xref: /freebsd/contrib/file/magic/Magdir/ispell (revision ae316d1d1cffd71ab7751f94e10118777a88e027)

#------------------------------------------------------------------------------
# $File: ispell,v 1.10 2023/10/23 19:49:58 christos Exp $
# ispell:  file(1) magic for ispell, MySpell, Hunspell and aspell
#
# Ispell 3.0 has a magic of 0x9601 and ispell 3.1 has 0x9602.  This magic
# will match 0x9600 through 0x9603 in *both* little endian and big endian.
# (No other current magic entries collide.)
#
# Updated by Daniel Quinlan (quinlan@yggdrasil.com)
#
0	leshort&0xFFFC	0x9600		little endian ispell
>0	byte		0		hash file (?),
>0	byte		1		3.0 hash file,
>0	byte		2		3.1 hash file,
>0	byte		3		hash file (?),
>2	leshort		0x00		8-bit, no capitalization, 26 flags
>2	leshort		0x01		7-bit, no capitalization, 26 flags
>2	leshort		0x02		8-bit, capitalization, 26 flags
>2	leshort		0x03		7-bit, capitalization, 26 flags
>2	leshort		0x04		8-bit, no capitalization, 52 flags
>2	leshort		0x05		7-bit, no capitalization, 52 flags
>2	leshort		0x06		8-bit, capitalization, 52 flags
>2	leshort		0x07		7-bit, capitalization, 52 flags
>2	leshort		0x08		8-bit, no capitalization, 128 flags
>2	leshort		0x09		7-bit, no capitalization, 128 flags
>2	leshort		0x0A		8-bit, capitalization, 128 flags
>2	leshort		0x0B		7-bit, capitalization, 128 flags
>2	leshort		0x0C		8-bit, no capitalization, 256 flags
>2	leshort		0x0D		7-bit, no capitalization, 256 flags
>2	leshort		0x0E		8-bit, capitalization, 256 flags
>2	leshort		0x0F		7-bit, capitalization, 256 flags
>4	leshort		>0		and %d string characters
0	beshort&0xFFFC	0x9600		big endian ispell
>1	byte		0		hash file (?),
>1	byte		1		3.0 hash file,
>1	byte		2		3.1 hash file,
>1	byte		3		hash file (?),
>2	beshort		0x00		8-bit, no capitalization, 26 flags
>2	beshort		0x01		7-bit, no capitalization, 26 flags
>2	beshort		0x02		8-bit, capitalization, 26 flags
>2	beshort		0x03		7-bit, capitalization, 26 flags
>2	beshort		0x04		8-bit, no capitalization, 52 flags
>2	beshort		0x05		7-bit, no capitalization, 52 flags
>2	beshort		0x06		8-bit, capitalization, 52 flags
>2	beshort		0x07		7-bit, capitalization, 52 flags
>2	beshort		0x08		8-bit, no capitalization, 128 flags
>2	beshort		0x09		7-bit, no capitalization, 128 flags
>2	beshort		0x0A		8-bit, capitalization, 128 flags
>2	beshort		0x0B		7-bit, capitalization, 128 flags
>2	beshort		0x0C		8-bit, no capitalization, 256 flags
>2	beshort		0x0D		7-bit, no capitalization, 256 flags
>2	beshort		0x0E		8-bit, capitalization, 256 flags
>2	beshort		0x0F		7-bit, capitalization, 256 flags
>4	beshort		>0		and %d string characters
# ispell 4.0 hash files  kromJx <kromJx@crosswinds.net>
# Ispell 4.0
0       string          ISPL            ispell
>4      long            x               hash file version %d,
>8      long            x               lexletters %d,
>12     long            x               lexsize %d,
>16     long            x               hashsize %d,
>20     long            x               stblsize %d

# Summary:	affixes defition text files for Ispell/MySpell/Hunspell
# From:		Joerg Jenderek
# URL:		https://www.openoffice.org/lingucomponent/affix.readme
#		https://man.archlinux.org/man/hunspell.5.en
# Reference:	http://mark0.net/download/triddefs_xml.7z/defs/a/affix.trid.xml
# Note:		called "Affix file" by TrID
# variant starting with comment character
0		ubyte		0x23
# look for SET character command followed by whitespace (seems to be often 1 space character) like in:
# /usr/share/calibre/dictionaries/en-GB/en-GB.aff
>0		search/60459	SET\040
# skip scripts like /bin/affixcompress /bin/setupcon /bin/imdbpy2sql.py by checking for valid character SET argument
# character SET argument like: UTF-8
>>&0		string		UTF-8
>>>0		use					spell-aff
# character SET argument like: ISO8859-1 - ISO8859-10 ISO8859-13 - ISO8859-15
>>&0		string		ISO8859-
>>>0		use				spell-aff
# character SET argument for Russian with Cyrillic alphabet like: KOI8-R KOI8-U
# no russian support until war against ukraine
>>&0		string		KOI8-
#>>>0		use				spell-aff
# character SET argument for languages with Cyrillic alphabet like: cp1251
# no cyrillic support until russia war against ukraine
>>&0		string		cp1251
#>>>0		use				spell-aff
# character SET argument for Indian Script Code for Information Interchange (ISCII) like: ISCII-DEVANAGARI
>>&0		string		ISCII-
# no example found
>>>0		use				spell-aff
# not "real" affix rule files but found as tests unit inside thunderbird sources like:
# 1463589.aff 1695964.aff 2970240.aff
>0		default		x
# look for suffix SFX command followed by whitespace like in:
# 1695964.aff
>>0		search/164	SFX\040
>>>0		use				spell-aff
# if not real Hunspell/MySpell affix look for ispell variant
>>0		default		x
# URL:		https://manpages.debian.org/testing/ispell/ispell.5.en.html
# look for ispell declaration like in: /usr/lib/ispell/espanol.aff
>>>0		search/8251	defstringtype
# defstringtype declaration start with unique name (like "list" "lat" "utf8" "iso" "nroff" often like formatter name)
# followed by formatter name (like "nroff" "tex")
# followed by suffix list (like ".mm" ".ms" ".me" ".man" ".NeXT" ".txt" ".list")
#>>>>&1		string		x		DECLARATION=%s
>>>>0		use				spell-aff
# ispell variant without declaration like in: /usr/lib/ispell/bulgarian.aff /usr/lib/ispell/russian.aff
>>>0		default		x
# skip /etc/nilfs_cleanerd.conf by looking for ispell suffix section
>>>>0		search/3233	suffixes\n
>>>>>0		use				spell-aff
# variant starting with empty line and comment character at the beginning of 2nd line like in: /usr/lib/ispell/polish.aff
0		ubeshort	0x0a23
# skip /etc/discover-modprobe.conf by looking for ispell declaration
>2		search/3118	defstringtype
>>0		use				spell-aff
# starting with UTF-8 Byte Order Mark (BOM) https://en.wikipedia.org/wiki/Byte_order_mark
0		string		\xEF\xBB\xBF
# starting with UTF-8 Byte Order Mark (BOM) followed by comment starting character
>3		string		\x23
# starting with UTF-8 BOM and with SET character command followed by whitespace
# like in: /opt/Wolfram/WolframEngine/13.1/SystemFiles/Components/SpellingData/SpellingDictionaries/lt.aff
# look for character SET command used in MySpell and Hunspell
>3		search/9883	SET\040
>>0		use				spell-aff
# look for FLAG type command used in MySpell and Hunspell
0		string		FLAG
# followed by space character like in
# /opt/Wolfram/WolframEngine/13.1/SystemFiles/Components/SpellingData/SpellingDictionaries/en_US.aff
>4		ubyte		0x20
>>0		use				spell-aff
# or followed by tabulator character like in
# /opt/Wolfram/WolframEngine/13.1/SystemFiles/Components/SpellingData/SpellingDictionaries/ar.aff
>4		ubyte		0x09
>>0		use				spell-aff
# starting with character SET command used in MySpell and Hunspell like in: org/languagetool/resource/sv/hunspell/sv_SE.aff
0		string		SET\040
>0		use				spell-aff
# starting with language code LANG used in MySpell and Hunspell like in: /usr/share/hunspell/tr_TR.aff
0		string		LANG\040
>0		use				spell-aff
# starting with affix flag command AF used in MySpell and Hunspell like in: /usr/lib/thunderbird/extensions/langpack-hu@thunderbird.mozilla.org/dictionaries/hu.aff
0		string		AF\040
# look for number of flag vector aliases
>3		regex		[0-9]{1,4}
>>0		use				spell-aff
#	display information (encoding,language,...) about affixes rules text for Ispell/MySpell/Hunspell
0		name				spell-aff
>1		ubeshort	x		affix definition
#!:mime		text/plain
!:mime		text/x-affix
!:ext		aff
# GRR: need extra test so that default clause works
>0		ubyte		x
# look for ispell declaration
>>0		search/8251	defstringtype	for Ispell
# ispell variant without declaration
>>0		default		x
# look for ispell suffixes command
>>>0		search/3233	suffixes
# skip "suffixes used to create first part of a compound" by checking for flag argument like in: languagetool\resource\sv\hunspell\sv_SE.aff
>>>>&0		search/2	flag		for Ispell
>>>>&0		default		x		for MySpell/Hunspell
# without suffixes keyword
>>>0		default		x		for MySpell/Hunspell
# look for language code command used in MySpell and Hunspell
# like in: /usr/share/hunspell/de_AT.aff /usr/share/hunspell/it_IT.aff /usr/share/hunspell/tr_TR.aff /usr/lib/firefox/browser/extensions/langpack-hu@firefox.mozilla.org/dictionaries/hu.aff
>>0		search/1117643	LANG\040	\b, language
# language code argument like: de_DE hu_HU it_IT mn_MN tr_TR
>>>&0		string		x		%s
# look for character SET command used in MySpell and Hunspell
>>0		search/1117729	SET
# skip SETTINGS like in /usr/lib/ispell/ngerman.aff
# SET command followed often by space character (0x20) or tabulator (0x09) like in
# /opt/Wolfram/WolframEngine/13.1/SystemFiles/Components/SpellingData/SpellingDictionaries/ar.aff
>>>&0	ubyte&0xD6	=0x00
# skip SSET	#     schosS in /usr/lib/ispell/ogerman.aff
>>>>&0		ubyte		>0x48		\b,
# character SET argument like: cp1251 ISCII-DEVANAGAR ISO8859-1 - ISO8859-10 ISO8859-13 - ISO8859-15 KOI8-R KOI8-U UTF-8
>>>>>&-1	string	x			"%s" encoded
# for control reasons show first non empty lines for ASCII or ISO-8859 text variant
>1		ubeshort	!0xBBBF
# 1st line starting with 0x0A like in /usr/src/dicts/sjp-ispell-pl-20140213/polish.aff
>>0		ubyte		=0x0A
>>>1		ubyte		!0x0A		\b, 2nd line
>>>>&-1		string		x		"%s"
# 3rd line starting with 0x0A like in polish.aff
>>>>>&1		ubyte		=0x0A
>>>>>>&0	string		x		\b, 4th line "%s"
# 1st line starting with ASCII text like:
# this is the affix file of the de_DE Hunspell dictionary
>>0		ubyte		!0x0A
>>>0		string		x		\b, 1st line "%s"
>>>>&1		ubyte		>0x1F		\b, 2nd line
>>>>>&-1	string		x		"%s"
# 2nd line starting with 0x0A like in /usr/lib/ispell/bulgarian.aff
>>>>&1		ubyte		=0x0A		\b, 3rd line
>>>>>&0		string		x		"%s"
# for control reasons show first lines for variant starting with ByteOrderMark (BOM=\xEF\xBB\xBF)
>1		ubeshort	=0xBBBF	   	\b, with BOM
>>3		string		x		\b, 1st line "%s"
>>>&1		ubyte		>0x1F		\b, 2nd line
>>>>&-1		string		x		"%s"

# From:		Joerg Jenderek
# URL:		https://en.wikipedia.org/wiki/GNU_Aspell
#		https://manpages.ubuntu.com/manpages/trusty/en/man8/aspell-autobuildhash.8.html
# Reference:	http://mark0.net/download/triddefs_xml.7z/defs/r/rws-aspell.trid.xml
#		https://ftp.gnu.org/gnu/aspell/aspell-0.60.8.tar.gz
#		aspell-0.60.8/modules/speller/default/data.cpp
#		aspell-0.60.8/modules/speller/default/readonly_ws.cpp
# Note:		called "aspell dictionary" by TrID
0	string	aspell\040default\040speller\040rowl	aspell dictionary
#!:mime	application/octet-stream
!:mime	application/x-aspell-dictionary
!:ext	rws
# version like: 1.10 1.4
>28	string	x					\b, version %s
# u32int endian_check; 12345678=00BC614Eh
#>64	ulelong	x					\b, endian_check=%u
>>64	ulelong	12345678				\b, little endian
# not tested
>>64	ubelong	12345678				\b, big endian
# older aspell version not like 0.60.8
>>64	default	x					\b, old
# URL:		https://en.wikipedia.org/wiki/GNU_Aspell
# Reference	http://aspell.net/man-html/Format-of-the-Personal-and-Replacement-Dictionaries.html
# personal_ws-1.1 lang num [encoding]
0	string	personal_				aspell personal
# Reference:	http://mark0.net/download/triddefs_xml.7z/defs/p/pws-aspell.trid.xml
# Note:		called "aspell Personal dictionary" by TrID
>9	string	ws-					dictionary
#!:mime	text/plain
!:mime	text/x-aspell-dictionary
# like: ~/.aspell.en.pws ~/.aspell.de_DE.pws ~/.aspell.it.pws
!:ext	pws
# Reference:	http://mark0.net/download/triddefs_xml.7z/defs/p/prepl-aspell.trid.xml
# Note:		called "aspell Personal Replacement dictionary" by TrID
# personal_repl-1.1 lang num [encoding]
>9	string	repl-					replacement dictionary
#!:mime	text/plain
!:mime	text/x-aspell-dictionary
# like: ~/.aspell.en.prepl ~/.aspell.de_DE.prepl ~/.aspell.it.prepl
!:ext	prepl