မဝ်ဂျူ:headword/data
Documentation for this module may be created at မဝ်ဂျူ:headword/data/doc
local headword_page_module = "Module:headword/page"
local list_to_set = require("Module:table").listToSet
local data = {}
------ 1. Lists which are converted into sets. ------
-- Zero-plurals (i.e. invariable plurals).
local irregular_plurals = list_to_set({
"cmavo",
"cmene",
"fu'ivla",
"gismu",
"Han tu",
"hanja",
"hanzi",
"jyutping",
"kana",
"kanji",
"lujvo",
"phrasebook",
"pinyin",
"rafsi",
}, function(item)
return item
end)
-- 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. The singular and
-- 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"
} do
irregular_plurals[sg], irregular_plurals[pl] = pl, pl
end
data.irregular_plurals = irregular_plurals
data.lemmas = list_to_set{
"အက္ခရ်ဂၠေံ",
"ဝေါဟာဂၠေံ",
"နာမဝိသေသန",
"အာက်နဝ်မာဲနဝ်",
"adpositions",
"ကြိယာဝိသေသန",
"affixes",
"ambipositions",
"လိက်ပရေၚ်",
"circumfixes",
"circumpositions",
"classifiers",
"cmavo",
"cmavo clusters",
"cmene",
"combining forms",
"သမ္ဗန္ဓ",
"counters",
"determiners",
"diacritical marks",
"digraphs",
"equative adjectives",
"fu'ivla",
"gismu",
"Han characters",
"Han tu",
"hanja",
"hanzi",
"ideophones",
"idioms",
"infixes",
"initialisms",
"iteration marks",
"interfixes",
"interjections",
"kana",
"kanji",
"letters",
"ligatures",
"logograms",
"lujvo",
"morae",
"morphemes",
"non-constituents",
"နာမ်",
"ဂၞန်သင်္ချာ",
"သင်္ကေတဂၞန်သင်္ချာ",
"ဂၞန်သင်္ချာ",
"particles",
"မအရေဝ်",
"postpositions",
"postpositional phrases",
"predicatives",
"prefixes",
"prepositional phrases",
"ဝိဘတ်",
"preverbs",
"pronominal adverbs",
"သဗ္ဗနာမ်",
"နာမ်မကိတ်ညဳ",
"proverbs",
"punctuation marks",
"relatives",
"တံရိုဟ်",
"stems",
"suffixes",
"syllables",
"symbols",
"ကြိယာ",
}
data.nonlemmas = list_to_set{
"ဗီုပြင်လုပ်ကၠောန်စွံလဝ်နကဵုမစိုပ်တရဴ",
"လုပ်ကၠောန်စွံလဝ်နကဵုမစိုပ်တရဴ",
"adjectival participles",
"ဗီုပြင်နာမဝိသေသန",
"နာမဝိသေသနဗီုပြင်ဣတ္တိလိင်",
"နာမဝိသေသနဗီုပြင်ကိုန်ဗဟုဝစ်",
"ဗီုပြင်ကြိယာဝိသေသန",
"adverb forms",
"adverbial participles",
"agent participles",
"article forms",
"circumfix forms",
"combined forms",
"ဗီုပြင်ပတုပ်ရံင်နာမဝိသေသန",
"နာမဝိသေသနပတုပ်ရံင်",
"ဗီုပြင်ပတုပ်ရံင်ကြိယာဝိသေသန",
"ကြိယာဝိသေသနပတုပ်ရံင်",
"ပွမထညောံ",
"contractions",
"converbs",
"determiner comparative forms",
"ဗီုပြင်ဖျေံလဝ်သန္နိဋ္ဌာန်",
"determiner superlative forms",
"diminutive nouns",
"elative adjectives",
"equative adjective forms",
"equative adjectives",
"future participles",
"gerunds",
"infinitive forms",
"infinitives",
"interjection forms",
"jyutping",
"kanji readings",
"negative participles",
"nominal participles",
"သဗ္ဗနာမ်ဝိဘတ်",
"ဗီုပြင်ရုပ်နာမ်",
"နာမ်ဗီုပြၚ်ၜါလ္ပာ်",
"ဗီုပြင်နာမ်",
"ဗီုပြင်နာမ်ပဝ်ကာယ်လ်",
"နာမ်ဗီုပြင်ကိုန်ဗဟုဝစ်",
"နာမ်ဗီုပြင်ပိုင်ပြဳ",
"နာမ်ဗီုပြင်ကိုန်ဨကဝုစ်",
"ဗီုပြင်ဂၞန်သင်္ချာ",
"လုပ်ကၠောန်စွံလဝ်",
"ဗီုပြင်လုပ်ကၠောန်စွံလဝ်",
"ဗီုပြင်အမှိက်",
"လုပ်ကၠောန်စွံလဝ်ဟွံတဝ်စၞေဟ်",
"လုပ်ကၠောန်စွံလဝ်နကဵုအတိတ်ပြဟ်ပြေဟ်",
"လုပ်ကၠောန်စွံလဝ်နကဵုအတိတ်",
"ဗီုပြင်လုပ်ကၠောန်စွံလဝ်နကဵုအတိတ်",
"လုပ်ကၠောန်စွံလဝ်ဗီုပြင်ဟွံတဝ်စၞေဟ်နူအတိတ်",
"လုပ်ကၠောန်စွံလဝ်မက္ဍိုပ်ပေင်ပြဟ်ပြေဟ်",
"လုပ်ကၠောန်စွံလဝ်ဗီုပြင်မက္ဍိုပ်ပေင်",
"လုပ်ကၠောန်စွံလဝ်မက္ဍိုပ်ပေင်ဟွံတဝ်စၞေဟ်",
"ဖေန်အိန်",
"ကိုန်ဗဟုဝစ်",
"ဗီုပြင်ပသ္ၚောဲထောံ",
"ဗီုပြင်မုက်နာမ်",
"ဝိဘတ်ပသ္ၚောဲထောံလဝ်",
"ဗီုပြင်ဝိဘတ်",
"ဝိဘတ်ဗီုပြင်သဗ္ဗနာမ်",
"လုပ်ကၠောန်စွံလဝ်ပစ္စုပ္ပန်ပြဟ်ပြေဟ်",
"လုပ်ကၠောန်စွံလဝ်ပစ္စုပ္ပန်",
"လုပ်ကၠောန်စွံလဝ်ပစ္စုပ္ပန်ဗီုပြင်ဟွံတဝ်စၞေဟ်",
"ဗီုပြင်သဗ္ဗနာမ်",
"သဗ္ဗနာမ်ဗီုပြင်ပိုၚ်ပြဳ",
"ဗီုပြင်နာမ်မကိတ်ညဳ",
"နာမ်မကိတ်ညဳဗီုပြင်ကိုန်ဗဟုဝစ်",
"rafsi",
"ဗီုအက္ခရ်ရောမ",
"ဗီုပြင်တံရိုဟ်",
"singulatives",
"ဗီုပြင်အဆက်လက္ကရဴ",
"ဗီုပြင်သဒ္ဒာနာမဝိသေသန",
"သဒ္ဒာနာမဝိသေသန",
"ဗီုပြင်သဒ္ဒာကြိယာဝိသေသန",
"သဒ္ဒာကြိယာဝိသေသန",
"ဗီုပြင်ကြိယာ",
"နာမ်ဝါစာ",
"နာမ်အပြံင်အသၠာဲ",
}
-- These langauges will not have links to separate parts of the headword.
data.no_multiword_links = list_to_set{
"zh",
}
-- These languages will not have "LANG multiword terms" categories added.
data.no_multiword_cat = list_to_set{
-------- Languages without spaces between words (sometimes spaces between phrases) --------
"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)
"nan-hbl", -- Hokkien (some words in Latin script; hyphens between syllables)
"nod", -- Northern Thai
"ojp", -- Old Japanese
"shn", -- Shan
"sou", -- Southern Thai
"tdd", -- Tai Nüa
"th", -- Thai
"tts", -- Isan
"twh", -- Tai Dón
"txg", -- Tangut
"zh", -- Chinese (all varieties with Chinese characters)
"zkt", -- Khitan
-------- Languages with spaces between syllables --------
"ahk", -- Akha
"aou", -- A'ou
"atb", -- Zaiwa
"byk", -- Biao
"cdy", -- Chadong
--"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 = list_to_set{
"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
"hnn", -- Hanunoo; too many false positives
"ilo", -- Ilocano; hyphens for mid-word glottal stops
"kne", -- Kankanaey; hyphens for mid-word glottal stops
"lcp", -- Western Lawa; dash as syllable joiner
"lwl", -- Eastern Lawa; dash as syllable joiner
"mfa", -- Pattani Malay in Thai script; 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
"yo", -- Yoruba; hyphens used to show lengthened nasal vowels
}
-- These languages will not have "LANG masculine nouns" and similar categories added.
data.no_gender_cat = list_to_set{
-- Languages without gender but which use the gender field for other purposes
"ja",
"th",
}
data.notranslit = list_to_set{
"ams",
"az",
"bbc",
"bug",
"cdo",
"cia",
"cjm",
"cjy",
"cmn",
"cnp",
"cpi",
"cpx",
"csp",
"czh",
"czo",
"gan",
"hak",
"hnm",
"hsn",
"ja",
"kzg",
"lad",
"ltc",
"luh",
"lzh",
"mnp",
"ms",
"mul",
"mvi",
"nan",
"nan-dat",
"nan-hbl",
"nan-hlh",
"nan-lnx",
"nan-tws",
"nan-zhe",
"nan-zsh",
"och",
"oj",
"okn",
"ryn",
"rys",
"ryu",
"sh",
"sjc",
"tgt",
"th",
"tkn",
"tly",
"txg",
"und",
"vi",
"wuu",
"xug",
"yoi",
"yox",
"yue",
"za",
"zh",
"zhx-sic",
"zhx-tai",
}
-- Script codes for which a script-tagged display title will be added.
data.toBeTagged = list_to_set{
"Ahom",
"Arab",
"fa-Arab",
"glk-Arab",
"kk-Arab",
"ks-Arab",
"ku-Arab",
"mzn-Arab",
"ms-Arab",
"ota-Arab",
"pa-Arab",
"ps-Arab",
"sd-Arab",
"tt-Arab",
"ug-Arab",
"ur-Arab",
"Armi",
"Armn",
"Avst",
"Bali",
"Bamu",
"Batk",
"Beng",
"as-Beng",
"Bopo",
"Brah",
"Brai",
"Bugi",
"Buhd",
"Cakm",
"Cans",
"Cari",
"Cham",
"Cher",
"Copt",
"Cprt",
"Cyrl",
"Cyrs",
"Deva",
"Dsrt",
"Egyd",
"Egyp",
"Ethi",
"Geok",
"Geor",
"Glag",
"Goth",
"Grek",
"Polyt",
"polytonic",
"Gujr",
"Guru",
"Hang",
"Hani",
"Hano",
"Hebr",
"Hira",
"Hluw",
"Ital",
"Java",
"Kali",
"Kana",
"Khar",
"Khmr",
"Knda",
"Kthi",
"Lana",
"Laoo",
"Latn",
"Latf",
"Latg",
"Latnx",
"Latinx",
"pjt-Latn",
"Lepc",
"Limb",
"Linb",
"Lisu",
"Lyci",
"Lydi",
"Mand",
"Mani",
"Marc",
"Merc",
"Mero",
"Mlym",
"Mong",
"mnc-Mong",
"sjo-Mong",
"xwo-Mong",
"Mtei",
"Mymr",
"Narb",
"Nkoo",
"Nshu",
"Ogam",
"Olck",
"Orkh",
"Orya",
"Osma",
"Ougr",
"Palm",
"Phag",
"Phli",
"Phlv",
"Phnx",
"Plrd",
"Prti",
"Rjng",
"Runr",
"Samr",
"Sarb",
"Saur",
"Sgnw",
"Shaw",
"Shrd",
"Sinh",
"Sora",
"Sund",
"Sylo",
"Syrc",
"Tagb",
"Tale",
"Talu",
"Taml",
"Tang",
"Tavt",
"Telu",
"Tfng",
"Tglg",
"Thaa",
"Thai",
"Tibt",
"Ugar",
"Vaii",
"Xpeo",
"Xsux",
"Yiii",
"Zmth",
"Zsym",
"Ipach",
"Music",
"Rumin",
}
-- Parts of speech which will not be categorised in categories like "English terms spelled with É" if
-- the term is the character in question (e.g. the letter entry for English [[é]]). This contrasts with
-- entries like the French adjective [[m̂]], which is a one-letter word spelled with the letter.
data.pos_not_spelled_with_self = list_to_set{
"diacritical marks",
"Han characters",
"Han tu",
"hanja",
"hanzi",
"iteration marks",
"kana",
"kanji",
"letters",
"ligatures",
"logograms",
"morae",
"numeral symbols",
"numerals",
"punctuation marks",
"syllables",
"symbols",
}
------ 2. Lists not converted into sets. ------
-- Recognized aliases for parts of speech (param 2=). Key is the short form and value is the canonical singular (not
-- pluralized) form. It is singular so that the same table can be used in [[Module:form of]] for the p=/POS= param
-- and [[Module:links]] for the pos= param.
data.pos_aliases = {
a = "adjective",
adj = "adjective",
adv = "adverb",
art = "article",
det = "determiner",
cnum = "cardinal number",
conj = "conjunction",
conv = "converb",
int = "interjection",
interj = "interjection",
intj = "interjection",
n = "နာမ်",
num = "numeral",
part = "participle",
pcl = "particle",
phr = "phrase",
pn = "proper noun",
postp = "postposition",
pre = "preposition",
prep = "preposition",
pro = "pronoun",
pron = "pronoun",
prop = "proper noun",
proper = "proper noun",
onum = "ordinal number",
rom = "romanization",
v = "verb",
vb = "verb",
vi = "intransitive verb",
vt = "transitive verb",
vti = "transitive and intransitive verb",
}
-- 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.
data.pos_for_gender_number_cat = {
["နာမ်"] = "နာမ်",
["proper nouns"] = "နာမ်",
["suffixes"] = "suffixes",
-- We include verbs because impf and pf are valid "genders".
["ကြိယာ"] = "ကြိယာ",
}
------ 3. Page-wide processing (so that it only needs to be done once per page). ------
data.page = require(headword_page_module).process_page()
-- Fuckme, random references to data.pagename and data.encoded_pagename are scattered throughout the codebase. FIXME!
data.pagename = data.page.pagename
data.encoded_pagename = data.page.encoded_pagename
return data