Improve detection of debian archives (Joerg Jenderek)

diff --git a/magic/Magdir/archive b/magic/Magdir/archive
index edbab37ee920d2d5138a9b94e4f7599418df36cd..4f905ff4db86f3d0eb25c2002a53350bb3a36d63 100644 (file)
--- a/magic/Magdir/archive
+++ b/magic/Magdir/archive
@@ -1,5 +1,5 @@
 #------------------------------------------------------------------------------
-# $File: archive,v 1.124 2019/02/20 15:07:44 christos Exp $
+# $File: archive,v 1.125 2019/03/03 17:11:28 christos Exp $
 # archive:  file(1) magic for archive formats (see also "msdos" for self-
 #           extracting compressed archives)
 #
@@ -226,21 +226,48 @@
 # a portable archive whose first member has a name beginning with
 # "debian".
 #
+# Update: Joerg Jenderek
+# URL: https://en.wikipedia.org/wiki/Deb_(file_format)
 0      string          =!<arch>\ndebian
->8     string          debian-split    part of multipart Debian package
+# https://manpages.debian.org/testing/dpkg/dpkg-split.1.en.html
+>14    string          -split  part of multipart Debian package
 !:mime application/vnd.debian.binary-package
->8     string          debian-binary   Debian binary package
+# udeb is used for stripped down deb file
+!:ext  deb/udeb
+>14    string          -binary Debian binary package
 !:mime application/vnd.debian.binary-package
->8     string          !debian
+!:ext  deb/udeb
+# This should not happen
+>14    default         x       Unknown Debian package
+# NL terminated version; for most Debian cases this is 2.0 or 2.1 for splitted
 >68    string          >\0             (format %s)
-# These next two lines do not work, because a bzip2 Debian archive
-# still uses gzip for the control.tar (first in the archive).  Only
-# data.tar varies, and the location of its filename varies too.
-# file/libmagic does not current have support for ascii-string based
-# (offsets) as of 2005-09-15.
-#>81   string          bz2             \b, uses bzip2 compression
-#>84   string          gz              \b, uses gzip compression
-#>136  ledate          x               created: %s
+#>68   string          !2.0\n
+#>>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
+# 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
+# for example like libreoffice-dev-doc_1%3a5.2.7-1+rpi1+deb9u3_all.deb
+>>>&0  string          x               %.4s
+# splitted debian package case
+>68    string          =2.1\n
+# dpkg-1.18.25/dpkg-split/info.c
+# NL terminated ASCII package name like ckermit
+>>&0   string          x               \b, %s
+# NL terminated package version like 302-5.3
+>>>&1  string          x               %s
+# NL terminated MD5 checksum
+>>>>&1 string          x               \b, MD5 %s
+# NL terminated original package length
+>>>>>&1        string          x               \b, unsplitted size %s
+# NL terminated part length
+>>>>>>&1       string  x               \b, part lenght %s
+# NL terminated package part like n/m
+>>>>>>>&1      string  x               \b, part %s
+# NL terminated package architecture like armhf since dpkg 1.16.1 or later
+>>>>>>>>&1     string  x               \b, %s
 
 #
 # MIPS archive; they're in the portable archive format, and need to go