diff options
Diffstat (limited to 'contrib/file/magic/Magdir/archive')
| -rw-r--r-- | contrib/file/magic/Magdir/archive | 574 |
1 files changed, 549 insertions, 25 deletions
diff --git a/contrib/file/magic/Magdir/archive b/contrib/file/magic/Magdir/archive index fb535ac0ff26..6e1f9678e7ac 100644 --- a/contrib/file/magic/Magdir/archive +++ b/contrib/file/magic/Magdir/archive @@ -1,5 +1,5 @@ #------------------------------------------------------------------------------ -# $File: archive,v 1.162 2022/05/27 21:27:59 christos Exp $ +# $File: archive,v 1.193 2023/07/27 17:55:58 christos Exp $ # archive: file(1) magic for archive formats (see also "msdos" for self- # extracting compressed archives) # @@ -25,7 +25,18 @@ >>>>>>155 ubyte&0xDF =0 # space or ascii digit 0 at start of check sum >>>>>>>148 ubyte&0xEF =0x20 ->>>>>>>>0 use tar-file +# FOR DEBUGGING: +#>>>>>>>>0 regex \^[0-9]{2,4}[.](png|jpg|jpeg|tif|tiff|gif|bmp) NAME "%s" +# check for 1st image main name with digits used for sorting +# and for name extension case insensitive like: PNG JPG JPEG TIF TIFF GIF BMP +>>>>>>>>0 regex \^[0-9]{2,4}[.](png|jpg|jpeg|tif|tiff|gif|bmp) +>>>>>>>>>0 use tar-cbt +# check for 1st member name with ovf suffix +>>>>>>>>0 regex \^.{1,96}[.](ovf) +>>>>>>>>>0 use tar-ova +# if 1st member name without digits and without used image suffix and without *.ovf then it is a TAR archive +>>>>>>>>0 default x +>>>>>>>>>0 use tar-file # minimal check and then display tar archive information which can also be # embedded inside others like Android Backup, Clam AntiVirus database 0 name tar-file @@ -146,6 +157,34 @@ >>508 default x # padding[255] in old tar sometimes comment field >>>257 string >\0 \b, comment: %-.40s +# Summary: Comic Book Archive *.CBT with TAR format +# URL: https://en.wikipedia.org/wiki/Comic_book_archive +# http://fileformats.archiveteam.org/wiki/Comic_Book_Archive +# Note: there exist also RAR, ZIP, ACE and 7Z packed variants +0 name tar-cbt +>0 string x Comic Book archive, tar archive +#!:mime application/x-tar +!:mime application/vnd.comicbook +#!:mime application/vnd.comicbook+tar +!:ext cbt +# name[100] probably like: 19.jpg 0001.png 0002.png +# or maybe like ComicInfo.xml +>0 string >\0 \b, 1st image %-.60s +# Summary: Open Virtualization Format *.OVF with disk images and more packed as TAR archive *.OVA +# From: Joerg Jenderek +# URL: https://en.wikipedia.org/wiki/Open_Virtualization_Format +# http://fileformats.archiveteam.org/wiki/OVF_(Open_Virtualization_Format) +# Reference: http://mark0.net/download/triddefs_xml.7z/defs/o/ova.trid.xml +# Note: called "Open Virtualization Format package" by TrID +# assuming *.ovf comes first +0 name tar-ova +>0 string x Open Virtualization Format Archive +#!:mime application/x-ustar +# http://extension.nirsoft.net/ova +!:mime application/x-virtualbox-ova +!:ext ova +# assuming name[100] like: DOS-0.9.ovf FreeDOS_1.ovf Win98SE_DE.ovf +>0 string >\0 \b, with %-.60s # Incremental snapshot gnu-tar format from: # https://www.gnu.org/software/tar/manual/html_node/Snapshot-Files.html @@ -163,16 +202,88 @@ # The SVR4 "cpio(4)" hints that there are additional formats, but they # are defined as "short"s; I think all the new formats are # character-header formats and thus are strings, not numbers. -0 short 070707 cpio archive +# URL: http://fileformats.archiveteam.org/wiki/Cpio +# https://en.wikipedia.org/wiki/Cpio +# Reference: https://people.freebsd.org/~kientzle/libarchive/man/cpio.5.txt +# Update: Joerg Jenderek +# +# Reference: http://mark0.net/download/triddefs_xml.7z/defs/a/ark-cpio-bin.trid.xml +# Note: called "CPIO archive (binary)" by TrID, "cpio/Binary LE" by 7-Zip and "CPIO" by DROID via PUID fmt/635 +0 short 070707 +# skip DROID fmt-635-signature-id-960.cpio by looking for pathname of 1st entry +>26 string >\0 cpio archive !:mime application/x-cpio +# https://download.opensuse.org/distribution/leap/15.4/iso/openSUSE-Leap-15.4-NET-x86_64-Media.iso +# boot/x86_64/loader/bootlogo +# message.cpi +!:ext /cpio/cpi +>>0 use cpio-bin +# Reference: http://mark0.net/download/triddefs_xml.7z/defs/a/ark-cpio-bin-sw.trid.xml +# Note: called "CPIO archive (byte swapped binary)" by TrID and "Cpio/Binary BE" by 7-Zip 0 short 0143561 byte-swapped cpio archive !:mime application/x-cpio # encoding: swapped +# https://telparia.com/fileFormatSamples/archive/cpio/skeleton2.cpio +!:ext cpio +>0 use cpio-bin-be +# Reference: http://mark0.net/download/triddefs_xml.7z/defs/a/ark-cpio.trid.xml +# Note: called "CPIO archive (portable)" by TrID, "cpio/Portable ASCII" by 7-Zip and "cpio/odc" by GNU cpio 0 string 070707 ASCII cpio archive (pre-SVR4 or odc) !:mime application/x-cpio +# https://telparia.com/fileFormatSamples/archive/cpio/ pthreads-1.60B5.osr5src.cpio cinema.cpi VOL.000.008 VOL.000.012 +!:ext cpio/cpi/008/012 +# Note: called "CPIO archive (portable)" by TrID, "cpio/New ASCII" by 7-Zip and "cpio/newc" by GNU cpio 0 string 070701 ASCII cpio archive (SVR4 with no CRC) !:mime application/x-cpio +# https://telparia.com/fileFormatSamples/archive/cpio/MainActor-2.06.3.cpio +!:ext cpio +# Note: called "CPIO archive (portable)" by TrID, "cpio/New CRC" by 7-Zip and "cpio/crc" by GNU cpio 0 string 070702 ASCII cpio archive (SVR4 with CRC) !:mime application/x-cpio +# http://ftp.gnu.org/gnu/tar/tar-1.27.cpio.gz +# https://telparia.com/fileFormatSamples/archive/cpio/pcmcia +!:ext /cpio +# display information of old binary cpio archive +# Note: verfied by 7-Zip `7z l -tcpio -slt *.cpio` and +# `cpio -ivt --numeric-uid-gid --file=clam.bin-le.cpio` +0 name cpio-bin +# c_dev; device number; WHAT IS THAT? +>2 uleshort x \b; device %u +# c_ino; truncated inode number; use `ls --inode` +>4 uleshort x \b, inode %u +# c_mode; mode specifies permissions and file type like: ?622~?rw-r--r-- by `ls -l` +>6 uleshort x \b, mode %o +# c_uid; numeric user id; use `ls --numeric-uid-gid` +>8 uleshort x \b, uid %u +# c_gid; numeric group id +>10 uleshort x \b, gid %u +# c_nlink; links to this file; directories at least 2 +>12 uleshort >1 \b, %u links +# c_rdev; device number for block and character entries; zero for all other entries by writers +# like 0x0440 for /dev/ttyS0 +>14 uleshort >0 \b, device %#4.4x +# c_mtime[2]; modification time in seconds since 1 January 1970; most-significant 16 bits first +>16 medate x \b, modified %s +# c_filesize[2]; size of pathname; most-significant 16 bits first like: 544 +>22 melong x \b, %u bytes +# c_namesize; bytes in the pathname that follows the header like: 9 +#>20 uleshort x \b, namesize %u +# pathname of entry like: "clam.exe" +>26 string x "%s" +# display information of old binary byte swapped cpio archive +# Note: verfied by 7-Zip `7z l -tcpio -slt *.cpio` and +# `LANGUAGE=C cpio -ivt --numeric-uid-gid --file=clam.bin-be.cpio` +0 name cpio-bin-be +>2 ubeshort x \b; device %u +>4 ubeshort x \b, inode %u +>6 ubeshort x \b, mode %o +>8 ubeshort x \b, uid %u +>10 ubeshort x \b, gid %u +>12 ubeshort >1 \b, %u links +>14 ubeshort >0 \b, device %#4.4x +>16 bedate x \b, modified %s +>22 ubelong x \b, %u bytes +#>20 ubeshort x \b, namesize %u +>26 string x "%s" # # Various archive formats used by various versions of the "ar" @@ -249,7 +360,8 @@ #>>68 string x (format %.3s) >68 string =2.0\n # 2nd archive name=control archive name like control.tar.gz or control.tar.xz ->>72 string >\0 \b, with %.14s +# or control.tar.zst +>>72 string >\0 \b, with %.15s # look for 3rd archive name=data archive name like data.tar.{gz,xz,bz2,lzma} >>0 search/0x93e4f data.tar. \b, data compression # the above line only works if FILE_BYTES_MAX in ../../src/file.h is raised @@ -484,11 +596,12 @@ >>>>0 use ttcomp 0 string \1\4 # TODO: -# skip Commodore PET BASIC 4.0 program *.prg -# variant ASCII, 1K dictionary (strength=48=50-2). With strength=49 wrong order! WHY? # skip shared library (strength=50) handled by ./ibm6000 !:strength -2 ->0 use ttcomp +# skip Commodore PET BASIC programs (Mastermind.prg) with last 3 nil bytes (\0~end of line followed by 0000h line offset) +#>-4 ubelong x LAST_BYTES=%8.8x +>-4 ubelong&0x00FFffFF !0 +>>0 use ttcomp # display information of TTComp archive 0 name ttcomp # (version 5.25) labeled the entry as "TTComp archive data" @@ -731,6 +844,88 @@ !:ext ??$ >>8 ulelong >0 \b, original size: %u bytes +# Summary: lzss compressed/EDI Pack +# From: Joerg Jenderek +# URL: http://fileformats.archiveteam.org/wiki/EDI_Install_packed_file +# Note: called "EDI Install LZS compressed data" by TrID and verified by +# command like `deark -l -m edi_pack -d2 BOOK01A.IC$` as "EDI Pack LZSS1" +0 string EDILZSS +>7 string 1 +# look for point character before orginal file name extension +>>8 search/9/b . +# check suffix of possible orginal file anme +#>>>&0 ubelong x SUFFIX=%8.8x +# samples without valid character after point in original file name field like: FENNEL.LZS PLANTAIN.LZS +>>>&0 ubyte <0x20 +>>>>0 use edi-lzs +# samples with valid character after point in original file name field +>>>&0 ubyte >0x1F +# check 2nd charcter of suffix +#>>>>&0 ubyte x 2ND_SUFFIX=%x +# sample with one valid character after point followed by \0 in original file name field like: SPELMATE.H$ +>>>>&0 ubyte =0 +>>>>>0 use edi-pack +>>>>&0 ubyte >0x1F +# check 3rd charcter of suffix +#>>>>>&0 ubyte x 3RD_SUFFIX=%x +# no sample with 2 valid characters after point followed by \0 in original file name field +>>>>>&0 ubyte =0 +>>>>>>0 use edi-pack +# samples with valid 3rd character after point in original file name field +>>>>>&0 ubyte >0x1F +# sample with 3 valid character after point followed by \0 in original file name field like: BOOK01A.IC$ CTL3D.DL$ +>>>>>>&0 ubyte =0 +>>>>>>>0 use edi-pack +# sample with 3 valid character after point followed by no \0 in original file name field like: HERBTEXT.LZS +>>>>>>&0 ubyte !0 +>>>>>>>0 use edi-lzs +# no sample with invalid 3rd character after point in original file name field +>>>>>&0 default x +>>>>>>0 use edi-lzs +# sample with invalid 2nd character after point in original file name field like: LACERATE.LZS SPLINTER.LZS +>>>>&0 default x +>>>>>0 use edi-lzs +# sample without point character in original file name field like GUNSHOT.LZS +>>8 default x +>>>0 use edi-lzs +# Reference: http://mark0.net/download/triddefs_xml.7z/defs/e/edi-lzss2.trid.xml +# Note: called "EDI Install Pro LZSS2 compressed data" by TrID and verified by +# command like `deark -l -m edi_pack -d2 4WAY.WA$` as "EDI Pack LZSS2" +>7 string 2 EDI LZSS2 packed +#!:mime application/octet-stream +!:mime application/x-edi-pack-lzss +# the name of a compressed file often ends in character '$' or '_' +!:ext ??$/??_ +# original filename, NUL-terminated, padded to 13 bytes like: mci.vbx 4way.wav skymap.exe cmdialog.vbx +>>8 string x "%-0.13s" +# original file size, as a 4-byte integer. +>>21 ulelong x \b, %u bytes +# compressed data like: ff5249464606ec00 ff4d5aa601010000 +>>>25 ubequad x \b, data %#16.16llx... +0 name edi-pack +# Note: verified by command like `deark -l -d2 SPELMATE.H$` as "EDI Pack LZSS1" +# original filename, NUL-terminated, padded to 13 bytes like: ctl3d.dll spelmate.h filemenu.rc owl.def index-it.exe +# but not like \377Aloe.lzs\273 (HERBTEXT.LZS) +>8 string x EDI LZSS packed "%-.13s" +#!:mime application/octet-stream +!:mime application/x-edi-pack-lzss +# the name of a compressed file often ends in character '$' or '_' +!:ext ??$/?$ +# compressed data like: f7000001eff02020 ff4d5aa900020000 ff2f2a207370656c +>21 ubequad x \b, data %#16.16llx... +# URL: http://fileformats.archiveteam.org/wiki/EDI_LZSSLib +# Note: verified partly by command like `deark -l -m edi_pack -d2 GUNSHOT.LZS` as "EDI LZSSLib" +0 name edi-lzs +# Note: verified by command like `deark -l -d2 GUNSHOT.LZS` as "EDI LZSSLib" +# no original filename looks like: \277BM\226.\0 \277BM.n\001 \277BM\226.\0 \277BM.g\001 \377Aloe.lzs\273 +>8 string x EDI LZSSLib packed +#!:mime application/octet-stream +!:mime application/x-edi-pack-lzss +# The name of a compressed file ends with LZS suffix +!:ext lzs +# compressed data like: bf424df6e10100f3 ff416c6f652e6c7a ff416c6f652e6c7a +>8 ubequad x \b, data %#16.16llx... + # Summary: CAZIP compressed file # From: Joerg Jenderek # URL: http://fileformats.archiveteam.org/wiki/CAZIP @@ -769,8 +964,6 @@ 3 string OctSqu Squash archive data # Terse 0 string \5\1\1\0 Terse archive data -# PUCrunch -0 string \x01\x08\x0b\x08\xef\x00\x9e\x32\x30\x36\x31 PUCrunch archive data # UHarc 0 string UHA UHarc archive data # ABComp @@ -799,8 +992,10 @@ # QFC 0 string \x1aFC\x1a QFC archive data 0 string \x1aQF\x1a QFC archive data -# PRO-PACK -0 string RNC PRO-PACK archive data +# PRO-PACK https://www.segaretro.org/Rob_Northen_compression +0 string RNC +>3 byte 1 PRO-PACK archive data (compression 1) +>3 byte 2 PRO-PACK archive data (compression 2) # 777 0 string 777 777 archive data # LZS221 @@ -903,11 +1098,39 @@ # TPac 0 string \4TPAC\3 TPac archive data # Ai +# Update: Joerg Jenderek +# URL: http://fileformats.archiveteam.org/wiki/Ai_Archiver 0 string Ai\1\1\0 Ai archive data +#!:mime application/octet-stream +!:mime application/x-compress-ai +!:ext ai 0 string Ai\1\0\0 Ai archive data +#!:mime application/octet-stream +!:mime application/x-compress-ai +!:ext ai # Ai32 +# Reference: http://mark0.net/download/triddefs_xml.7z/defs/a/ark-ai.trid.xml +# Note: called "Ai Archivator compressed archive" by TrID 0 string Ai\2\0 Ai32 archive data +#!:mime application/octet-stream +!:mime application/x-compress-ai +!:ext ai +# original file name +>8 pstring/h x "%s" +# according to TrID the next 3 bytes are nil +>5 ubyte !0 \b, at 5 %#x +>6 ubyte !0 \b, at 6 %#x +>7 ubyte !0 \b, at 7 %#x +# the fourth byte with value 0 is probably a flag for "non solid" mode +#>3 ubyte =0x00 \b, unsolid mode 0 string Ai\2\1 Ai32 archive data +#!:mime application/octet-stream +!:mime application/x-compress-ai +!:ext ai +# original file name +>8 pstring/h x "%s" +# the fourth byte with value 0x01 is probably a flag for "solid" mode; this is not the default +>3 ubyte =0x01 \b, solid mode # SBC 0 string SBC SBC archive data # Ybs @@ -1212,7 +1435,7 @@ >>>>>>3 regex \^lh[01] LHarc 1.x/ARX archive data # LHice archiver use ".ICE" as name extension instead usual one ".lzh" # FOOBAR archiver use ".foo" as name extension instead usual one -# "Florain Orjanov's and Olga Bachetska's ARchiver" not found at the moment +# "Florian Orjanov's and Olga Bachetska's ARchiver" not found at the moment >>>>>>>2 string -lh1 \b !:ext lha/lzh/ice >>>>>>3 regex \^lh[23d] LHa 2.x? archive data @@ -1400,6 +1623,83 @@ !:mime application/zip !:ext zip/cbz +# Android APK file (Zip archive) +0 string PK\003\004 +!:strength +1 +# Starts with AndroidManifest.xml (file name length = 19) +>26 uleshort 19 +>>30 string AndroidManifest.xml Android package (APK), with AndroidManifest.xml +!:mime application/vnd.android.package-archive +!:ext apk +>>>-22 string PK\005\006 +>>>>(-6.l-16) string APK\x20Sig\x20Block\x2042 \b, with APK Signing Block +# Starts with META-INF/com/android/build/gradle/app-metadata.properties +>26 uleshort 57 +>>30 string META-INF/com/android/build/gradle/ +>>>&0 string app-metadata.properties Android package (APK), with gradle app-metadata.properties +!:mime application/vnd.android.package-archive +!:ext apk +>>>>-22 string PK\005\006 +>>>>>(-6.l-16) string APK\x20Sig\x20Block\x2042 \b, with APK Signing Block +# Starts with classes.dex (file name length = 11) +>26 uleshort 11 +>>30 string classes.dex Android package (APK), with classes.dex +!:mime application/vnd.android.package-archive +!:ext apk +>>>-22 string PK\005\006 +>>>>(-6.l-16) string APK\x20Sig\x20Block\x2042 \b, with APK Signing Block +# Starts with META-INF/MANIFEST.MF (file name length = 20) +# NB: checks for resources.arsc, classes.dex, etc. as well to avoid matching JAR files +>26 uleshort 20 +>>30 string META-INF/MANIFEST.MF +# Contains resources.arsc (near the end, in the central directory) +>>>-512 search resources.arsc Android package (APK), with MANIFEST.MF and resources.arsc +!:mime application/vnd.android.package-archive +!:ext apk +>>>>-22 string PK\005\006 +>>>>>(-6.l-16) string APK\x20Sig\x20Block\x2042 \b, with APK Signing Block +>>>-512 default x +# Contains classes.dex (near the end, in the central directory) +>>>>-512 search classes.dex Android package (APK), with MANIFEST.MF and classes.dex +!:mime application/vnd.android.package-archive +!:ext apk +>>>>>-22 string PK\005\006 +>>>>>>(-6.l-16) string APK\x20Sig\x20Block\x2042 \b, with APK Signing Block +>>>>-512 default x +# Contains lib/armeabi (near the end, in the central directory) +>>>>>-512 search lib/armeabi Android package (APK), with MANIFEST.MF and armeabi lib +!:mime application/vnd.android.package-archive +!:ext apk +>>>>>>-22 string PK\005\006 +>>>>>>>(-6.l-16) string APK\x20Sig\x20Block\x2042 \b, with APK Signing Block +>>>>>-512 default x +# Contains drawables (near the end, in the central directory) +>>>>>>-512 search res/drawable Android package (APK), with MANIFEST.MF and drawables +!:mime application/vnd.android.package-archive +!:ext apk +>>>>>>>-22 string PK\005\006 +>>>>>>>>(-6.l-16) string APK\x20Sig\x20Block\x2042 \b, with APK Signing Block +# It may or may not be an APK file, but it's definitely a Java JAR file +>>>>>>-512 default x Java archive data (JAR) +!:mime application/java-archive +!:ext jar +# Starts with zipflinger virtual entry (28 + 104 = 132 bytes) +# See https://github.com/obfusk/apksigcopier/blob/666f5b7/apksigcopier/__init__.py#L230 +>4 string \x00\x00\x00\x00\x00\x00 +>>&0 string \x21\x08\x21\x02 +>>>&0 string \x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00 +>>>>&0 string \x00\x00 Android package (APK), with zipflinger virtual entry +!:mime application/vnd.android.package-archive +!:ext apk +>>>>>-22 string PK\005\006 +>>>>>>(-6.l-16) string APK\x20Sig\x20Block\x2042 \b, with APK Signing Block +# APK Signing Block +>0 default x +>>-22 string PK\005\006 +>>>(-6.l-16) string APK\x20Sig\x20Block\x2042 Android package (APK), with APK Signing Block +!:mime application/vnd.android.package-archive +!:ext apk + # Zip archives (Greg Roelofs, c/o zip-bugs@wkuvx1.wku.edu) 0 string PK\005\006 Zip archive data (empty) !:mime application/zip @@ -1502,9 +1802,13 @@ >>>>77 string -web HTML Document Template !:mime application/vnd.oasis.opendocument.text-web !:ext oth ->>>>77 string -master Master Document +>>>>77 string -master +>>>>>84 byte !0x2d Master Document !:mime application/vnd.oasis.opendocument.text-master !:ext odm +>>>>>84 string -template Master Template +!:mime application/vnd.oasis.opendocument.text-master-template +!:ext otm >>>73 string graphics >>>>81 byte !0x2d Drawing !:mime application/vnd.oasis.opendocument.graphics @@ -1547,8 +1851,7 @@ # Valid for LibreOffice Base 6.0.1.1 at least >>>73 string base Database # https://bugs.documentfoundation.org/show_bug.cgi?id=45854 -!:mime application/vnd.oasis.opendocument.database -#!:mime application/vnd.oasis.opendocument.base +!:mime application/vnd.oasis.opendocument.base !:ext odb >>>73 string image >>>>78 byte !0x2d Image @@ -1564,6 +1867,16 @@ >>50 string epub+zip EPUB document !:mime application/epub+zip +# From: Hajin Jang <jb6804@naver.com> +# hwpx (OWPML) document format follows OCF specification. +# Hangul Word Processor 2010+ supports HWPX format. +# URL: https://www.hancom.com/etc/hwpDownload.do +# https://standard.go.kr/KSCI/standardIntro/getStandardSearchView.do?menuId=503&topMenuId=502&ksNo=KSX6101 +# https://e-ks.kr/streamdocs/view/sd;streamdocsId=72059197557727331 +>>50 string hwp+zip Hancom HWP (Hangul Word Processor) file, HWPX +!:mime application/x-hwp+zip +!:ext hwpx + # From: Joerg Jenderek # URL: http://en.wikipedia.org/wiki/CorelDRAW # NOTE: version; til 2 WL-based; from 3 til 13 by ./riff; from 14 zip based @@ -1617,9 +1930,10 @@ >>>38 regex [!-OQ-~]+ Zip data (MIME type "%s"?) !:mime application/zip -# Java Jar files +# Java Jar files (see also APK files above) >(26.s+30) leshort 0xcafe Java archive data (JAR) !:mime application/java-archive +!:ext jar # iOS App >(26.s+30) leshort !0xcafe @@ -1652,16 +1966,116 @@ >8 belong x \b, size %d # Zoo archiver -20 lelong 0xfdc4a7dc Zoo archive data +# Update: Joerg Jenderek +# URL: https://en.wikipedia.org/wiki/Zoo_(file_format) +# http://fileformats.archiveteam.org/wiki/Zoo +# Reference: http://mark0.net/download/triddefs_xml.7z/defs/a/ark-zoo-strict.trid.xml +# http://distcache.freebsd.org/ports-distfiles/zoo-2.10pl1.tar.gz/zoo.h +# Note: called "ZOO compressed archive (strict)" by TrID and "ZOO Compressed Archive" by DROID via PUID x-fmt/269 +# verified by command like `deark -m zoo -l -d2 WHRCGA.ZOO` +20 lelong 0xfdc4a7dc +# skip DROID x-fmt-269-signature-id-621.zoo by looking for valid major version to manipulate archive +>32 byte >0 Zoo archive data !:mime application/x-zoo ->4 byte >48 \b, v%c. ->>6 byte >47 \b%c ->>>7 byte >47 \b%c ->32 byte >0 \b, modify: v%d ->>33 byte x \b.%d+ ->42 lelong 0xfdc4a7dc \b, ->>70 byte >0 extract: v%d ->>>71 byte x \b.%d+ +# bak is extension of backup-ed zoo +!:ext zoo/bak +# version in text form like: 1.50 2.00 2.10 +>>4 byte >48 \b, v%c. +>>>6 byte >47 \b%c +>>>>7 byte >47 \b%c +# ZOO files typically start with "ZOO ?.?? Archive.", followed by the bytes 0x1a 0x0 0x0; not used by Zoo and they may be anything +>>8 string !\040Archive.\032 \b, at 8 +>>>8 string x text "%0.10s" +# major_ver.minor_ver; minimum version needed to manipulate archive like: 1.0 2.0 +>>32 byte >0 \b, modify: v%d +>>>33 byte x \b.%d+ +# major_ver.minor_ver; minimum version needed to extract after modify like in old versions +>>(24.l+28) ubyte x \b, extract: v%u +>>(24.l+29) ubyte x \b.%u+ +# with zoo 2.00 additional fields have been added in the archive header +>>32 byte >1 +# type; type of archive header like: 1 2 +>>>34 ubyte !1 \b, header type %u +# acmt_pos; position of archive comment like: 6258 30599 61369 149501 +>>>35 lelong >0 \b, at %d +# acmt_len; length of archive comment like: 258 +>>>>39 uleshort x %u bytes comment +#>>>>(35.l) ubequad x COMMENT=%16.16llx +# 1st character of comment maybe is CarriageReturn (0x0d) +>>>>(35.l) ubyte <040 +# 2nd character of comment maybe is LineFeed (0x0a) +>>>>>(35.l+1) ubyte <040 +# comment string after CRLF like "Anonymous ftp site garbo.uwasa.fi 128.214.87.1 moderated by" +>>>>>>(35.l+2) string x %s +# next character of remaining comment maybe is CarriageReturn (0x0d) +>>>>>>>&0 ubyte <040 +>>>>>>>>&0 ubyte <040 +# 2nd comment part like: Timo Salmi ts@chyde.uwasa.fi PC directories and uploads\015\012Harri Valkama hv@chyde.uwasa.fi PC, Mac, Unix files, and upload +>>>>>>>>>&0 string >037 %s +# vdata; archive-level versioning byte like: 1 3 +>>>41 ubyte !1 \b, vdata %#x +# zoo_start; pointer to 1st entry header +>>24 lelong x \b; at %u +# zoo_minus; zoo_start -1 for consistency checking +#>>28 lelong x \b, zoo_minus %#x +# zoo_tag; tag for check +#>>(24.l+0) ulelong !0xfdc4a7dc \b, zoo_tag=%8.8x +# type; type of directory entry like: 1 2 +>>(24.l+4) ubyte !2 type=%u +# packing_method; 0~no packing 1~normal LZW 2~lzh +>>(24.l+5) ubyte x method= +>>>(24.l+5) ubyte 0 \bnot-compressed +>>>(24.l+5) ubyte 1 \blzd +>>>(24.l+5) ubyte 2 \blzh +# next; position of next directory entry +>>(24.l+6) ulelong x \b, next entry at %u +# offset; position of file data for this entry +#>>(24.l+10) ulelong x \b, data at %u +# file_crc; CRC-16 of file data +>>(24.l+18) uleshort x \b, CRC %#4.4x +# comment; zero if none or points to entry comment like ADD9h (WHRCGA.ZOO) +>>(24.l+32) lelong >0 \b, at %#x +# cmt_size; if not 0 for none then length of entry comment like: 46 +>>>(24.l+36) uleshort >0 %u bytes comment +# entry comment itself like: "CGA .GL file showing menu input from keyboard" +>>>>(&-6.l) string x "%s" +# org_size; original size of file +>>(24.l+20) ulelong x \b, size %u +# size_now; compressed size of file +>>(24.l+24) ulelong x (%u compressed) +# major_ver.minor_ver; minimum version needed to extract already done +# deleted; will be 1 if deleted, 0 if not +>>(24.l+30) ubyte =1 \b, deleted +# struc; file structure if any; WHAT IS THAT? +>>(24.l+31) ubyte !0 \b, structured +# fname[13]; short/DOS file name like 12345678.012 +>>(24.l+38) string x \b, %0.13s +# for directory entry type 2 with variable part +>>(24.l+4) ubyte =2 +# var_dir_len; length of variable part of dir entry +>>>(24.l+51) uleshort >0 +#>>>(24.l+51) uleshort >0 \b, variable part length %u +# namlen; length of long filename +#>>>>(24.l+56) ubyte x \b, namlen %u +# dirlen; length of directory name +#>>>>(24.l+57) ubyte x \b, dirlen %u +# if file length positive then show long file name +>>>>(24.l+56) ubyte >0 +# lfname[256]; long file name \0-terminated +>>>>>(24.l+58) string x "%s" +# if directory length positive then jump before file name field and then jump this addtional length plus 2 (\0-terminator + dirlen field) to following directory name +>>>>(24.l+57) ubyte >0 +>>>>>(24.l+55) ubyte x +# dirname[256]; directory name \0-terminated +>>>>>>&(&0.b+2) string x in "%s" +# dir_crc; CRC of directory entry +#>>>(24.l+54) uleshort x \b, entry CRC %#4.4x +# tz; timezone where file was archived; 7Fh~unknown 4~1.00hoursWestOfUTC 12 16 20~5.00hoursWestOfUTC -107~26.75hoursEastOfUTC -4~1.00hoursEastOfUTC +>>>(24.l+53) byte !0x7f \b, time zone %d/4 +# date; last mod file date in DOS format +>>>(24.l+14) lemsdosdate x \b, modified %s +# time; last mod file time in DOS format +>>>(24.l+16) lemsdostime x %s # Shell archives 10 string #\ This\ is\ a\ shell\ archive shell archive text @@ -1724,13 +2138,17 @@ # Felix von Leitner <felix-file@fefe.de> 0 string d8:announce BitTorrent file !:mime application/x-bittorrent +!:ext torrent # Durval Menezes, <jmgthbfile at durval dot com> 0 string d13:announce-list BitTorrent file !:mime application/x-bittorrent +!:ext torrent 0 string d7:comment BitTorrent file !:mime application/x-bittorrent +!:ext torrent 0 string d4:info BitTorrent file !:mime application/x-bittorrent +!:ext torrent # Atari MSA archive - Teemu Hukkanen <tjhukkan@iki.fi> # URL: http://fileformats.archiveteam.org/wiki/MSA_(Magic_Shadow_Archiver) @@ -1763,6 +2181,19 @@ !:mime application/zip !:ext zip/cbz +# Recognize ZIP archives with prepended data by end-of-central-directory record +# https://en.wikipedia.org/wiki/ZIP_(file_format)#End_of_central_directory_record_(EOCD) +# by Michal Gorny <mgorny@gentoo.org> +-2 uleshort 0 +>&-22 string PK\005\006 +# without #! +>>0 string !#! Zip archive, with extra data prepended +!:mime application/zip +!:ext zip/cbz +# with #! +>>0 string/w #!\ a +>>>&-1 string/T x %s script executable (Zip archive) + # ACE archive (from http://www.wotsit.org/download.asp?f=ace) # by Stefan `Sec` Zehl <sec@42.org> 7 string **ACE** ACE archive data @@ -2007,7 +2438,28 @@ >3 byte x version %d # LyNX archive +# Update: Joerg Jenderek +# URL: http://fileformats.archiveteam.org/wiki/Lynx_archive +# Reference: http://ist.uwaterloo.ca/~schepers/formats/LNX.TXT +# http://mark0.net/download/triddefs_xml.7z/defs/a/ark-lnx.trid.xml +# Note: called "Lynx archive" by TrID and "Commodore C64 BASIC program" with "POKE 53280" by ./c64 +# TODO: merge and unify with Commodore C64 BASIC program 56 string USE\040LYNX\040TO\040DISSOLVE\040THIS\040FILE LyNX archive +# display "Lynx archive" (strength=330) before Commodore C64 BASIC program (strength=50) handled by ./c64 +#!:strength +0 +#!:mime application/octet-stream +!:mime application/x-commodore-lnx +!:ext lnx +# afterwards look for BASIC tokenized GOTO (89h) 10, line terminator \0, end of programm tag \0\0 and CarriageReturn +>86 search/10 \x8910\0\0\0\r \b, +# for DEBUGGING +#>>&0 string x STRING="%s" +# number in ASCII of directory blocks with spaces on both sides like: 1 2 3 5 +>>&0 regex [0-9]{1,5} %s directory blocks +# signature like: "*LYNX XII BY WILL CORLEY" " LYNX IX BY WILL CORLEY" "*LYNX BY CBMCONVERT 2.0*" +>>>&2 regex [^\r]{1,24} \b, signature "%s" +# number of files in ASCII surrounded by spaces and delimited by CR like: 2 3 6 13 69 144 (maximum?) +>>>>&1 regex [0-9]{1,3} \b, %s files # From: Joerg Jenderek # URL: https://www.acronis.com/ @@ -2040,6 +2492,7 @@ # https://gitweb.gentoo.org/proj/portage.git/tree/man/xpak.5 -4 string STOP >-16 string XPAKSTOP Gentoo binary package (XPAK) +!:mime application/vnd.gentoo.xpak # From: Joerg Jenderek # URL: https://kodi.wiki/view/TexturePacker @@ -2081,3 +2534,74 @@ # URL: http://mattmahoney.net/dc/#paq9a # Note: Line 1186 of paq9a.cpp gives the magic bytes 0 string pQ9\001 PAQ9A archive + +# From wof (wof@stachelkaktus.net) +0 string Unison\ archive\ format Unison archive format + +# https://ankiweb.net +30 string collection.anki2 Anki APKG file +#!:ext .apkg + +# Synology archive (DiskStation Manager 7.0+) +# From: Alexandre Iooss <erdnaxe@crans.org> +# Note: These archives are signed and encrypted. +0 ulelong&0xFFFFFF00 0xEFBEAD00 +# MessagePack header (fixarray of 5 elements starting with a bin of 32 bytes) +>8 ulelong&0x00FFFFFF 0x20C495 Synology archive +!:ext spk +# Extract some properties from MessagePack third item +>>43 search/0x10000 package= +>>>&0 string x \b, package %s +>>43 search/0x10000 arch= +>>>&0 string x %s +>>43 search/0x10000 version= +>>>&0 string x %s +>>43 search/0x10000 create_time= +>>>&0 string x \b, created on %s + +# MonoGame/XNA processed assets archive +# From: Alexandre Iooss <erdnaxe@crans.org> +# URL: https://github.com/MonoGame/MonoGame/blob/v3.8.1/MonoGame.Framework/Content/ContentManager.cs +0 string XNB +# XNB must be version 4 or 5 +>4 byte <6 +>>4 byte >3 +# Size must be positive +>>>6 lelong >0 MonoGame/XNA processed assets +!:ext xnb +>>>>3 string =w \b, for Windows +>>>>3 string =x \b, for Xbox360 +>>>>3 string =i \b, for iOS +>>>>3 string =a \b, for Android +>>>>3 string =d \b, for DesktopGL +>>>>3 string =X \b, for MacOSX +>>>>3 string =W \b, for WindowsStoreApp +>>>>3 string =n \b, for NativeClient +>>>>3 string =M \b, for WindowsPhone8 +>>>>3 string =r \b, for RaspberryPi +>>>>3 string =P \b, for PlayStation4 +>>>>3 string =5 \b, for PlayStation5 +>>>>3 string =O \b, for XboxOne +>>>>3 string =S \b, for Nintendo Switch +>>>>3 string =G \b, for Google Stadia +>>>>3 string =b \b, for WebAssembly and Bridge.NET +>>>>3 string =m \b, for WindowsPhone7.0 (XNA) +>>>>3 string =p \b, for PlayStationMobile +>>>>3 string =v \b, for PSVita +>>>>3 string =g \b, for Windows (OpenGL) +>>>>3 string =l \b, for Linux +>>>>4 byte x \b, version %d +>>>>5 byte &0x80 \b, LZX compressed +>>>>>10 lelong x \b, decompressed size: %d bytes +>>>>5 byte &0x40 \b, LZ4 compressed +>>>>>10 lelong x \b, decompressed size: %d bytes + +# Electron ASAR archive +# From: Alexandre Iooss <erdnaxe@crans.org> +# URL: https://github.com/electron/asar +0 ulelong 4 +# Match JSON header start and end +>16 string {"files":{" +>>(12.l+12) string }}}} Electron ASAR archive +!:ext asar +>>>12 ulelong x \b, header length: %d bytes |