size of per-cabinet reserved area 14h 1800h
1277 >>36 uleshort >0 %u in head
1278 # cbCFFolder is optional size of per-folder reserved area
1279 >>38 ubyte >0 %u in folder
1280 # cbCFData is optional size of per-datablock reserved area
1281 >>39 ubyte >0 %u in data block
1282 # optional per-cabinet reserved area abReserve[cbCFHeader]
1284 # 1st CFFOLDER after reserved area in header
1285 >>>(36.s+40) use cab-folder
1286 # no reserved area in header
1287 >30 uleshort ^0x0004
1288 # no previous and next cab archive
1289 >>30 uleshort =0x0000
1290 >>>36 use cab-folder
1291 # only previous cab archive
1292 >>30 uleshort =0x0001 \b, previous
1293 >>>36 use cab-anchor
1294 # only next cab archive
1295 >>30 uleshort =0x0002 \b, next
1296 >>>36 use cab-anchor
1297 # previous+next cab archive
1298 # can not use sub routine cab-anchor to display previous and next cabinet together
1299 #>>>36 use cab-anchor
1300 #>>>>&0 use cab-anchor
1301 >>30 uleshort =0x0003 \b, previous
1303 # optional name of previous disk szDisk*
1304 >>>>&1 string x disk %s
1305 >>>>>&1 string x \b, next %s
1306 # optional name of previous disk szDisk*
1307 >>>>>>&1 string x disk %s
1308 >>>>>>>&1 use cab-folder
1309 # display filename and disk name of previous or next cabinet
1311 # optional name of previous/next cabinet file szCabinet*[255]
1313 # optional name of previous/next disk szDisk*[255]
1314 >>&1 string x disk %s
1315 # display folder structure CFFOLDER information like compression of cabinet
1317 # offset of the CFDATA block in this folder
1318 #>0 ulelong x \b, coffCabStart 0x%x
1319 # number of CFDATA blocks in folder
1320 >4 uleshort x \b, %u datablock
1323 # compression typeCompress: 0~None 1~MSZIP 0x1503~LZX:21 0x1003~LZX:16 0x0f03~LZX:15
1324 >6 uleshort x \b, 0x%x compression
1325 # optional per-folder reserved area
1326 #>8 ubequad x \b, abReserve 0x%llx
1327 # display member structure CFFILE information like member name of cabinet
1329 # cbFile is uncompressed size of file in bytes
1330 #>0 ulelong x \b, cbFile %u
1331 # uoffFolderStart is uncompressed offset of file in folder
1332 #>4 ulelong >0 \b, uoffFolderStart 0x%x
1333 # iFolder is index into the CFFOLDER area. 0 indicates first folder in cabinet
1334 # define ifoldCONTINUED_FROM_PREV (0xFFFD)
1335 # define ifoldCONTINUED_TO_NEXT (0xFFFE)
1336 # define ifoldCONTINUED_PREV_AND_NEXT (0xFFFF)
1337 >8 uleshort >0 \b, iFolder 0x%x
1338 # date stamp for file
1339 #>10 uleshort x \b, date 0x%x
1340 # time stamp for file
1341 #>12 uleshort x \b, time 0x%x
1342 # attribs is attribute flags for file
1343 # define _A_RDONLY (0x01) file is read-only
1344 # define _A_HIDDEN (0x02) file is hidden
1345 # define _A_SYSTEM (0x04) file is a system file
1346 # define _A_ARCH (0x20) file modified since last backup
1347 # example http://sebastien.kirche.free.fr/pebuilder_plugins/depends.cab
1348 # define _A_EXEC (0x40) run after extraction
1349 # define _A_NAME_IS_UTF (0x80) szName[] contains UTF
1350 # define UNKNOWN (0x0100) undocumented or accident
1351 #>14 uleshort x \b, attribs 0x%x
1353 >>14 uleshort &0x0001 \bR
1354 >>14 uleshort &0x0002 \bH
1355 >>14 uleshort &0x0004 \bS
1356 >>14 uleshort &0x0020 \bA
1357 >>14 uleshort &0x0040 \bX
1358 >>14 uleshort &0x0080 \bUtf
1359 # unknown 0x0100 flag found on one XP_CD:\I386\DRIVER.CAB
1360 >>14 uleshort &0x0100 \b?
1361 # szName is name of archive member
1363 # next archive member name if more files
1364 #>>&17 string >\0 \b, NEXT NAME %-.50s
1366 # InstallShield Cabinet files
1367 0 string/b ISc( InstallShield Cabinet archive data
1368 >5 byte&0xf0 =0x60 version 6,
1369 >5 byte&0xf0 !0x60 version 4/5,
1370 >(12.l+40) lelong x %u files
1372 # Windows CE package files
1373 0 string/b MSCE\0\0\0\0 Microsoft WinCE install header
1374 >20 lelong 0 \b, architecture-independent
1375 >20 lelong 103 \b, Hitachi SH3
1376 >20 lelong 104 \b, Hitachi SH4
1377 >20 lelong 0xA11 \b, StrongARM
1378 >20 lelong 4000 \b, MIPS R4000
1379 >20 lelong 10003 \b, Hitachi SH3
1380 >20 lelong 10004 \b, Hitachi SH3E
1381 >20 lelong 10005 \b, Hitachi SH4
1382 >20 lelong 70001 \b, ARM 7TDMI
1383 >52 leshort 1 \b, 1 file
1384 >52 leshort >1 \b, %u files
1385 >56 leshort 1 \b, 1 registry entry
1386 >56 leshort >1 \b, %u registry entries
1389 # Windows Enhanced Metafile (EMF)
1390 # See msdn.microsoft.com/archive/en-us/dnargdi/html/msdn_enhmeta.asp
1391 # for further information.
1393 >40 string \ EMF Windows Enhanced Metafile (EMF) image data
1394 >>44 ulelong x version 0x%x
1397 0 string/b \224\246\056 Microsoft Word Document
1398 !:mime application/msword
1400 512 string R\0o\0o\0t\0\ \0E\0n\0t\0r\0y Microsoft Word Document
1401 !:mime application/msword
1403 # From: "Nelson A. de Oliveira" <naoliv@gmail.com>
1404 # Magic type for Dell's BIOS .hdr files
1407 >23 string Dell %s system BIOS
1409 >>48 byte x version %d.
1413 >>48 string x version %.3s
1415 # Type: Microsoft Document Imaging Format (.mdi)
1416 # URL: https://en.wikipedia.org/wiki/Microsoft_Document_Imaging_Format
1417 # From: Daniele Sempione <scrows@oziosi.org>
1419 #0 short 0x5045 Microsoft Document Imaging Format
1421 # MS eBook format (.lit)
1422 0 string/b ITOLITLS Microsoft Reader eBook Data
1423 >8 lelong x \b, version %u
1424 !:mime application/x-ms-reader
1426 # Windows CE Binary Image Data Format
1427 # From: Dr. Jesus <j@hug.gs>
1428 0 string/b B000FF\n Windows Embedded CE binary image
1430 # The second byte of these signatures is a file version; I don't know what,
1431 # if anything, produced files with version numbers 0-2.
1432 # From: John Elliott <johne@seasip.demon.co.uk>
1433 0 string \xfc\x03\x00 Mallard BASIC program data (v1.11)
1434 0 string \xfc\x04\x00 Mallard BASIC program data (v1.29+)
1435 0 string \xfc\x03\x01 Mallard BASIC protected program data (v1.11)
1436 0 string \xfc\x04\x01 Mallard BASIC protected program data (v1.29+)
1438 0 string MIOPEN Mallard BASIC Jetsam data
1439 0 string Jetsam0 Mallard BASIC Jetsam index data
1441 # DOS backup 2.0 to 3.2
1445 # plausibility check for date
1449 # actually 121 nul bytes
1450 >>>0x7 string \0\0\0\0\0\0\0\0
1451 >>>>0x1 ubyte x DOS 2.0 backup id file, sequence %d
1453 >>>>0x0 ubyte 0xff \b, last disk
1457 # skip some AppleWorks word like Tomahawk.Awp, WIN98SE-DE.vhd
1458 # by looking for trailing nul of maximal file name string
1460 # test for flag byte: FFh~complete file, 00h~split file
1461 # FFh -127 = -1 -127 = -128
1462 # 00h -127 = 0 -127 = -127
1464 # plausibility check for file name length
1466 # looking for terminating nul of file name string
1467 >>>(0x53.b+4) ubyte 0
1468 # looking if last char of string is valid DOS file name
1469 >>>>(0x53.b+3) ubyte >0x1F
1470 # actually 44 nul bytes
1471 # but sometimes garbage according to Ralf Quint. So can not be used as test
1472 #>0x54 string \0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0
1473 # first char of full file name is DOS (5Ch) or UNIX (2Fh) path separator
1474 # only DOS variant found. UNIX variant according to V32SLASH.TXT in archive PD0315.EXE
1475 >>>>>5 ubyte&0x8C 0x0C
1476 # ./msdos (version 5.30) labeled the entry as
1477 # "DOS 2.0 backed up file %s, split file, sequence %d" or
1478 # "DOS 2.0 backed up file %s, complete file"
1479 >>>>>>0 ubyte x DOS 2.0-3.2 backed up
1480 #>>>>>>0 ubyte 0xff complete
1482 >>>>>>>1 uleshort x sequence %d of
1483 # full file name with path but without drive letter and colon stored from 0x05 til 0x52
1484 >>>>>>0x5 string x file %s
1485 # backup name is original filename
1487 # magic/Magdir/msdos, 1169: Warning: EXTENSION type ` *' has bad char '*'
1488 # file: line 1169: Bad magic entry ' *'
1489 # after header original file content
1490 >>>>>>128 indirect x \b;
1493 # DOS backup 3.3 to 5.x
1496 0 string \x8bBACKUP\x20
1497 # actually 128 nul bytes
1498 >0xa string \0\0\0\0\0\0\0\0
1499 >>0x9 ubyte x DOS 3.3 backup control file, sequence %d
1500 >>0x8a ubyte 0xff \b, last disk
1502 # NB: The BACKUP.nnn files consist of the files backed up,