Modul:headword/data

local data = {}

data.invariable = {
	"betűk",
	"determinánsok",
	"elöljárószók",
	"posztpozíciók",
	"felsőfokú melléknevek",
	"földrajzi nevek",
	"főnevek",
	"főnévalakok",
	"gyökök",
	"határozószók",
	"hímnemű főnevek",
	"igealakok",
	"igék",
	"indulatszók",
	"kicsinyítő főnevek",
	"többes számú főnevek",
	"kifejezések",
	"kötőszók",
	"melléknevek",
	"melléknévi igenevek",
	"névmások",
	"kérdő névmások",
	"névelők",
	"nőnemű főnevek",
	"partikulák",
	"semlegesnemű főnevek",
	"számjegyek",
	"számnevek",
	"szóalakok",
	"tulajdonnevek",
	"többes számú alakok",
	
}

data.lemmas = {
	"elöljárószók",
	"determinánsok",
	"földrajzi nevek",
	"főnevek",
	"határozószók",
	"hímnemű főnevek",
	"igekötők",
	"igék",
	"indulatszók",
	"kicsinyítő főnevek",
	"kifejezések",
	"kötőszók",
	"közmondások",
	"melléknevek",
	"melléknévi igenevek",
	"mozaikszók",
	"névmások",
	"névelők",
	"nőnemű főnevek",
	"partikulák",
	"posztpozíciók",
	"semlegesnemű főnevek",
	"számnevek",
	"szóalakok",
	"szókapcsolatok",
	"tulajdonnevek",
	"szuffixumok",
 
}

data.nonlemmas = {
	"nonlemma",
	"nonlemmas",
	"többes számú alakok",
	"többes számú főnevek",
	"főnévalakok",
	"igealakok",
	"betűk",
	"számjegyek",
	"felsőfokú melléknevek",
}

-- These languages will not have "LANG multiword terms" categories added.
data.no_multiword_cat = {
	-------- Languages without spaces between words (sometimes spaces between phrases) --------
	"aho", -- Ahom
	"blt", -- Tai Dam
	"ja", -- Japanese
	"khb", -- Lü
	"km", -- Khmer
	"lo", -- Lao
	"mnw", -- Mon
	"my", -- Burmese
	"nan", -- Min Nan (some words in Latin script; hyphens between syllables)
	"nod", -- Northern Thai
	"ojp", -- Old Japanese
	"tdd", -- Tai Nüa
	"th", -- Thai
	"tts", -- Isan
	"twh", -- Tai Dón
	"shn", -- Shan
	"sou", -- Southern Thai
	"zh", -- Chinese (all varieties with Chinese characters)

	-------- Languages with spaces between syllables --------
	"ahk", -- Akha
	"aou", -- A'ou
	"atb", -- Zaiwa
	"byk", -- Biao
	--"duu", -- Drung; not sure
	--"hmx-pro", -- Proto-Hmong-Mien
	--"hnj", -- Green Hmong; not sure
	"huq", -- Tsat
	"ium", -- Iu Mien
	--"lis", -- Lisu; not sure
	"mtq", -- Muong
	--"mww", -- White Hmong; not sure
	"onb", -- Lingao
	--"sit-gkh", -- Gokhy; not sure
	--"swi", -- Sui; not sure
	"tbq-lol-pro", -- Proto-Loloish
	"tdh", -- Thulung
	"ukk", -- Muak Sa-aak
	"vi", -- Vietnamese
	"yig", -- Wusa Nasu
	"zng", -- Mang

	-------- Languages with ~ with surrounding spaces used to separate variants --------
	"mkh-ban-pro", -- Proto-Bahnaric
	"sit-pro", -- Proto-Sino-Tibetan; listed above
	
	-------- Other weirdnesses --------
	"mul", -- Translingual; gestures, Morse code, etc.
	"aot", -- Atong (India); bullet is a letter

	-------- All sign languages	--------
	"ads",
	"aed",
	"aen",
	"afg",
	"ase",
	"asf",
	"asp",
	"asq",
	"asw",
	"bfi",
	"bfk",
	"bog",
	"bqn",
	"bqy",
	"bvl",
	"bzs",
	"cds",
	"csc",
	"csd",
	"cse",
	"csf",
	"csg",
	"csl",
	"csn",
	"csq",
	"csr",
	"doq",
	"dse",
	"dsl",
	"ecs",
	"esl",
	"esn",
	"eso",
	"eth",
	"fcs",
	"fse",
	"fsl",
	"fss",
	"gds",
	"gse",
	"gsg",
	"gsm",
	"gss",
	"gus",
	"hab",
	"haf",
	"hds",
	"hks",
	"hos",
	"hps",
	"hsh",
	"hsl",
	"icl",
	"iks",
	"ils",
	"inl",
	"ins",
	"ise",
	"isg",
	"isr",
	"jcs",
	"jhs",
	"jls",
	"jos",
	"jsl",
	"jus",
	"kgi",
	"kvk",
	"lbs",
	"lls",
	"lsl",
	"lso",
	"lsp",
	"lst",
	"lsy",
	"lws",
	"mdl",
	"mfs",
	"mre",
	"msd",
	"msr",
	"mzc",
	"mzg",
	"mzy",
	"nbs",
	"ncs",
	"nsi",
	"nsl",
	"nsp",
	"nsr",
	"nzs",
	"okl",
	"pgz",
	"pks",
	"prl",
	"prz",
	"psc",
	"psd",
	"psg",
	"psl",
	"pso",
	"psp",
	"psr",
	"pys",
	"rms",
	"rsl",
	"rsm",
	"sdl",
	"sfb",
	"sfs",
	"sgg",
	"sgx",
	"slf",
	"sls",
	"sqk",
	"sqs",
	"ssp",
	"ssr",
	"svk",
	"swl",
	"syy",
	"tse",
	"tsm",
	"tsq",
	"tss",
	"tsy",
	"tza",
	"ugn",
	"ugy",
	"ukl",
	"uks",
	"vgt",
	"vsi",
	"vsl",
	"vsv",
	"xki",
	"xml",
	"xms",
	"ygs",
	"ysl",
	"zib",
	"zsl",
}

-- In these languages, the hyphen is not considered a word separator for the "multiword terms" category.
data.hyphen_not_multiword_sep = {
	"akk", -- Akkadian; hyphens between syllables
	"akl", -- Aklanon; hyphens for mid-word glottal stops
	"ber-pro", -- Proto-Berber; morphemes separated by hyphens
	"ceb", -- Cebuano; hyphens for mid-word glottal stops
	"cnk", -- Khumi Chin; hyphens used in single words
	"cpi", -- Chinese Pidgin English; Chinese-derived words with hyphens between syllables
	"de", -- too many false positives
	"esx-esk-pro", -- hyphen used to separate morphemes
	"fi", -- Finnish; hyphen used to separate components in compound words if the final and initial vowels match, respectively
	"hil", -- Hiligaynon; hyphens for mid-word glottal stops
	"ilo", -- Ilocano; hyphens for mid-word glottal stops
	"lcp", -- Western Lawa; dash as syllable joiner
	"lwl", -- Eastern Lawa; dash as syllable joiner
	"mkh-vie-pro", -- Proto-Vietic; morphemes separated by hyphens
	"msb", -- Masbatenyo; too many false positives
	"tl", -- Tagalog; too many false positives
	"war", -- Waray-Waray; too many false positives
}

-- These languages will not have "LANG masculine nouns" and similar categories added.
data.no_gender_cat = {
	-- Languages without gender but which use the gender field for other purposes
	"ja",
	"th",
}

data.notranslit = {
	"ams",
	"az",
	"bbc",
	"bug",
	"cia",
	"cjm",
	"cmn",
	"hak",
	"ja",
	"kzg",
	"lad",
	"lzh",
	"ms",
	"mul",
	"mvi",
	"nan",
	"oj",
	"okn",
	"pi",
	"ro",
	"ryn",
	"rys",
	"ryu",
	"sh",
	"tgt",
	"th",
	"tkn",
	"tly",
	"und",
	"vi",
	"xug",
	"yue",
	"yoi",
	"yox",
	"za",
	"zh",
}

-- Script codes for which a script-tagged display title will be added.	
data.toBeTagged = {
	"Ahom",
	"Arab",
	"Avst",
	"Bali",
	"Cham",
	"Copt",
	"Kali",
	"Hani",
	"Hebr",
	"Lana",
	"Linb",
	"Mand",
	"Mong",
	"polytonic",
	"Rjng",
	"Samr",
	"Sund",
	"Sylo",
	"Tang",
	"Tavt",
	"Xsux",
}

for key, list in pairs(data) do
	data = require("Module:utils").list_to_set(list)
end
-- Parts of speech for which categories like "German masculine nouns" or "Russian imperfective verbs"
-- will be generated if the headword is of the appropriate gender/number. We put this at the bottom
-- because it's a map, not a list.
data.pos_for_gender_number_cat = {
	 = "nouns",
	 = "nouns",
	 = "suffixes",
	-- We include verbs because impf and pf are valid "genders".
	 = "verbs",
}

return data