path: root/contrib/file/magic/Magdir/wordprocessors

#------------------------------------------------------------------------------
# $File: wordprocessors,v 1.27 2021/12/06 15:05:16 christos Exp $
# wordprocessors:  file(1) magic fo word processors.
#
####### PWP file format used on Smith Corona Personal Word Processors:
2	string	\040\040\040\040\040\040\040\040\040\040\040ML4D\040'92	Smith Corona PWP
>24	byte	2	\b, single spaced
>24	byte	3	\b, 1.5 spaced
>24	byte	4	\b, double spaced
>25	byte	0x42	\b, letter
>25	byte	0x54	\b, legal
>26	byte	0x46	\b, A4

# URL:	http://fileformats.archiveteam.org/wiki/Microsoft_Works_Word_Processor
# reference:	http://mark0.net/download/triddefs_xml.7z
#		/defs/w/wps-works-dos.trid.xml
# From:	Joerg Jenderek
# Note:	older non OLE 2 Compound based versions
0	ubeshort	=0x01FE
>112	ubeshort	=0x0100		Microsoft Works 1-3 (DOS) or 2 (Windows) document
# title like THE GREAT KHAN GAME
>>0x100	string		x		%s
!:mime	application/vnd-ms-works
#!:mime	application/x-msworks
# https://www.macdisk.com/macsigen.php
!:apple	????AWWP
!:ext	wps

# Corel/WordPerfect
0	string	\xffWPC
# WordPerfect
>8	byte	1
>>9	byte	1	WordPerfect macro
>>9	byte	2	WordPerfect help file
>>9	byte	3	WordPerfect keyboard file
>>9	byte	10	WordPerfect document
>>9	byte	11	WordPerfect dictionary
>>9	byte	12	WordPerfect thesaurus
>>9	byte	13	WordPerfect block
>>9	byte	14	WordPerfect rectangular block
>>9	byte	15	WordPerfect column block
>>9	byte	16	WordPerfect printer data
>>9	byte	19	WordPerfect printer data
>>9	byte	20	WordPerfect driver resource data
>>9	byte	22	WordPerfect graphic image
>>9	byte	23	WordPerfect hyphenation code
>>9	byte	24	WordPerfect hyphenation data
>>9	byte	25	WordPerfect macro resource data
>>9	byte	27	WordPerfect hyphenation lex
>>9	byte	29	WordPerfect wordlist
>>9	byte	30	WordPerfect equation resource data
>>9	byte	33	WordPerfect spell rules
>>9	byte	34	WordPerfect dictionary rules
>>9	byte	39	WordPerfect spell rules (Microlytics)
>>9	byte	43	WordPerfect settings file
>>9	byte	44	WordPerfect 3.5 document
>>9	byte	45	WordPerfect 4.2 document
>>9	byte	69	WordPerfect dialog file
>>9	byte	76	WordPerfect button bar
>>9	default x
>>>9	byte	x	Corel WordPerfect: Unknown filetype %d
# Corel Shell
>8	byte	2
>>9	byte	1	Corel shell macro
>>9	byte	10	Corel shell definition
>>9	default x
>>>9	byte	x	Corel Shell: Unknown filetype %d
# Corel Notebook
>8	byte	3
>>9	byte	1	Corel Notebook macro
>>9	byte	2	Corel Notebook help file
>>9	byte	3	Corel Notebook keyboard file
>>9	byte	10	Corel Notebook definition
>>9	default	x
>>>9	byte	x	Corel Notebook: Unknown filetype %d
# Corel Calculator
>8	byte	4
>>9	byte	2	Corel Calculator help file
>>9	default	x
>>>9	byte	x	Corel Calculator: Unknown filetype %d
# Corel File Manager
>8	byte	5
>>9	default	x
>>>9	byte	x	Corel File Manager: Unknown filetype %d
# Corel Calendar
>8	byte	6
>>9	byte 	2	Corel Calendar help file
>>9	byte 	10	Corel Calendar data file
>>9	default	x
>>>9	byte	x	Corel Calendar: Unknown filetype %d
# Corel Program Editor/Ed Editor
>8	byte	7
>>9	byte	1	Corel Editor macro
>>9	byte	2	Corel Editor help file
>>9	byte	3	Corel Editor keyboard file
>>9	byte	25	Corel Editor macro resource file
>>9	default	x
>>>9	byte	x	Corel Program Editor/Ed Editor: Unknown filetype %d
# Corel Macro Editor
>8	byte	8
>>9	byte 	1	Corel Macro editor macro
>>9	byte 	2	Corel Macro editor help file
>>9	byte	3	Corel Macro editor keyboard file
>>9	default	x
>>>9	byte	x	Corel Macro Editor: Unknown filetype %d
# Corel Plan Perfect
>8	byte	9
>>9	default	x
>>>9	byte	x	Corel Plan Perfect: Unknown filetype %d
# Corel DataPerfect
>8	byte	10
# CHECK: Don't these belong into product 9?
>>9	byte	1	Corel PlanPerfect macro
>>9	byte	2	Corel PlanPerfect help file
>>9	byte	3	Corel PlanPerfect keyboard file
>>9	byte	10	Corel PlanPerfect worksheet
>>9	byte	15	Corel PlanPerfect printer definition
>>9	byte	18	Corel PlanPerfect graphic definition
>>9	byte	19	Corel PlanPerfect data
>>9	byte	20	Corel PlanPerfect temporary printer
>>9	byte	25	Corel PlanPerfect macro resource data
>>9	default	x
>>>9	byte	x	Corel DataPerfect: Unknown filetype %d
# Corel Mail
>8	byte	11
>>9	byte	2	Corel Mail help file
>>9	byte	5	Corel Mail distribution list
>>9	byte	10	Corel Mail out box
>>9	byte	11	Corel Mail in box
>>9	byte	20	Corel Mail users archived mailbox
>>9	byte	21	Corel Mail archived message database
>>9	byte	22	Corel Mail archived attachments
>>9	default	x
>>>9	byte	x	Corel Mail: Unknown filetype %d
# Corel Printer
>8	byte	12
>>9	byte	11	Corel Printer temporary file
>>9	default	x
>>>9	byte	x	Corel Printer: Unknown filetype %d
# Corel Scheduler
>8	byte	13
>>9	byte	2	Corel Scheduler help file
>>9	byte	10	Corel Scheduler in file
>>9	byte	11	Corel Scheduler out file
>>9	default	x
>>>9	byte	x	Corel Scheduler: Unknown filetype %d
# Corel WordPerfect Office
>8	byte	14
>>9	byte	10	Corel GroupWise settings file
>>9	byte	17	Corel GroupWise directory services
>>9	byte	43	Corel GroupWise settings file
>>9	default	x
>>>9	byte	x	Corel WordPerfect Office: Unknown filetype %d
# Corel DrawPerfect
>8	byte	15
>>9	default	x
>>>9	byte	x	Corel DrawPerfect: Unknown filetype %d
# Corel LetterPerfect
>8	byte	16
>>9	default	x
>>>9	byte	x	Corel LetterPerfect: Unknown filetype %d
# Corel Terminal
>8	byte	17
>>9	byte	10	Corel Terminal resource data
>>9	byte	11	Corel Terminal resource data
>>9	byte	43	Corel Terminal resource data
>>9	default	x
>>>9	byte	x	Corel Terminal: Unknown filetype %d
# Corel loadable file
>8	byte	18
>>9	byte	10	Corel loadable file
>>9	byte	11	Corel GUI loadable text
>>9	byte	12	Corel graphics resource data
>>9	byte	13	Corel printer settings file
>>9	byte	14	Corel port definition file
>>9	byte	15	Corel print queue parameters
>>9	byte	16	Corel compressed file
>>9	default	x
>>>9	byte	x	Corel loadable file: Unknown filetype %d
>>15	byte	0	\b, optimized for Intel
>>15	byte	1	\b, optimized for Non-Intel
# Network service
>8	byte	20
>>9	byte	10	Corel Network service msg file
>>9	byte	11	Corel Network service msg file
>>9	byte	12	Corel Async gateway login msg
>>9	byte	14	Corel GroupWise message file
>>9	default	x
>>>9	byte	x	Corel Network service: Unknown filetype %d
# GroupWise
>8	byte	31
>>9	byte	20	GroupWise admin domain database
>>9	byte	21	GroupWise admin host database
>>9	byte	23	GroupWise admin remote host database
>>9	byte	24	GroupWise admin ADS deferment data file
>>9	default	x
>>>9	byte	x	GroupWise: Unknown filetype %d
# IntelliTAG
>8	byte	33
>>9	byte	10	IntelliTAG (SGML) compiled DTD
>>9	default	x
>>>9	byte	x	IntelliTAG: Unknown filetype %d
# everything else
>8	default x
>>8	byte	x	Unknown Corel/Wordperfect product %d,
>>>9	byte	x	file type %d
>10	byte	0	\b, v5.
>10	byte	!0	\b, v%d.
>11	byte	x	\b%d

# Hangul (Korean) Word Processor File
0	string	HWP\ Document\ File	Hangul (Korean) Word Processor File 3.0

# CosmicBook, from Benoit Rouits
0       string  CSBK    Ted Neslson's CosmicBook hypertext file

2       string  EYWR    AmigaWriter file

# chi:  file(1) magic for ChiWriter files
0       string          \\1cw\          ChiWriter file
>5      string          >\0             version %s
0       string          \\1cw           ChiWriter file

# Quark Express from https://www.garykessler.net/library/file_sigs.html
2	string	IIXPR3			Intel Quark Express Document (English)
2	string	IIXPRa			Intel Quark Express Document (Korean)
2	string	MMXPR3			Motorola Quark Express Document (English)
!:mime	application/x-quark-xpress-3
2	string	MMXPRa			Motorola Quark Express Document (Korean)

# From:		Joerg Jenderek
# URL:		http://fileformats.archiveteam.org/wiki/PageMaker
#		https://en.wikipedia.org/wiki/Adobe_PageMaker
# Reference:	http://mark0.net/download/triddefs_xml.7z/defs/p
#		pm4-pagemaker.trid.xml
#		pm5-pagemaker.trid.xml
# Note:		since version 6 in 1995 called Adobe PageMaker and
#		embedded in Compound Document handled by ./ole2compounddocs
#		mainly tested little endian variant
4	ubelong		=0x0000FF99
>0	use		PageMaker
# big endian variant
4	ubelong		=0x000099FF
>0	use		\^PageMaker
#	display information of Aldus/Adobe PageMaker document/publication
0	name		PageMaker
>110	uleshort	<0x0600			Aldus
>110	uleshort	>0x05FF			Adobe
>110	uleshort	x			PageMaker
# "MP" marker for newer version 4 and above according to TrID
#>108	string		x			\b, MARKER "%.2s"
# http://www.nationalarchives.gov.uk/pronom/fmt/876
!:mime		application/vnd.pagemaker	
#!:mime		application/x-pagemaker
# different file name extensions are used depending on version
# older version like 3
>110	uleshort/256	=0			document
# https://www.macdisk.com/macsigen.php
!:apple	ALB3ALD3
# PT3 for template and no example for PageMaker document/publiction with PM3 extension
!:ext	pm3/pt3
>110	uleshort/256	=4			document
!:apple	ALD4ALB4
# no example for PT4 template
!:ext	pm4/pt4
>110	uleshort/256	=5			document
!:apple	ALD5ALB5
# no example for PT5 template
!:ext	pm5/pt5
>110	uleshort	=0x0600			document
!:apple	ALD6ALB6
# PT6 for template
!:ext	pm6/pt6
# HOWTO to distinguish version 7 from 6.5 ?
>110	uleshort	=0x0632			document
!:apple	AD65AB65
# no example for T65 template
!:ext	p65/t65/pmd/pmt
# version 7 with PMT extension for template
#!:ext	pmd/pmt
#!:apple	????PUBF
# endian marker FF 99 for little endian
>6	ubyte	=0xFF			\b, little-endian
>6	ubyte	=0x99			\b, big-endian
# newer numeric version like: 4 5 6 6.50
#>110	uleshort	x			\b, VERSION=%#x
>110	uleshort	>0x03FF
>>110	uleshort/256	x			\b, version %u
>>110	uleshort%256	>0			\b.%u
# older version like 3
>110	uleshort	<0x0400			\b, maybe version 3

# adobe indesign (document, whatever...) from querkan
0	belong	0x0606edf5		Adobe InDesign
>16	string	DOCUMENT		Document

#------------------------------------------------------------------------------
# ichitaro456: file(1) magic for Just System Word Processor Ichitaro
#
# Contributor kenzo-:
# Reversed-engineered JS Ichitaro magic numbers
#

0	string		DOC
>43	byte		0x14	Just System Word Processor Ichitaro v4
!:mime	application/x-ichitaro4
>144	string	JDASH		application/x-ichitaro4

0	string		DOC
>43	byte		0x15	Just System Word Processor Ichitaro v5
!:mime	application/x-ichitaro5

0	string		DOC
>43	byte		0x16	Just System Word Processor Ichitaro v6
!:mime	application/x-ichitaro6

# Type: Freemind mindmap documents
# From: Jamie Thompson <debian-bugs@jamie-thompson.co.uk>
0	string/w	\<map\ version	Freemind document
!:mime	application/x-freemind

# Type: Freeplane mindmap documents
# From: Felix Natter <fnatter@gmx.net>
0       string/w        \<map\ version="freeplane  Freeplane document
!:mime  application/x-freeplane

# Type:        Scribus
# From:        Werner Fink <werner@suse.de>
0	string	\<SCRIBUSUTF8\ Version		Scribus Document
0	string	\<SCRIBUSUTF8NEW\ Version	Scribus Document
!:mime	application/x-scribus

# help files .hlp compiled from html and used by gfxboot added by Joerg Jenderek
# markups page=0x04,label=0x12, followed by strings like "opt" or "main" and title=0x14
0	ulelong&0x8080FFFF	0x00001204	gfxboot compiled html help file

# From:		Joerg Jenderek
# URL:		https://en.wikipedia.org/wiki/StarOffice
# Reference:	http://mark0.net/download/triddefs_xml.7z
#		/defs/t/thm-staroffice.trid.xml
# Note:		used in Star-, Open- and Libre-Office
# named as soffice.StarConfigFile.6 or OpenOffice.org configuration by others
0		ubeshort	0x0400
# non nil gap
#>(2.s+8)	ubequad		x		\b, gap %#16.16llx
# test for null value in gap after theme name maybe unreliable
#>(2.s+9)	ubyte		0		\b, 0-byte
# look for keyword GALRESRV near the end
# "C:\Program Files (x86)\StarOffice6.0\share\gallery\sg27.thm" Navigation, 238 objects
#>0		search/8415	GALRESRV	\b, GALRESRV found
# "neues thema6.thm" MorePictures, 315 objects
#>0		search/19299	GALRESRV	\b, GALRESRV FOUND
#>2		uleshort	x		\b, name length %u
# skip file2147.chk by check for positive name length like for sg16.thm "3D"
>2		uleshort	>0
# skip dBase printer form T6.PRF with misidentified gallery 
# name :\DBASE\IV\T6.txts by check for 1st object name or RESRV keyword
# https://www.clicketyclick.dk/databases/xbase/xbase/dbase_ex.zip
# template/t6/with_data/T6.PRF
# by first char of object name or RESRV part of keyword GALRESRV
>>(2.s+13)	ubyte		>0x1F		StarOffice Gallery theme
!:mime		application/x-stargallery-thm
# thm is also used for JPEG thumbnail images
!:ext		thm
# gallery name often 1 word like: 3D sounds Diagrams Flussdiagramme Fotos
# or like private://gallery/hidden/imgppt "Cisco - WAN - LAN"
>>>2		pstring/h	x		%s
# number of objects
>>>(2.s+4)	ulelong		x		\b, %u object
# plural s
>>>(2.s+4)	ulelong		!1		\bs
# if available then display first object name 
>>>(2.s+4)	ulelong		>0
# partial file name, URL or internal name like "dd2*" of 1st object or RESRV
>>>>(2.s+11)	pstring/h	x		\b, 1st %s

# From:	Joerg Jenderek
# URL:	http://fileformats.archiveteam.org/wiki/StarOffice_Gallery
# Note:	used in Star-, Open- and Libre-Office and found in directories like
#	%APPDATA%\Roaming\LibreOffice\4\user\gallery
#	$HOME/.config/libreoffice/4/user/gallery
0	string		SGA3	StarOffice Gallery thumbnails
# Unknown like 0x04000?0001000142
#>4	ubequad		x	\b, UNKNOWN %#16.16llx
#!:mime	application/x-sdg
!:mime	application/x-stargallery-sdg
!:ext	sdg
# display image magic for debugging purpose like 'BM'
# looking like PC bitmap, Windows 3.x format with unknown compression
#>11	string		x	\b, image magic '%-.2s'
# inspect 1st GALLERY thumbnail magic by ./images with 1 space at end
#>11	indirect	x	\b; contains