Module:headword/data - Revision history

Sware at 21:44, 14 November 2025

2025-11-14T21:44:00Z

← Older revision		Revision as of 21:44, 14 November 2025
Line 149:		Line 149:
	"nominal participles",		"nominal participles",
	"noun case forms",		"noun case forms",
			"noun construct forms",
	"noun dual forms",		"noun dual forms",
	"noun forms",		"noun forms",
Line 680:		Line 681:
	adv = "adverb",		adv = "adverb",
	art = "article",		art = "article",
			aug = "augmentative",
	det = "determiner",		det = "determiner",
	~~cnum~~ = "~~cardinal number~~",		dim = "diminutive",
	compadj = "comparative adjective",		compadj = "comparative adjective",
	compadv = "comparative adverb",		compadv = "comparative adverb",
	conj = "conjunction",		conj = "conjunction",
			contr = "contraction",
	conv = "converb",		conv = "converb",
	int = "interjection",		int = "interjection",
Line 690:		Line 693:
	intj = "interjection",		intj = "interjection",
	n = "noun",		n = "noun",
			-- the next two support Algonquian languages; see also vii/vai/vti/vta below
			na = "animate noun",
			ni = "inanimate noun",
	num = "numeral",		num = "numeral",
	part = "participle",		part = "participle",
Line 698:		Line 704:
	pref = "prefix",		pref = "prefix",
	prep = "preposition",		prep = "preposition",
			prepphr = "prepositional phrase",
	pron = "pronoun",		pron = "pronoun",
	prop = "proper noun",		prop = "proper noun",
	proper = "proper noun",		proper = "proper noun",
	propn = "proper noun",		propn = "proper noun",
	~~onum = "ordinal number",~~
	rom = "romanization",		rom = "romanization",
	suf = "suffix",		suf = "suffix",
	supadj = "superlative adjective",		supadj = "superlative adjective",
	supadv = "superlative adverb",		supadv = "superlative adverb",
			sym = "symbol",
	v = "verb",		v = "verb",
	vb = "verb",		vb = "verb",
	vi = "intransitive verb",		vi = "intransitive verb",
	vt = "transitive verb",		vt = "transitive verb",
	vti = "transitive ~~and intransitive~~ verb",		-- the next four support Algonquian languages
			vii = "inanimate intransitive verb",
			vai = "animate intransitive verb",
			vti = "transitive inanimate verb",
			vta = "transitive animate verb",
	}		}

Line 722:		Line 733:
	-- We include verbs because impf and pf are valid "genders".		-- We include verbs because impf and pf are valid "genders".
	["verbs"] = "verbs",		["verbs"] = "verbs",
			}

			-- Lower limit for a "long" word in a particular language.
			-- Used to categorize terms into e.g. [[:Category:Long English words]] automatically.
			-- Languages with no mapping here do not get categorized.
			data.long_word_thresholds = {
			["af"] = 20,
			["bg"] = 20,
			["cy"] = 25,
			["de"] = 20,
			["en"] = 25,
			["es"] = 20,
			["fr"] = 20,
			["ka"] = 20,
			["sv"] = 20,
			["tl"] = 25,
	}		}

Sware at 12:26, 8 January 2025

2025-01-08T12:26:42Z

← Older revision		Revision as of 12:26, 8 January 2025
Line 23:		Line 23:
	"pinyin",		"pinyin",
	"rafsi",		"rafsi",
	~~"romaji",~~		}, function(_, item)
	}, function(item)
	return item		return item
	end)		end)

	-- Irregular non-zero plurals AND any regular plurals where the singular ends in "s",		-- Irregular non-zero plurals AND any regular plurals where the singular ends in "s",
	-- because the module assumes that inputs ending in "s" are plurals.		-- because the module assumes that inputs ending in "s" are plurals. The singular and
	for k, v in next, {		-- plural both need to be added, as the module will generate a default plural if
			-- the input doesn't match a key in this table.
			for sg, pl in next, {
	mora = "morae"		mora = "morae"
	} do		} do
	irregular_plurals[k] ~~= v~~		irregular_plurals[sg], irregular_plurals[pl] = pl, pl
	irregular_plurals[v] = ~~v -- Ensures singular and plural inputs work as expected.~~
	end		end

	~~data.invariable = irregular_plurals -- To be removed.~~
	data.irregular_plurals = irregular_plurals		data.irregular_plurals = irregular_plurals

Line 162:		Line 161:
	"passive participles",		"passive participles",
	"past active participles",		"past active participles",
			"past adverbial participles",
	"past participles",		"past participles",
	"past participle forms",		"past participle forms",
Line 176:		Line 176:
	"prepositional pronouns",		"prepositional pronouns",
	"present active participles",		"present active participles",
			"present adverbial participles",
	"present participles",		"present participles",
	"present passive participles",		"present passive participles",
			"preverb forms",
	"pronoun forms",		"pronoun forms",
	"pronoun possessive forms",		"pronoun possessive forms",
Line 413:		Line 415:
	"fi", -- Finnish; hyphen used to separate components in compound words if the final and initial vowels match, respectively		"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		"hil", -- Hiligaynon; hyphens for mid-word glottal stops
			"hnn", -- Hanunoo; too many false positives
	"ilo", -- Ilocano; hyphens for mid-word glottal stops		"ilo", -- Ilocano; hyphens for mid-word glottal stops
	"kne", -- Kankanaey; hyphens for mid-word glottal stops		"kne", -- Kankanaey; hyphens for mid-word glottal stops
Line 437:		Line 440:
	"bbc",		"bbc",
	"bug",		"bug",
			"cdo",
	"cia",		"cia",
	"cjm",		"cjm",
			"cjy",
	"cmn",		"cmn",
			"cnp",
	"cpi",		"cpi",
			"cpx",
			"csp",
			"czh",
			"czo",
			"gan",
	"hak",		"hak",
			"hnm",
			"hsn",
	"ja",		"ja",
	"kzg",		"kzg",
	"lad",		"lad",
			"ltc",
			"luh",
	"lzh",		"lzh",
			"mnp",
	"ms",		"ms",
	"mul",		"mul",
	"mvi",		"mvi",
	"nan",		"nan",
			"nan-dat",
	"nan-hbl",		"nan-hbl",
	"nan-~~hnm~~",		"nan-hlh",
	"nan-~~luh~~",		"nan-lnx",
	"nan-tws",		"nan-tws",
			"nan-zhe",
			"nan-zsh",
			"och",
	"oj",		"oj",
	"okn",		"okn",
Line 460:		Line 480:
	"ryu",		"ryu",
	"sh",		"sh",
			"sjc",
	"tgt",		"tgt",
	"th",		"th",
Line 467:		Line 488:
	"und",		"und",
	"vi",		"vi",
			"wuu",
	"xug",		"xug",
	"yoi",		"yoi",
Line 473:		Line 495:
	"za",		"za",
	"zh",		"zh",
			"zhx-sic",
			"zhx-tai",
	}		}

Line 658:		Line 682:
	det = "determiner",		det = "determiner",
	cnum = "cardinal number",		cnum = "cardinal number",
			compadj = "comparative adjective",
			compadv = "comparative adverb",
	conj = "conjunction",		conj = "conjunction",
	conv = "converb",		conv = "converb",
Line 670:		Line 696:
	pn = "proper noun",		pn = "proper noun",
	postp = "postposition",		postp = "postposition",
	~~pre~~ = "~~preposition~~",		pref = "prefix",
	prep = "preposition",		prep = "preposition",
	~~pro = "pronoun",~~
	pron = "pronoun",		pron = "pronoun",
	prop = "proper noun",		prop = "proper noun",
	proper = "proper noun",		proper = "proper noun",
			propn = "proper noun",
	onum = "ordinal number",		onum = "ordinal number",
			rom = "romanization",
			suf = "suffix",
			supadj = "superlative adjective",
			supadv = "superlative adverb",
	v = "verb",		v = "verb",
	vb = "verb",		vb = "verb",

Sware at 09:39, 31 July 2024

2024-07-31T09:39:32Z

Show changes

Sware at 18:07, 6 July 2021

2021-07-06T18:07:04Z

← Older revision		Revision as of 18:07, 6 July 2021
Line 77:		Line 77:
	"proper nouns",		"proper nouns",
	"punctuation marks",		"punctuation marks",
			"relative pronouns",
	"relatives",		"relatives",
	"roots",		"roots",

Sware at 22:20, 21 May 2021

2021-05-21T22:20:50Z

← Older revision		Revision as of 22:20, 21 May 2021
Line 31:		Line 31:
	"circumpositions",		"circumpositions",
	"classifiers",		"classifiers",
			"clitics",
	"cmavo",		"cmavo",
	"cmavo clusters",		"cmavo clusters",

Sware: Created page with "local data = {} data.invariable = { "cmavo", "cmene", "fu'ivla", "gismu", "Han tu", "hanzi", "hanja", "jyutping", "kanji", "lujvo", "phrasebook", "pinyin", "rafs..."

2021-02-15T14:28:10Z

Created page with "local data = {} data.invariable = { "cmavo", "cmene", "fu'ivla", "gismu", "Han tu", "hanzi", "hanja", "jyutping", "kanji", "lujvo", "phrasebook", "pinyin", "rafs..."

New page

local data = {}

data.invariable = {
"cmavo",
"cmene",
"fu'ivla",
"gismu",
"Han tu",
"hanzi",
"hanja",
"jyutping",
"kanji",
"lujvo",
"phrasebook",
"pinyin",
"rafsi",
"romaji",
}

data.lemmas = {
"abbreviations",
"acronyms",
"adjectives",
"adnominals",
"adpositions",
"adverbs",
"affixes",
"ambipositions",
"articles",
"circumfixes",
"circumpositions",
"classifiers",
"cmavo",
"cmavo clusters",
"cmene",
"combining forms",
"conjunctions",
"counters",
"determiners",
"diacritical marks",
"equative adjectives",
"fu'ivla",
"gismu",
"Han characters",
"Han tu",
"hanzi",
"hanja",
"ideophones",
"idioms",
"infixes",
"interfixes",
"initialisms",
"interjections",
"kanji",
"letters",
"ligatures",
"lujvo",
"morphemes",
"non-constituents",
"nouns",
"numbers",
"numeral symbols",
"numerals",
"particles",
"phrases",
"postpositions",
"postpositional phrases",
"predicatives",
"prefixes",
"prepositions",
"prepositional phrases",
"preverbs",
"pronominal adverbs",
"pronouns",
"proverbs",
"proper nouns",
"punctuation marks",
"relatives",
"roots",
"stems",
"suffixes",
"syllables",
"symbols",
"verbs",
}

data.nonlemmas = {
"active participles",
"adjectival participles",
"adjective forms",
"adjective feminine forms",
"adjective plural forms",
"adverb forms",
"adverbial participles",
"agent participles",
"article forms",
"circumfix forms",
"combined forms",
"comparative adjective forms",
"comparative adjectives",
"comparative adverb forms",
"comparative adverbs",
"contractions",
"converbs",
"determiner comparative forms",
"determiner forms",
"determiner superlative forms",
"diminutive nouns",
"equative adjective forms",
"equative adjectives",
"future participles",
"gerunds",
"infinitive forms",
"infinitives",
"interjection forms",
"jyutping",
"kanji readings",
"misspellings",
"negative participles",
"nominal participles",
"noun case forms",
"noun dual forms",
"noun forms",
"noun plural forms",
"noun possessive forms",
"noun singulative forms",
"numeral forms",
"participles",
"participle forms",
"particle forms",
"passive participles",
"past active participles",
"past participles",
"past participle forms",
"past passive participles",
"perfect active participles",
"perfect participles",
"perfect passive participles",
"pinyin",
"plurals",
"postposition forms",
"prefix forms",
"preposition contractions",
"preposition forms",
"prepositional pronouns",
"present active participles",
"present participles",
"present passive participles",
"pronoun forms",
"pronoun possessive forms",
"proper noun forms",
"proper noun plural forms",
"rafsi",
"romanizations",
"root forms",
"singulatives",
"suffix forms",
"superlative adjective forms",
"superlative adjectives",
"superlative adverb forms",
"superlative adverbs",
"verb forms",
"verbal nouns",
}

-- 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
--"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.
"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
"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
"lcp", -- Western Lawa; dash as syllable joiner
"lwl", -- Eastern Lawa; dash as syllable joiner
"mkh-vie-pro", -- Proto-Vietic; morphemes separated by hyphens
}

-- 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[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 = {
["nouns"] = "nouns",
["proper nouns"] = "nouns",
-- We include verbs because impf and pf are valid "genders".
["verbs"] = "verbs",
}

return data