xref: /freebsd/contrib/file/magic/Magdir/compress (revision 9e5787d2284e187abb5b654d924394a65772e004)
1#------------------------------------------------------------------------------
2# $File: compress,v 1.79 2020/05/30 23:53:04 christos Exp $
3# compress:  file(1) magic for pure-compression formats (no archives)
4#
5# compress, gzip, pack, compact, huf, squeeze, crunch, freeze, yabba, etc.
6#
7# Formats for various forms of compressed data
8# Formats for "compress" proper have been moved into "compress.c",
9# because it tries to uncompress it to figure out what's inside.
10
11# standard unix compress
120	string		\037\235	compress'd data
13!:mime	application/x-compress
14!:apple	LZIVZIVU
15>2	byte&0x80	>0		block compressed
16>2	byte&0x1f	x		%d bits
17
18# gzip (GNU zip, not to be confused with Info-ZIP or PKWARE zip archiver)
19# URL: https://en.wikipedia.org/wiki/Gzip
20# Reference: https://tools.ietf.org/html/rfc1952
21# Update: Joerg Jenderek, Apr 2019
22#   Edited by Chris Chittleborough <cchittleborough@yahoo.com.au>, March 2002
23#	* Original filename is only at offset 10 if "extra field" absent
24#	* Produce shorter output - notably, only report compression methods
25#         other than 8 ("deflate", the only method defined in RFC 1952).
26# Note: find defs -iname '*.trid.xml' -exec grep -q '<Bytes>1F8B08' {} \; -ls
27# TODO:
28# FBR	Blueberry FlashBack screen Record	https://www.flashbackrecorder.com/
29# KPR	KOffice/Calligra KPresenter		application/x-kpresenter
30# KPT	KOffice/Calligra KPresenter template?	application/x-kpresenter
31# SAV	Diggles Saved Game File			http://www.innonics.com
32# SAV	FarCry (demo) saved game		http://www.farcry-thegame.com
33# DAT	ZOAGZIP game data format		http://en.wikipedia.org/wiki/SD_Gundam_Capsule_Fighter
340       string          \037\213
35# to display gzip compressed (strength=100=2*50) before other (strength=50)?
36#!:strength * 2
37# no FNAME and FCOMMENT bit implies no file name/comment. That means only binary
38>3	byte&0x18	=0
39# For binary gzipped no ASCII text should occur
40#	mcd-monu-cad.trid.xml
41>>10	string		MCD			Monu-Cad Drawing, Component or Font
42#>>36	string		Created\ with\ MONU-CAD
43#!:mime	application/octet-stream
44# http://fileformats.archiveteam.org/wiki/Monu-CAD
45#	http://www.monucad.com/downloads/FullDemo-2005.EXE
46#	/HANDS96.MCC	Component
47#	/DEMO_DD01.MCD	Drawing
48#	/MCALF020.FNT	Font
49!:ext	mcc/mcd/fnt
50# http://www.generalcadd.com
51>>10	string		GXD			General CADD, Drawing or Component
52#!:mime	application/octet-stream
53#	/gxc/BUILDINGEDGE.gxc			Component
54#	/gxd/HOCKETT-STPAUL-WRHSE.gxd		Drawing
55#	/gxd/POWERLAND-MILL-ADD-11.gxd		Drawing		v9.1.06
56!:ext	gxc/gxd
57#>>>13	ubyte		0			\b, version 0
58>>>13	string		09			\b, version 9
59# other gzipped binary like gzipped tar, VirtualBox extension package,...
60>>10	default		x		gzip compressed data
61!:mime	application/gzip
62>>>0	use	gzip-info
63# size of the original (uncompressed) input data modulo 2^32
64>>-0	offset		>48
65>>>-4	ulelong		x		\b, original size modulo 2^32 %u
66>>-0	offset		<48		\b, truncated
67# gzipped TAR or VirtualBox extension package
68#!:mime	application/x-compressed-tar
69#!:mime	application/x-virtualbox-vbox-extpack
70# https://www.w3.org/TR/SVG/mimereg.html
71#!:mime	image/image/svg+xml-compressed
72#	zlib.3.gz
73#	microcode-20180312.tgz
74#	tpz same as tgz
75#	lua-md5_1.2-1_i386_i486.ipk	https://en.wikipedia.org/wiki/Opkg
76#	Oracle_VM_VirtualBox_Extension_Pack-5.0.12-104815.vbox-extpack
77!:ext	gz/tgz/tpz/ipk/vbox-extpack/svgz
78# FNAME/FCOMMENT bit implies file name/comment as iso-8859-1 text
79>3	byte&0x18	>0		gzip compressed data
80!:mime	application/gzip
81# gzipped tar, gzipped Abiword document
82#!:mime	application/x-compressed-tar
83#!:mime	application/x-abiword-compressed
84#!:mime	image/image/svg+xml-compressed
85#	kleopatra_splashscreen.svgz	gzipped .svg
86!:ext	gz/tgz/tpz/zabw/svgz
87>>0	use	gzip-info
88# size of the original (uncompressed) input data modulo 2^32
89>>-0	offset		>48
90>>>-4	ulelong		x		\b, original size modulo 2^32 %u
91>>-0	offset		<48		\b, truncated
92#	display information of gzip compressed files
930	name				gzip-info
94#>2	byte		x		THIS iS GZIP
95>2	byte		<8		\b, reserved method
96>2	byte		>8		\b, unknown method
97>3	byte		&0x01		\b, ASCII
98>3	byte		&0x02		\b, has CRC
99>3	byte		&0x04		\b, extra field
100>3	byte&0xC	=0x08
101>>10	string		x		\b, was "%s"
102>3	byte		&0x10		\b, has comment
103>3	byte		&0x20		\b, encrypted
104>4	ledate		>0		\b, last modified: %s
105>8	byte		2		\b, max compression
106>8	byte		4		\b, max speed
107>9	byte		=0x00		\b, from FAT filesystem (MS-DOS, OS/2, NT)
108>9	byte		=0x01		\b, from Amiga
109>9	byte		=0x02		\b, from VMS
110>9	byte		=0x03		\b, from Unix
111>9	byte		=0x04		\b, from VM/CMS
112>9	byte		=0x05		\b, from Atari
113>9	byte		=0x06		\b, from HPFS filesystem (OS/2, NT)
114>9	byte		=0x07		\b, from MacOS
115>9	byte		=0x08		\b, from Z-System
116>9	byte		=0x09		\b, from CP/M
117>9	byte		=0x0A		\b, from TOPS/20
118>9	byte		=0x0B		\b, from NTFS filesystem (NT)
119>9	byte		=0x0C		\b, from QDOS
120>9	byte		=0x0D		\b, from Acorn RISCOS
121# size of the original (uncompressed) input data modulo 2^32
122#>-4	ulelong		x		\b, original size modulo 2^32 %u
123#ERROR: line 114: non zero offset 1048572 at level 1
124
125# packed data, Huffman (minimum redundancy) codes on a byte-by-byte basis
1260	string		\037\036	packed data
127!:mime	application/octet-stream
128>2	belong		>1		\b, %d characters originally
129>2	belong		=1		\b, %d character originally
130#
131# This magic number is byte-order-independent.
1320	short		0x1f1f		old packed data
133!:mime	application/octet-stream
134
135# XXX - why *two* entries for "compacted data", one of which is
136# byte-order independent, and one of which is byte-order dependent?
137#
1380	short		0x1fff		compacted data
139!:mime	application/octet-stream
140# This string is valid for SunOS (BE) and a matching "short" is listed
141# in the Ultrix (LE) magic file.
1420	string		\377\037	compacted data
143!:mime	application/octet-stream
1440	short		0145405		huf output
145!:mime	application/octet-stream
146
147# bzip2
1480	string		BZh		bzip2 compressed data
149!:mime	application/x-bzip2
150>3	byte		>47		\b, block size = %c00k
151
152# bzip	a block-sorting file compressor
153#	by Julian Seward <sewardj@cs.man.ac.uk> and others
1540	string		BZ0		bzip compressed data
155!:mime	application/x-bzip
156>3	byte		>47		\b, block size = %c00k
157
158# lzip
1590	string		LZIP		lzip compressed data
160!:mime application/x-lzip
161>4	byte		x		\b, version: %d
162
163# squeeze and crunch
164# Michael Haardt <michael@cantor.informatik.rwth-aachen.de>
1650	beshort		0x76FF		squeezed data,
166>4	string		x		original name %s
1670	beshort		0x76FE		crunched data,
168>2	string		x		original name %s
1690	beshort		0x76FD		LZH compressed data,
170>2	string		x		original name %s
171
172# Freeze
1730	string		\037\237	frozen file 2.1
1740	string		\037\236	frozen file 1.0 (or gzip 0.5)
175
176# SCO compress -H (LZH)
1770	string		\037\240	SCO compress -H (LZH) data
178
179# European GSM 06.10 is a provisional standard for full-rate speech
180# transcoding, prI-ETS 300 036, which uses RPE/LTP (residual pulse
181# excitation/long term prediction) coding at 13 kbit/s.
182#
183# There's only a magic nibble (4 bits); that nibble repeats every 33
184# bytes.  This isn't suited for use, but maybe we can use it someday.
185#
186# This will cause very short GSM files to be declared as data and
187# mismatches to be declared as data too!
188#0	byte&0xF0	0xd0		data
189#>33	byte&0xF0	0xd0
190#>66	byte&0xF0	0xd0
191#>99	byte&0xF0	0xd0
192#>132	byte&0xF0	0xd0		GSM 06.10 compressed audio
193
194# lzop from <markus.oberhumer@jk.uni-linz.ac.at>
1950	string		\x89\x4c\x5a\x4f\x00\x0d\x0a\x1a\x0a	lzop compressed data
196>9	beshort		<0x0940
197>>9	byte&0xf0	=0x00		- version 0.
198>>9	beshort&0x0fff	x		\b%03x,
199>>13	byte		1		LZO1X-1,
200>>13	byte		2		LZO1X-1(15),
201>>13	byte		3		LZO1X-999,
202## >>22	bedate		>0		last modified: %s,
203>>14	byte		=0x00		os: MS-DOS
204>>14	byte		=0x01		os: Amiga
205>>14	byte		=0x02		os: VMS
206>>14	byte		=0x03		os: Unix
207>>14	byte		=0x05		os: Atari
208>>14	byte		=0x06		os: OS/2
209>>14	byte		=0x07		os: MacOS
210>>14	byte		=0x0A		os: Tops/20
211>>14	byte		=0x0B		os: WinNT
212>>14	byte		=0x0E		os: Win32
213>9	beshort		>0x0939
214>>9	byte&0xf0	=0x00		- version 0.
215>>9	byte&0xf0	=0x10		- version 1.
216>>9	byte&0xf0	=0x20		- version 2.
217>>9	beshort&0x0fff	x		\b%03x,
218>>15	byte		1		LZO1X-1,
219>>15	byte		2		LZO1X-1(15),
220>>15	byte		3		LZO1X-999,
221## >>25	bedate		>0		last modified: %s,
222>>17	byte		=0x00		os: MS-DOS
223>>17	byte		=0x01		os: Amiga
224>>17	byte		=0x02		os: VMS
225>>17	byte		=0x03		os: Unix
226>>17	byte		=0x05		os: Atari
227>>17	byte		=0x06		os: OS/2
228>>17	byte		=0x07		os: MacOS
229>>17	byte		=0x0A		os: Tops/20
230>>17	byte		=0x0B		os: WinNT
231>>17	byte		=0x0E		os: Win32
232
233# 4.3BSD-Quasijarus Strong Compression
234# https://minnie.tuhs.org/Quasijarus/compress.html
2350	string		\037\241	Quasijarus strong compressed data
236
237# From: Cory Dikkers <cdikkers@swbell.net>
2380	string		XPKF		Amiga xpkf.library compressed data
2390	string		PP11		Power Packer 1.1 compressed data
2400	string		PP20		Power Packer 2.0 compressed data,
241>4	belong		0x09090909	fast compression
242>4	belong		0x090A0A0A	mediocre compression
243>4	belong		0x090A0B0B	good compression
244>4	belong		0x090A0C0C	very good compression
245>4	belong		0x090A0C0D	best compression
246
247# 7-zip archiver, from Thomas Klausner (wiz@danbala.tuwien.ac.at)
248# https://www.7-zip.org or DOC/7zFormat.txt
249#
2500	string		7z\274\257\047\034	7-zip archive data,
251>6	byte		x			version %d
252>7	byte		x			\b.%d
253!:mime	application/x-7z-compressed
254!:ext 7z/cb7
255
256# Type: LZMA
2570	lelong&0xffffff	=0x5d
258>12	leshort		0xff			LZMA compressed data,
259!:mime	application/x-lzma
260>>5	lequad		=0xffffffffffffffff	streamed
261>>5	lequad		!0xffffffffffffffff	non-streamed, size %lld
262>12	leshort		0			LZMA compressed data,
263>>5	lequad		=0xffffffffffffffff	streamed
264>>5	lequad		!0xffffffffffffffff	non-streamed, size %lld
265
266# http://tukaani.org/xz/xz-file-format.txt
2670	ustring		\xFD7zXZ\x00		XZ compressed data
268!:strength * 2
269!:mime	application/x-xz
270
271# https://github.com/ckolivas/lrzip/blob/master/doc/magic.header.txt
2720	string		LRZI			LRZIP compressed data
273>4	byte		x			- version %d
274>5	byte		x			\b.%d
275!:mime	application/x-lrzip
276
277# https://fastcompression.blogspot.fi/2013/04/lz4-streaming-format-final.html
2780	lelong		0x184d2204	LZ4 compressed data (v1.4+)
279!:mime	application/x-lz4
280# Added by osm0sis@xda-developers.com
2810 	lelong		0x184c2103	LZ4 compressed data (v1.0-v1.3)
282!:mime	application/x-lz4
2830	lelong		0x184c2102	LZ4 compressed data (v0.1-v0.9)
284!:mime	application/x-lz4
285
286# Zstandard/LZ4 skippable frames
287# https://github.com/facebook/zstd/blob/dev/zstd_compression_format.md
2880         lelong&0xFFFFFFF0  0x184D2A50
289>(4.l+8)  indirect	x
290
291# Zstandard Dictionary ID subroutine
2920     name        zstd-dictionary-id
293# Single Segment = True
294>0    byte        &0x20   \b, Dictionary ID:
295>>0   byte&0x03   0       None
296>>0   byte&0x03   1
297>>>1  byte        x       %u
298>>0   byte&0x03   2
299>>>1  leshort     x       %u
300>>0   byte&0x03   3
301>>>1  lelong      x       %u
302# Single Segment = False
303>0    byte        ^0x20   \b, Dictionary ID:
304>>0   byte&0x03   0       None
305>>0   byte&0x03   1
306>>>2  byte        x       %u
307>>0   byte&0x03   2
308>>>2  leshort     x       %u
309>>0   byte&0x03   3
310>>>2  lelong      x       %u
311
312# Zstandard compressed data
313# https://github.com/facebook/zstd/blob/dev/zstd_compression_format.md
3140     lelong       0xFD2FB522  Zstandard compressed data (v0.2)
315!:mime  application/zstd
3160     lelong       0xFD2FB523  Zstandard compressed data (v0.3)
317!:mime  application/zstd
3180     lelong       0xFD2FB524  Zstandard compressed data (v0.4)
319!:mime  application/zstd
3200     lelong       0xFD2FB525  Zstandard compressed data (v0.5)
321!:mime  application/zstd
3220     lelong       0xFD2FB526  Zstandard compressed data (v0.6)
323!:mime  application/zstd
3240     lelong       0xFD2FB527  Zstandard compressed data (v0.7)
325!:mime  application/zstd
326>4    use          zstd-dictionary-id
3270     lelong       0xFD2FB528  Zstandard compressed data (v0.8+)
328!:mime  application/zstd
329>4    use          zstd-dictionary-id
330
331# https://github.com/facebook/zstd/blob/dev/zstd_compression_format.md
3320  lelong    0xEC30A437  Zstandard dictionary
333!:mime  application/x-std-dictionary
334>4 lelong    x           (ID %u)
335
336# AFX compressed files (Wolfram Kleff)
3372	string		-afx-		AFX compressed file data
338
339# Supplementary magic data for the file(1) command to support
340# rzip(1).  The format is described in magic(5).
341#
342# Copyright (C) 2003 by Andrew Tridgell.  You may do whatever you want with
343# this file.
344#
3450	string		RZIP		rzip compressed data
346>4	byte		x		- version %d
347>5	byte		x		\b.%d
348>6	belong		x		(%d bytes)
349
3500	string		ArC\x01		FreeArc archive <http://freearc.org>
351
352# Type:	DACT compressed files
3530	long	0x444354C3	DACT compressed data
354>4	byte	>-1		(version %i.
355>5	byte	>-1		%i.
356>6	byte	>-1		%i)
357>7	long	>0		, original size: %i bytes
358>15	long	>30		, block size: %i bytes
359
360# Valve Pack (VPK) files
3610	lelong	0x55aa1234	Valve Pak file
362>0x4	lelong	x		\b, version %u
363>0x8	lelong	x		\b, %u entries
364
365# Snappy framing format
366# https://code.google.com/p/snappy/source/browse/trunk/framing_format.txt
3670	string	\377\006\0\0sNaPpY	snappy framed data
368!:mime	application/x-snappy-framed
369
370# qpress, https://www.quicklz.com/
3710	string	qpress10	qpress compressed data
372!:mime	application/x-qpress
373
374# Zlib https://www.ietf.org/rfc/rfc6713.txt
3750	string/b	x
376>0	beshort%31	=0
377>>0	byte&0xf	=8
378>>>0	byte&0x80 	=0	zlib compressed data
379!:mime	application/zlib
380
381# BWC compression
3820	string		BWC
383>3	byte		0	BWC compressed data
384
385# UCL compression
3860	bequad		0x00e955434cff011a	UCL compressed data
387
388# Softlib archive
3890	string		SLIB	Softlib archive
390>4	leshort		x	\b, version %d
391>6	leshort		x	(contains %d files)
392
393# URL:  https://github.com/lzfse/lzfse/blob/master/src/lzfse_internal.h#L276
394# From: Eric Hall <eric.hall@darkart.com>
3950	string	bvx-	lzfse encoded, no compression
3960	string	bvx1	lzfse compressed, uncompressed tables
3970	string	bvx2	lzfse compressed, compressed tables
3980	string	bvxn	lzfse encoded, lzvn compressed
399
400# pcxLib.exe compression program
401# http://www.shikadi.net/moddingwiki/PCX_Library
4020	string/b	pcxLib
403>0x0A	string/b	Copyright\020(c)\020Genus\020Microprogramming,\020Inc.	pcxLib compressed
404