မော်ဂျူး:headword/data
Documentation for this module may be created at မော်ဂျူး:headword/data/doc
local data = {}
data.invariable = {
"cmavo",
"cmene",
"fu'ivla",
"gismu",
"Han tu",
"hanzi",
"hanja",
"jyutping",
"kanji",
"lujvo",
"phrasebook",
"pinyin",
"rafsi",
"romaji",
}
data.lemmas = {
"နာမ်ႏ",
"နာမ်ႏဆဲင်ႏတဖြာꩻ",
"နာမ်ႏဆဲင်ႏလိုꩻအာ",
"စိတ္တဇနာမ်ႏဖုံႏ",
"အွဉ်ႏနယ်ခြွဉ်းနာမ်ႏဖုံႏ",
"ကြိယာႏ",
"ကြိယာႏဝိသေသန",
"နာမဝိသေသန",
"နာမ်ႏတင်",
"နာမ်ႏခြွိုင်းဖုံႏ",
"ဝိဘတ်",
"အဆွိုင်ꩻဝင်ꩻဖုံႏ",
"အအဲဉ်ႏ",
"ရောမ်ဖြုဲင်ꩻ",
"အီဒီယမ်",
"အာမေဍိတ်",
"အက္ခရာႏ",
"လိတ်ဖြုံႏ",
"ငဝ်းခြွဉ်းဖုံႏ",
"အမုဲင်စဲဉ်ႏဖုံႏ",
"ဂဏန်ꩻ",
"ကိန်ꩻဂဏန်ꩻအမုဲင်ဖုံႏ",
"ဒေါ့ꩻရိုꩻသေꩻငဝ်းဖုံႏ",
"ငဝ်းပွုံႏခွိုင်ꩻဖုံႏ",
"ဖပုဒ်အုံယွိုင်းပုဒ်သင်္ကေတဖုံႏ",
"အက္ခရာႏဖုံႏ",
"အမုဲင်(သင်္ကေတ)ဖုံႏ",
"အဒွေါင်ႏနယ်ꩻ",
"ဝိဘတ်",
"ကတဲက်ထွားနွောင်ꩻဒါႏ ကြိယာဝိသေသနဖုံႏ",
"ကတဲက်ထွားနွောင်ꩻဒါႏ နာမဝိသေသနဖုံႏ",
"အလွိုကဲꩻသွတ်ꩻ ကြိယာဝိသေသနဖုံႏ",
"အလွိုကဲꩻသွတ်ꩻ နာမဝိသေသနဖုံႏ",
"အသွုပ်ဆုဲင်ꩻဖုံႏ",
"အခြွိုင်းဖုံႏ",
"ငဝ်းငွါအကွို့ꩻအခဝ်",
"abbreviations",
"acronyms",
"adjectives",
"adnominals",
"adpositions",
"adverbs",
"affixes",
"ambipositions",
"articles",
"circumfixes",
"circumpositions",
"classifiers",
"cmavo",
"cmavo clusters",
"cmene",
"combining forms",
"comparative adjectives",
"comparative adverbs",
"conjunctions",
"counters",
"determiners",
"diacritical marks",
"equative adjectives",
"fu'ivla",
"gismu",
"Han characters",
"Han tu",
"hanzi",
"hanja",
"idioms",
"infixes",
"interfixes",
"initialisms",
"interjections",
"kanji",
"letters",
"ligatures",
"lujvo",
"morphemes",
"non-constituents",
"nouns",
"numbers",
"numeral symbols",
"numerals",
"particles",
"phrases",
"postpositions",
"predicatives",
"prefixes",
"prepositions",
"prepositional phrases",
"preverbs",
"pronominal adverbs",
"pronouns",
"proverbs",
"proper nouns",
"punctuation marks",
"relatives",
"roots",
"stems",
"suffixes",
"superlative adjectives",
"superlative adverbs",
"syllables",
"symbols",
"verbs",
}
data.nonlemmas = {
"active participles",
"adjectival participles",
"adjective forms",
"adjective comparative forms",
"adjective feminine forms",
"adjective equative forms",
"adjective plural forms",
"adjective superlative forms",
"adverb forms",
"adverb comparative forms",
"adverb superlative forms",
"adverbial participles",
"agent participles",
"article forms",
"circumfix forms",
"combined forms",
"ငဝ်းအွဉ်ႏဒင်ႏဒွေါင်ႏထိုꩻဖုံႏ",
"converbs",
"determiner comparative forms",
"determiner forms",
"determiner superlative forms",
"diminutive nouns",
"future participles",
"gerunds",
"infinitive forms",
"infinitives",
"interjection forms",
"jyutping",
"kanji readings",
"misspellings",
"negative participles",
"nominal participles",
"noun case forms",
"noun dual forms",
"နာမ်ႏပုဒ်",
"နာမ်ႏအအာကိန်ꩻပုံႏစံႏဖုံႏ",
"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",
"အအာကိန်ꩻဖုံႏ",
"postposition forms",
"prefix forms",
"preposition contractions",
"preposition forms",
"prepositional pronouns",
"present active participles",
"အွဉ်ႏနယ်အဝ်ႏထွာတွင်ꩻ ကြိယာႏသဏ္ဍာန်ႏဖုံႏ",
"present passive participles",
"pronoun forms",
"pronoun possessive forms",
"နာမ်ႏဆဲင်ႏတဖြာꩻပုဒ်",
"နာမ်ႏဆဲင်ႏတဖြာꩻ ပုဒ်အအာကိန်ꩻဖုံႏ",
"နာမ်ႏဆဲင်ႏတဖြာꩻ ပုဒ်အအာကိန်ꩻဖုံႏ",
"rafsi",
"လုဲင်ႏတွမ်ႏရောမအက္ခရာႏဖုံႏ",
"singulatives",
"suffix forms",
"ကြိယာႏပုဒ်",
"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
"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 = {
"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
"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 = {
-- 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",
"txg",
"und",
"vi",
"xug",
"yoi",
"yox",
"yue",
"za",
"zh",
}
-- Script codes for which a script-tagged display title will be added.
data.toBeTagged = {
"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",
"polytonic",
"Gujr",
"Guru",
"Hang",
"Hani",
"Hano",
"Hebr",
"Hira",
"Hluw",
"Ital",
"Java",
"Kali",
"Kana",
"Khar",
"Khmr",
"Knda",
"Kthi",
"Lana",
"Laoo",
"Latn",
"Latf",
"Latg",
"Latinx",
"nv-Latn",
"pjt-Latn",
"Lepc",
"Limb",
"Linb",
"Lisu",
"Lyci",
"Lydi",
"Mand",
"Mani",
"Merc",
"Mero",
"Mlym",
"Mong",
"mnc-Mong",
"sjo-Mong",
"xwo-Mong",
"Mtei",
"Mymr",
"Narb",
"Nkoo",
"Ogam",
"Olck",
"Orkh",
"Orya",
"Osma",
"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",
"xzh-Tibt",
"Ugar",
"Vaii",
"Xpeo",
"Xsux",
"Yiii",
"Zmth",
"Zsym",
"IPAchar",
"musical",
"Ruminumerals",
}
for key, list in pairs(data) do
data[key] = {}
for _, item in ipairs(list) do
data[key][item] = true
end
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"] = "နာမ်ႏ",
["proper nouns"] = "နာမ်ႏ",
["suffixes"] = "suffixes",
-- We include verbs because impf and pf are valid "genders".
["verbs"] = "ကြိယာႏ",
}
return data