file/Magdir/archive

#------------------------------------------------------------------------------
# archive:  file(1) magic for archive formats (see also "msdos" for self-
#           extracting compressed archives)
#
# cpio, ar, arc, arj, hpack, lha/lharc, rar, squish, uc2, zip, zoo, etc.
# pre-POSIX "tar" archives are handled in the C code.

# POSIX tar archives
257	string		ustar\0		POSIX tar archive
257	string		ustar\040\040\0	GNU tar archive

# cpio archives
#
# Yes, the top two "cpio archive" formats *are* supposed to just be "short".
# The idea is to indicate archives produced on machines with the same
# byte order as the machine running "file" with "cpio archive", and
# to indicate archives produced on machines with the opposite byte order
# from the machine running "file" with "byte-swapped cpio archive".
#
# 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
0	short		0143561		byte-swapped cpio archive
0	string		070707		ASCII cpio archive (pre-SVR4 or odc)
0	string		070701		ASCII cpio archive (SVR4 with no CRC)
0	string		070702		ASCII cpio archive (SVR4 with CRC)

# Debian package (needs to go before regular portable archives)
#
0	string		!<arch>\ndebian
>8	string		debian-split	part of multipart Debian package
>8	string		debian-binary	Debian binary package
>68	string		>\n		(format %s)
>136	ledate		x		created: %s

# other archives
0	long		0177555		very old archive
0	short		0177555		very old PDP-11 archive
0	long		0177545		old archive
0	short		0177545		old PDP-11 archive
0	long		0100554		apl workspace
0	string		=<ar>		archive

# MIPS archive (needs to go before regular portable archives)
#
0	string	!<arch>\n__________E	MIPS archive
>20	string	U			with MIPS Ucode members
>21	string	L			with MIPSEL members
>21	string	B			with MIPSEB members
>19	string	L			and an EL hash table
>19	string	B			and an EB hash table
>22	string	X			-- out of date

0	string		-h-		Software Tools format archive text

#
# XXX - why are there multiple <ar> thingies?  Note that 0x213c6172 is
# "!<ar", so, for new-style (4.xBSD/SVR2andup) archives, we have:
#
# 0	string		!<arch>		current ar archive
# 0	long		0x213c6172	archive file
#
# and for SVR1 archives, we have:
#
# 0	string		\<ar>		System V Release 1 ar archive
# 0	string		=<ar>		archive
#
# XXX - did Aegis really store shared libraries, breakpointed modules,
# and absolute code program modules in the same format as new-style
# "ar" archives?
#
0	string		!<arch>		current ar archive
>8	string		__.SYMDEF	random library
>0	belong		=65538		- pre SR9.5
>0	belong		=65539		- post SR9.5
>0	beshort		2		- object archive
>0	beshort		3		- shared library module
>0	beshort		4		- debug break-pointed module
>0	beshort		5		- absolute code program module
0	string		\<ar>		System V Release 1 ar archive
0	string		=<ar>		archive
#
# XXX - from "vax", which appears to collect a bunch of byte-swapped
# thingies, to help you recognize VAX files on big-endian machines;
# with "leshort", "lelong", and "string", that's no longer necessary....
#
0	belong		0x65ff0000	VAX 3.0 archive
0	belong		0x3c61723e	VAX 5.0 archive
#
0	long		0x213c6172	archive file
0	lelong		0177555		very old VAX archive
0	leshort		0177555		very old PDP-11 archive
#
# XXX - "pdp" claims that 0177545 can have an __.SYMDEF member and thus
# be a random library (it said 0xff65 rather than 0177545).
#
0	lelong		0177545		old VAX archive
>8	string		__.SYMDEF	random library
0	leshort		0177545		old PDP-11 archive
>8	string		__.SYMDEF	random library
#
# From "pdp" (but why a 4-byte quantity?)
#
0	lelong		0x39bed		PDP-11 old archive
0	lelong		0x39bee		PDP-11 4.0 archive

# ARC archiver, from Daniel Quinlan (quinlan@yggdrasil.com)
#
# The first byte is the magic (0x1a), byte 2 is the compression type for
# the first file (0x01 through 0x09), and bytes 3 to 15 are the MS-DOS
# filename of the first file (null terminated).  Since some types collide
# we only test some types on basis of frequency: 0x08 (83%), 0x09 (5%),
# 0x02 (5%), 0x03 (3%), 0x04 (2%), 0x06 (2%).  0x01 collides with terminfo.
0	lelong&0x8080ffff	0x0000081a	ARC archive data, dynamic LZW
0	lelong&0x8080ffff	0x0000091a	ARC archive data, squashed
0	lelong&0x8080ffff	0x0000021a	ARC archive data, uncompressed
0	lelong&0x8080ffff	0x0000031a	ARC archive data, packed
0	lelong&0x8080ffff	0x0000041a	ARC archive data, squeezed
0	lelong&0x8080ffff	0x0000061a	ARC archive data, crunched

# Acorn archive formats (Disaster prone simpleton, m91dps@ecs.ox.ac.uk)
# I can't create either SPARK or ArcFS archives so I have not tested this stuff
# [GRR:  the original entries collide with ARC, above; replaced with combined
#  version (not tested)]
#0	byte		0x1a		RISC OS archive
#>1	string		archive		(ArcFS format)
0	string		\032archive	RISC OS archive (ArcFS format)

# ARJ archiver (jason@jarthur.Claremont.EDU)
0	leshort		0xea60		ARJ archive data
>5	byte		x		\b, v%d,
>8	byte		&0x04		multi-volume,
>8	byte		&0x10		slash-switched,
>8	byte		&0x20		backup,
>34	string		x		original name: %s,
>7	byte		0		os: MS-DOS
>7	byte		1		os: PRIMOS
>7	byte		2		os: Unix
>7	byte		3		os: Amiga
>7	byte		4		os: Macintosh
>7	byte		5		os: OS/2
>7	byte		6		os: Apple ][ GS
>7	byte		7		os: Atari ST
>7	byte		8		os: NeXT
>7	byte		9		os: VAX/VMS
>3	byte		>0		%d]

# HA archiver (Greg Roelofs, newt@uchicago.edu)
# This is a really bad format. A file containing HAWAII will match this...
#0	string		HA		HA archive data,
#>2	leshort		=1		1 file,
#>2	leshort		>1		%u files,
#>4	byte&0x0f	=0		first is type CPY
#>4	byte&0x0f	=1		first is type ASC
#>4	byte&0x0f	=2		first is type HSC
#>4	byte&0x0f	=0x0e		first is type DIR
#>4	byte&0x0f	=0x0f		first is type SPECIAL

# HPACK archiver (Peter Gutmann, pgut1@cs.aukuni.ac.nz)
0	string		HPAK		HPACK archive data

# JAM Archive volume format, by Dmitry.Kohmanyuk@UA.net
0	string		\351,\001JAM\		JAM archive,
>7	string		>\0			version %.4s
>0x26	byte		=0x27			-
>>0x2b	string          >\0			label %.11s,
>>0x27	lelong		x			serial %08x,
>>0x36	string		>\0			fstype %.8s

# LHARC/LHA archiver (Greg Roelofs, newt@uchicago.edu)
2	string		-lh0-		LHarc 1.x archive data [lh0]
2	string		-lh1-		LHarc 1.x archive data [lh1]
2	string		-lz4-		LHarc 1.x archive data [lz4]
2	string		-lz5-		LHarc 1.x archive data [lz5]
#	[never seen any but the last; -lh4- reported in comp.compression:]
2	string		-lzs-		LHa 2.x? archive data [lzs]
2	string		-lh\40-		LHa 2.x? archive data [lh ]
2	string		-lhd-		LHa 2.x? archive data [lhd]
2	string		-lh2-		LHa 2.x? archive data [lh2]
2	string		-lh3-		LHa 2.x? archive data [lh3]
2	string		-lh4-		LHa (2.x) archive data [lh4]
2	string		-lh5-		LHa (2.x) archive data [lh5]
>20	byte		x		- header level %d

# RAR archiver (Greg Roelofs, newt@uchicago.edu)
0	string		Rar!		RAR archive data

# SQUISH archiver (Greg Roelofs, newt@uchicago.edu)
0	string		SQSH		squished archive data (Acorn RISCOS)

# UC2 archiver (Greg Roelofs, newt@uchicago.edu)
# I can't figure out the self-extracting form of these buggers...
0	string		UC2\x1a		UC2 archive data

# ZIP archives (Greg Roelofs, c/o zip-bugs@wkuvx1.wku.edu)
0	string		PK\003\004	Zip archive data
>4	byte		0x09		\b, at least v0.9 to extract
>4	byte		0x0a		\b, at least v1.0 to extract
>4	byte		0x0b		\b, at least v1.1 to extract
>4	byte		0x14		\b, at least v2.0 to extract

# Zoo archiver
20	lelong		0xfdc4a7dc	Zoo archive data
>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+

# Shell archives
10	string		#\ This\ is\ a\ shell\ archive	shell archive text

#
# Debian Packages, from Peter Tobias <tobias@server.et-inf.fho-emden.de>
#0	string		0.9
#>8	byte		0x0a		old Debian binary package
#>>3	string		>\n		(format 0.9%s)