1 #------------------------------------------------------------------------------
2 # $File: archive,v 1.91 2015/09/16 13:49:33 christos Exp $
3 # archive: file(1) magic for archive formats (see also "msdos" for self-
4 # extracting compressed archives)
6 # cpio, ar, arc, arj, hpack, lha/lharc, rar, squish, uc2, zip, zoo, etc.
7 # pre-POSIX "tar" archives are handled in the C code.
10 257 string ustar\0 POSIX tar archive
11 !:mime application/x-tar # encoding: posix
12 257 string ustar\040\040\0 GNU tar archive
13 !:mime application/x-tar # encoding: gnu
15 # Incremental snapshot gnu-tar format from:
16 # http://www.gnu.org/software/tar/manual/html_node/Snapshot-Files.html
17 0 string GNU\ tar- GNU tar incremental snapshot data
18 >&0 regex [0-9]\.[0-9]+-[0-9]+ version %s
22 # Yes, the top two "cpio archive" formats *are* supposed to just be "short".
23 # The idea is to indicate archives produced on machines with the same
24 # byte order as the machine running "file" with "cpio archive", and
25 # to indicate archives produced on machines with the opposite byte order
26 # from the machine running "file" with "byte-swapped cpio archive".
28 # The SVR4 "cpio(4)" hints that there are additional formats, but they
29 # are defined as "short"s; I think all the new formats are
30 # character-header formats and thus are strings, not numbers.
31 0 short 070707 cpio archive
32 !:mime application/x-cpio
33 0 short 0143561 byte-swapped cpio archive
34 !:mime application/x-cpio # encoding: swapped
35 0 string 070707 ASCII cpio archive (pre-SVR4 or odc)
36 0 string 070701 ASCII cpio archive (SVR4 with no CRC)
37 0 string 070702 ASCII cpio archive (SVR4 with CRC)
40 # Various archive formats used by various versions of the "ar"
45 # Original UNIX archive formats.
46 # They were written with binary values in host byte order, and
47 # the magic number was a host "int", which might have been 16 bits
48 # or 32 bits. We don't say "PDP-11" or "VAX", as there might have
49 # been ports to little-endian 16-bit-int or 32-bit-int platforms
50 # (x86?) using some of those formats; if none existed, feel free
51 # to use "PDP-11" for little-endian 16-bit and "VAX" for little-endian
52 # 32-bit. There might have been big-endian ports of that sort as
55 0 leshort 0177555 very old 16-bit-int little-endian archive
56 0 beshort 0177555 very old 16-bit-int big-endian archive
57 0 lelong 0177555 very old 32-bit-int little-endian archive
58 0 belong 0177555 very old 32-bit-int big-endian archive
60 0 leshort 0177545 old 16-bit-int little-endian archive
61 >2 string __.SYMDEF random library
62 0 beshort 0177545 old 16-bit-int big-endian archive
63 >2 string __.SYMDEF random library
64 0 lelong 0177545 old 32-bit-int little-endian archive
65 >4 string __.SYMDEF random library
66 0 belong 0177545 old 32-bit-int big-endian archive
67 >4 string __.SYMDEF random library
70 # From "pdp" (but why a 4-byte quantity?)
72 0 lelong 0x39bed PDP-11 old archive
73 0 lelong 0x39bee PDP-11 4.0 archive
76 # XXX - what flavor of APL used this, and was it a variant of
77 # some ar archive format? It's similar to, but not the same
78 # as, the APL workspace magic numbers in pdp.
80 0 long 0100554 apl workspace
83 # System V Release 1 portable(?) archive format.
85 0 string =<ar> System V Release 1 ar archive
86 !:mime application/x-archive
89 # Debian package; it's in the portable archive format, and needs to go
90 # before the entry for regular portable archives, as it's recognized as
91 # a portable archive whose first member has a name beginning with
94 0 string =!<arch>\ndebian
95 >8 string debian-split part of multipart Debian package
96 !:mime application/vnd.debian.binary-package
97 >8 string debian-binary Debian binary package
98 !:mime application/vnd.debian.binary-package
100 >68 string >\0 (format %s)
101 # These next two lines do not work, because a bzip2 Debian archive
102 # still uses gzip for the control.tar (first in the archive). Only
103 # data.tar varies, and the location of its filename varies too.
104 # file/libmagic does not current have support for ascii-string based
105 # (offsets) as of 2005-09-15.
106 #>81 string bz2 \b, uses bzip2 compression
107 #>84 string gz \b, uses gzip compression
108 #>136 ledate x created: %s
111 # MIPS archive; they're in the portable archive format, and need to go
112 # before the entry for regular portable archives, as it's recognized as
113 # a portable archive whose first member has a name beginning with
116 0 string =!<arch>\n__________E MIPS archive
117 !:mime application/x-archive
118 >20 string U with MIPS Ucode members
119 >21 string L with MIPSEL members
120 >21 string B with MIPSEB members
121 >19 string L and an EL hash table
122 >19 string B and an EB hash table
123 >22 string X -- out of date
125 0 search/1 -h- Software Tools format archive text
128 # BSD/SVR2-and-later portable archive formats.
130 0 string =!<arch> current ar archive
131 !:mime application/x-archive
132 >8 string __.SYMDEF random library
133 >68 string __.SYMDEF\ SORTED random library
136 # "Thin" archive, as can be produced by GNU ar.
138 0 string =!<thin>\n thin archive with
139 >68 belong 0 no symbol entries
140 >68 belong 1 %d symbol entry
141 >68 belong >1 %d symbol entries
143 # ARC archiver, from Daniel Quinlan (quinlan@yggdrasil.com)
145 # The first byte is the magic (0x1a), byte 2 is the compression type for
146 # the first file (0x01 through 0x09), and bytes 3 to 15 are the MS-DOS
147 # filename of the first file (null terminated). Since some types collide
148 # we only test some types on basis of frequency: 0x08 (83%), 0x09 (5%),
149 # 0x02 (5%), 0x03 (3%), 0x04 (2%), 0x06 (2%). 0x01 collides with terminfo.
150 0 lelong&0x8080ffff 0x0000081a ARC archive data, dynamic LZW
151 !:mime application/x-arc
152 0 lelong&0x8080ffff 0x0000091a ARC archive data, squashed
153 !:mime application/x-arc
154 0 lelong&0x8080ffff 0x0000021a ARC archive data, uncompressed
155 !:mime application/x-arc
156 0 lelong&0x8080ffff 0x0000031a ARC archive data, packed
157 !:mime application/x-arc
158 0 lelong&0x8080ffff 0x0000041a ARC archive data, squeezed
159 !:mime application/x-arc
160 0 lelong&0x8080ffff 0x0000061a ARC archive data, crunched
161 !:mime application/x-arc
162 # [JW] stuff taken from idarc, obviously ARC successors:
163 0 lelong&0x8080ffff 0x00000a1a PAK archive data
164 !:mime application/x-arc
165 0 lelong&0x8080ffff 0x0000141a ARC+ archive data
166 !:mime application/x-arc
167 0 lelong&0x8080ffff 0x0000481a HYP archive data
168 !:mime application/x-arc
170 # Acorn archive formats (Disaster prone simpleton, m91dps@ecs.ox.ac.uk)
171 # I can't create either SPARK or ArcFS archives so I have not tested this stuff
172 # [GRR: the original entries collide with ARC, above; replaced with combined
173 # version (not tested)]
174 #0 byte 0x1a RISC OS archive (spark format)
175 0 string \032archive RISC OS archive (ArcFS format)
176 0 string Archive\000 RISC OS archive (ArcFS format)
178 # All these were taken from idarc, many could not be verified. Unfortunately,
179 # there were many low-quality sigs, i.e. easy to trigger false positives.
180 # Please notify me of any real-world fishy/ambiguous signatures and I'll try
181 # to get my hands on the actual archiver and see if I find something better. [JW]
182 # probably many can be enhanced by finding some 0-byte or control char near the start
184 # idarc calls this Crush/Uncompressed... *shrug*
185 0 string CRUSH Crush archive data
187 0 string HLSQZ Squeeze It archive data
189 0 string SQWEZ SQWEZ archive data
191 0 string HPAK HPack archive data
193 0 string \x91\x33HF HAP archive data
195 0 string MDmd MDCD archive data
197 0 string LIM\x1a LIM archive data
199 3 string LH5 SAR archive data
201 0 string \212\3SB\020\0 BSArc/BS2 archive data
202 # Bethesda Softworks Archive (Oblivion)
203 0 string BSA\0 BSArc archive data
204 >4 lelong x version %d
206 2 string =-ah MAR archive data
208 #0 belong&0x00f800ff 0x00800000 ACB archive data
210 # TODO, this is what idarc says: 0 string \0\0\0 CPZ archive data
212 0 string JRchive JRC archive data
214 0 string DS\0 Quantum archive data
216 0 string PK\3\6 ReSOF archive data
218 0 string 7\4 QuArk archive data
220 14 string YC YAC archive data
222 0 string X1 X1 archive data
223 0 string XhDr X1 archive data
225 0 belong&0xffffe000 0x76ff2000 CDC Codec archive data
227 0 string \xad6" AMGC archive data
229 0 string N\xc3\xb5F\xc3\xa9lx\xc3\xa5 NuLIB archive data
231 0 string LEOLZW PAKLeo archive data
233 0 string SChF ChArc archive data
235 0 string PSA PSA archive data
237 0 string DSIGDCC CrossePAC archive data
239 0 string \x1f\x9f\x4a\x10\x0a Freeze archive data
241 0 string \xc2\xa8MP\xc2\xa8 KBoom archive data
242 # NSQ, must go after CDC Codec
243 0 string \x76\xff NSQ archive data
245 0 string Dirk\ Paehl DPA archive data
247 # TODO: idarc says "bytes 0-2 == bytes 3-5"
249 0 string \0\6 TTComp archive data
250 # ESP, could this conflict with Easy Software Products' (e.g.ESP ghostscript) documentation?
251 0 string ESP ESP archive data
253 0 string \1ZPK\1 ZPack archive data
255 0 string \xbc\x40 Sky archive data
257 0 string UFA UFA archive data
259 0 string =-H2O DRY archive data
261 0 string FOXSQZ FoxSQZ archive data
263 0 string ,AR7 AR7 archive data
265 0 string PPMZ PPMZ archive data
267 4 string \x88\xf0\x27 MS Compress archive data
268 # updated by Joerg Jenderek
271 >>>7 string \321\003 MS Compress archive data
272 >>>>14 ulong >0 \b, original size: %d bytes
274 >>>>>18 string x \b, was %.8s
275 >>>>>(10.b-4) string x \b.%.3s
276 # MP3 (archiver, not lossy audio compression)
277 0 string MP3\x1a MP3-Archiver archive data
279 0 string OZ\xc3\x9d ZET archive data
281 0 string \x65\x5d\x13\x8c\x08\x01\x03\x00 TSComp archive data
283 0 string gW\4\1 ARQ archive data
285 3 string OctSqu Squash archive data
287 0 string \5\1\1\0 Terse archive data
289 0 string \x01\x08\x0b\x08\xef\x00\x9e\x32\x30\x36\x31 PUCrunch archive data
291 0 string UHA UHarc archive data
293 0 string \2AB ABComp archive data
294 0 string \3AB2 ABComp archive data
296 0 string CO\0 CMP archive data
298 0 string \x93\xb9\x06 Splint archive data
300 0 string \x13\x5d\x65\x8c InstallShield Z archive Data
302 1 string GTH Gather archive data
304 0 string BOA BOA archive data
306 0 string ULEB\xa RAX archive data
308 0 string ULEB\0 Xtreme archive data
310 0 string @\xc3\xa2\1\0 Pack Magic archive data
312 0 belong&0xfeffffff 0x1a034465 BTS archive data
314 0 string Ora\ ELI 5750 archive data
316 0 string \x1aFC\x1a QFC archive data
317 0 string \x1aQF\x1a QFC archive data
319 0 string RNC PRO-PACK archive data
321 0 string 777 777 archive data
323 0 string sTaC LZS221 archive data
325 0 string HPA HPA archive data
327 0 string LG Arhangel archive data
329 0 string 0123456789012345BZh EXP1 archive data
331 0 string IMP\xa IMP archive data
333 0 string \x00\x9E\x6E\x72\x76\xFF NRV archive data
335 0 string \x73\xb2\x90\xf4 Squish archive data
337 0 string PHILIPP Par archive data
338 0 string PAR Par archive data
340 0 string UB HIT archive data
342 0 belong&0xfffff000 0x53423000 SBX archive data
344 0 string NSK NaShrink archive data
346 0 string #\ CAR\ archive\ header SAPCAR archive data
347 0 string CAR\ 2.00RG SAPCAR archive data
349 0 string DST Disintegrator archive data
351 0 string ASD ASD archive data
353 0 string ISc( InstallShield CAB
355 0 string T4\x1a TOP4 archive data
356 # BatComp left out: sig looks like COM executable
357 # so TODO: get real 4dos batcomp file and find sig
359 0 string BH\5\7 BlakHole archive data
361 0 string BIX0 BIX archive data
363 0 string ChfLZ ChiefLZA archive data
365 0 string Blink Blink archive data
367 0 string \xda\xfa Logitech Compress archive data
368 # ARS-Sfx (FIXME: really a SFX? then goto COM/EXE)
369 1 string (C)\ STEPANYUK ARS-Sfx archive data
371 0 string AKT32 AKT32 archive data
372 0 string AKT AKT archive data
374 0 string MSTSM NPack archive data
376 0 string \0\x50\0\x14 PFT archive data
378 0 string SEM SemOne archive data
380 0 string \x8f\xaf\xac\x84 PPMD archive data
382 0 string FIZ FIZ archive data
384 0 belong&0xfffff0f0 0x4d530000 MSXiE archive data
386 0 belong&0xfffffff0 0x797a3030 DeepFreezer archive data
388 0 string =<DC- DC archive data
390 0 string \4TPAC\3 TPac archive data
392 0 string Ai\1\1\0 Ai archive data
393 0 string Ai\1\0\0 Ai archive data
395 0 string Ai\2\0 Ai32 archive data
396 0 string Ai\2\1 Ai32 archive data
398 0 string SBC SBC archive data
400 0 string YBS Ybs archive data
402 0 string \x9e\0\0 DitPack archive data
404 0 string DMS! DMS archive data
406 0 string \x8f\xaf\xac\x8c EPC archive data
408 0 string VS\x1a VSARC archive data
410 0 string PDZ PDZ archive data
412 0 string rdqx ReDuq archive data
414 0 string GCAX GCA archive data
416 0 string pN PPMN archive data
418 3 string WINIMAGE WinImage archive data
420 0 string CMP0CMP Compressia archive data
422 0 string UHB UHBC archive data
424 0 string \x61\x5C\x04\x05 WinHKI archive data
426 0 string WWP WWPack archive data
428 0 string \xffBSG BSN archive data
429 1 string \xffBSG BSN archive data
430 3 string \xffBSG BSN archive data
431 1 string \0\xae\2 BSN archive data
432 1 string \0\xae\3 BSN archive data
433 1 string \0\xae\7 BSN archive data
435 0 string \x33\x18 AIN archive data
436 0 string \x33\x17 AIN archive data
437 # XPA32 test moved and merged with XPA by Joerg Jenderek at Sep 2015
438 # SZip (TODO: doesn't catch all versions)
439 0 string SZ\x0a\4 SZip archive data
441 # *.XDI updated by Joerg Jenderek Sep 2015
442 # ftp://ftp.sac.sk/pub/sac/pack/0index.txt
443 # GRR: this test is still too general as it catches also text files starting with jm
445 # only found examples with this additional characteristic 2 bytes
446 >2 string \x2\x4 Xpack DiskImage archive data
449 # *.xpa updated by Joerg Jenderek Sep 2015
450 # ftp://ftp.elf.stuba.sk/pub/pc/pack/
454 # ftp://ftp.elf.stuba.sk/pub/pc/pack/xpa32.zip
455 # created by XPA32.EXE version 1.0.2 for Windows
456 >0 string xpa\0\1 \b32 archive data
457 # created by XPACK.COM version 1.67m or 1.67r with short 0x1800
458 >3 ubeshort !0x0001 \bck archive data
460 # changed by Joerg Jenderek Sep 2015 back to like in version 5.12
461 # letter 'I'+ acute accent is equivalent to \xcd
462 0 string \xcd\ jm Xpack single archive data
463 #!:mime application/x-xpa-compressed
466 # TODO: missing due to unknown magic/magic at end of file:
476 # These were inspired by idarc, but actually verified
477 # Dzip archiver (.dz)
478 0 string DZ Dzip archive data
479 >2 byte x \b, version %i
481 # ZZip archiver (.zz)
482 0 string ZZ\ \0\0 ZZip archive data
483 0 string ZZ0 ZZip archive data
484 # PAQ archiver (.paq)
485 0 string \xaa\x40\x5f\x77\x1f\xe5\x82\x0d PAQ archive data
486 0 string PAQ PAQ archive data
489 # JAR archiver (.j), this is the successor to ARJ, not Java's JAR (which is essentially ZIP)
490 0xe string \x1aJar\x1b JAR (ARJ Software, Inc.) archive data
491 0 string JARCS JAR (ARJ Software, Inc.) archive data
493 # ARJ archiver (jason@jarthur.Claremont.EDU)
494 0 leshort 0xea60 ARJ archive data
495 !:mime application/x-arj
497 >8 byte &0x04 multi-volume,
498 >8 byte &0x10 slash-switched,
499 >8 byte &0x20 backup,
500 >34 string x original name: %s,
505 >7 byte 4 os: Macintosh
507 >7 byte 6 os: Apple ][ GS
508 >7 byte 7 os: Atari ST
510 >7 byte 9 os: VAX/VMS
512 # [JW] idarc says this is also possible
513 2 leshort 0xea60 ARJ archive data
515 # HA archiver (Greg Roelofs, newt@uchicago.edu)
516 # This is a really bad format. A file containing HAWAII will match this...
517 #0 string HA HA archive data,
518 #>2 leshort =1 1 file,
519 #>2 leshort >1 %hu files,
520 #>4 byte&0x0f =0 first is type CPY
521 #>4 byte&0x0f =1 first is type ASC
522 #>4 byte&0x0f =2 first is type HSC
523 #>4 byte&0x0f =0x0e first is type DIR
524 #>4 byte&0x0f =0x0f first is type SPECIAL
525 # suggestion: at least identify small archives (<1024 files)
526 0 belong&0xffff00fc 0x48410000 HA archive data
527 >2 leshort =1 1 file,
528 >2 leshort >1 %u files,
529 >4 byte&0x0f =0 first is type CPY
530 >4 byte&0x0f =1 first is type ASC
531 >4 byte&0x0f =2 first is type HSC
532 >4 byte&0x0f =0x0e first is type DIR
533 >4 byte&0x0f =0x0f first is type SPECIAL
535 # HPACK archiver (Peter Gutmann, pgut1@cs.aukuni.ac.nz)
536 0 string HPAK HPACK archive data
538 # JAM Archive volume format, by Dmitry.Kohmanyuk@UA.net
539 0 string \351,\001JAM\ JAM archive,
540 >7 string >\0 version %.4s
542 >>0x2b string >\0 label %.11s,
543 >>0x27 lelong x serial %08x,
544 >>0x36 string >\0 fstype %.8s
546 # LHARC/LHA archiver (Greg Roelofs, newt@uchicago.edu)
547 2 string -lh0- LHarc 1.x/ARX archive data [lh0]
548 !:mime application/x-lharc
549 2 string -lh1- LHarc 1.x/ARX archive data [lh1]
550 !:mime application/x-lharc
551 2 string -lz4- LHarc 1.x archive data [lz4]
552 !:mime application/x-lharc
553 2 string -lz5- LHarc 1.x archive data [lz5]
554 !:mime application/x-lharc
555 # [never seen any but the last; -lh4- reported in comp.compression:]
556 2 string -lzs- LHa/LZS archive data [lzs]
557 !:mime application/x-lha
558 2 string -lh\40- LHa 2.x? archive data [lh ]
559 !:mime application/x-lha
560 2 string -lhd- LHa 2.x? archive data [lhd]
561 !:mime application/x-lha
562 2 string -lh2- LHa 2.x? archive data [lh2]
563 !:mime application/x-lha
564 2 string -lh3- LHa 2.x? archive data [lh3]
565 !:mime application/x-lha
566 2 string -lh4- LHa (2.x) archive data [lh4]
567 !:mime application/x-lha
568 2 string -lh5- LHa (2.x) archive data [lh5]
569 !:mime application/x-lha
570 2 string -lh6- LHa (2.x) archive data [lh6]
571 !:mime application/x-lha
572 2 string -lh7- LHa (2.x)/LHark archive data [lh7]
573 !:mime application/x-lha
574 >20 byte x - header level %d
575 # taken from idarc [JW]
576 2 string -lZ PUT archive data
577 2 string -lz LZS archive data
578 2 string -sw1- Swag archive data
580 # RAR archiver (Greg Roelofs, newt@uchicago.edu)
581 0 string Rar! RAR archive data,
582 !:mime application/x-rar
585 >>10 byte &0x01 Archive volume,
586 >>10 byte &0x02 Commented,
587 >>10 byte &0x04 Locked,
588 >>10 byte &0x08 Solid,
589 >>10 byte &0x20 Authenticated,
590 >35 byte 0 os: MS-DOS
594 # some old version? idarc says:
595 0 string RE\x7e\x5e RAR archive data
597 # SQUISH archiver (Greg Roelofs, newt@uchicago.edu)
598 0 string SQSH squished archive data (Acorn RISCOS)
600 # UC2 archiver (Greg Roelofs, newt@uchicago.edu)
601 # [JW] see exe section for self-extracting version
602 0 string UC2\x1a UC2 archive data
604 # PKZIP multi-volume archive
605 0 string PK\x07\x08PK\x03\x04 Zip multi-volume archive data, at least PKZIP v2.50 to extract
606 !:mime application/zip
608 # Zip archives (Greg Roelofs, c/o zip-bugs@wkuvx1.wku.edu)
609 0 string PK\005\006 Zip archive data (empty)
612 # Specialised zip formats which start with a member named 'mimetype'
613 # (stored uncompressed, with no 'extra field') containing the file's MIME type.
614 # Check for have 8-byte name, 0-byte extra field, name "mimetype", and
615 # contents starting with "application/":
616 >26 string \x8\0\0\0mimetypeapplication/
618 # KOffice / OpenOffice & StarOffice / OpenDocument formats
619 # From: Abel Cheung <abel@oaka.org>
621 # KOffice (1.2 or above) formats
622 # (mimetype contains "application/vnd.kde.<SUBTYPE>")
623 >>50 string vnd.kde. KOffice (>=1.2)
624 >>>58 string karbon Karbon document
625 >>>58 string kchart KChart document
626 >>>58 string kformula KFormula document
627 >>>58 string kivio Kivio document
628 >>>58 string kontour Kontour document
629 >>>58 string kpresenter KPresenter document
630 >>>58 string kspread KSpread document
631 >>>58 string kword KWord document
633 # OpenOffice formats (for OpenOffice 1.x / StarOffice 6/7)
634 # (mimetype contains "application/vnd.sun.xml.<SUBTYPE>")
635 >>50 string vnd.sun.xml. OpenOffice.org 1.x
636 >>>62 string writer Writer
637 >>>>68 byte !0x2e document
638 >>>>68 string .template template
639 >>>>68 string .global global document
640 >>>62 string calc Calc
641 >>>>66 byte !0x2e spreadsheet
642 >>>>66 string .template template
643 >>>62 string draw Draw
644 >>>>66 byte !0x2e document
645 >>>>66 string .template template
646 >>>62 string impress Impress
647 >>>>69 byte !0x2e presentation
648 >>>>69 string .template template
649 >>>62 string math Math document
650 >>>62 string base Database file
652 # OpenDocument formats (for OpenOffice 2.x / StarOffice >= 8)
653 # http://lists.oasis-open.org/archives/office/200505/msg00006.html
654 # (mimetype contains "application/vnd.oasis.opendocument.<SUBTYPE>")
655 >>50 string vnd.oasis.opendocument. OpenDocument
657 >>>>77 byte !0x2d Text
658 !:mime application/vnd.oasis.opendocument.text
659 >>>>77 string -template Text Template
660 !:mime application/vnd.oasis.opendocument.text-template
661 >>>>77 string -web HTML Document Template
662 !:mime application/vnd.oasis.opendocument.text-web
663 >>>>77 string -master Master Document
664 !:mime application/vnd.oasis.opendocument.text-master
665 >>>73 string graphics
666 >>>>81 byte !0x2d Drawing
667 !:mime application/vnd.oasis.opendocument.graphics
668 >>>>81 string -template Template
669 !:mime application/vnd.oasis.opendocument.graphics-template
670 >>>73 string presentation
671 >>>>85 byte !0x2d Presentation
672 !:mime application/vnd.oasis.opendocument.presentation
673 >>>>85 string -template Template
674 !:mime application/vnd.oasis.opendocument.presentation-template
675 >>>73 string spreadsheet
676 >>>>84 byte !0x2d Spreadsheet
677 !:mime application/vnd.oasis.opendocument.spreadsheet
678 >>>>84 string -template Template
679 !:mime application/vnd.oasis.opendocument.spreadsheet-template
681 >>>>78 byte !0x2d Chart
682 !:mime application/vnd.oasis.opendocument.chart
683 >>>>78 string -template Template
684 !:mime application/vnd.oasis.opendocument.chart-template
686 >>>>80 byte !0x2d Formula
687 !:mime application/vnd.oasis.opendocument.formula
688 >>>>80 string -template Template
689 !:mime application/vnd.oasis.opendocument.formula-template
690 >>>73 string database Database
691 !:mime application/vnd.oasis.opendocument.database
693 >>>>78 byte !0x2d Image
694 !:mime application/vnd.oasis.opendocument.image
695 >>>>78 string -template Template
696 !:mime application/vnd.oasis.opendocument.image-template
698 # EPUB (OEBPS) books using OCF (OEBPS Container Format)
699 # http://www.idpf.org/ocf/ocf1.0/download/ocf10.htm, section 4.
700 # From: Ralf Brown <ralf.brown@gmail.com>
701 >>50 string epub+zip EPUB document
702 !:mime application/epub+zip
704 # Catch other ZIP-with-mimetype formats
705 # In a ZIP file, the bytes immediately after a member's contents are
706 # always "PK". The 2 regex rules here print the "mimetype" member's
707 # contents up to the first 'P'. Luckily, most MIME types don't contain
708 # any capital 'P's. This is a kludge.
709 # (mimetype contains "application/<OTHER>")
710 >>50 string !epub+zip
711 >>>50 string !vnd.oasis.opendocument.
712 >>>>50 string !vnd.sun.xml.
713 >>>>>50 string !vnd.kde.
714 >>>>>>38 regex [!-OQ-~]+ Zip data (MIME type "%s"?)
715 !:mime application/zip
716 # (mimetype contents other than "application/*")
717 >26 string \x8\0\0\0mimetype
718 >>38 string !application/
719 >>>38 regex [!-OQ-~]+ Zip data (MIME type "%s"?)
720 !:mime application/zip
723 >(26.s+30) leshort 0xcafe Java archive data (JAR)
724 !:mime application/java-archive
726 # Generic zip archives (Greg Roelofs, c/o zip-bugs@wkuvx1.wku.edu)
727 # Next line excludes specialized formats:
728 >(26.s+30) leshort !0xcafe
729 >>26 string !\x8\0\0\0mimetype Zip archive data
730 !:mime application/zip
731 >>>4 byte 0x09 \b, at least v0.9 to extract
732 >>>4 byte 0x0a \b, at least v1.0 to extract
733 >>>4 byte 0x0b \b, at least v1.1 to extract
734 >>>4 byte 0x14 \b, at least v2.0 to extract
735 >>>4 byte 0x2d \b, at least v4.5 to extract
736 >>>0x161 string WINZIP \b, WinZIP self-extracting
739 # From Pierre Ducroquet <pinaraf@pinaraf.info>
740 0 string VCLMTF StarView MetaFile
741 >6 beshort x \b, version %d
742 >8 belong x \b, size %d
745 20 lelong 0xfdc4a7dc Zoo archive data
746 !:mime application/x-zoo
750 >32 byte >0 \b, modify: v%d
752 >42 lelong 0xfdc4a7dc \b,
753 >>70 byte >0 extract: v%d
757 10 string #\ This\ is\ a\ shell\ archive shell archive text
758 !:mime application/octet-stream
761 # LBR. NB: May conflict with the questionable
762 # "binary Computer Graphics Metafile" format.
764 0 string \0\ \ \ \ \ \ \ \ \ \ \ \0\0 LBR archive data
766 # PMA (CP/M derivative of LHA)
768 2 string -pm0- PMarc archive data [pm0]
769 2 string -pm1- PMarc archive data [pm1]
770 2 string -pm2- PMarc archive data [pm2]
771 2 string -pms- PMarc SFX archive (CP/M, DOS)
772 5 string -pc1- PopCom compressed executable (CP/M)
774 # From Rafael Laboissiere <rafael@laboissiere.net>
775 # The Project Revision Control System (see
776 # http://prcs.sourceforge.net) generates a packaged project
777 # file which is recognized by the following entry:
778 0 leshort 0xeb81 PRCS packaged project
781 # by David Necas (Yeti) <yeti@physics.muni.cz>
782 #0 string MSCF\0\0\0\0 Microsoft cabinet file data,
785 # MPi: All CABs have version 1.3, so this is pointless.
786 # Better magic in debian-additions.
789 # by David Necas (Yeti) <yeti@physics.muni.cz>
790 4 string gtktalog\ GTKtalog catalog data,
791 >13 string 3 version 3
792 >>14 beshort 0x677a (gzipped)
793 >>14 beshort !0x677a (not gzipped)
794 >13 string >3 version %s
796 ############################################################################
797 # Parity archive reconstruction file, the 'par' file format now used on Usenet.
798 0 string PAR\0 PARity archive data
799 >48 leshort =0 - Index file
800 >48 leshort >0 - file number %d
802 # Felix von Leitner <felix-file@fefe.de>
803 0 string d8:announce BitTorrent file
804 !:mime application/x-bittorrent
806 # Atari MSA archive - Teemu Hukkanen <tjhukkan@iki.fi>
807 0 beshort 0x0e0f Atari MSA archive data
808 >2 beshort x \b, %d sectors per track
809 >4 beshort 0 \b, 1 sided
810 >4 beshort 1 \b, 2 sided
811 >6 beshort x \b, starting track: %d
812 >8 beshort x \b, ending track: %d
814 # Alternate ZIP string (amc@arwen.cs.berkeley.edu)
815 0 string PK00PK\003\004 Zip archive data
817 # ACE archive (from http://www.wotsit.org/download.asp?f=ace)
818 # by Stefan `Sec` Zehl <sec@42.org>
819 7 string **ACE** ACE archive data
820 >15 byte >0 version %d
821 >16 byte =0x00 \b, from MS-DOS
822 >16 byte =0x01 \b, from OS/2
823 >16 byte =0x02 \b, from Win/32
824 >16 byte =0x03 \b, from Unix
825 >16 byte =0x04 \b, from MacOS
826 >16 byte =0x05 \b, from WinNT
827 >16 byte =0x06 \b, from Primos
828 >16 byte =0x07 \b, from AppleGS
829 >16 byte =0x08 \b, from Atari
830 >16 byte =0x09 \b, from Vax/VMS
831 >16 byte =0x0A \b, from Amiga
832 >16 byte =0x0B \b, from Next
833 >14 byte x \b, version %d to extract
834 >5 leshort &0x0080 \b, multiple volumes,
835 >>17 byte x \b (part %d),
836 >5 leshort &0x0002 \b, contains comment
837 >5 leshort &0x0200 \b, sfx
838 >5 leshort &0x0400 \b, small dictionary
839 >5 leshort &0x0800 \b, multi-volume
840 >5 leshort &0x1000 \b, contains AV-String
841 >>30 string \x16*UNREGISTERED\x20VERSION* (unregistered)
842 >5 leshort &0x2000 \b, with recovery record
843 >5 leshort &0x4000 \b, locked
844 >5 leshort &0x8000 \b, solid
845 # Date in MS-DOS format (whatever that is)
846 #>18 lelong x Created on
848 # sfArk : compression program for Soundfonts (sf2) by Dirk Jagdmann
850 0x1A string sfArk sfArk compressed Soundfont
852 >>0x1 string >\0 Version %s
853 >>0x2A string >\0 : %s
855 # DR-DOS 7.03 Packed File *.??_
856 0 string Packed\ File\ Personal NetWare Packed File
857 >12 string x \b, was "%.12s"
860 # From: Tilman Sauerbeck <tilman@code-monkey.de>
861 0 belong 0x1ee7ff00 EET archive
862 !:mime application/x-eet
865 0 string RZIP rzip compressed data
866 >4 byte x - version %d
868 >6 belong x (%d bytes)
870 # From: "Robert Dale" <robdale@gmail.com>
871 0 belong 123 dar archive,
872 >4 belong x label "%.8x
874 >>>12 beshort x %.4x"
875 >14 byte 0x54 end slice
876 >14 beshort 0x4e4e multi-part
877 >14 beshort 0x4e53 multi-part, with -S
879 # Symbian installation files
880 # http://www.thouky.co.uk/software/psifs/sis.html
881 # http://developer.symbian.com/main/downloads/papers/SymbianOSv91/softwareinstallsis.pdf
882 8 lelong 0x10000419 Symbian installation file
883 !:mime application/vnd.symbian.install
884 >4 lelong 0x1000006D (EPOC release 3/4/5)
885 >4 lelong 0x10003A12 (EPOC release 6)
886 0 lelong 0x10201A7A Symbian installation file (Symbian OS 9.x)
887 !:mime x-epoc/x-sisx-app
889 # From "Nelson A. de Oliveira" <naoliv@gmail.com>
890 0 string MPQ\032 MoPaQ (MPQ) archive
892 # From: Dirk Jagdmann <doj@cubic.org>
893 # xar archive format: http://code.google.com/p/xar/
894 0 string xar! xar archive
895 >6 beshort x - version %d
897 # From: "Nelson A. de Oliveira" <naoliv@gmail.com>
899 0 string KGB_arch KGB Archiver file
900 >10 string x with compression level %.1s
902 # xar (eXtensible ARchiver) archive
903 # From: "David Remahl" <dremahl@apple.com>
904 0 string xar! xar archive
905 #>4 beshort x header size %d
906 >6 beshort x version %d,
907 #>8 quad x compressed TOC: %d,
908 #>16 quad x uncompressed TOC: %d,
909 >24 belong 0 no checksum
910 >24 belong 1 SHA-1 checksum
911 >24 belong 2 MD5 checksum
913 # Type: Parity Archive
914 # From: Daniel van Eeden <daniel_e@dds.nl>
915 0 string PAR2 Parity Archive Volume Set
917 # Bacula volume format. (Volumes always start with a block header.)
918 # URL: http://bacula.org/3.0.x-manuals/en/developers/developers/Block_Header.html
919 # From: Adam Buchbinder <adam.buchbinder@gmail.com>
920 12 string BB02 Bacula volume
921 >20 bedate x \b, started %s
923 # ePub is XHTML + XML inside a ZIP archive. The first member of the
924 # archive must be an uncompressed file called 'mimetype' with contents
925 # 'application/epub+zip'
928 # From: "Michael Gorny" <mgorny@gentoo.org>
929 # ZPAQ: http://mattmahoney.net/dc/zpaq.html
930 0 string zPQ ZPAQ stream
931 >3 byte x \b, level %d
932 # From: Barry Carter <carter.barry@gmail.com>
933 # http://encode.ru/threads/456-zpaq-updates/page32
934 0 string 7kSt ZPAQ file
936 # BBeB ebook, unencrypted (LRF format)
937 # URL: http://www.sven.de/librie/Librie/LrfFormat
938 # From: Adam Buchbinder <adam.buchbinder@gmail.com>
939 0 string L\0R\0F\0\0\0 BBeB ebook data, unencrypted
940 >8 beshort x \b, version %d
941 >36 byte 1 \b, front-to-back
942 >36 byte 16 \b, back-to-front
943 >42 beshort x \b, (%dx,
946 # Symantec GHOST image by Joerg Jenderek at May 2014
947 # http://us.norton.com/ghost/
948 # http://www.garykessler.net/library/file_sigs.html
949 0 ubelong&0xFFFFf7f0 0xFEEF0100 Norton GHost image
951 >2 ubyte&0x08 0x00 \b, first file
952 # *.GHS or *.[0-9] with cns program option
953 >2 ubyte&0x08 0x08 \b, split file
954 # part of split index interesting for *.ghs
956 # compression tag minus one equals numeric compression command line switch z[1-9]
957 >3 ubyte 0 \b, no compression
958 >3 ubyte 2 \b, fast compression (Z1)
959 >3 ubyte 3 \b, medium compression (Z2)
961 >>3 ubyte <11 \b, compression (Z%d-1)
963 # ~ 30 byte password field only for *.gho
964 >>12 ubequad !0 \b, password protected
966 # 1~Image All, sector-by-sector only for *.gho
967 >>>10 ubyte 1 \b, sector copy
968 # 1~Image Boot track only for *.gho
969 >>>43 ubyte 1 \b, boot track
970 # 1~Image Disc only for *.gho implies Image Boot track and sector copy
971 >>44 ubyte 1 \b, disc sector copy
972 # optional image description only *.gho
973 >>0xff string >\0 "%-.254s"
974 # look for DOS sector end sequence
975 >0xE08 search/7776 \x55\xAA
976 >>&-512 indirect x \b; contains