diff options
Diffstat (limited to 'tex/context/base/font-ott.lua')
| -rw-r--r-- | tex/context/base/font-ott.lua | 1353 |
1 files changed, 700 insertions, 653 deletions
diff --git a/tex/context/base/font-ott.lua b/tex/context/base/font-ott.lua index ec915b878..1dbf626ca 100644 --- a/tex/context/base/font-ott.lua +++ b/tex/context/base/font-ott.lua @@ -6,683 +6,728 @@ if not modules then modules = { } end modules ['font-otf'] = { license = "see context related readme files" } -local type, next, tonumber, tostring = type, next, tonumber, tostring -local gsub, lower, format = string.gsub, string.lower, string.format +local type, next, tonumber, tostring, rawget, setmetatable = type, next, tonumber, tostring, rawget, setmetatable +local gsub, lower, format, match = string.gsub, string.lower, string.format, string.match local is_boolean = string.is_boolean local allocate = utilities.storage.allocate -fonts = fonts or { } -- needed for font server local fonts = fonts -fonts.otf = fonts.otf or { } -local otf = fonts.otf +local otf = fonts.handlers.otf -otf.tables = otf.tables or { } -local tables = otf.tables +local tables = { } +otf.tables = tables -otf.meanings = otf.meanings or { } -local meanings = otf.meanings +local otffeatures = fonts.constructors.newfeatures("otf") +local registerotffeature = otffeatures.register local scripts = allocate { - ['dflt'] = 'Default', - - ['arab'] = 'Arabic', - ['armn'] = 'Armenian', - ['bali'] = 'Balinese', - ['beng'] = 'Bengali', - ['bopo'] = 'Bopomofo', - ['brai'] = 'Braille', - ['bugi'] = 'Buginese', - ['buhd'] = 'Buhid', - ['byzm'] = 'Byzantine Music', - ['cans'] = 'Canadian Syllabics', - ['cher'] = 'Cherokee', - ['copt'] = 'Coptic', - ['cprt'] = 'Cypriot Syllabary', - ['cyrl'] = 'Cyrillic', - ['deva'] = 'Devanagari', - ['dsrt'] = 'Deseret', - ['ethi'] = 'Ethiopic', - ['geor'] = 'Georgian', - ['glag'] = 'Glagolitic', - ['goth'] = 'Gothic', - ['grek'] = 'Greek', - ['gujr'] = 'Gujarati', - ['guru'] = 'Gurmukhi', - ['hang'] = 'Hangul', - ['hani'] = 'CJK Ideographic', - ['hano'] = 'Hanunoo', - ['hebr'] = 'Hebrew', - ['ital'] = 'Old Italic', - ['jamo'] = 'Hangul Jamo', - ['java'] = 'Javanese', - ['kana'] = 'Hiragana and Katakana', - ['khar'] = 'Kharosthi', - ['khmr'] = 'Khmer', - ['knda'] = 'Kannada', - ['lao' ] = 'Lao', - ['latn'] = 'Latin', - ['limb'] = 'Limbu', - ['linb'] = 'Linear B', - ['math'] = 'Mathematical Alphanumeric Symbols', - ['mlym'] = 'Malayalam', - ['mong'] = 'Mongolian', - ['musc'] = 'Musical Symbols', - ['mymr'] = 'Myanmar', - ['nko' ] = "N'ko", - ['ogam'] = 'Ogham', - ['orya'] = 'Oriya', - ['osma'] = 'Osmanya', - ['phag'] = 'Phags-pa', - ['phnx'] = 'Phoenician', - ['runr'] = 'Runic', - ['shaw'] = 'Shavian', - ['sinh'] = 'Sinhala', - ['sylo'] = 'Syloti Nagri', - ['syrc'] = 'Syriac', - ['tagb'] = 'Tagbanwa', - ['tale'] = 'Tai Le', - ['talu'] = 'Tai Lu', - ['taml'] = 'Tamil', - ['telu'] = 'Telugu', - ['tfng'] = 'Tifinagh', - ['tglg'] = 'Tagalog', - ['thaa'] = 'Thaana', - ['thai'] = 'Thai', - ['tibt'] = 'Tibetan', - ['ugar'] = 'Ugaritic Cuneiform', - ['xpeo'] = 'Old Persian Cuneiform', - ['xsux'] = 'Sumero-Akkadian Cuneiform', - ['yi' ] = 'Yi', + ['arab'] = 'arabic', + ['armn'] = 'armenian', + ['bali'] = 'balinese', + ['beng'] = 'bengali', + ['bopo'] = 'bopomofo', + ['brai'] = 'braille', + ['bugi'] = 'buginese', + ['buhd'] = 'buhid', + ['byzm'] = 'byzantine music', + ['cans'] = 'canadian syllabics', + ['cher'] = 'cherokee', + ['copt'] = 'coptic', + ['cprt'] = 'cypriot syllabary', + ['cyrl'] = 'cyrillic', + ['deva'] = 'devanagari', + ['dsrt'] = 'deseret', + ['ethi'] = 'ethiopic', + ['geor'] = 'georgian', + ['glag'] = 'glagolitic', + ['goth'] = 'gothic', + ['grek'] = 'greek', + ['gujr'] = 'gujarati', + ['guru'] = 'gurmukhi', + ['hang'] = 'hangul', + ['hani'] = 'cjk ideographic', + ['hano'] = 'hanunoo', + ['hebr'] = 'hebrew', + ['ital'] = 'old italic', + ['jamo'] = 'hangul jamo', + ['java'] = 'javanese', + ['kana'] = 'hiragana and katakana', + ['khar'] = 'kharosthi', + ['khmr'] = 'khmer', + ['knda'] = 'kannada', + ['lao' ] = 'lao', + ['latn'] = 'latin', + ['limb'] = 'limbu', + ['linb'] = 'linear b', + ['math'] = 'mathematical alphanumeric symbols', + ['mlym'] = 'malayalam', + ['mong'] = 'mongolian', + ['musc'] = 'musical symbols', + ['mymr'] = 'myanmar', + ['nko' ] = "n'ko", + ['ogam'] = 'ogham', + ['orya'] = 'oriya', + ['osma'] = 'osmanya', + ['phag'] = 'phags-pa', + ['phnx'] = 'phoenician', + ['runr'] = 'runic', + ['shaw'] = 'shavian', + ['sinh'] = 'sinhala', + ['sylo'] = 'syloti nagri', + ['syrc'] = 'syriac', + ['tagb'] = 'tagbanwa', + ['tale'] = 'tai le', + ['talu'] = 'tai lu', + ['taml'] = 'tamil', + ['telu'] = 'telugu', + ['tfng'] = 'tifinagh', + ['tglg'] = 'tagalog', + ['thaa'] = 'thaana', + ['thai'] = 'thai', + ['tibt'] = 'tibetan', + ['ugar'] = 'ugaritic cuneiform', + ['xpeo'] = 'old persian cuneiform', + ['xsux'] = 'sumero-akkadian cuneiform', + ['yi' ] = 'yi', } local languages = allocate { - ['dflt'] = 'Default', - - ['aba'] = 'Abaza', - ['abk'] = 'Abkhazian', - ['ady'] = 'Adyghe', - ['afk'] = 'Afrikaans', - ['afr'] = 'Afar', - ['agw'] = 'Agaw', - ['als'] = 'Alsatian', - ['alt'] = 'Altai', - ['amh'] = 'Amharic', - ['ara'] = 'Arabic', - ['ari'] = 'Aari', - ['ark'] = 'Arakanese', - ['asm'] = 'Assamese', - ['ath'] = 'Athapaskan', - ['avr'] = 'Avar', - ['awa'] = 'Awadhi', - ['aym'] = 'Aymara', - ['aze'] = 'Azeri', - ['bad'] = 'Badaga', - ['bag'] = 'Baghelkhandi', - ['bal'] = 'Balkar', - ['bau'] = 'Baule', - ['bbr'] = 'Berber', - ['bch'] = 'Bench', - ['bcr'] = 'Bible Cree', - ['bel'] = 'Belarussian', - ['bem'] = 'Bemba', - ['ben'] = 'Bengali', - ['bgr'] = 'Bulgarian', - ['bhi'] = 'Bhili', - ['bho'] = 'Bhojpuri', - ['bik'] = 'Bikol', - ['bil'] = 'Bilen', - ['bkf'] = 'Blackfoot', - ['bli'] = 'Balochi', - ['bln'] = 'Balante', - ['blt'] = 'Balti', - ['bmb'] = 'Bambara', - ['bml'] = 'Bamileke', - ['bos'] = 'Bosnian', - ['bre'] = 'Breton', - ['brh'] = 'Brahui', - ['bri'] = 'Braj Bhasha', - ['brm'] = 'Burmese', - ['bsh'] = 'Bashkir', - ['bti'] = 'Beti', - ['cat'] = 'Catalan', - ['ceb'] = 'Cebuano', - ['che'] = 'Chechen', - ['chg'] = 'Chaha Gurage', - ['chh'] = 'Chattisgarhi', - ['chi'] = 'Chichewa', - ['chk'] = 'Chukchi', - ['chp'] = 'Chipewyan', - ['chr'] = 'Cherokee', - ['chu'] = 'Chuvash', - ['cmr'] = 'Comorian', - ['cop'] = 'Coptic', - ['cos'] = 'Corsican', - ['cre'] = 'Cree', - ['crr'] = 'Carrier', - ['crt'] = 'Crimean Tatar', - ['csl'] = 'Church Slavonic', - ['csy'] = 'Czech', - ['dan'] = 'Danish', - ['dar'] = 'Dargwa', - ['dcr'] = 'Woods Cree', - ['deu'] = 'German', - ['dgr'] = 'Dogri', - ['div'] = 'Divehi', - ['djr'] = 'Djerma', - ['dng'] = 'Dangme', - ['dnk'] = 'Dinka', - ['dri'] = 'Dari', - ['dun'] = 'Dungan', - ['dzn'] = 'Dzongkha', - ['ebi'] = 'Ebira', - ['ecr'] = 'Eastern Cree', - ['edo'] = 'Edo', - ['efi'] = 'Efik', - ['ell'] = 'Greek', - ['eng'] = 'English', - ['erz'] = 'Erzya', - ['esp'] = 'Spanish', - ['eti'] = 'Estonian', - ['euq'] = 'Basque', - ['evk'] = 'Evenki', - ['evn'] = 'Even', - ['ewe'] = 'Ewe', - ['fan'] = 'French Antillean', - ['far'] = 'Farsi', - ['fin'] = 'Finnish', - ['fji'] = 'Fijian', - ['fle'] = 'Flemish', - ['fne'] = 'Forest Nenets', - ['fon'] = 'Fon', - ['fos'] = 'Faroese', - ['fra'] = 'French', - ['fri'] = 'Frisian', - ['frl'] = 'Friulian', - ['fta'] = 'Futa', - ['ful'] = 'Fulani', - ['gad'] = 'Ga', - ['gae'] = 'Gaelic', - ['gag'] = 'Gagauz', - ['gal'] = 'Galician', - ['gar'] = 'Garshuni', - ['gaw'] = 'Garhwali', - ['gez'] = "Ge'ez", - ['gil'] = 'Gilyak', - ['gmz'] = 'Gumuz', - ['gon'] = 'Gondi', - ['grn'] = 'Greenlandic', - ['gro'] = 'Garo', - ['gua'] = 'Guarani', - ['guj'] = 'Gujarati', - ['hai'] = 'Haitian', - ['hal'] = 'Halam', - ['har'] = 'Harauti', - ['hau'] = 'Hausa', - ['haw'] = 'Hawaiin', - ['hbn'] = 'Hammer-Banna', - ['hil'] = 'Hiligaynon', - ['hin'] = 'Hindi', - ['hma'] = 'High Mari', - ['hnd'] = 'Hindko', - ['ho'] = 'Ho', - ['hri'] = 'Harari', - ['hrv'] = 'Croatian', - ['hun'] = 'Hungarian', - ['hye'] = 'Armenian', - ['ibo'] = 'Igbo', - ['ijo'] = 'Ijo', - ['ilo'] = 'Ilokano', - ['ind'] = 'Indonesian', - ['ing'] = 'Ingush', - ['inu'] = 'Inuktitut', - ['iri'] = 'Irish', - ['irt'] = 'Irish Traditional', - ['isl'] = 'Icelandic', - ['ism'] = 'Inari Sami', - ['ita'] = 'Italian', - ['iwr'] = 'Hebrew', - ['jan'] = 'Japanese', - ['jav'] = 'Javanese', - ['jii'] = 'Yiddish', - ['jud'] = 'Judezmo', - ['jul'] = 'Jula', - ['kab'] = 'Kabardian', - ['kac'] = 'Kachchi', - ['kal'] = 'Kalenjin', - ['kan'] = 'Kannada', - ['kar'] = 'Karachay', - ['kat'] = 'Georgian', - ['kaz'] = 'Kazakh', - ['keb'] = 'Kebena', - ['kge'] = 'Khutsuri Georgian', - ['kha'] = 'Khakass', - ['khk'] = 'Khanty-Kazim', - ['khm'] = 'Khmer', - ['khs'] = 'Khanty-Shurishkar', - ['khv'] = 'Khanty-Vakhi', - ['khw'] = 'Khowar', - ['kik'] = 'Kikuyu', - ['kir'] = 'Kirghiz', - ['kis'] = 'Kisii', - ['kkn'] = 'Kokni', - ['klm'] = 'Kalmyk', - ['kmb'] = 'Kamba', - ['kmn'] = 'Kumaoni', - ['kmo'] = 'Komo', - ['kms'] = 'Komso', - ['knr'] = 'Kanuri', - ['kod'] = 'Kodagu', - ['koh'] = 'Korean Old Hangul', - ['kok'] = 'Konkani', - ['kon'] = 'Kikongo', - ['kop'] = 'Komi-Permyak', - ['kor'] = 'Korean', - ['koz'] = 'Komi-Zyrian', - ['kpl'] = 'Kpelle', - ['kri'] = 'Krio', - ['krk'] = 'Karakalpak', - ['krl'] = 'Karelian', - ['krm'] = 'Karaim', - ['krn'] = 'Karen', - ['krt'] = 'Koorete', - ['ksh'] = 'Kashmiri', - ['ksi'] = 'Khasi', - ['ksm'] = 'Kildin Sami', - ['kui'] = 'Kui', - ['kul'] = 'Kulvi', - ['kum'] = 'Kumyk', - ['kur'] = 'Kurdish', - ['kuu'] = 'Kurukh', - ['kuy'] = 'Kuy', - ['kyk'] = 'Koryak', - ['lad'] = 'Ladin', - ['lah'] = 'Lahuli', - ['lak'] = 'Lak', - ['lam'] = 'Lambani', - ['lao'] = 'Lao', - ['lat'] = 'Latin', - ['laz'] = 'Laz', - ['lcr'] = 'L-Cree', - ['ldk'] = 'Ladakhi', - ['lez'] = 'Lezgi', - ['lin'] = 'Lingala', - ['lma'] = 'Low Mari', - ['lmb'] = 'Limbu', - ['lmw'] = 'Lomwe', - ['lsb'] = 'Lower Sorbian', - ['lsm'] = 'Lule Sami', - ['lth'] = 'Lithuanian', - ['ltz'] = 'Luxembourgish', - ['lub'] = 'Luba', - ['lug'] = 'Luganda', - ['luh'] = 'Luhya', - ['luo'] = 'Luo', - ['lvi'] = 'Latvian', - ['maj'] = 'Majang', - ['mak'] = 'Makua', - ['mal'] = 'Malayalam Traditional', - ['man'] = 'Mansi', - ['map'] = 'Mapudungun', - ['mar'] = 'Marathi', - ['maw'] = 'Marwari', - ['mbn'] = 'Mbundu', - ['mch'] = 'Manchu', - ['mcr'] = 'Moose Cree', - ['mde'] = 'Mende', - ['men'] = "Me'en", - ['miz'] = 'Mizo', - ['mkd'] = 'Macedonian', - ['mle'] = 'Male', - ['mlg'] = 'Malagasy', - ['mln'] = 'Malinke', - ['mlr'] = 'Malayalam Reformed', - ['mly'] = 'Malay', - ['mnd'] = 'Mandinka', - ['mng'] = 'Mongolian', - ['mni'] = 'Manipuri', - ['mnk'] = 'Maninka', - ['mnx'] = 'Manx Gaelic', - ['moh'] = 'Mohawk', - ['mok'] = 'Moksha', - ['mol'] = 'Moldavian', - ['mon'] = 'Mon', - ['mor'] = 'Moroccan', - ['mri'] = 'Maori', - ['mth'] = 'Maithili', - ['mts'] = 'Maltese', - ['mun'] = 'Mundari', - ['nag'] = 'Naga-Assamese', - ['nan'] = 'Nanai', - ['nas'] = 'Naskapi', - ['ncr'] = 'N-Cree', - ['ndb'] = 'Ndebele', - ['ndg'] = 'Ndonga', - ['nep'] = 'Nepali', - ['new'] = 'Newari', - ['ngr'] = 'Nagari', - ['nhc'] = 'Norway House Cree', - ['nis'] = 'Nisi', - ['niu'] = 'Niuean', - ['nkl'] = 'Nkole', - ['nko'] = "N'ko", - ['nld'] = 'Dutch', - ['nog'] = 'Nogai', - ['nor'] = 'Norwegian', - ['nsm'] = 'Northern Sami', - ['nta'] = 'Northern Tai', - ['nto'] = 'Esperanto', - ['nyn'] = 'Nynorsk', - ['oci'] = 'Occitan', - ['ocr'] = 'Oji-Cree', - ['ojb'] = 'Ojibway', - ['ori'] = 'Oriya', - ['oro'] = 'Oromo', - ['oss'] = 'Ossetian', - ['paa'] = 'Palestinian Aramaic', - ['pal'] = 'Pali', - ['pan'] = 'Punjabi', - ['pap'] = 'Palpa', - ['pas'] = 'Pashto', - ['pgr'] = 'Polytonic Greek', - ['pil'] = 'Pilipino', - ['plg'] = 'Palaung', - ['plk'] = 'Polish', - ['pro'] = 'Provencal', - ['ptg'] = 'Portuguese', - ['qin'] = 'Chin', - ['raj'] = 'Rajasthani', - ['rbu'] = 'Russian Buriat', - ['rcr'] = 'R-Cree', - ['ria'] = 'Riang', - ['rms'] = 'Rhaeto-Romanic', - ['rom'] = 'Romanian', - ['roy'] = 'Romany', - ['rsy'] = 'Rusyn', - ['rua'] = 'Ruanda', - ['rus'] = 'Russian', - ['sad'] = 'Sadri', - ['san'] = 'Sanskrit', - ['sat'] = 'Santali', - ['say'] = 'Sayisi', - ['sek'] = 'Sekota', - ['sel'] = 'Selkup', - ['sgo'] = 'Sango', - ['shn'] = 'Shan', - ['sib'] = 'Sibe', - ['sid'] = 'Sidamo', - ['sig'] = 'Silte Gurage', - ['sks'] = 'Skolt Sami', - ['sky'] = 'Slovak', - ['sla'] = 'Slavey', - ['slv'] = 'Slovenian', - ['sml'] = 'Somali', - ['smo'] = 'Samoan', - ['sna'] = 'Sena', - ['snd'] = 'Sindhi', - ['snh'] = 'Sinhalese', - ['snk'] = 'Soninke', - ['sog'] = 'Sodo Gurage', - ['sot'] = 'Sotho', - ['sqi'] = 'Albanian', - ['srb'] = 'Serbian', - ['srk'] = 'Saraiki', - ['srr'] = 'Serer', - ['ssl'] = 'South Slavey', - ['ssm'] = 'Southern Sami', - ['sur'] = 'Suri', - ['sva'] = 'Svan', - ['sve'] = 'Swedish', - ['swa'] = 'Swadaya Aramaic', - ['swk'] = 'Swahili', - ['swz'] = 'Swazi', - ['sxt'] = 'Sutu', - ['syr'] = 'Syriac', - ['tab'] = 'Tabasaran', - ['taj'] = 'Tajiki', - ['tam'] = 'Tamil', - ['tat'] = 'Tatar', - ['tcr'] = 'TH-Cree', - ['tel'] = 'Telugu', - ['tgn'] = 'Tongan', - ['tgr'] = 'Tigre', - ['tgy'] = 'Tigrinya', - ['tha'] = 'Thai', - ['tht'] = 'Tahitian', - ['tib'] = 'Tibetan', - ['tkm'] = 'Turkmen', - ['tmn'] = 'Temne', - ['tna'] = 'Tswana', - ['tne'] = 'Tundra Nenets', - ['tng'] = 'Tonga', - ['tod'] = 'Todo', - ['trk'] = 'Turkish', - ['tsg'] = 'Tsonga', - ['tua'] = 'Turoyo Aramaic', - ['tul'] = 'Tulu', - ['tuv'] = 'Tuvin', - ['twi'] = 'Twi', - ['udm'] = 'Udmurt', - ['ukr'] = 'Ukrainian', - ['urd'] = 'Urdu', - ['usb'] = 'Upper Sorbian', - ['uyg'] = 'Uyghur', - ['uzb'] = 'Uzbek', - ['ven'] = 'Venda', - ['vit'] = 'Vietnamese', - ['wa' ] = 'Wa', - ['wag'] = 'Wagdi', - ['wcr'] = 'West-Cree', - ['wel'] = 'Welsh', - ['wlf'] = 'Wolof', - ['xbd'] = 'Tai Lue', - ['xhs'] = 'Xhosa', - ['yak'] = 'Yakut', - ['yba'] = 'Yoruba', - ['ycr'] = 'Y-Cree', - ['yic'] = 'Yi Classic', - ['yim'] = 'Yi Modern', - ['zhh'] = 'Chinese Hong Kong', - ['zhp'] = 'Chinese Phonetic', - ['zhs'] = 'Chinese Simplified', - ['zht'] = 'Chinese Traditional', - ['znd'] = 'Zande', - ['zul'] = 'Zulu' + ['aba'] = 'abaza', + ['abk'] = 'abkhazian', + ['ady'] = 'adyghe', + ['afk'] = 'afrikaans', + ['afr'] = 'afar', + ['agw'] = 'agaw', + ['als'] = 'alsatian', + ['alt'] = 'altai', + ['amh'] = 'amharic', + ['ara'] = 'arabic', + ['ari'] = 'aari', + ['ark'] = 'arakanese', + ['asm'] = 'assamese', + ['ath'] = 'athapaskan', + ['avr'] = 'avar', + ['awa'] = 'awadhi', + ['aym'] = 'aymara', + ['aze'] = 'azeri', + ['bad'] = 'badaga', + ['bag'] = 'baghelkhandi', + ['bal'] = 'balkar', + ['bau'] = 'baule', + ['bbr'] = 'berber', + ['bch'] = 'bench', + ['bcr'] = 'bible cree', + ['bel'] = 'belarussian', + ['bem'] = 'bemba', + ['ben'] = 'bengali', + ['bgr'] = 'bulgarian', + ['bhi'] = 'bhili', + ['bho'] = 'bhojpuri', + ['bik'] = 'bikol', + ['bil'] = 'bilen', + ['bkf'] = 'blackfoot', + ['bli'] = 'balochi', + ['bln'] = 'balante', + ['blt'] = 'balti', + ['bmb'] = 'bambara', + ['bml'] = 'bamileke', + ['bos'] = 'bosnian', + ['bre'] = 'breton', + ['brh'] = 'brahui', + ['bri'] = 'braj bhasha', + ['brm'] = 'burmese', + ['bsh'] = 'bashkir', + ['bti'] = 'beti', + ['cat'] = 'catalan', + ['ceb'] = 'cebuano', + ['che'] = 'chechen', + ['chg'] = 'chaha gurage', + ['chh'] = 'chattisgarhi', + ['chi'] = 'chichewa', + ['chk'] = 'chukchi', + ['chp'] = 'chipewyan', + ['chr'] = 'cherokee', + ['chu'] = 'chuvash', + ['cmr'] = 'comorian', + ['cop'] = 'coptic', + ['cos'] = 'corsican', + ['cre'] = 'cree', + ['crr'] = 'carrier', + ['crt'] = 'crimean tatar', + ['csl'] = 'church slavonic', + ['csy'] = 'czech', + ['dan'] = 'danish', + ['dar'] = 'dargwa', + ['dcr'] = 'woods cree', + ['deu'] = 'german', + ['dgr'] = 'dogri', + ['div'] = 'divehi', + ['djr'] = 'djerma', + ['dng'] = 'dangme', + ['dnk'] = 'dinka', + ['dri'] = 'dari', + ['dun'] = 'dungan', + ['dzn'] = 'dzongkha', + ['ebi'] = 'ebira', + ['ecr'] = 'eastern cree', + ['edo'] = 'edo', + ['efi'] = 'efik', + ['ell'] = 'greek', + ['eng'] = 'english', + ['erz'] = 'erzya', + ['esp'] = 'spanish', + ['eti'] = 'estonian', + ['euq'] = 'basque', + ['evk'] = 'evenki', + ['evn'] = 'even', + ['ewe'] = 'ewe', + ['fan'] = 'french antillean', + ['far'] = 'farsi', + ['fin'] = 'finnish', + ['fji'] = 'fijian', + ['fle'] = 'flemish', + ['fne'] = 'forest nenets', + ['fon'] = 'fon', + ['fos'] = 'faroese', + ['fra'] = 'french', + ['fri'] = 'frisian', + ['frl'] = 'friulian', + ['fta'] = 'futa', + ['ful'] = 'fulani', + ['gad'] = 'ga', + ['gae'] = 'gaelic', + ['gag'] = 'gagauz', + ['gal'] = 'galician', + ['gar'] = 'garshuni', + ['gaw'] = 'garhwali', + ['gez'] = "ge'ez", + ['gil'] = 'gilyak', + ['gmz'] = 'gumuz', + ['gon'] = 'gondi', + ['grn'] = 'greenlandic', + ['gro'] = 'garo', + ['gua'] = 'guarani', + ['guj'] = 'gujarati', + ['hai'] = 'haitian', + ['hal'] = 'halam', + ['har'] = 'harauti', + ['hau'] = 'hausa', + ['haw'] = 'hawaiin', + ['hbn'] = 'hammer-banna', + ['hil'] = 'hiligaynon', + ['hin'] = 'hindi', + ['hma'] = 'high mari', + ['hnd'] = 'hindko', + ['ho'] = 'ho', + ['hri'] = 'harari', + ['hrv'] = 'croatian', + ['hun'] = 'hungarian', + ['hye'] = 'armenian', + ['ibo'] = 'igbo', + ['ijo'] = 'ijo', + ['ilo'] = 'ilokano', + ['ind'] = 'indonesian', + ['ing'] = 'ingush', + ['inu'] = 'inuktitut', + ['iri'] = 'irish', + ['irt'] = 'irish traditional', + ['isl'] = 'icelandic', + ['ism'] = 'inari sami', + ['ita'] = 'italian', + ['iwr'] = 'hebrew', + ['jan'] = 'japanese', + ['jav'] = 'javanese', + ['jii'] = 'yiddish', + ['jud'] = 'judezmo', + ['jul'] = 'jula', + ['kab'] = 'kabardian', + ['kac'] = 'kachchi', + ['kal'] = 'kalenjin', + ['kan'] = 'kannada', + ['kar'] = 'karachay', + ['kat'] = 'georgian', + ['kaz'] = 'kazakh', + ['keb'] = 'kebena', + ['kge'] = 'khutsuri georgian', + ['kha'] = 'khakass', + ['khk'] = 'khanty-kazim', + ['khm'] = 'khmer', + ['khs'] = 'khanty-shurishkar', + ['khv'] = 'khanty-vakhi', + ['khw'] = 'khowar', + ['kik'] = 'kikuyu', + ['kir'] = 'kirghiz', + ['kis'] = 'kisii', + ['kkn'] = 'kokni', + ['klm'] = 'kalmyk', + ['kmb'] = 'kamba', + ['kmn'] = 'kumaoni', + ['kmo'] = 'komo', + ['kms'] = 'komso', + ['knr'] = 'kanuri', + ['kod'] = 'kodagu', + ['koh'] = 'korean old hangul', + ['kok'] = 'konkani', + ['kon'] = 'kikongo', + ['kop'] = 'komi-permyak', + ['kor'] = 'korean', + ['koz'] = 'komi-zyrian', + ['kpl'] = 'kpelle', + ['kri'] = 'krio', + ['krk'] = 'karakalpak', + ['krl'] = 'karelian', + ['krm'] = 'karaim', + ['krn'] = 'karen', + ['krt'] = 'koorete', + ['ksh'] = 'kashmiri', + ['ksi'] = 'khasi', + ['ksm'] = 'kildin sami', + ['kui'] = 'kui', + ['kul'] = 'kulvi', + ['kum'] = 'kumyk', + ['kur'] = 'kurdish', + ['kuu'] = 'kurukh', + ['kuy'] = 'kuy', + ['kyk'] = 'koryak', + ['lad'] = 'ladin', + ['lah'] = 'lahuli', + ['lak'] = 'lak', + ['lam'] = 'lambani', + ['lao'] = 'lao', + ['lat'] = 'latin', + ['laz'] = 'laz', + ['lcr'] = 'l-cree', + ['ldk'] = 'ladakhi', + ['lez'] = 'lezgi', + ['lin'] = 'lingala', + ['lma'] = 'low mari', + ['lmb'] = 'limbu', + ['lmw'] = 'lomwe', + ['lsb'] = 'lower sorbian', + ['lsm'] = 'lule sami', + ['lth'] = 'lithuanian', + ['ltz'] = 'luxembourgish', + ['lub'] = 'luba', + ['lug'] = 'luganda', + ['luh'] = 'luhya', + ['luo'] = 'luo', + ['lvi'] = 'latvian', + ['maj'] = 'majang', + ['mak'] = 'makua', + ['mal'] = 'malayalam traditional', + ['man'] = 'mansi', + ['map'] = 'mapudungun', + ['mar'] = 'marathi', + ['maw'] = 'marwari', + ['mbn'] = 'mbundu', + ['mch'] = 'manchu', + ['mcr'] = 'moose cree', + ['mde'] = 'mende', + ['men'] = "me'en", + ['miz'] = 'mizo', + ['mkd'] = 'macedonian', + ['mle'] = 'male', + ['mlg'] = 'malagasy', + ['mln'] = 'malinke', + ['mlr'] = 'malayalam reformed', + ['mly'] = 'malay', + ['mnd'] = 'mandinka', + ['mng'] = 'mongolian', + ['mni'] = 'manipuri', + ['mnk'] = 'maninka', + ['mnx'] = 'manx gaelic', + ['moh'] = 'mohawk', + ['mok'] = 'moksha', + ['mol'] = 'moldavian', + ['mon'] = 'mon', + ['mor'] = 'moroccan', + ['mri'] = 'maori', + ['mth'] = 'maithili', + ['mts'] = 'maltese', + ['mun'] = 'mundari', + ['nag'] = 'naga-assamese', + ['nan'] = 'nanai', + ['nas'] = 'naskapi', + ['ncr'] = 'n-cree', + ['ndb'] = 'ndebele', + ['ndg'] = 'ndonga', + ['nep'] = 'nepali', + ['new'] = 'newari', + ['ngr'] = 'nagari', + ['nhc'] = 'norway house cree', + ['nis'] = 'nisi', + ['niu'] = 'niuean', + ['nkl'] = 'nkole', + ['nko'] = "n'ko", + ['nld'] = 'dutch', + ['nog'] = 'nogai', + ['nor'] = 'norwegian', + ['nsm'] = 'northern sami', + ['nta'] = 'northern tai', + ['nto'] = 'esperanto', + ['nyn'] = 'nynorsk', + ['oci'] = 'occitan', + ['ocr'] = 'oji-cree', + ['ojb'] = 'ojibway', + ['ori'] = 'oriya', + ['oro'] = 'oromo', + ['oss'] = 'ossetian', + ['paa'] = 'palestinian aramaic', + ['pal'] = 'pali', + ['pan'] = 'punjabi', + ['pap'] = 'palpa', + ['pas'] = 'pashto', + ['pgr'] = 'polytonic greek', + ['pil'] = 'pilipino', + ['plg'] = 'palaung', + ['plk'] = 'polish', + ['pro'] = 'provencal', + ['ptg'] = 'portuguese', + ['qin'] = 'chin', + ['raj'] = 'rajasthani', + ['rbu'] = 'russian buriat', + ['rcr'] = 'r-cree', + ['ria'] = 'riang', + ['rms'] = 'rhaeto-romanic', + ['rom'] = 'romanian', + ['roy'] = 'romany', + ['rsy'] = 'rusyn', + ['rua'] = 'ruanda', + ['rus'] = 'russian', + ['sad'] = 'sadri', + ['san'] = 'sanskrit', + ['sat'] = 'santali', + ['say'] = 'sayisi', + ['sek'] = 'sekota', + ['sel'] = 'selkup', + ['sgo'] = 'sango', + ['shn'] = 'shan', + ['sib'] = 'sibe', + ['sid'] = 'sidamo', + ['sig'] = 'silte gurage', + ['sks'] = 'skolt sami', + ['sky'] = 'slovak', + ['sla'] = 'slavey', + ['slv'] = 'slovenian', + ['sml'] = 'somali', + ['smo'] = 'samoan', + ['sna'] = 'sena', + ['snd'] = 'sindhi', + ['snh'] = 'sinhalese', + ['snk'] = 'soninke', + ['sog'] = 'sodo gurage', + ['sot'] = 'sotho', + ['sqi'] = 'albanian', + ['srb'] = 'serbian', + ['srk'] = 'saraiki', + ['srr'] = 'serer', + ['ssl'] = 'south slavey', + ['ssm'] = 'southern sami', + ['sur'] = 'suri', + ['sva'] = 'svan', + ['sve'] = 'swedish', + ['swa'] = 'swadaya aramaic', + ['swk'] = 'swahili', + ['swz'] = 'swazi', + ['sxt'] = 'sutu', + ['syr'] = 'syriac', + ['tab'] = 'tabasaran', + ['taj'] = 'tajiki', + ['tam'] = 'tamil', + ['tat'] = 'tatar', + ['tcr'] = 'th-cree', + ['tel'] = 'telugu', + ['tgn'] = 'tongan', + ['tgr'] = 'tigre', + ['tgy'] = 'tigrinya', + ['tha'] = 'thai', + ['tht'] = 'tahitian', + ['tib'] = 'tibetan', + ['tkm'] = 'turkmen', + ['tmn'] = 'temne', + ['tna'] = 'tswana', + ['tne'] = 'tundra nenets', + ['tng'] = 'tonga', + ['tod'] = 'todo', + ['trk'] = 'turkish', + ['tsg'] = 'tsonga', + ['tua'] = 'turoyo aramaic', + ['tul'] = 'tulu', + ['tuv'] = 'tuvin', + ['twi'] = 'twi', + ['udm'] = 'udmurt', + ['ukr'] = 'ukrainian', + ['urd'] = 'urdu', + ['usb'] = 'upper sorbian', + ['uyg'] = 'uyghur', + ['uzb'] = 'uzbek', + ['ven'] = 'venda', + ['vit'] = 'vietnamese', + ['wa' ] = 'wa', + ['wag'] = 'wagdi', + ['wcr'] = 'west-cree', + ['wel'] = 'welsh', + ['wlf'] = 'wolof', + ['xbd'] = 'tai lue', + ['xhs'] = 'xhosa', + ['yak'] = 'yakut', + ['yba'] = 'yoruba', + ['ycr'] = 'y-cree', + ['yic'] = 'yi classic', + ['yim'] = 'yi modern', + ['zhh'] = 'chinese hong kong', + ['zhp'] = 'chinese phonetic', + ['zhs'] = 'chinese simplified', + ['zht'] = 'chinese traditional', + ['znd'] = 'zande', + ['zul'] = 'zulu' } local features = allocate { - ['aalt'] = 'Access All Alternates', - ['abvf'] = 'Above-Base Forms', - ['abvm'] = 'Above-Base Mark Positioning', - ['abvs'] = 'Above-Base Substitutions', - ['afrc'] = 'Alternative Fractions', - ['akhn'] = 'Akhands', - ['blwf'] = 'Below-Base Forms', - ['blwm'] = 'Below-Base Mark Positioning', - ['blws'] = 'Below-Base Substitutions', - ['c2pc'] = 'Petite Capitals From Capitals', - ['c2sc'] = 'Small Capitals From Capitals', - ['calt'] = 'Contextual Alternates', - ['case'] = 'Case-Sensitive Forms', - ['ccmp'] = 'Glyph Composition/Decomposition', - ['cjct'] = 'Conjunct Forms', - ['clig'] = 'Contextual Ligatures', - ['cpsp'] = 'Capital Spacing', - ['cswh'] = 'Contextual Swash', - ['curs'] = 'Cursive Positioning', - ['dflt'] = 'Default Processing', - ['dist'] = 'Distances', - ['dlig'] = 'Discretionary Ligatures', - ['dnom'] = 'Denominators', - ['dtls'] = 'Dotless Forms', -- math - ['expt'] = 'Expert Forms', - ['falt'] = 'Final glyph Alternates', - ['fin2'] = 'Terminal Forms #2', - ['fin3'] = 'Terminal Forms #3', - ['fina'] = 'Terminal Forms', - ['flac'] = 'Flattened Accents Over Capitals', -- math - ['frac'] = 'Fractions', - ['fwid'] = 'Full Width', - ['half'] = 'Half Forms', - ['haln'] = 'Halant Forms', - ['halt'] = 'Alternate Half Width', - ['hist'] = 'Historical Forms', - ['hkna'] = 'Horizontal Kana Alternates', - ['hlig'] = 'Historical Ligatures', - ['hngl'] = 'Hangul', - ['hojo'] = 'Hojo Kanji Forms', - ['hwid'] = 'Half Width', - ['init'] = 'Initial Forms', - ['isol'] = 'Isolated Forms', - ['ital'] = 'Italics', - ['jalt'] = 'Justification Alternatives', - ['jp04'] = 'JIS2004 Forms', - ['jp78'] = 'JIS78 Forms', - ['jp83'] = 'JIS83 Forms', - ['jp90'] = 'JIS90 Forms', - ['kern'] = 'Kerning', - ['lfbd'] = 'Left Bounds', - ['liga'] = 'Standard Ligatures', - ['ljmo'] = 'Leading Jamo Forms', - ['lnum'] = 'Lining Figures', - ['locl'] = 'Localized Forms', - ['mark'] = 'Mark Positioning', - ['med2'] = 'Medial Forms #2', - ['medi'] = 'Medial Forms', - ['mgrk'] = 'Mathematical Greek', - ['mkmk'] = 'Mark to Mark Positioning', - ['mset'] = 'Mark Positioning via Substitution', - ['nalt'] = 'Alternate Annotation Forms', - ['nlck'] = 'NLC Kanji Forms', - ['nukt'] = 'Nukta Forms', - ['numr'] = 'Numerators', - ['onum'] = 'Old Style Figures', - ['opbd'] = 'Optical Bounds', - ['ordn'] = 'Ordinals', - ['ornm'] = 'Ornaments', - ['palt'] = 'Proportional Alternate Width', - ['pcap'] = 'Petite Capitals', - ['pnum'] = 'Proportional Figures', - ['pref'] = 'Pre-base Forms', - ['pres'] = 'Pre-base Substitutions', - ['pstf'] = 'Post-base Forms', - ['psts'] = 'Post-base Substitutions', - ['pwid'] = 'Proportional Widths', - ['qwid'] = 'Quarter Widths', - ['rand'] = 'Randomize', - ['rkrf'] = 'Rakar Forms', - ['rlig'] = 'Required Ligatures', - ['rphf'] = 'Reph Form', - ['rtbd'] = 'Right Bounds', - ['rtla'] = 'Right-To-Left Alternates', - ['rtlm'] = 'Right To Left Math', -- math - ['ruby'] = 'Ruby Notation Forms', - ['salt'] = 'Stylistic Alternates', - ['sinf'] = 'Scientific Inferiors', - ['size'] = 'Optical Size', - ['smcp'] = 'Small Capitals', - ['smpl'] = 'Simplified Forms', - ['ss01'] = 'Stylistic Set 1', - ['ss02'] = 'Stylistic Set 2', - ['ss03'] = 'Stylistic Set 3', - ['ss04'] = 'Stylistic Set 4', - ['ss05'] = 'Stylistic Set 5', - ['ss06'] = 'Stylistic Set 6', - ['ss07'] = 'Stylistic Set 7', - ['ss08'] = 'Stylistic Set 8', - ['ss09'] = 'Stylistic Set 9', - ['ss10'] = 'Stylistic Set 10', - ['ss11'] = 'Stylistic Set 11', - ['ss12'] = 'Stylistic Set 12', - ['ss13'] = 'Stylistic Set 13', - ['ss14'] = 'Stylistic Set 14', - ['ss15'] = 'Stylistic Set 15', - ['ss16'] = 'Stylistic Set 16', - ['ss17'] = 'Stylistic Set 17', - ['ss18'] = 'Stylistic Set 18', - ['ss19'] = 'Stylistic Set 19', - ['ss20'] = 'Stylistic Set 20', - ['ssty'] = 'Script Style', -- math - ['subs'] = 'Subscript', - ['sups'] = 'Superscript', - ['swsh'] = 'Swash', - ['titl'] = 'Titling', - ['tjmo'] = 'Trailing Jamo Forms', - ['tnam'] = 'Traditional Name Forms', - ['tnum'] = 'Tabular Figures', - ['trad'] = 'Traditional Forms', - ['twid'] = 'Third Widths', - ['unic'] = 'Unicase', - ['valt'] = 'Alternate Vertical Metrics', - ['vatu'] = 'Vattu Variants', - ['vert'] = 'Vertical Writing', - ['vhal'] = 'Alternate Vertical Half Metrics', - ['vjmo'] = 'Vowel Jamo Forms', - ['vkna'] = 'Vertical Kana Alternates', - ['vkrn'] = 'Vertical Kerning', - ['vpal'] = 'Proportional Alternate Vertical Metrics', - ['vrt2'] = 'Vertical Rotation', - ['zero'] = 'Slashed Zero', + ['aalt'] = 'access all alternates', + ['abvf'] = 'above-base forms', + ['abvm'] = 'above-base mark positioning', + ['abvs'] = 'above-base substitutions', + ['afrc'] = 'alternative fractions', + ['akhn'] = 'akhands', + ['blwf'] = 'below-base forms', + ['blwm'] = 'below-base mark positioning', + ['blws'] = 'below-base substitutions', + ['c2pc'] = 'petite capitals from capitals', + ['c2sc'] = 'small capitals from capitals', + ['calt'] = 'contextual alternates', + ['case'] = 'case-sensitive forms', + ['ccmp'] = 'glyph composition/decomposition', + ['cjct'] = 'conjunct forms', + ['clig'] = 'contextual ligatures', + ['cpsp'] = 'capital spacing', + ['cswh'] = 'contextual swash', + ['curs'] = 'cursive positioning', + ['dflt'] = 'default processing', + ['dist'] = 'distances', + ['dlig'] = 'discretionary ligatures', + ['dnom'] = 'denominators', + ['dtls'] = 'dotless forms', -- math + ['expt'] = 'expert forms', + ['falt'] = 'final glyph alternates', + ['fin2'] = 'terminal forms #2', + ['fin3'] = 'terminal forms #3', + ['fina'] = 'terminal forms', + ['flac'] = 'flattened accents over capitals', -- math + ['frac'] = 'fractions', + ['fwid'] = 'full width', + ['half'] = 'half forms', + ['haln'] = 'halant forms', + ['halt'] = 'alternate half width', + ['hist'] = 'historical forms', + ['hkna'] = 'horizontal kana alternates', + ['hlig'] = 'historical ligatures', + ['hngl'] = 'hangul', + ['hojo'] = 'hojo kanji forms', + ['hwid'] = 'half width', + ['init'] = 'initial forms', + ['isol'] = 'isolated forms', + ['ital'] = 'italics', + ['jalt'] = 'justification alternatives', + ['jp04'] = 'jis2004 forms', + ['jp78'] = 'jis78 forms', + ['jp83'] = 'jis83 forms', + ['jp90'] = 'jis90 forms', + ['kern'] = 'kerning', + ['lfbd'] = 'left bounds', + ['liga'] = 'standard ligatures', + ['ljmo'] = 'leading jamo forms', + ['lnum'] = 'lining figures', + ['locl'] = 'localized forms', + ['mark'] = 'mark positioning', + ['med2'] = 'medial forms #2', + ['medi'] = 'medial forms', + ['mgrk'] = 'mathematical greek', + ['mkmk'] = 'mark to mark positioning', + ['mset'] = 'mark positioning via substitution', + ['nalt'] = 'alternate annotation forms', + ['nlck'] = 'nlc kanji forms', + ['nukt'] = 'nukta forms', + ['numr'] = 'numerators', + ['onum'] = 'old style figures', + ['opbd'] = 'optical bounds', + ['ordn'] = 'ordinals', + ['ornm'] = 'ornaments', + ['palt'] = 'proportional alternate width', + ['pcap'] = 'petite capitals', + ['pnum'] = 'proportional figures', + ['pref'] = 'pre-base forms', + ['pres'] = 'pre-base substitutions', + ['pstf'] = 'post-base forms', + ['psts'] = 'post-base substitutions', + ['pwid'] = 'proportional widths', + ['qwid'] = 'quarter widths', + ['rand'] = 'randomize', + ['rkrf'] = 'rakar forms', + ['rlig'] = 'required ligatures', + ['rphf'] = 'reph form', + ['rtbd'] = 'right bounds', + ['rtla'] = 'right-to-left alternates', + ['rtlm'] = 'right to left math', -- math + ['ruby'] = 'ruby notation forms', + ['salt'] = 'stylistic alternates', + ['sinf'] = 'scientific inferiors', + ['size'] = 'optical size', + ['smcp'] = 'small capitals', + ['smpl'] = 'simplified forms', + ['ss01'] = 'stylistic set 1', + ['ss02'] = 'stylistic set 2', + ['ss03'] = 'stylistic set 3', + ['ss04'] = 'stylistic set 4', + ['ss05'] = 'stylistic set 5', + ['ss06'] = 'stylistic set 6', + ['ss07'] = 'stylistic set 7', + ['ss08'] = 'stylistic set 8', + ['ss09'] = 'stylistic set 9', + ['ss10'] = 'stylistic set 10', + ['ss11'] = 'stylistic set 11', + ['ss12'] = 'stylistic set 12', + ['ss13'] = 'stylistic set 13', + ['ss14'] = 'stylistic set 14', + ['ss15'] = 'stylistic set 15', + ['ss16'] = 'stylistic set 16', + ['ss17'] = 'stylistic set 17', + ['ss18'] = 'stylistic set 18', + ['ss19'] = 'stylistic set 19', + ['ss20'] = 'stylistic set 20', + ['ssty'] = 'script style', -- math + ['subs'] = 'subscript', + ['sups'] = 'superscript', + ['swsh'] = 'swash', + ['titl'] = 'titling', + ['tjmo'] = 'trailing jamo forms', + ['tnam'] = 'traditional name forms', + ['tnum'] = 'tabular figures', + ['trad'] = 'traditional forms', + ['twid'] = 'third widths', + ['unic'] = 'unicase', + ['valt'] = 'alternate vertical metrics', + ['vatu'] = 'vattu variants', + ['vert'] = 'vertical writing', + ['vhal'] = 'alternate vertical half metrics', + ['vjmo'] = 'vowel jamo forms', + ['vkna'] = 'vertical kana alternates', + ['vkrn'] = 'vertical kerning', + ['vpal'] = 'proportional alternate vertical metrics', + ['vrt2'] = 'vertical rotation', + ['zero'] = 'slashed zero', - ['trep'] = 'Traditional TeX Replacements', - ['tlig'] = 'Traditional TeX Ligatures', + ['trep'] = 'traditional tex replacements', + ['tlig'] = 'traditional tex ligatures', + + ['ss'] = 'stylistic set %s', } local baselines = allocate { - ['hang'] = 'Hanging baseline', - ['icfb'] = 'Ideographic character face bottom edge baseline', - ['icft'] = 'Ideographic character face tope edige baseline', - ['ideo'] = 'Ideographic em-box bottom edge baseline', - ['idtp'] = 'Ideographic em-box top edge baseline', - ['math'] = 'Mathmatical centered baseline', - ['romn'] = 'Roman baseline' + ['hang'] = 'hanging baseline', + ['icfb'] = 'ideographic character face bottom edge baseline', + ['icft'] = 'ideographic character face tope edige baseline', + ['ideo'] = 'ideographic em-box bottom edge baseline', + ['idtp'] = 'ideographic em-box top edge baseline', + ['math'] = 'mathmatical centered baseline', + ['romn'] = 'roman baseline' } +tables.scripts = scripts +tables.languages = languages +tables.features = features +tables.baselines = baselines -local function swap(h) -- can be a tables.swap when we get a better name +if otffeatures.features then + for k, v in next, otffeatures.features do + features[k] = v + end + otffeatures.features = features +end + +local function swapped(h) local r = { } for k, v in next, h do - r[v] = lower(gsub(k," ","")) + r[gsub(v,"[^a-z0-9]","")] = k -- is already lower end return r end -local verbosescripts = allocate(swap(scripts )) -local verboselanguages = allocate(swap(languages)) -local verbosefeatures = allocate(swap(features )) +local verbosescripts = allocate(swapped(scripts )) +local verboselanguages = allocate(swapped(languages)) +local verbosefeatures = allocate(swapped(features )) +local verbosebaselines = allocate(swapped(baselines)) + +-- lets forget about trailing spaces -tables.scripts = scripts -tables.languages = languages -tables.features = features -tables.baselines = baselines +local function resolve(t,k) + if k then + k = gsub(lower(k),"[^a-z0-9]","") + local v = rawget(t,k) + if v then + return v + end + end + return "dflt" +end + +setmetatable(verbosescripts, { __index = resolve }) +setmetatable(verboselanguages, { __index = resolve }) +setmetatable(verbosefeatures, { __index = resolve }) +setmetatable(verbosebaselines, { __index = resolve }) -tables.verbosescripts = verbosescripts -tables.verboselanguages = verboselanguages -tables.verbosefeatures = verbosefeatures +local function resolve(t,k) + if k then + k = lower(k) + local v = rawget(t,k) or rawget(t,gsub(k," ","")) + if v then + return v + end + end + return "dflt" +end -for k, v in next, verbosefeatures do - local stripped = gsub(k,"%-"," ") - verbosefeatures[stripped] = v - local stripped = gsub(k,"[^a-zA-Z0-9]","") - verbosefeatures[stripped] = v +local function assign(t,k,v) + -- forget about it end -for k, v in next, verbosefeatures do - verbosefeatures[lower(k)] = v + +setmetatable(scripts, { __index = resolve, __newindex = assign }) +setmetatable(languages, { __index = resolve, __newindex = assign }) +setmetatable(baselines, { __index = resolve, __newindex = assign }) + +local function resolve(t,k) + if k then + k = lower(k) + local v = rawget(t,k) + if v then + return v + end + k = gsub(k," ","") + local v = rawget(t,k) + if v then + return v + end + local tag, dd = match(k,"(..)(%d+)") + if tag and dd then + local v = rawget(t,tag) + if v then + return format(v,tonumber(dd)) + end + end + end + return "dflt" end -local function resolve(tab,id) - if tab and id then - id = lower(id) - return tab[id] or tab[gsub(id," ","")] or tab['dflt'] or '' - else - return "unknown" +local function assign(t,k,v) + if k then + v = lower(v) + rawset(t,k,v) + rawset(features,gsub(v,"[^a-z0-9]",""),k) end end -function meanings.script (id) return resolve(scripts, id) end -function meanings.language(id) return resolve(languages,id) end -function meanings.feature (id) return resolve(features, id) end -function meanings.baseline(id) return resolve(baselines,id) end +setmetatable(features, { __index = resolve, __newindex = assign }) local checkers = { rand = function(v) @@ -690,26 +735,24 @@ local checkers = { end } -meanings.checkers = checkers - -function meanings.normalize(features) +function otf.features.normalize(features) -- no longer 'lang' if features then local h = { } for k,v in next, features do k = lower(k) - if k == "language" or k == "lang" then - v = gsub(lower(v),"[^a-z0-9%-]","") - if not languages[v] then - h.language = verboselanguages[v] or "dflt" - else + if k == "language" then + v = gsub(lower(v),"[^a-z0-9]","") + if rawget(languages,v) then h.language = v + else + h.language = rawget(verboselanguages,v) or "dflt" end elseif k == "script" then - v = gsub(lower(v),"[^a-z0-9%-]","") - if not scripts[v] then - h.script = verbosescripts[v] or "dflt" - else + v = gsub(lower(v),"[^a-z0-9]","") + if rawget(scripts,v) then h.script = v + else + h.script = rawget(verbosescripts,v) or "dflt" end else if type(v) == "string" then @@ -720,7 +763,9 @@ function meanings.normalize(features) v = b end end - k = verbosefeatures[k] or k + if not rawget(features,k) then + k = rawget(verbosefeatures,k) or k + end local c = checkers[k] h[k] = c and c(v) or v end @@ -729,6 +774,8 @@ function meanings.normalize(features) end end +--~ table.print(otf.features.normalize({ language = "dutch", liga = "yes", ss99 = true, aalt = 3, abcd = "yes" } )) + -- When I feel the need ... --~ tables.aat = { |