# $File: compress,v 1.91 2023/06/16 19:37:47 christos Exp $

#------------------------------------------------------------------------------
# $File: compress,v 1.91 2023/06/16 19:37:47 christos Exp $
# compress: file(1) magic for pure-compression formats (no archives)
#
# compress, gzip, pack, compact, huf, squeeze, crunch, freeze, yabba, etc.
#
# Formats for various forms of compressed data
# Formats for "compress" proper have been moved into "compress.c",
# because it tries to uncompress it to figure out what's inside.

# standard unix compress
0 string \037\235 compress'd data
!:mime application/x-compress
!:apple LZIVZIVU
!:ext Z
>2 byte&0x80 >0 block compressed
>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, Dec 2022
# Edited by Chris Chittleborough <[email protected]>, 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).
# 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
!:mime application/gzip
>>>0 use gzip-info
# size of the original (uncompressed) input data modulo 2^32
# TODO: check for GXD MCD cad the reported size
>>>-4 ulelong x \b, original size modulo 2^32 %u
# gzipped TAR or VirtualBox extension package
#!:mime application/x-compressed-tar
#!:mime application/x-virtualbox-vbox-extpack
# https://www.w3.org/TR/SVG/mimereg.html
#!:mime 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
# trees.blend http://fileformats.archiveteam.org/wiki/BLEND
# 2020-07-19-Note-16-24.xoj https://xournal.sourceforge.net/manual.html
# MYgnucash-gz.gnucash https://wiki.gnucash.org/wiki/GnuCash_XML_format
# text-rotate.dia https://en.wikipedia.org/wiki/Dia_(software)
# MYrdata.RData https://en.wikipedia.org/wiki/R_(programming_language)
!:ext gz/tgz/tpz/ipk/vbox-extpack/svgz/blend/dia/gnucash/rdata/xoj
# 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
# RSI-Mega-Demo_Disk1.adz gzipped .adf http://fileformats.archiveteam.org/wiki/ADF_(Amiga)
# PostbankTest.kmy gzipped XML https://docs.kde.org/stable5/en/kmymoney/kmymoney/details.formats.compressed.html
# Logo.xcfgz gzipped .xcf http://fileformats.archiveteam.org/wiki/XCF
!:ext gz/tgz/tpz/zabw/svgz/adz/kmy/xcfgz
>>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
>3 byte &0x02 \b, has CRC
>3 byte &0x04 \b, extra field
>3 byte&0xC =0x08
>>10 string x \b, was "%s"
>3 byte &0x10 \b, has comment
>3 byte &0x20 \b, encrypted
>4 ledate >0 \b, last modified: %s
>8 byte 2 \b, max compression
>8 byte 4 \b, max speed
>9 byte =0x00 \b, from FAT filesystem (MS-DOS, OS/2, NT)
>9 byte =0x01 \b, from Amiga
>9 byte =0x02 \b, from VMS
>9 byte =0x03 \b, from Unix
>9 byte =0x04 \b, from VM/CMS
>9 byte =0x05 \b, from Atari
>9 byte =0x06 \b, from HPFS filesystem (OS/2, NT)
>9 byte =0x07 \b, from MacOS
>9 byte =0x08 \b, from Z-System
>9 byte =0x09 \b, from CP/M
>9 byte =0x0A \b, from TOPS/20
>9 byte =0x0B \b, from NTFS filesystem (NT)
>9 byte =0x0C \b, from QDOS
>9 byte =0x0D \b, from Acorn RISCOS
# 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
!:mime application/octet-stream
!:ext z
>2 belong >1 \b, %d characters originally
>2 belong =1 \b, %d character originally
#
# This magic number is byte-order-independent.
0 short 0x1f1f old packed data
!:mime application/octet-stream

# XXX - why *two* entries for "compacted data", one of which is
# byte-order independent, and one of which is byte-order dependent?
#
0 short 0x1fff compacted data
!:mime application/octet-stream
# This string is valid for SunOS (BE) and a matching "short" is listed
# in the Ultrix (LE) magic file.
0 string \377\037 compacted data
!:mime application/octet-stream
0 short 0145405 huf output
!:mime application/octet-stream

# bzip2
0 string BZh bzip2 compressed data
!:mime application/x-bzip2
!:ext bz2
>3 byte >47 \b, block size = %c00k

# bzip a block-sorting file compressor
# by Julian Seward <[email protected]> and others
0 string BZ0 bzip compressed data
!:mime application/x-bzip
>3 byte >47 \b, block size = %c00k

# lzip
0 string LZIP lzip compressed data
!:mime application/x-lzip
!:ext lz
>4 byte x \b, version: %d

# squeeze and crunch
# Michael Haardt <[email protected]>
0 beshort 0x76FF squeezed data,
>4 string x original name %s
0 beshort 0x76FE crunched data,
>2 string x original name %s
0 beshort 0x76FD LZH compressed data,
>2 string x original name %s

# Freeze
0 string \037\237 frozen file 2.1
0 string \037\236 frozen file 1.0 (or gzip 0.5)

# SCO compress -H (LZH)
0 string \037\240 SCO compress -H (LZH) data

# European GSM 06.10 is a provisional standard for full-rate speech
# transcoding, prI-ETS 300 036, which uses RPE/LTP (residual pulse
# excitation/long term prediction) coding at 13 kbit/s.
#
# There's only a magic nibble (4 bits); that nibble repeats every 33
# bytes. This isn't suited for use, but maybe we can use it someday.
#
# This will cause very short GSM files to be declared as data and
# mismatches to be declared as data too!
#0 byte&0xF0 0xd0 data
#>33 byte&0xF0 0xd0
#>66 byte&0xF0 0xd0
#>99 byte&0xF0 0xd0
#>132 byte&0xF0 0xd0 GSM 06.10 compressed audio

# lzop from <[email protected]>
0 string \x89\x4c\x5a\x4f\x00\x0d\x0a\x1a\x0a lzop compressed data
!:ext lzo
>9 beshort <0x0940
>>9 byte&0xf0 =0x00 - version 0.
>>9 beshort&0x0fff x \b%03x,
>>13 byte 1 LZO1X-1,
>>13 byte 2 LZO1X-1(15),
>>13 byte 3 LZO1X-999,
## >>22 bedate >0 last modified: %s,
>>14 byte =0x00 os: MS-DOS
>>14 byte =0x01 os: Amiga
>>14 byte =0x02 os: VMS
>>14 byte =0x03 os: Unix
>>14 byte =0x05 os: Atari
>>14 byte =0x06 os: OS/2
>>14 byte =0x07 os: MacOS
>>14 byte =0x0A os: Tops/20
>>14 byte =0x0B os: WinNT
>>14 byte =0x0E os: Win32
>9 beshort >0x0939
>>9 byte&0xf0 =0x00 - version 0.
>>9 byte&0xf0 =0x10 - version 1.
>>9 byte&0xf0 =0x20 - version 2.
>>9 beshort&0x0fff x \b%03x,
>>15 byte 1 LZO1X-1,
>>15 byte 2 LZO1X-1(15),
>>15 byte 3 LZO1X-999,
## >>25 bedate >0 last modified: %s,
>>17 byte =0x00 os: MS-DOS
>>17 byte =0x01 os: Amiga
>>17 byte =0x02 os: VMS
>>17 byte =0x03 os: Unix
>>17 byte =0x05 os: Atari
>>17 byte =0x06 os: OS/2
>>17 byte =0x07 os: MacOS
>>17 byte =0x0A os: Tops/20
>>17 byte =0x0B os: WinNT
>>17 byte =0x0E os: Win32

# 4.3BSD-Quasijarus Strong Compression
# https://minnie.tuhs.org/Quasijarus/compress.html
0 string \037\241 Quasijarus strong compressed data

# From: Cory Dikkers <[email protected]>
0 string XPKF Amiga xpkf.library compressed data
0 string PP11 Power Packer 1.1 compressed data
0 string PP20 Power Packer 2.0 compressed data,
>4 belong 0x09090909 fast compression
>4 belong 0x090A0A0A mediocre compression
>4 belong 0x090A0B0B good compression
>4 belong 0x090A0C0C very good compression
>4 belong 0x090A0C0D best compression

# 7-zip archiver, from Thomas Klausner ([email protected])
# https://www.7-zip.org or DOC/7zFormat.txt
#
0 string 7z\274\257\047\034 7-zip archive data,
>6 byte x version %d
>7 byte x \b.%d
!:mime application/x-7z-compressed
!:ext 7z/cb7

0 name lzma LZMA compressed data,
!:mime application/x-lzma
!:ext lzma
>5 lequad =0xffffffffffffffff streamed
>5 lequad !0xffffffffffffffff non-streamed, size %lld

# Type: LZMA
0 lelong&0xffffff =0x5d
>12 leshort 0xff
>>0 use lzma
>12 leshort 0
>>0 use lzma

# http://tukaani.org/xz/xz-file-format.txt
0 ustring \xFD7zXZ\x00 XZ compressed data, checksum
!:strength * 2
!:mime application/x-xz
!:ext xz
>7 byte&0xf 0x0 NONE
>7 byte&0xf 0x1 CRC32
>7 byte&0xf 0x4 CRC64
>7 byte&0xf 0xa SHA-256

# https://github.com/ckolivas/lrzip/blob/master/doc/magic.header.txt
0 string LRZI LRZIP compressed data
!:mime application/x-lrzip
>4 byte x - version %d
>5 byte x \b.%d
>22 byte 1 \b, encrypted

# https://fastcompression.blogspot.fi/2013/04/lz4-streaming-format-final.html
0 lelong 0x184d2204 LZ4 compressed data (v1.4+)
!:mime application/x-lz4
!:ext lz4
# Added by [email protected]
0 lelong 0x184c2103 LZ4 compressed data (v1.0-v1.3)
!:mime application/x-lz4
0 lelong 0x184c2102 LZ4 compressed data (v0.1-v0.9)
!:mime application/x-lz4

# Zstandard/LZ4 skippable frames
# https://github.com/facebook/zstd/blob/dev/zstd_compression_format.md
0 lelong&0xFFFFFFF0 0x184D2A50
>(4.l+8) indirect x

# Zstandard Dictionary ID subroutine
0 name zstd-dictionary-id
# Single Segment = True
>0 byte &0x20 \b, Dictionary ID:
>>0 byte&0x03 0 None
>>0 byte&0x03 1
>>>1 byte x %u
>>0 byte&0x03 2
>>>1 leshort x %u
>>0 byte&0x03 3
>>>1 lelong x %u
# Single Segment = False
>0 byte ^0x20 \b, Dictionary ID:
>>0 byte&0x03 0 None
>>0 byte&0x03 1
>>>2 byte x %u
>>0 byte&0x03 2
>>>2 leshort x %u
>>0 byte&0x03 3
>>>2 lelong x %u

# Zstandard compressed data
# https://github.com/facebook/zstd/blob/dev/zstd_compression_format.md
0 lelong 0xFD2FB522 Zstandard compressed data (v0.2)
!:mime application/zstd
!:ext zst
0 lelong 0xFD2FB523 Zstandard compressed data (v0.3)
!:mime application/zstd
!:ext zst
0 lelong 0xFD2FB524 Zstandard compressed data (v0.4)
!:mime application/zstd
!:ext zst
0 lelong 0xFD2FB525 Zstandard compressed data (v0.5)
!:mime application/zstd
!:ext zst
0 lelong 0xFD2FB526 Zstandard compressed data (v0.6)
!:mime application/zstd
!:ext zst
0 lelong 0xFD2FB527 Zstandard compressed data (v0.7)
!:mime application/zstd
!:ext zst
>4 use zstd-dictionary-id
0 lelong 0xFD2FB528 Zstandard compressed data (v0.8+)
!:mime application/zstd
!:ext zst
>4 use zstd-dictionary-id

# https://github.com/facebook/zstd/blob/dev/zstd_compression_format.md
0 lelong 0xEC30A437 Zstandard dictionary
!:mime application/x-std-dictionary
>4 lelong x (ID %u)

# AFX compressed files (Wolfram Kleff)
2 string -afx- AFX compressed file data

# Supplementary magic data for the file(1) command to support
# rzip(1). The format is described in magic(5).
#
# Copyright (C) 2003 by Andrew Tridgell. You may do whatever you want with
# this file.
#
0 string RZIP rzip compressed data
>4 byte x - version %d
>5 byte x \b.%d
>6 belong x (%d bytes)

0 string ArC\x01 FreeArc archive <http://freearc.org>

# Type: DACT compressed files
0 long 0x444354C3 DACT compressed data
>4 byte >-1 (version %i.
>5 byte >-1 %i.
>6 byte >-1 %i)
>7 long >0 , original size: %i bytes
>15 long >30 , block size: %i bytes

# Valve Pack (VPK) files
0 lelong 0x55aa1234 Valve Pak file
>0x4 lelong x \b, version %u
>0x8 lelong x \b, %u entries

# Snappy framing format
# https://code.google.com/p/snappy/source/browse/trunk/framing_format.txt
0 string \377\006\0\0sNaPpY snappy framed data
!:mime application/x-snappy-framed

# qpress, https://www.quicklz.com/
0 string qpress10 qpress compressed data
!:mime application/x-qpress

# Zlib https://www.ietf.org/rfc/rfc6713.txt
0 string/b x
>0 beshort%31 =0
>>0 byte&0xf =8
>>>0 byte&0x80 =0 zlib compressed data
!:mime application/zlib

# BWC compression
0 string BWC
>3 byte 0 BWC compressed data

# UCL compression
0 bequad 0x00e955434cff011a UCL compressed data

# Softlib archive
0 string SLIB Softlib archive
>4 leshort x \b, version %d
>6 leshort x (contains %d files)

# URL: https://github.com/lzfse/lzfse/blob/master/src/lzfse_internal.h#L276
# From: Eric Hall <[email protected]>
0 string bvx- lzfse encoded, no compression
0 string bvx1 lzfse compressed, uncompressed tables
0 string bvx2 lzfse compressed, compressed tables
0 string bvxn lzfse encoded, lzvn compressed

# pcxLib.exe compression program
# http://www.shikadi.net/moddingwiki/PCX_Library
0 string/b pcxLib
>0x0A string/b Copyright\020(c)\020Genus\020Microprogramming,\020Inc. pcxLib compressed

# https://support-docs.illumina.com/SW/ORA_Format_Specification/Content/SW/ORA/ORAFormatSpecification.htm
0 uleshort 0x7c49
>2 lelong 0x80 ORA FASTQ compressed file
>>6 ulelong x \b, DNA size %u
>>10 ulelong x \b, read names size %u
>>14 ulelong x \b, quality buffer 1 size %u
>>18 ulelong x \b, quality buffer 2 size %u
>>22 ulelong x \b, sequence buffer size %u
>>26 ulelong x \b, N-position buffer size %u
>>30 ulelong x \b, crypto buffer size %u
>>34 ulelong x \b, misc buffer 1 size %u
>>38 ulelong x \b, misc buffer 2 size %u
>>42 ulelong x \b, flags %#x
>>46 lelong x \b, read size %d
>>50 lelong x \b, number of reads %d
>>54 leshort x \b, version %d

# https://github.com/kspalaiologos/bzip3/blob/master/doc/file_format.md
0 string/b BZ3v1 bzip3 compressed data
>5 ulelong x \b, blocksize %u

# https://support-docs.illumina.com/SW/ORA_Format_Specification/Content/\
# SW/ORA/ORAFormatSpecification.htm
# From Guillaume Rizk
0 short =0x7C49 DRAGEN ORA file,
>-261 short =0x7C49 with metadata:
>-125 u8 x NB reads: %llu,
>-109 u8 x NB bases: %llu.
>-219 u4&0x02 2 File contains interleaved paired reads