1 2#------------------------------------------------------------------------------ 3# $File: ispell,v 1.11 2026/04/16 18:06:17 christos Exp $ 4# ispell: file(1) magic for ispell, MySpell, Hunspell and aspell 5# 6# Ispell 3.0 has a magic of 0x9601 and ispell 3.1 has 0x9602. This magic 7# will match 0x9600 through 0x9603 in *both* little endian and big endian. 8# (No other current magic entries collide.) 9# 10# Updated by Daniel Quinlan (quinlan@yggdrasil.com) 11# 120 leshort&0xFFFC 0x9600 little endian ispell 13>0 byte 0 hash file (?), 14>0 byte 1 3.0 hash file, 15>0 byte 2 3.1 hash file, 16>0 byte 3 hash file (?), 17>2 leshort 0x00 8-bit, no capitalization, 26 flags 18>2 leshort 0x01 7-bit, no capitalization, 26 flags 19>2 leshort 0x02 8-bit, capitalization, 26 flags 20>2 leshort 0x03 7-bit, capitalization, 26 flags 21>2 leshort 0x04 8-bit, no capitalization, 52 flags 22>2 leshort 0x05 7-bit, no capitalization, 52 flags 23>2 leshort 0x06 8-bit, capitalization, 52 flags 24>2 leshort 0x07 7-bit, capitalization, 52 flags 25>2 leshort 0x08 8-bit, no capitalization, 128 flags 26>2 leshort 0x09 7-bit, no capitalization, 128 flags 27>2 leshort 0x0A 8-bit, capitalization, 128 flags 28>2 leshort 0x0B 7-bit, capitalization, 128 flags 29>2 leshort 0x0C 8-bit, no capitalization, 256 flags 30>2 leshort 0x0D 7-bit, no capitalization, 256 flags 31>2 leshort 0x0E 8-bit, capitalization, 256 flags 32>2 leshort 0x0F 7-bit, capitalization, 256 flags 33>4 leshort >0 and %d string characters 340 beshort&0xFFFC 0x9600 big endian ispell 35>1 byte 0 hash file (?), 36>1 byte 1 3.0 hash file, 37>1 byte 2 3.1 hash file, 38>1 byte 3 hash file (?), 39>2 beshort 0x00 8-bit, no capitalization, 26 flags 40>2 beshort 0x01 7-bit, no capitalization, 26 flags 41>2 beshort 0x02 8-bit, capitalization, 26 flags 42>2 beshort 0x03 7-bit, capitalization, 26 flags 43>2 beshort 0x04 8-bit, no capitalization, 52 flags 44>2 beshort 0x05 7-bit, no capitalization, 52 flags 45>2 beshort 0x06 8-bit, capitalization, 52 flags 46>2 beshort 0x07 7-bit, capitalization, 52 flags 47>2 beshort 0x08 8-bit, no capitalization, 128 flags 48>2 beshort 0x09 7-bit, no capitalization, 128 flags 49>2 beshort 0x0A 8-bit, capitalization, 128 flags 50>2 beshort 0x0B 7-bit, capitalization, 128 flags 51>2 beshort 0x0C 8-bit, no capitalization, 256 flags 52>2 beshort 0x0D 7-bit, no capitalization, 256 flags 53>2 beshort 0x0E 8-bit, capitalization, 256 flags 54>2 beshort 0x0F 7-bit, capitalization, 256 flags 55>4 beshort >0 and %d string characters 56# ispell 4.0 hash files kromJx <kromJx@crosswinds.net> 57# Ispell 4.0 580 string ISPL ispell 59>4 long x hash file version %d, 60>8 long x lexletters %d, 61>12 long x lexsize %d, 62>16 long x hashsize %d, 63>20 long x stblsize %d 64 65# Summary: affixes defition text files for Ispell/MySpell/Hunspell 66# From: Joerg Jenderek 67# URL: https://www.openoffice.org/lingucomponent/affix.readme 68# https://man.archlinux.org/man/hunspell.5.en 69# Reference: http://mark0.net/download/triddefs_xml.7z/defs/a/affix.trid.xml 70# Note: called "Affix file" by TrID 71# variant starting with comment character 720 ubyte 0x23 73# look for SET character command followed by whitespace (seems to be often 1 space character) like in: 74# /usr/share/calibre/dictionaries/en-GB/en-GB.aff 75>0 search/60459 SET\040 76# skip scripts like /bin/affixcompress /bin/setupcon /bin/imdbpy2sql.py by checking for valid character SET argument 77# character SET argument like: UTF-8 78>>&0 string UTF-8 79>>>0 use spell-aff 80# character SET argument like: ISO8859-1 - ISO8859-10 ISO8859-13 - ISO8859-15 81>>&0 string ISO8859- 82>>>0 use spell-aff 83# character SET argument for Russian with Cyrillic alphabet like: KOI8-R KOI8-U 84# no russian support until war against ukraine 85>>&0 string KOI8- 86#>>>0 use spell-aff 87# character SET argument for languages with Cyrillic alphabet like: cp1251 88# no cyrillic support until russia war against ukraine 89>>&0 string cp1251 90#>>>0 use spell-aff 91# character SET argument for Indian Script Code for Information Interchange (ISCII) like: ISCII-DEVANAGARI 92>>&0 string ISCII- 93# no example found 94>>>0 use spell-aff 95# not "real" affix rule files but found as tests unit inside thunderbird sources like: 96# 1463589.aff 1695964.aff 2970240.aff 97>0 default x 98# look for suffix SFX command followed by whitespace like in: 99# 1695964.aff 100>>0 search/164 SFX\040 101>>>0 use spell-aff 102# if not real Hunspell/MySpell affix look for ispell variant 103>>0 default x 104# URL: https://manpages.debian.org/testing/ispell/ispell.5.en.html 105# look for ispell declaration like in: /usr/lib/ispell/espanol.aff 106>>>0 search/8251 defstringtype 107# defstringtype declaration start with unique name (like "list" "lat" "utf8" "iso" "nroff" often like formatter name) 108# followed by formatter name (like "nroff" "tex") 109# followed by suffix list (like ".mm" ".ms" ".me" ".man" ".NeXT" ".txt" ".list") 110#>>>>&1 string x DECLARATION=%s 111>>>>0 use spell-aff 112# ispell variant without declaration like in: /usr/lib/ispell/bulgarian.aff /usr/lib/ispell/russian.aff 113# XXX: too weak 114#>>>0 default x 115# skip /etc/nilfs_cleanerd.conf by looking for ispell suffix section 116#>>>>0 search/3233 suffixes\n 117#>>>>>0 use spell-aff 118# variant starting with empty line and comment character at the beginning of 2nd line like in: /usr/lib/ispell/polish.aff 1190 ubeshort 0x0a23 120# skip /etc/discover-modprobe.conf by looking for ispell declaration 121>2 search/3118 defstringtype 122>>0 use spell-aff 123# starting with UTF-8 Byte Order Mark (BOM) https://en.wikipedia.org/wiki/Byte_order_mark 1240 string \xEF\xBB\xBF 125# starting with UTF-8 Byte Order Mark (BOM) followed by comment starting character 126>3 string \x23 127# starting with UTF-8 BOM and with SET character command followed by whitespace 128# like in: /opt/Wolfram/WolframEngine/13.1/SystemFiles/Components/SpellingData/SpellingDictionaries/lt.aff 129# look for character SET command used in MySpell and Hunspell 130>3 search/9883 SET\040 131>>0 use spell-aff 132# look for FLAG type command used in MySpell and Hunspell 1330 string FLAG 134# followed by space character like in 135# /opt/Wolfram/WolframEngine/13.1/SystemFiles/Components/SpellingData/SpellingDictionaries/en_US.aff 136>4 ubyte 0x20 137>>0 use spell-aff 138# or followed by tabulator character like in 139# /opt/Wolfram/WolframEngine/13.1/SystemFiles/Components/SpellingData/SpellingDictionaries/ar.aff 140>4 ubyte 0x09 141>>0 use spell-aff 142# starting with character SET command used in MySpell and Hunspell like in: org/languagetool/resource/sv/hunspell/sv_SE.aff 1430 string SET\040 144>0 use spell-aff 145# starting with language code LANG used in MySpell and Hunspell like in: /usr/share/hunspell/tr_TR.aff 1460 string LANG\040 147>0 use spell-aff 148# 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 1490 string AF\040 150# look for number of flag vector aliases 151>3 regex [0-9]{1,4} 152>>0 use spell-aff 153# display information (encoding,language,...) about affixes rules text for Ispell/MySpell/Hunspell 1540 name spell-aff 155>1 ubeshort x affix definition 156#!:mime text/plain 157!:mime text/x-affix 158!:ext aff 159# GRR: need extra test so that default clause works 160>0 ubyte x 161# look for ispell declaration 162>>0 search/8251 defstringtype for Ispell 163# ispell variant without declaration 164>>0 default x 165# look for ispell suffixes command 166>>>0 search/3233 suffixes 167# skip "suffixes used to create first part of a compound" by checking for flag argument like in: languagetool\resource\sv\hunspell\sv_SE.aff 168>>>>&0 search/2 flag for Ispell 169>>>>&0 default x for MySpell/Hunspell 170# without suffixes keyword 171>>>0 default x for MySpell/Hunspell 172# look for language code command used in MySpell and Hunspell 173# 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 174>>0 search/1117643 LANG\040 \b, language 175# language code argument like: de_DE hu_HU it_IT mn_MN tr_TR 176>>>&0 string x %s 177# look for character SET command used in MySpell and Hunspell 178>>0 search/1117729 SET 179# skip SETTINGS like in /usr/lib/ispell/ngerman.aff 180# SET command followed often by space character (0x20) or tabulator (0x09) like in 181# /opt/Wolfram/WolframEngine/13.1/SystemFiles/Components/SpellingData/SpellingDictionaries/ar.aff 182>>>&0 ubyte&0xD6 =0x00 183# skip SSET # schosS in /usr/lib/ispell/ogerman.aff 184>>>>&0 ubyte >0x48 \b, 185# character SET argument like: cp1251 ISCII-DEVANAGAR ISO8859-1 - ISO8859-10 ISO8859-13 - ISO8859-15 KOI8-R KOI8-U UTF-8 186>>>>>&-1 string x "%s" encoded 187# for control reasons show first non empty lines for ASCII or ISO-8859 text variant 188>1 ubeshort !0xBBBF 189# 1st line starting with 0x0A like in /usr/src/dicts/sjp-ispell-pl-20140213/polish.aff 190>>0 ubyte =0x0A 191>>>1 ubyte !0x0A \b, 2nd line 192>>>>&-1 string x "%s" 193# 3rd line starting with 0x0A like in polish.aff 194>>>>>&1 ubyte =0x0A 195>>>>>>&0 string x \b, 4th line "%s" 196# 1st line starting with ASCII text like: 197# this is the affix file of the de_DE Hunspell dictionary 198>>0 ubyte !0x0A 199>>>0 string x \b, 1st line "%s" 200>>>>&1 ubyte >0x1F \b, 2nd line 201>>>>>&-1 string x "%s" 202# 2nd line starting with 0x0A like in /usr/lib/ispell/bulgarian.aff 203>>>>&1 ubyte =0x0A \b, 3rd line 204>>>>>&0 string x "%s" 205# for control reasons show first lines for variant starting with ByteOrderMark (BOM=\xEF\xBB\xBF) 206>1 ubeshort =0xBBBF \b, with BOM 207>>3 string x \b, 1st line "%s" 208>>>&1 ubyte >0x1F \b, 2nd line 209>>>>&-1 string x "%s" 210 211# From: Joerg Jenderek 212# URL: https://en.wikipedia.org/wiki/GNU_Aspell 213# https://manpages.ubuntu.com/manpages/trusty/en/man8/aspell-autobuildhash.8.html 214# Reference: http://mark0.net/download/triddefs_xml.7z/defs/r/rws-aspell.trid.xml 215# https://ftp.gnu.org/gnu/aspell/aspell-0.60.8.tar.gz 216# aspell-0.60.8/modules/speller/default/data.cpp 217# aspell-0.60.8/modules/speller/default/readonly_ws.cpp 218# Note: called "aspell dictionary" by TrID 2190 string aspell\040default\040speller\040rowl aspell dictionary 220#!:mime application/octet-stream 221!:mime application/x-aspell-dictionary 222!:ext rws 223# version like: 1.10 1.4 224>28 string x \b, version %s 225# u32int endian_check; 12345678=00BC614Eh 226#>64 ulelong x \b, endian_check=%u 227>>64 ulelong 12345678 \b, little endian 228# not tested 229>>64 ubelong 12345678 \b, big endian 230# older aspell version not like 0.60.8 231>>64 default x \b, old 232# URL: https://en.wikipedia.org/wiki/GNU_Aspell 233# Reference http://aspell.net/man-html/Format-of-the-Personal-and-Replacement-Dictionaries.html 234# personal_ws-1.1 lang num [encoding] 2350 string personal_ aspell personal 236# Reference: http://mark0.net/download/triddefs_xml.7z/defs/p/pws-aspell.trid.xml 237# Note: called "aspell Personal dictionary" by TrID 238>9 string ws- dictionary 239#!:mime text/plain 240!:mime text/x-aspell-dictionary 241# like: ~/.aspell.en.pws ~/.aspell.de_DE.pws ~/.aspell.it.pws 242!:ext pws 243# Reference: http://mark0.net/download/triddefs_xml.7z/defs/p/prepl-aspell.trid.xml 244# Note: called "aspell Personal Replacement dictionary" by TrID 245# personal_repl-1.1 lang num [encoding] 246>9 string repl- replacement dictionary 247#!:mime text/plain 248!:mime text/x-aspell-dictionary 249# like: ~/.aspell.en.prepl ~/.aspell.de_DE.prepl ~/.aspell.it.prepl 250!:ext prepl 251