Module:Headword/data

維基詞典,自由的多語言詞典
跳到导航 跳到搜索
local data = {}

data.invariable = {
	"cmavo",
	"cmene",
	"fu'ivla",
	"gismu",
	"Han tu","漢字","汉字",
	"hanzi","漢字","汉字",
	"hanja","漢字","汉字",
	"jyutping","粤语拼音","粵語拼音",
	"kanji","漢字","汉字",
	"lujvo",
	"phrasebook",
	"pinyin","拼音",
	"rafsi",
	"romaji","羅馬字","罗马字",
}

data.lemmas = {
	"abbreviation","縮寫","缩写",
	"acronym","首字母縮略詞","首字母缩略词",
	"adjective","形容詞","形容词",
	"adnominal",
	"adposition",
	"adverb","副詞","副词",
	"affix","綴詞","缀词",
	"ambiposition",
	"article","冠詞","冠词",
	"circumfix","環綴","环缀",
	"circumposition",
	"classifier","量詞","量词",
	"cmavo",
	"cmavo cluster",
	"cmene",
	"combining form",
	"comparative adjective",
	"comparative adverb",
	"conjunction","連詞","连词",
	"counter","量詞","量词",
	"determiner","限定詞","限定词",
	"diacritical mark","附加符號","附加符号",
	"equative adjective",
	"fu'ivla",
	"gismu",
	"Han character","漢字","汉字",
	"Han tu","漢字","汉字",
	"hanzi","漢字","汉字",
	"hanja","漢字","汉字",
	"ideophones","擬態詞",
	"idiom","熟語","熟语","俗語","俗语",
	"infix","中綴","中缀",
	"interfix","間綴","间缀",
	"initialism","首字母縮略詞","首字母缩略词",
	"interjection","感嘆詞","感叹词","感歎詞",
	"kanji","漢字","汉字",
	"letter","字母",
	"ligature","合字",
	"lujvo",
	"morpheme","詞素","词素",
	"non-constituent",
	"noun","名詞","名词",
	"number","數字","数字",
	"numeral symbol","數字符號","数字符号",
	"numeral","數詞","数词",
	"particle","助詞","助词",
	"phrase","短語","短语",
	"postposition","後置詞", "后置词",
	"predicative", "表語", "表语",
	"prefix","前綴","前缀",
	"preposition","介詞","介词",
	"prepositional phrase","介詞短語","介词短语",
	"preverb",
	"pronominal adverb",
	"pronoun","代詞","代词",
	"proverb","諺語","谚语",
	"proper noun","專有名詞","专有名词",
	"punctuation mark","標點符號", "标点符号",
	"relative","關係詞",
	"root","詞根","词根",
	"stem","詞幹","词干",
	"suffix","後綴","后缀",
	"superlative adjective",
	"superlative adverb",
	"syllable","音節","音节",
	"symbol","符號","符号",
	"verb","動詞","动词",
}

data.nonlemmas = {
	"active participle","主動分詞","主动分词",
	"adjectival participle",
	"adjective form","形容詞形式","形容词形式","形容詞變格形","形容词变格形",
	"adjective comparative form","形容詞比較級","形容词比较级",
	"adjective feminine form","形容詞陰性變格形","形容词阴性变格形",
	"adjective equative form",
	"adjective plural form","形容詞複數變格形","形容词复数变格形",
	"adjective superlative form","形容詞最高級","形容词最高级",
	"adverb form","副詞形式","副词形式","副詞變格形","副词变格形",
	"adverb comparative form","副詞比較級","副词比较级",
	"adverb superlative form","副詞最高級","副词最高级",
	"adverbial participle",
	"agent participle",
	"article form","冠詞形式","冠词形式","冠詞變格形","冠词变格形",
	"circumfix form",
	"combined form",
	"contraction","縮約形","缩约形",
	"converb",
	"determiner comparative form","限定詞比較級","限定词比较级",
	"determiner form","限定詞形式","限定词形式","限定詞變格形","限定词变格形",
	"determiner superlative form","限定詞最高級","限定词最高级",
	"diminutive noun","名詞指小詞","名词指小词",
	"future participle",
	"gerund","動名詞","动名词",
	"infinitive form","不定式",
	"infinitive",
	"interjection form","感嘆詞形式","感叹词形式","感嘆詞變格形","感叹词变格形",
	"jyutping",
	"kanji reading",
	"misspelling","拼錯","拼错","拼寫錯誤","拼写错误",
	"negative participle","否定分詞","否定分词",
	"nominal participle",
	"noun case form",
	"noun dual form","名詞雙數形式",
	"noun form","名詞形式","名词形式","名詞變格形","名词变格形",
	"noun plural form","名詞複數形式","名词复数形式",
	"noun possessive form","名詞所有格","名词所有格",
	"noun singulative form",
	"numeral form","數詞形式","数词形式","數詞變格形","数词变格形",
	"participle","分詞","分词",
	"participle form","分詞變格形","分词变格形",
	"particle form","助詞形式","助词形式","助詞變格形","助词变格形",
	"passive participle","被動分詞","被动分词",
	"past active participle","過去主動分詞","过去主动分词",
	"past participle","過去分詞","过去分词",
	"past participle form","過去分詞變格形","过去分词变格形","過去分詞形式","过去分词形式",
	"past passive participle","過去被動分詞","过去被动分词",
	"perfect active participle","完成主動分詞","完成主动分词",
	"perfect participle","完成分詞","完成分词",
	"perfect passive participle","完成被動分詞","完成被动分词",
	"pinyin","拼音",
	"plural","複數","复数",
	"postposition form","後置形式","后置形式",
	"prefix form","前綴形式","前缀形式",
	"preposition contraction",
	"preposition form","介詞形式","介词形式","介詞變格形","介词变格形",
	"prepositional pronoun","介詞性代詞",
	"present active participle","現在主動分詞","现在主动分词",
	"present participle","現在分詞","现在分词",
	"present passive participle","現在被動分詞","现在被动分词",
	"pronoun form","代詞形式","代词形式","代詞變格形","代词变格形",
	"pronoun possessive form",
	"proper noun form","專有名詞形式","专有名词形式","專有名詞變格形","专有名词变格形",
	"proper noun plural form","專有名詞複數形式","专有名词复数形式",
	"rafsi",
	"romanization","羅馬化","罗马化",
	"romaji","羅馬字","罗马字",
	"singulative",
	"suffix form","後綴形式","后缀形式",
	"verb form","動詞形式","动词形式","動詞變位形式","动词变位形式",
	"verbal noun","動名詞","动名词",
}

data.notranslit = {
	"am",
	"az",
	"bbc",
	"bug",
	"cia",
	"cjm",
	"cmn",
	"hak",
	"ja",
	"kzg",
	"lad",
	"lzh",
	"m",
	"mul",
	"mvi",
	"nan",
	"oj",
	"okn",
	"pi",
	"ro",
	"ryn",
	"ry",
	"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",
}
-- These languages will not have "LANG multiword terms" categories added.
data.no_multiword_cat = {
	-------- Languages without spaces between words (sometimes spaces between phrases) --------
	--"blt", -- Tai Nüa; not sure
	"ja", -- Japanese
	"km", -- Khmer
	"lo", -- Lao; to be checked
	"mnw", -- Mon
	"my", -- Burmese
	"nan", -- Min Nan (some words in Latin script; hyphens between syllables)
	"ojp", -- Old Japanese
	--"tdd", -- Tai Nüa; not sure
	--"th", -- Thai; there could be phrases, to be checked
	--"twh", -- Tai Dón; not sure
	"zh", -- Chinese (all varieties with Chinese characters)

	-------- Languages with spaces between syllables --------
	"ahk", -- Akha
	"aho", -- Ahom
	"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
	"my", -- Burmese
	--"sit-gkh", -- Gokhy; not sure
	--"swi", -- Sui; not sure
	"tbq-lol-pro", -- Proto-Loloish
	"tdh", -- Thulung
	"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.
	"lcp", -- Western Lawa; dash as syllable joiner
	"lwl", -- Eastern Lawa; dash as syllable joiner

	-------- 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",
}
-- 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",
}

-- 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
	"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
	"mkh-vie-pro", -- Proto-Vietic; morphemes separated by hyphens
}


for key, list in pairs(data) do
	data[key] = 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 = {
	["名詞"] = "名詞",
	["專有名詞"] = "名詞",
	["後綴"] = "後綴",
	-- We include verbs because impf and pf are valid "genders".
	["動詞"] = "動詞",
}

return data