improve gzip detection (extensions) Joerg Jenderek

diff --git a/magic/Magdir/compress b/magic/Magdir/compress
index 4c74337551d26e49cb8283d6d280e592d3d39f92..ced96e88729266bf33b927647759436f6ba4fe52 100644 (file)
--- a/magic/Magdir/compress
+++ b/magic/Magdir/compress
@@ -1,5 +1,5 @@
 #------------------------------------------------------------------------------
-# $File: compress,v 1.73 2018/09/01 13:52:39 christos Exp $
+# $File: compress,v 1.74 2019/04/19 00:35:18 christos Exp $
 # compress:  file(1) magic for pure-compression formats (no archives)
 #
 # compress, gzip, pack, compact, huf, squeeze, crunch, freeze, yabba, etc.
@@ -16,13 +16,78 @@
 >2     byte&0x1f       x               %d bits
 
 # gzip (GNU zip, not to be confused with Info-ZIP or PKWARE zip archiver)
+# URL: https://en.wikipedia.org/wiki/Gzip
+# Reference: https://tools.ietf.org/html/rfc1952
+# Update: Joerg Jenderek, Apr 2019
 #   Edited by Chris Chittleborough <cchittleborough@yahoo.com.au>, March 2002
 #      * Original filename is only at offset 10 if "extra field" absent
 #      * Produce shorter output - notably, only report compression methods
 #         other than 8 ("deflate", the only method defined in RFC 1952).
-0       string          \037\213        gzip compressed data
-!:mime application/x-gzip
-!:strength * 2
+# Note: find defs -iname '*.trid.xml' -exec grep -q '<Bytes>1F8B08' {} \; -ls
+# TODO:
+# FBR  Blueberry FlashBack screen Record       https://www.flashbackrecorder.com/
+# KPR  KOffice/Calligra KPresenter             application/x-kpresenter
+# KPT  KOffice/Calligra KPresenter template?   application/x-kpresenter
+# SAV  Diggles Saved Game File                 http://www.innonics.com
+# SAV  FarCry (demo) saved game                http://www.farcry-thegame.com
+# DAT  ZOAGZIP game data format                http://en.wikipedia.org/wiki/SD_Gundam_Capsule_Fighter
+0       string          \037\213
+# to display gzip compressed (strength=100=2*50) before other (strength=50)?
+#!:strength * 2
+# no FNAME and FCOMMENT bit implies no file name/comment. That means only binary
+>3     byte&0x18       =0
+# For binary gzipped no ASCII text should occur
+#      mcd-monu-cad.trid.xml
+>>10   string          MCD                     Monu-Cad Drawing, Component or Font
+#>>36  string          Created\ with\ MONU-CAD 
+#!:mime        application/octet-stream
+# http://fileformats.archiveteam.org/wiki/Monu-CAD
+#      http://www.monucad.com/downloads/FullDemo-2005.EXE
+#      /HANDS96.MCC    Component
+#      /DEMO_DD01.MCD  Drawing
+#      /MCALF020.FNT   Font
+!:ext  mcc/mcd/fnt
+# http://www.generalcadd.com
+>>10   string          GXD                     General CADD, Drawing or Component
+#!:mime        application/octet-stream
+#      /gxc/BUILDINGEDGE.gxc                   Component
+#      /gxd/HOCKETT-STPAUL-WRHSE.gxd           Drawing
+#      /gxd/POWERLAND-MILL-ADD-11.gxd          Drawing         v9.1.06
+!:ext  gxc/gxd
+#>>>13 ubyte           0                       \b, version 0
+>>>13  string          09                      \b, version 9
+# other gzipped binary like gzipped tar, VirtualBox extension package,...
+>>10   default         x               gzip compressed data
+>>>0   use     gzip-info
+# size of the original (uncompressed) input data modulo 2^32
+>>>-4  ulelong         x               \b, original size modulo 2^32 %u
+# gzipped TAR or VirtualBox extension package
+!:mime application/gzip
+#!:mime        application/x-compressed-tar
+#!:mime        application/x-virtualbox-vbox-extpack
+# https://www.w3.org/TR/SVG/mimereg.html
+#!:mime        image/image/svg+xml-compressed
+#      zlib.3.gz
+#      microcode-20180312.tgz
+#      tpz same as tgz
+#      lua-md5_1.2-1_i386_i486.ipk     https://en.wikipedia.org/wiki/Opkg
+#      Oracle_VM_VirtualBox_Extension_Pack-5.0.12-104815.vbox-extpack
+!:ext  gz/tgz/tpz/ipk/vbox-extpack/svgz
+# FNAME/FCOMMENT bit implies file name/comment as iso-8859-1 text
+>3     byte&0x18       >0              gzip compressed data
+!:mime application/gzip
+# gzipped tar, gzipped Abiword document
+#!:mime        application/x-compressed-tar
+#!:mime        application/x-abiword-compressed
+#!:mime        image/image/svg+xml-compressed
+#      kleopatra_splashscreen.svgz     gzipped .svg
+!:ext  gz/tgz/tpz/zabw/svgz
+>>0    use     gzip-info
+# size of the original (uncompressed) input data modulo 2^32
+>>-4   ulelong         x               \b, original size modulo 2^32 %u
+#      display information of gzip compressed files
+0      name                            gzip-info
+#>2    byte            x               THIS iS GZIP
 >2     byte            <8              \b, reserved method
 >2     byte            >8              \b, unknown method
 >3     byte            &0x01           \b, ASCII
@@ -49,7 +114,9 @@
 >9     byte            =0x0B           \b, from NTFS filesystem (NT)
 >9     byte            =0x0C           \b, from QDOS
 >9     byte            =0x0D           \b, from Acorn RISCOS
->-4    lelong          x               \b, original size %u
+# size of the original (uncompressed) input data modulo 2^32
+#>-4   ulelong         x               \b, original size modulo 2^32 %u
+#ERROR: line 114: non zero offset 1048572 at level 1
 
 # packed data, Huffman (minimum redundancy) codes on a byte-by-byte basis
 0      string          \037\036        packed data