ဝိက်ရှေန်နရဳ mnwwiktionary https://mnw.wiktionary.org/wiki/%E1%80%9D%E1%80%AD%E1%80%80%E1%80%BA%E1%80%9B%E1%80%BE%E1%80%B1%E1%80%94%E1%80%BA%E1%80%94%E1%80%9B%E1%80%B3:%E1%80%99%E1%80%AF%E1%80%80%E1%80%BA%E1%80%9C%E1%80%AD%E1%80%80%E1%80%BA%E1%80%90%E1%80%99%E1%80%BA MediaWiki 1.44.0-wmf.1 case-sensitive မဳဒဳယာ တၟေင် ဓရီုကျာ ညးလွပ် ညးလွပ် ဓရီုကျာ ဝိက်ရှေန်နရဳ ဝိက်ရှေန်နရဳ ဓရီုကျာ ဝှာင် ဝှာင် ဓရီုကျာ မဳဒဳယာဝဳကဳ မဳဒဳယာဝဳကဳ ဓရီုကျာ ထာမ်ပလိက် ထာမ်ပလိက် ဓရီုကျာ ရီု ရီု ဓရီုကျာ ကဏ္ဍ ကဏ္ဍ ဓရီုကျာ အဆက်လက္ကရဴ အဆက်လက္ကရဴ ဓရီုကျာ ကာရန် ကာရန် ဓရီုကျာ ဗီုပြင်သိုင်တၟိ ဗီုပြင်သိုင်တၟိ ဓရီုကျာ TimedText TimedText talk မဝ်ဂျူ မဝ်ဂျူ ဓရီုကျာ မဝ်ဂျူ:languages/data/2 828 653 103863 103755 2024-11-01T08:32:22Z 咽頭べさ 33 103863 Scribunto text/plain local u = mw.ustring.char -- UTF-8 encoded strings for some commonly-used diacritics local GRAVE = u(0x0300) local ACUTE = u(0x0301) local CIRC = u(0x0302) local TILDE = u(0x0303) local MACRON = u(0x0304) local BREVE = u(0x0306) local DOTABOVE = u(0x0307) local DIAER = u(0x0308) local CARON = u(0x030C) local DGRAVE = u(0x030F) local INVBREVE = u(0x0311) local DOTBELOW = u(0x0323) local RINGBELOW = u(0x0325) local CEDILLA = u(0x0327) local OGONEK = u(0x0328) local DOUBLEINVBREVE = u(0x0361) -- Punctuation to be used for standardChars field local PUNCTUATION = ' !#%&*+,-./:;<=>?@^_`|~\'()' local Cyrl = {"Cyrl"} local Latn = {"Latn"} local LatnArab = {"Latn", "Arab"} local m = {} m["aa"] = { canonicalName = "အဖှာင်", otherNames = {"Qafar"}, scripts = {"Latn"}, family = "cus", } m["ab"] = { canonicalName = "အာပ်ဟန်", otherNames = {"Abkhaz", "Abkhazian", "Abxazo"}, scripts = {"Cyrl", "Geor", "Latn"}, family = "cau-abz", translit_module = "ab-translit", override_translit = true, entry_name = { from = {GRAVE, ACUTE}, to = {}} , } m["ae"] = { "အဗါတ်သတေန်", 29572, "ira-cen", scripts = {"Avst", "Gujr"}, translit_module = "Avst-translit", wikipedia_article = "Avestan", } m["af"] = { canonicalName = "အေက်ဖရိကာန်", scripts = {"Latn", "Arab"}, family = "gmw", ancestors = {"nl"}, sort_key = { from = {"[äáâà]", "[ëéêè]", "[ïíîì]", "[öóôò]", "[üúûù]", "[ÿýŷỳ]", "^-", "'"}, to = {"a" , "e" , "i" , "o" , "u" , "y" }} , wikipedia_article = "Afrikaans", } m["ak"] = { canonicalName = "အကာန်", otherNames = {"Akan", "Twi-Fante", "Twi", "Fante", "Fanti", "Asante", "Akuapem"}, scripts = {"Latn"}, family = "alv-kwa", } m["am"] = { canonicalName = "အာန်ဟာရိစ်", otherNames = {"Amharic"}, scripts = {"Ethi"}, family = "sem-eth", translit_module = "Ethi-translit", wikipedia_article = "Amharic", } m["an"] = { canonicalName = "အာဒါဂေန်", otherNames = {"Aragonese"}, scripts = {"Latn"}, family = "roa", ancestors = {"ine-pro", "itc-pro", "itc-ola", "la", "roa-oan"}, } m["ar"] = { canonicalName = "အာရဗဳ", otherNames = {"Modern Standard Arabic", "Standard Arabic", "Literary Arabic", "Classical Arabic", "Arabic", "အာရက်လ်"}, scripts = {"Arab", "Brai"}, family = "sem-arb", -- alif waṣl to alif, remove diacritics entry_name = { from = {u(0x0671), u(0x064B), u(0x064C), u(0x064D), u(0x064E), u(0x064F), u(0x0650), u(0x0651), u(0x0652), u(0x0670), u(0x0640)}, to = {u(0x0627)}}, translit_module = "ar-translit", wikipedia_article = "Arabic", ancestors = {"sem-pro"}, } m["as"] = { canonicalName = "အိသ်ဇြာံမဳ", otherNames ={"Assamese"}, scripts = {"Beng"}, family = "inc", ancestors = {"inc-mgd"}, translit_module = "as-translit", } m["av"] = { "အာဗာ", "Q29561", "cau-nec", aliases = {"Avaric"}, scripts = Cyrl, ancestors = {"oav"}, translit_module = "translit-redirect", override_translit = true, entry_name = { from = {GRAVE, ACUTE}, to = {}} , } m["ay"] = { canonicalName = "အိုင်မာရ", otherNames = {"Aymara", "Southern Aymara", "Central Aymara"}, scripts = {"Latn"}, family = "sai-aym", } m["az"] = { "အာက်သေတ်ဗါဲဇြေနဳ", 9292, "trk-ogz", {"Latn", "Cyrl", "fa-Arab"}, ancestors = {"trk-oat"}, dotted_dotless_i = true, } m["ba"] = { canonicalName = "ဗေတ်ခဳ", otherNames = {"Bashkir"}, scripts = {"Cyrl"}, family = "trk-kip", translit_module = "ba-translit", override_translit = true, } m["be"] = { canonicalName = "ဗါလာရုဇ်", otherNames = {"Belarusian", "Belorussian", "Belarusan", "Bielorussian", "Byelorussian", "Belarussian", "White Russian"}, scripts = {"Cyrl"}, family = "zle", ancestors = {"orv"}, translit_module = "be-translit", sort_key = { from = {"Ё", "ё"}, to = {"Е" , "е"}}, entry_name = { from = {"Ѐ", "ѐ", GRAVE, ACUTE}, to = {"Е", "е"}}, } m["bg"] = { canonicalName = "ဗူလ်ဂရဳယာန်", otherNames = {"Bulgarian"}, scripts = {"Cyrl"}, family = "zls", translit_module = "bg-translit", entry_name = { from = {"Ѐ", "ѐ", "Ѝ", "ѝ", GRAVE, ACUTE}, to = {"Е", "е", "И", "и"}}, } m["bh"] = { canonicalName = "ဘဳဟာရဳ", otherNames = {"Bihari"}, scripts = {"Deva"}, family = "inc", ancestors = {"inc-mgd"}, wikipedia_article = "ဘာသာဘဳဟာရဳ", } m["bi"] = { canonicalName = "ဗဳသလာမာ", otherNames = {"Bislama"}, scripts = {"Latn"}, family = "crp", ancestors = {"ine-pro", "gem-pro", "gmw-pro", "ang", "enm", "en-ear", "en"}, wikipedia_article = "Bislama", } m["bm"] = { canonicalName = "ဗီုဗရာ", otherNames = {"Bamanankan"}, scripts = {"Latn"}, family = "dmn", } m["bn"] = { canonicalName = "ဘင်္ဂါလဳ", otherNames = {"Bangla", "Bengali"}, scripts = {"Beng"}, family = "inc", ancestors = {"inc-mgd"}, translit_module = "bn-translit", } m["bo"] = { canonicalName = "တဳဗဝ်", otherNames = {"Tibetan", "Ü", "Dbus", "Lhasa", "Lhasa Tibetan", "Amdo Tibetan", "Amdo", "Panang", "Khams", "Khams Tibetan", "Khamba", "Tseku", "Dolpo", "Humla", "Limi", "Lhomi", "Shing Saapa", "Mugom", "Mugu", "Nubri", "Walungge", "Gola", "Thudam", "Lowa", "Loke", "Mustang", "Tichurong", "တိဗက်"}, scripts = {"Tibt"}, family = "tbq", ancestors = {"xct"}, translit_module = "bo-translit", override_translit = true, wikipedia_article = "Standard Tibetan", -- may need verification } m["br"] = { canonicalName = "ဗရဳတေန်", otherNames = {"Breton"}, scripts = {"Latn"}, family = "cel-bry", ancestors = {"xbm"}, } m["ca"] = { canonicalName = "ကတလာန်", otherNames = {"Valencian", "Catalan"}, scripts = {"Latn"}, family = "roa", ancestors = {"roa-oca"}, sort_key = { from = {"à", "[èé]", "[íï]", "[òó]", "[úü]", "ç", "l·l"}, to = {"a", "e" , "i" , "o" , "u" , "c", "ll" }} , } m["ce"] = { canonicalName = "ချက်ခ်ချေင်", otherNames = {"Chechen"}, scripts = {"Cyrl", "Latn", "Arab"}, family = "cau-nkh", translit_module = "translit-redirect", override_translit = true, ancestors = {"ccn-pro", "cau-nec-pro", "cau-nkh-pro"}, entry_name = { from = {MACRON}, to = {}}, } m["ch"] = { canonicalName = "ချာမဝ်ရဝ်", otherNames = {"Chamorro", "Chamoru"}, scripts = {"Latn"}, family = "poz-sus", } m["co"] = { canonicalName = "ခဝ်သဳကာန်", otherNames = {"Corsican", "Corsu"}, scripts = {"Latn"}, family = "roa", } m["cr"] = { canonicalName = "ခရေဝ်", scripts = {"Cree", "Cans", "Latn"}, family = "alg", translit_module = "cr-translit", } m["cs"] = { canonicalName = "ချက်ခ်", otherNames = {"Czech"}, scripts = {"Latn"}, family = "zlw", ancestors = {"zlw-ocs", "sla-pro"}, sort_key = { from = {"á", "é", "í", "ó", "[úů]", "ý"}, to = {"a", "e", "i", "o", "u" , "y"}} , } m["cu"] = { "ခရေတ်သလာဗဝ်နေတ်တြေံ", "Q35499", "zls", aliases = {"Old Church Slavic"}, scripts = {"Cyrs", "Glag"}, translit_module = "Cyrs-Glag-translit", ancestors = {"ine-pro", "ine-bsl-pro", "sla-pro"}, entry_name = { from = {u(0x0484)}, -- kamora to = {}}, sort_key = { from = {"оу", "є"}, to = {"у" , "е"}} , } m["cv"] = { "ချူဝါတ်", "Q33348", "trk-ogr", scripts = Cyrl, ancestors = {"xbo"}, translit_module = "cv-translit", sort_key = { from = {"ӑ", "ё", "ӗ", "ҫ", "ӳ"}, to = { "а" .. u(0xF000), "е" .. u(0xF000), "е" .. u(0xF001), "с" .. u(0xF000), "у" .. u(0xF000) } }, override_translit = true, } m["cy"] = { canonicalName = "ဝေလ", otherNames ={"Welsh"}, scripts = {"Latn"}, family = "cel-bry", ancestors = {"wlm"}, sort_key = { from = {"[âáàä]", "[êéèë]", "[îíìï]", "[ôóòö]", "[ûúùü]", "[ŵẃẁẅ]", "[ŷýỳÿ]", "'"}, to = {"a" , "e" , "i" , "o" , "u" , "w" , "y" }} , } m["da"] = { canonicalName = "ဒိန်နေတ်", otherNames ={"Danish"}, scripts = {"Latn"}, family = "gmq", ancestors = {"gmq-oda"}, } m["de"] = { canonicalName = "ဂျာမာန်", otherNames = {"High German", "New High German", "Deutsch", "German", "ဂျာမနဳ"}, scripts = {"Latn", "Latf"}, family = "gmw", ancestors = {"gmh"}, sort_key = { from = {"[äàáâå]", "[ëèéê]", "[ïìíî]", "[öòóô]", "[üùúû]", "ß" }, to = {"a" , "e" , "i" , "o" , "u" , "ss"}} , } m["dv"] = { canonicalName = "ဒိဝေဟဳ", otherNames = {"Dhivehi", "Divehi", "Mahal", "Mahl", "Maldivian"}, scripts = {"Thaa"}, family = "inc", ancestors = {"pmh"}, -- or Helu? translit_module = "dv-translit", override_translit = true, wikipedia_article = "ဘာသာမောဝ်ဒိုက်", } m["dz"] = { canonicalName = "သောင်ခါ", otherNames = {"Dzongkha"}, scripts = {"Tibt"}, family = "tbq", ancestors = {"xct"}, translit_module = "bo-translit", override_translit = true, wikipedia_article = "Dzongkha", } m["ee"] = { canonicalName = "အဳဝါ", otherNames = {"Ewe"}, scripts = {"Latn"}, family = "alv-von", } m["el"] = { canonicalName = "ဂရေတ်", otherNames = {"Greek", "Modern Greek", "Neo-Hellenic"}, scripts = {"Grek", "Brai", "Polyt", "Latn"}, family = "grk", ancestors = {"ine-pro", "grk-pro", "grc-att", "grc-koi", "gkm-med", "el-kth", "grc"}, translit_module = "el-translit", override_translit = true, sort_key = { -- Keep this synchronized with grc, cpg, pnt from = {"[ᾳάᾴὰᾲᾶᾷἀᾀἄᾄἂᾂἆᾆἁᾁἅᾅἃᾃἇᾇ]", "[έὲἐἔἒἑἕἓ]", "[ῃήῄὴῂῆῇἠᾐἤᾔἢᾒἦᾖἡᾑἥᾕἣᾓἧᾗ]", "[ίὶῖἰἴἲἶἱἵἳἷϊΐῒῗ]", "[όὸὀὄὂὁὅὃ]", "[ύὺῦὐὔὒὖὑὕὓὗϋΰῢῧ]", "[ῳώῴὼῲῶῷὠᾠὤᾤὢᾢὦᾦὡᾡὥᾥὣᾣὧᾧ]", "ῥ", "ς"}, to = {"α" , "ε" , "η" , "ι" , "ο" , "υ" , "ω" , "ρ", "σ"}} , standardChars = "ͺ;΄-ώϜϝ" .. PUNCTUATION .. "ἀ-῾" } m["en"] = { canonicalName = "အင်္ဂလိက်", otherNames = {"English", "Modern English", "New English", "Hawaiian Creole English", "Hawai'ian Creole English", "Hawaiian Creole", "Hawai'ian Creole", "Polari", "Yinglish"}, -- all but the first three are names of subsumed dialects which once had codes scripts = {"Latn", "Brai", "Shaw", "Dsrt"}, -- entries in Shaw or Dsrt might require prior discussion family = "gmw", ancestors = {"enm"}, wikipedia_article = "ဘာသာအင်္ဂလိက်", sort_key = { Latn = { -- Many of these are needed for sorting language names. remove_diacritics = "'\"%-%.,%sʻʼ" .. c.diacritics, -- These are found in entry names. from = {"æ", "🅱", "[¢©ᴄ]", "[ðđ]", "[əǝ]", "[ħʜ]", "ɨ", "ł", "[ŋɲ]", "[øɔ]", "œ", "ꝓ", "ß", "ʋ"}, to = {"ae", "b", "c", "d", "e", "h", "i", "l", "n", "o", "oe", "p", "ss", "v"} }, }, standardChars = { Latn = "AaBbCcDdEeFfGgHhIiJjKkLlMmNnOoPpQqRrSsTtUuVvWwXxYyZz", Brai = c.braille, c.punc }, } m["eo"] = { canonicalName = "အေက်သပရေန်တဝ်", otherNames = {"Esperanto"}, scripts = {"Latn"}, family = "art", sort_key = { from = {"[áà]", "[éè]", "[íì]", "[óò]", "[úù]", "[ĉ]", "[ĝ]", "[ĥ]", "[ĵ]", "[ŝ]", "[ŭ]"}, to = {"a" , "e" , "i" , "o" , "u", "cĉ", "gĉ", "hĉ", "jĉ", "sĉ", "uĉ"}} , wikipedia_article = "Esperanto", } m["es"] = { "သပုင်", 1321, "roa-ibe", {"Latn", "Brai"}, ancestors = {"ine-pro", "itc-pro", "itc-ola", "la", "osp"}, sort_key = { from = {"á", "é", "í", "ó", "[úü]", "ç", "ñ"}, to = {"a", "e", "i", "o", "u" , "c", "n"}}, standardChars = "A-VXYZa-vxyz0-9ÁáÉéÍíÓóÚúÑñ¿¡" .. PUNCTUATION, } m["et"] = { canonicalName = "အေက်သတဝ်နဳယာန်", otherNames = {"Estonian"}, scripts = {"Latn"}, family = "urj-fin", } m["eu"] = { canonicalName = "ဗက်ခ်", otherNames = {"Basque", "Euskara"}, scripts = {"Latn"}, family = "euq", } m["fa"] = { canonicalName = "ပါရှေန်", otherNames = {"ပါရှာ", "ဖာသဳ", "ဖာစဳ", "Persian", "Farsi", "New Persian", "Modern Persian", "Western Persian", "Iranian Persian", "Eastern Persian", "Dari", "Aimaq", "Aimak", "Aymaq", "Eimak"}, scripts = {"fa-Arab"}, family = "ira-wes", ancestors = {"pal", "ira-pro", "iir-pro", "ine-pro"}, entry_name = { from = {u(0x064E), u(0x064F), u(0x0650), u(0x0651), u(0x0652)}, to = {}} , } m["ff"] = { canonicalName = "ဖှောတ်လာ", otherNames = {"Fula", "Adamawa Fulfulde", "Bagirmi Fulfulde", "Borgu Fulfulde", "Central-Eastern Niger Fulfulde", "Fulani", "Fulfulde", "Maasina Fulfulde", "Nigerian Fulfulde", "Pular", "Pulaar", "Western Niger Fulfulde"}, -- Maasina, etc are dialects, subsumed into this code scripts = {"Latn"}, family = "alv-sng", } m["fi"] = { "ဖေန်လာန်", "Q1412", "urj-fin", aliases = {"Suomi"}, scripts = Latn, entry_name = { from = {"ˣ"}, -- Used to indicate gemination of the next consonant to = {}}, sort_key = { from = {"[áàâã]", "[éèêẽ]", "[íìîĩ]", "[óòôõ]", "[úùûũ]", "[ýỳŷüű]", "[øõő]", "æ" , "œ" , "[čç]", "š", "ž", "ß" , "[':]"}, to = {"a" , "e" , "i" , "o" , "u" , "y" , "ö" , "ae", "oe", "c" , "s", "z", "ss"}} , } m["fj"] = { canonicalName = "ဖရဳဂျိ", otherNames = {"Fijian"}, scripts = {"Latn"}, family = "poz-occ", } m["fo"] = { canonicalName = "ဖာရဝ်သဳ", otherNames = {"Faroese"}, scripts = {"Latn"}, family = "gmq", ancestors = {"non"}, } m["fr"] = { canonicalName = "ပြင်သေတ်", otherNames = {"French", "Modern French"}, scripts = {"Latn", "Brai"}, family = "roa-oil", ancestors = {"frm", "la"}, sort_key = { from = {"[áàâä]", "[éèêë]", "[íìîï]", "[óòôö]", "[úùûü]", "[ýỳŷÿ]", "ç", "æ" , "œ" , "'"}, to = {"a" , "e" , "i" , "o" , "u" , "y" , "c", "ae", "oe"}}, standardChars = "A-Za-z0-9ÀÂÇÉÈÊËÎÏÔŒÛÙÜàâçéèêëîïôœûùü«»" .. PUNCTUATION } m["fy"] = { canonicalName = "ဖရေဝ်သဳယာန်လက္ကရဴ", otherNames = {"West Frisian", "Western Frisian", "Frisian"}, scripts = {"Latn"}, family = "gmw-fri", ancestors = {"ofs"}, } m["ga"] = { canonicalName = "အာဲယျာလာန်", otherNames = {"Irish", "Irish Gaelic", "အိုင်ရစ်ရှ်"}, scripts = {"Latn"}, family = "cel-gae", ancestors = {"mga"}, sort_key = { from = {"á", "é", "í", "ó", "ú", "ý", "ḃ" , "ċ" , "ḋ" , "ḟ" , "ġ" , "ṁ" , "ṗ" , "ṡ" , "ṫ" }, to = {"a", "e", "i", "o", "u", "y", "bh", "ch", "dh", "fh", "gh", "mh", "ph", "sh", "th"}} , } m["gd"] = { canonicalName = "သကတ်ဂဴလိစ်", otherNames = {"Scottish Gaelic", "Gàidhlig", "Highland Gaelic", "Scots Gaelic", "Scottish"}, scripts = {"Latn"}, family = "cel-gae", ancestors = {"mga"}, sort_key = { from = {"[áà]", "[éè]", "[íì]", "[óò]", "[úù]", "[ýỳ]"}, to = {"a" , "e" , "i" , "o" , "u" , "y" }} , wikipedia_article = "Scottish Gaelic", } m["gl"] = { canonicalName = "ဂလဳသဳယာန်", otherNames = {"Galician"}, scripts = {"Latn"}, family = "roa", ancestors = {"ine-pro", "itc-pro", "inc-pro", "itc-ola", "la", "roa-opt"}, sort_key = { from = {"á", "é", "í", "ó", "ú"}, to = {"a", "e", "i", "o", "u"}} , } m["gn"] = { canonicalName = "ဂူရာန်နဳ", otherNames = {"Guaraní"}, scripts = {"Latn"}, family = "tup-gua", wikipedia_article = "ဘာသာဂူရာန်နဳ", } m["gu"] = { canonicalName = "ဂုဂျာရတဳ", otherNames = {"Gujarati"}, scripts = {"Gujr"}, family = "inc", ancestors = {"inc-ogu"}, translit_module = "gu-translit", } m["gv"] = { canonicalName = "မာက်", otherNames = {"Manx", "Manx Gaelic"}, scripts = {"Latn"}, family = "cel-gae", ancestors = {"mga"}, sort_key = { from = {"ç", "-"}, to = {"c"}} , } m["ha"] = { canonicalName = "ဟဴသာ", otherNames = {"Hausa"}, scripts = {"Latn", "Arab"}, family = "cdc-wst", sort_key = { from = {"ɓ", "ɗ", "ƙ", "'y", "ƴ", "'" }, to = {"b~" , "d~" , "k~", "y~", "y~", "" }}, entry_name = { from = {"R̃", "r̃", "À", "à", "È", "è", "Ì", "ì", "Ò", "ò", "Ù", "ù", "Â", "â", "Ê", "ê", "Î", "î", "Ô", "ô", "Û", "û", "Ā", "ā", "Ē", "ē", "Ī", "ī", "Ō", "ō", "Ū", "ū", "Á", "á", "É", "é", "Í", "í", "Ó", "ó", "Ú", "ú", "Ā̀", "ā̀", "Ḕ", "ḕ", "Ī̀", "ī̀", "Ṑ", "ṑ", "Ū̀", "ū̀", GRAVE, ACUTE}, to = {"R", "r", "A", "a", "E", "e", "I", "i", "O", "o", "U", "u", "A", "a", "E", "e", "I", "i", "O", "o", "U", "u", "A", "a", "E", "e", "I", "i", "O", "o", "U", "u", "A", "a", "E", "e", "I", "i", "O", "o", "U", "u", "A", "a", "E", "e", "I", "i", "O", "o", "U", "u"}}, } m["he"] = { canonicalName = "ဟဳဘရဝ်", otherNames = {"Hebrew", "Ivrit"}, scripts = {"Hebr", "Phnx", "Brai"}, family = "sem-can", ancestors = {"afa-pro", "sem-pro", "sem-wes-pro", "hbo", "he-mis", "he-med"}, translit_module = "he-translit", entry_name = { from = {"[" .. u(0x0591) .. "-" .. u(0x05BD) .. u(0x05BF) .. "-" .. u(0x05C5) .. u(0x05C7) .. "]"}, to = {}} , } m["hi"] = { canonicalName = "ဟိန္ဒဳ", otherNames = {"ဟိန္ဒဳ", "Hindi", "Braj", "Brij Bhasha", "Braj Bhasha", "Braj Bhāshā", "Braj Bhakha", "Dehaati Zabaan"}, scripts = {"Deva", "Guru"}, -- Guru for the subsumed variety Braj family = "inc-hnd", ancestors = {"inc-ohi"}, translit_module = "hi-translit", wikipedia_article = "Hindi", } m["ho"] = { canonicalName = "ဟဳရဳမိုတု", otherNames = {"Hiri Motu", "Pidgin Motu", "Police Motu"}, scripts = {"Latn"}, family = "crp", ancestors = {"meu"}, wikipedia_article = "Hiri Motu", } m["ht"] = { "ဟေဲယှေန် ခရေဝ်အဝ်လ်", 33491, "crp", Latn, ancestors = {"fr"}, } m["hu"] = { canonicalName = "ဟာန်ဂါရေဝ်", otherNames = {"Hungarian", "Magyar"}, scripts = {"Latn", "Hung"}, family = "urj-ugr", ancestors = {"urj-pro", "urj-ugr-pro", "ohu"}, sort_key = { from = {"é", "í", "ó", "ú", "ő", "ö", "ü", "á"}, to = {"e", "i", "o", "u", "o", "o", "u", "a"}} , } m["hy"] = { canonicalName = "အာမေနဳယျာ", otherNames = {"Armenian", "Modern Armenian", "Eastern Armenian", "Western Armenian", "အမေရိကာန်ဗၟံက်", "အမေရိကာန်ပလိုတ်", "အမေရိကာန်အခေတ်တၟိ"}, scripts = {"Armn", "Brai"}, family = "hyx", ancestors = {"axm"}, translit_module = "Armn-translit", override_translit = true, sort_key = { from = {"ու", "և", "եւ"}, to = {"ւ", "եվ", "եվ"}}, entry_name = { from = {"՞", "՜", "՛", "՟", "և", "<sup>յ</sup>", "<sup>ի</sup>"}, to = {"", "", "", "", "եւ", "յ", "ի"}} , } m["hz"] = { canonicalName = "ဟဳရဲရို", otherNames = {"Herero"}, scripts = {"Latn"}, family = "bnt", } m["ia"] = { canonicalName = "အေန်တာလိင်ဂဝ်", otherNames = {"Interlingua"}, scripts = {"Latn"}, family = "art", wikipedia_article = "Interlingua", } m["id"] = { canonicalName = "အိန်ဒဝ်နဳသဳယျာ", otherNames = {"Indonesian"}, scripts = {"Latn"}, family = "poz-mly", ancestors = {"map-pro", "poz-pro", "poz-sus-pro", "poz-msa-pro", "poz-mcm-pro", "poz-mly-pro", "ms-old", "ms-cla", "ms"}, } m["ie"] = { canonicalName = "အေန်တာလိင်ဂဝေ", otherNames = {"Interlingue", "Occidental"}, scripts = {"Latn"}, family = "art", wikipedia_article = "Occidental language", } m["ig"] = { canonicalName = "အေတ်ဗါဝ်", otherNames = {"Igbo", "အစ္ဂဘို"}, scripts = {"Latn"}, family = "nic-bco", } m["ii"] = { canonicalName = "သေဲဆိုန်ယဳ", otherNames = {"Sichuan Yi", "Nuosu", "Nosu", "Northern Yi", "Liangshan Yi"}, scripts = {"Yiii"}, family = "tbq-lol", wikipedia_article = "Nuosu language", translit_module = "ii-translit", override_translit = true, } m["ik"] = { canonicalName = "အဳနုဗဳယာတ်", otherNames = {"Inupiak", "Inupiaq", "Iñupiaq", "Inupiatun"}, scripts = {"Latn"}, family = "esx-inu", wikipedia_article = "Inupiaq", } m["io"] = { canonicalName = "ဣဒဝ်", otherNames = {"Ido"}, scripts = {"Latn"}, family = "art", } m["is"] = { canonicalName = "အာက်သလာန်", otherNames = {"Icelandic", "အာက်သလာန်"}, scripts = {"Latn"}, family = "gmq", ancestors = {"non", "gem-pro", "ine-pro"}, sort_key = { from = {"ð", "ö", "ó", "æ", "á", "í", "ú"}, to = {"o", "o", "o", "ae", "a", "i", "u"}} , } m["it"] = { canonicalName = "အဳတခ်လဳ", otherNames = {"Italian"}, scripts = {"Latn"}, family = "roa", sort_key = { from = {"[àáâäå]", "[èéêë]", "[ìíîï]", "[òóôö]", "[ùúûü]"}, to = {"a" , "e" , "i" , "o" , "u" }} , } m["iu"] = { canonicalName = "ဣနုက်တိတုတ်", otherNames = {"Inuktitut", "Eastern Canadian Inuktitut", "Eastern Canadian Inuit", "Western Canadian Inuktitut", "Western Canadian Inuit", "Western Canadian Inuktun", "Inuinnaq", "Inuinnaqtun", "Inuvialuk", "Inuvialuktun", "Nunavimmiutit", "Nunatsiavummiut", "Aivilimmiut", "Natsilingmiut", "Kivallirmiut", "Siglit", "Siglitun"}, scripts = {"Cans", "Latn"}, family = "esx-inu", translit_module = "iu-translit", override_translit = true, wikipedia_article = "Inuktitut", } m["ja"] = { canonicalName = "ဂျပါန်", otherNames = {"Japanese", "Modern Japanese", "Nipponese", "Nihongo"}, scripts = {"Jpan", "Latn", "Hira", "Brai"}, family = "jpx", ancestors = {"ojp"}, --[[ sort_key = { from = {"[ぁァア]", "[ぃィイ]", "[ぅゔゥウヴ]", "[ぇェエ]", "[ぉォオ]", "[がゕカガヵ]", "[ぎキギ]", "[ぐクグㇰ]", "[げゖケゲヶ]", "[ごコゴ]", "[ざサザ]", "[じシジㇱ]", "[ずスズㇲ]", "[ぜセゼ]", "[ぞソゾ]", "[だタダ]", "[ぢチヂ]", "[っづッツヅ]", "[でテデ]", "[どトドㇳ]", "ナ", "ニ", "[ヌㇴ]", "ネ", "ノ", "[ばぱハバパㇵ]", "[びぴヒビピㇶ]", "[ぶぷフブプㇷ]", "[べぺヘベペㇸ]", "[ぼぽホボポㇹ]", "マ", "ミ", "[ムㇺ]", "メ", "モ", "[ゃャヤ]", "[ゅュユ]", "[ょョヨ]", "[ラㇻ]", "[リㇼ]", "[ルㇽ]", "[レㇾ]", "[ロㇿ]", "[ゎヮワヷ]", "[ヰヸ]", "[ヱヹ]", "[ヲヺ]", "ン", "[゙゚゛゜ゝゞ・ヽヾ]", "𛀀", "1", "2", "3", "4", "5", "6", "7", "8", "9", "0"}, to = {"あ", "い", "う", "え", "お", "か", "き", "く", "け", "こ", "さ", "し", "す", "せ", "そ", "た", "ち", "つ", "て", "と", "な", "に", "ぬ", "ね", "の", "は", "ひ", "ふ", "へ", "ほ", "ま", "み", "む", "め", "も", "や", "ゆ", "よ", "ら", "り", "る", "れ", "ろ", "わ", "ゐ", "ゑ", "を", "ん", "", "え", "い", "に", "み", "よ", "ご", "ろ", "な", "は", "き", "れ"}}, ]] } m["jv"] = { canonicalName = "ဂျာဗာ", otherNames = {"Javanese"}, scripts = {"Latn", "Java"}, family = "poz-sus", translit_module = "jv-translit", ancestors = {"kaw"}, link_tr = true, } m["ka"] = { canonicalName = "ဂျဝ်ဂျဳယျာ", otherNames = {"Georgian", "Kartvelian", "Judeo-Georgian", "Kivruli", "Gruzinic"}, scripts = {"Geor", "Geok", "Hebr"}, -- Hebr is used to write Judeo-Georgian family = "ccs-gzn", ancestors = {"oge"}, translit_module = "Geor-translit", override_translit = true, entry_name = { from = {"̂"}, to = {""}}, } m["kg"] = { canonicalName = "ခါမ်ဂဝ်", otherNames = {"Kongo", "Kikongo", "Koongo", "Laari", "San Salvador Kongo", "Yombe"}, scripts = {"Latn"}, family = "bnt", } m["ki"] = { canonicalName = "ခဳခူယူ", otherNames = {"Kikuyu", "Gikuyu", "Gĩkũyũ"}, scripts = {"Latn"}, family = "bnt", } m["kj"] = { canonicalName = "ကောန်ယာမာ", otherNames = {"Kwanyama", "Kuanyama", "Oshikwanyama"}, scripts = {"Latn"}, family = "bnt", wikipedia_article = "Kwanyama dialect", } m["kk"] = { canonicalName = "ကဇက်", scripts = {"Kazakh", "Cyrl", "Latn", "Arab", "kk-Arab"}, family = "trk-kip", ancestors = {"trk-pro"}, translit_module = "kk-translit", override_translit = true, } m["kl"] = { canonicalName = "ဂရိန်လာန်", otherNames = {"Greenlandic", "Kalaallisut"}, scripts = {"Latn"}, family = "esx-inu", } m["km"] = { "ခမေန်", "Q9205", family = "mkh-kmr", aliases = {"Khmer", "Cambodian"}, scripts = {"Khmr"}, ancestors = {"aav-pro", "mkh-pro", "mkh-kmr-pro", "okz", "xhm"}, translit_module = "km-translit", } m["kn"] = { canonicalName = "ကာန်နဒါ", otherNames = {"Kannada", "ကန္နာဒါ"}, scripts = {"Knda"}, family = "dra", translit_module = "kn-translit", wikipedia_article = "Kannada", ancestors = {"dra-mkn"}, } m["ko"] = { "ကိုဝ်ရဳယျာ", "Q9176", "qfa-kor", aliases = {"Korean", "Modern Korean"}, scripts = {"Kore", "Brai"}, ancestors = {"ko-ear"}, -- 20210122 trial idea: strip parenthesized hanja from entry link -- Hani regex is a reasonable subset of Hani from [[Module:scripts/data]], -- last updated on 20210203. entry_name = { from = { "%([一-鿿㐀-䶿𠀀-𮯯"..u(0x2F800).."-𯨟𰀀-𱍏﨎﨏﨑﨓﨔﨟﨡﨣﨤﨧﨨﨩]+%)", }, to = { "", }}, translit_module = "ko-translit", } m["kr"] = { canonicalName = "ကနူရဳ", otherNames = {"Kanuri", "Kanembu", "Bilma Kanuri", "Central Kanuri", "Manga Kanuri", "Tumari Kanuri"}, scripts = {"Latn", "Arab"}, family = "ssa-sah", sort_key = { from = {"ny", "ǝ", "sh"}, to = {"n~", "e~", "s~"}} , -- the sortkey and entry_name are only for standard Kanuri; when dialectal entries get added, someone will have to work out how the dialects should be represented orthographically entry_name = { from = {"À", "à", "È", "è", "Ǝ̀", "ǝ̀", "Ì", "ì", "Ò", "ò", "Ù", "ù", "Â", "â", "Ê", "ê", "Ǝ̂", "ǝ̂", "Î", "î", "Ô", "ô", "Û", "û", "Ă", "ă", "Ĕ", "ĕ", "Ǝ̆", "ǝ̆", "Ĭ", "ĭ", "Ŏ", "ŏ", "Ŭ", "ŭ", "Á", "á", "É", "é", "Ǝ́", "ǝ́", "Í", "í", "Ó", "ó", "Ú", "ú", GRAVE, ACUTE}, to = {"A", "a", "E", "e", "Ǝ", "ǝ", "I", "i", "O", "o", "U", "u", "A", "a", "E", "e", "Ǝ", "ǝ", "I", "i", "O", "o", "U", "u", "A", "a", "E", "e", "Ǝ", "ǝ", "I", "i", "O", "o", "U", "u", "A", "a", "E", "e", "Ǝ", "ǝ", "I", "i", "O", "o", "U", "u"}}, } m["ks"] = { "ကာဒ်ရှ်မဳယျာ", 33552, "inc-dar", {"ks-Arab", "Deva", "Shrd", "Latn"}, translit_module = "translit-redirect", ancestors = {"sa"}, } m["ku"] = { canonicalName = "ကာဒဳ", otherNames = {"Kurdish"}, scripts = {"Latn", "ku-Arab", "Armn", "Cyrl"}, family = "ira-wes", wikipedia_article = "Kurdish languages", } -- "kv" IS TREATED AS "koi", "kpv", SEE WT:LT m["kw"] = { canonicalName = "ခမ်နေတ်", otherNames = {"Cornish"}, scripts = {"Latn"}, family = "cel-bry", ancestors = {"ine-pro", "cel-pro", "cel-bry-pro", "oco", "cnx"}, } m["ky"] = { canonicalName = "ကာဇေတ်", otherNames = {"Kyrgyz", "Kirghiz", "Kirgiz"}, scripts = {"Cyrl", "Latn", "Arab"}, family = "trk-kip", translit_module = "ky-translit", override_translit = true, ancestors = {"trk-pro", "qwm"}, } m["la"] = { canonicalName = "လပ်တေန်", otherNames = {"Latin"}, scripts = {"Latn"}, family = "itc", ancestors = {"itc-ola"}, entry_name = { from = {"[ĀĂ]", "[āă]", "[ĒĔ]", "[ēĕë]", "[ĪĬÏ]", "[īĭï]", "[ŌŎ]", "[ōŏ]", "[ŪŬÜ]", "[ūŭü]", "Ȳ", "ȳ", MACRON, BREVE, DIAER}, to = {"A", "a", "E", "e", "I", "i", "O", "o", "U", "u", "Y", "y"}}, wikipedia_article = "Latin", standardChars = "A-Za-zÆæŒœĀ-ăĒ-ĕĪ-ĭŌ-ŏŪ-ŭȲȳ" .. MACRON .. BREVE .. PUNCTUATION } m["lb"] = { canonicalName = "လူဇေန်ဘာဂျ်", otherNames = {"Luxembourgish"}, scripts = {"Latn"}, family = "gmw", ancestors = {"gmh"}, wikipedia_article = "Luxembourgish", } m["lg"] = { canonicalName = "လုဂန်ဒါ", otherNames = {"ဂန်ဒါ", "Luganda", "Ganda", "Oluganda"}, scripts = {"Latn"}, family = "bnt", entry_name = { from = {"á", "Á", "é", "É", "í", "Í", "ó", "Ó", "ú", "Ú", "ń", "Ń", "ḿ", "Ḿ", "â", "Â", "ê", "Ê", "î", "Î", "ô", "Ô", "û", "Û" }, to = {"a", "A", "e", "E", "i", "I", "o", "O", "u", "U", "n", "N", "m", "M", "a", "A", "e", "E", "i", "I", "o", "O", "u", "U",}}, sort_key = { from = {"ŋ"}, to = {"n"}} , wikipedia_article = "Luganda", } m["li"] = { canonicalName = "လိမ်ဗူရ်ဂိသ်", otherNames = {"Limburgish", "Limburgan", "Limburgian", "Limburgic"}, scripts = {"Latn"}, family = "gmw", ancestors = {"dum"}, } m["ln"] = { canonicalName = "လေန်ဂါလာ", otherNames = {"Lingala", "Ngala"}, scripts = {"Latn"}, family = "bnt", wikipedia_article = "Lingala", } m["lo"] = { canonicalName = "သေံလဴ", otherNames = {"သေံလဴ", "Lao", "Laotian"}, scripts = {"Laoo"}, family = "tai-swe", translit_module = "lo-translit", sort_key = { from = {"ຼ", "ຽ", "ໜ", "ໝ", "([ເແໂໃໄ])([ກ-ຮ])"}, to = {"ລ", "ຍ", "ຫນ", "ຫມ", "%2%1"}}, ancestors = {"qfa-tak-pro", "qfa-bet-pro", "tai-pro", "tai-swe-pro"}, } m["lt"] = { canonicalName = "လေတ်တူယဵုနဳယျာ", otherNames = {"Lithuanian", "လေတ်တူယဵုနဳယျာ"}, scripts = {"Latn"}, family = "bat", ancestors = {"ine-pro", "ine-bsl-pro", "bat-pro", "olt"}, entry_name = { from = {"[áãà]", "[ÁÃÀ]", "[éẽè]", "[ÉẼÈ]", "[íĩì]", "[ÍĨÌ]", "[ýỹ]", "[ÝỸ]", "ñ", "[óõò]", "[ÓÕÒ]", "[úũù]", "[ÚŨÙ]", ACUTE, GRAVE, TILDE}, to = {"a", "A", "e", "E", "i", "I", "y", "Y", "n", "o", "O", "u", "U"}} , } m["lu"] = { canonicalName = "ဠူဘ-ကာတေန်ဂါ", scripts = {"Latn"}, family = "bnt", } m["lv"] = { canonicalName = "လပ်ဗဳယာ", otherNames = {"Latvian", "Lettish", "Lett"}, scripts = {"Latn"}, family = "bat", ancestors = {"ine-bsl-pro", "bat-pro"}, entry_name = { -- This attempts to convert vowels with tone marks to vowels either with -- or without macrons. Specifically, there should be no macrons if the -- vowel is part of a diphthong (including resonant diphthongs such -- pìrksts -> pirksts not #pīrksts). What we do is first convert the -- vowel + tone mark to a vowel + tilde in a decomposed fashion, -- then remove the tilde in diphthongs, then convert the remaining -- vowel + tilde sequences to macroned vowels, then delete any other -- tilde. We leave already-macroned vowels alone: Both e.g. ar and ār -- occur before consonants. FIXME: This still might not be sufficient. from = {"Ȩ", "ȩ", "[ÂÃÀ]", "[âãà]", "[ÊẼÈ]", "[êẽè]", "[ÎĨÌ]", "[îĩì]", "[ÔÕÒ]", "[ôõò]", "[ÛŨÙ]", "[ûũù]", "[ÑǸ]", "[ñǹ]", "[" .. CIRC .. TILDE ..GRAVE .."]", "([aAeEiIoOuU])" .. TILDE .."?([lrnmuiLRNMUI])" .. TILDE .. "?([^aAeEiIoOuUāĀēĒīĪūŪ])", "([aAeEiIoOuU])" .. TILDE .."?([lrnmuiLRNMUI])" .. TILDE .."?$", "([iI])" .. TILDE .. "?([eE])" .. TILDE .. "?", "A" .. TILDE, "a" .. TILDE, "E" .. TILDE, "e" .. TILDE, "I" .. TILDE, "i" .. TILDE, "U" .. TILDE, "u" .. TILDE, TILDE}, to = {"E", "e", "A" .. TILDE, "a" .. TILDE, "E" .. TILDE, "e" .. TILDE, "I" .. TILDE, "i" .. TILDE, "O", "o", "U" .. TILDE, "u" .. TILDE, "N", "n", TILDE, "%1%2%3", "%1%2", "%1%2", "Ā", "ā", "Ē", "ē", "Ī", "ī", "Ū", "ū", ""}}, } m["mg"] = { canonicalName = "မာလာဂါသဳ", otherNames = {"Malagasy", "Betsimisaraka Malagasy", "Betsimisaraka", "Northern Betsimisaraka Malagasy", "Northern Betsimisaraka", "Southern Betsimisaraka Malagasy", "Southern Betsimisaraka", "Bara Malagasy", "Bara", "Masikoro Malagasy", "Masikoro", "Antankarana", "Antankarana Malagasy", "Plateau Malagasy", "Sakalava", "Tandroy Malagasy", "Tandroy", "Tanosy", "Tanosy Malagasy", "Tesaka", "Tsimihety", "Tsimihety Malagasy", "Bushi", "Shibushi", "Kibushi", "Sakalava"}, scripts = {"Latn"}, family = "poz-bre", } m["mh"] = { canonicalName = "မာချဲလဳ", otherNames = {"Marshallese"}, scripts = {"Latn"}, family = "poz-mic", sort_key = { from = {"ā" , "ļ" , "m̧" , "ņ" , "n̄" , "o̧" , "ō" , "ū" }, to = {"a~", "l~", "m~", "n~", "n~~", "o~", "o~~", "u~"}} , } m["mi"] = { canonicalName = "မဝ်ရဳ", otherNames = {"Maori", "Māori"}, scripts = {"Latn"}, family = "poz-pol", wikipedia_article = "Māori language", sort_key = { from = {"ā" , "ļ" , "m̧" , "ņ" , "n̄" , "o̧" , "ō" , "ū" }, to = {"a~", "l~", "m~", "n~", "n~~", "o~", "o~~", "u~"}} , } m["mk"] = { canonicalName = "မက်သဳဒဝ်နဳယျာ", otherNames = {"Macedonian"}, scripts = {"Cyrl"}, family = "zls", translit_module = "mk-translit", ancestors = {"ine-pro", "ine-bsl-pro", "sla-pro"}, entry_name = { from = {ACUTE}, to = {}}, } m["ml"] = { canonicalName = "မလေဝ်ယျလာမ်", otherNames = {"Malayalam"}, scripts = {"Mlym"}, family = "dra", translit_module = "ml-translit", override_translit = true, wikipedia_article = "Malayalam", } m["mn"] = { canonicalName = "မန်ဂဝ်လဳယျာ", otherNames = {"မန်ဂဝ်လဳယျာ", "ခန်ခါ မန်ဂဝ်လဳယျာ"}, scripts = {"Cyrl", "Mong", "Soyo", "Zanb"}, -- entries in Soyo or Zanb might require prior discussion family = "xgn", ancestors = {"cmg"}, translit_module = "mn-translit", override_translit = true, } -- "mo" IS TREATED AS "ro", SEE WT:LT m["mr"] = { canonicalName = "မာရဒဳ", otherNames = {"Marathi"}, scripts = {"Deva", "Modi"}, family = "inc", ancestors = {"omr"}, translit_module = "hi-translit", } m["ms"] = { canonicalName = "မလေဝ်", otherNames = {"Malay", "Malaysian", "Standard Malay", "Orang Seletar", "Orang Kanaq", "Jakun", "Temuan"}, scripts = {"Latn", "ms-Arab"}, family = "poz-mly", ancestors = {"map-pro", "poz-pro", "poz-sus-pro", "poz-msa-pro", "poz-mcm-pro", "poz-mly-pro", "ms-old", "ms-cla"}, } m["mt"] = { canonicalName = "မာလ်တဳ", otherNames = {"Maltese"}, scripts = {"Latn"}, family = "sem-arb", ancestors = {"sqr"}, } m["my"] = { canonicalName = "ဗၟာ", otherNames = {"Burmese", "Myanmar", "ဗၟာ"}, scripts = {"Mymr"}, family = "tbq-brm", ancestors = {"obr", "sit-pro", "tbq-pro"}, wikipedia_article = "ဘာသာဗၟာ", translit_module = "my-translit", override_translit = true, } m["na"] = { canonicalName = "နာဥူလောန်", otherNames = {"Nauruan","Nauru"}, scripts = {"Latn"}, family = "poz-mic", } m["nb"] = { canonicalName = "နဝ်ဝေ ဗော်ခ်မဝ်", otherNames = {"Norwegian Bokmål", "Bokmål"}, scripts = {"Latn"}, family = "gmq", ancestors = {"gmq-mno", "gem-pro"}, wikimedia_codes = {"no"}, wikipedia_article = "Bokmål", } m["nd"] = { canonicalName = "Northern Ndebele", otherNames = {"North Ndebele"}, scripts = {"Latn"}, family = "bnt-ngu", entry_name = { from = {"[āàáâǎ]", "[ēèéêě]", "[īìíîǐ]", "[ōòóôǒ]", "[ūùúûǔ]", "ḿ", "[ǹńň]", MACRON, ACUTE, GRAVE, CIRC, CARON}, to = {"a" , "e" , "i" , "o" , "u" , "m", "n" }}, } m["ne"] = { "နဳပဝ်", 33823, "inc-pah", scripts = {"Deva", "Newa"}, ancestors = {"ine-pro", "iir-pro", "inc-pro", "sa", "inc-ash", "pra-kha"}, translit_module = "ne-translit", } m["ng"] = { canonicalName = "အွန်ဒွန်ဂါ", otherNames = {"Ndonga"}, scripts = {"Latn"}, family = "bnt", wikipedia_article = "Ndonga dialect", } m["nl"] = { canonicalName = "ဒါတ်", otherNames = {"Dutch", "Netherlandic", "Flemish"}, scripts = {"Latn"}, family = "gmw", ancestors = {"dum"}, sort_key = { from = {"[äáâå]", "[ëéê]", "[ïíî]", "[öóô]", "[üúû]", "ç", "ñ", "^-"}, to = {"a" , "e" , "i" , "o" , "u" , "c", "n"}} , standardChars = "A-Za-z0-9" .. PUNCTUATION .. u(0x2800) .. "-" .. u(0x28FF), } m["nn"] = { canonicalName = "နဝ်ဝေ နဳနိုတ်", otherNames = {"Norwegian Nynorsk", "New Norwegian", "Nynorsk"}, scripts = {"Latn"}, family = "gmq", ancestors = {"gmq-mno"}, wikipedia_article = "Nynorsk", } m["no"] = { canonicalName = "နဝ်ဝေ", otherNames = {"Norwegian"}, scripts = {"Latn"}, family = "gmq", ancestors = {"gmq-mno"}, } m["nr"] = { canonicalName = "အာန်ဒေဗေလေဝ် လ္ပာ်ဒိုဟ်သမၠုင်ကျာ", otherNames = {"South Ndebele"}, scripts = {"Latn"}, family = "bnt-ngu", entry_name = { from = {"[āàáâǎ]", "[ēèéêě]", "[īìíîǐ]", "[ōòóôǒ]", "[ūùúûǔ]", "ḿ", "[ǹńň]", MACRON, ACUTE, GRAVE, CIRC, CARON}, to = {"a" , "e" , "i" , "o" , "u" , "m", "n" }}, } m["nv"] = { "နာဝါဟဝ်", 13310, "apa", Latn, sort_key = { from = {"[áą]", "[éę]", "[íį]", "[óǫ]", "ń", "^n([djlt])", "ł" , "[ʼ’']", ACUTE}, to = {"a" , "e" , "i" , "o" , "n", "ni%1" , "l~"}}, -- the tilde is used to guarantee that ł will always be sorted after all other words with l } m["ny"] = { canonicalName = "ချဳချေန်ဝါ", otherNames = {"နရန်ဂျာ", "Chichewa", "Chicheŵa", "Chinyanja", "Nyanja", "Chewa", "Cicewa", "Cewa", "Cinyanja"}, scripts = {"Latn"}, family = "bnt", entry_name = { from = {"ŵ", "Ŵ", "á", "Á", "é", "É", "í", "Í", "ó", "Ó", "ú", "Ú", "ń", "Ń", "ḿ", "Ḿ" }, to = {"w", "W", "a", "A", "e", "E", "i", "I", "o", "O", "u", "U", "n", "N", "m", "M"}}, sort_key = { from = {"ng'"}, to = {"ng"}} , wikipedia_article = "Chewa language", } m["oc"] = { "အောက်စဳတာန်", "Q14185", "roa-ocr", aliases = {"အောက်စဳတာန်"}, -- don't list varieties here that are in [[Module:etymology languages/data]] scripts = {"Latn", "Hebr"}, ancestors = {"pro"}, sort_key = { from = {"[àá]", "[èé]", "[íï]", "[òó]", "[úü]", "ç", "([lns])·h"}, to = {"a" , "e" , "i" , "o" , "u" , "c", "%1h" }} , } m["oj"] = { canonicalName = "အဝ်ဂျဳဗဝေ", otherNames = {"Ojibwe", "Chippewa", "Ojibway", "Ojibwemowin", "Southwestern Ojibwa"}, scripts = {"Cans", "Latn"}, family = "alg", } m["om"] = { canonicalName = "အဝ်ရဝ်မဝ်", otherNames = {"Oromo", "Orma", "Borana-Arsi-Guji Oromo", "West Central Oromo"}, scripts = {"Latn", "Ethi"}, family = "cus-eas", } m["or"] = { canonicalName = "အဝ်ရေဝ်ယာ", otherNames = {"Oriya", "Odia", "Oorya"}, scripts = {"Orya"}, family = "inc", ancestors = {"inc-mgd"}, translit_module = "or-translit", wikipedia_article = "Odia language", } m["os"] = { canonicalName = "အဝ်ဇြဳယာန်", otherNames = {"Ossetian", "Ossete", "Ossetic", "Digor", "Iron"}, scripts = {"Cyrl", "Geor", "Latn"}, family = "ira", ancestors = {"oos"}, translit_module = "os-translit", override_translit = true, entry_name = { from = {GRAVE, ACUTE}, to = {}} , } m["pa"] = { canonicalName = "ပါန်ချာပဳ", otherNames = {"Punjabi", "Panjabi"}, scripts = {"Guru", "pa-Arab"}, family = "inc-opa", ancestors = {"inc-opa"}, translit_module = "translit-redirect", entry_name = { from = {u(0x064B), u(0x064C), u(0x064D), u(0x064E), u(0x064F), u(0x0650), u(0x0651), u(0x0652), u(0x0658), u(0x08C7), u(0x0768)}, to = {"", "", "", "", "", "", "", "", "", "ل", "ن"}} , } m["pi"] = { "ပါဠိ", "Q36727", "inc-mid", scripts = {"Latn", "Brah", "Deva", "Beng", "Sinh", "Mymr", "Thai", "Lana", "Laoo", "Khmr"}, ancestors = {"sa"}, translit_module = "pi-translit", sort_key = { from = {"ā", "ī", "ū", "ḍ", "ḷ", "[ṁṃ]", "ṅ", "ñ", "ṇ", "ṭ", "([เโ])([ก-ฮ])", "([ເໂ])([ກ-ຮ])", "ᩔ", "ᩕ", "ᩖ", "ᩘ", "([ᨭ-ᨱ])ᩛ", "([ᨷ-ᨾ])ᩛ", "ᩤ", u(0xFE00), u(0x200D)}, to = {"a~", "i~", "u~", "d~", "l~", "m~", "n~", "n~~", "n~~~", "t~", "%2%1", "%2%1", "ᩈ᩠ᩈ", "᩠ᩁ", "᩠ᩃ", "ᨦ᩠", "%1᩠ᨮ", "%1᩠ᨻ", "ᩣ"}} , entry_name = { from = {u(0xFE00)}, to = {}}, } m["pl"] = { canonicalName = "ပဝ်လာန်", otherNames = {"Polish"}, scripts = {"Latn"}, family = "zlw", ancestors = {"zlw-opl", "sla-pro"}, sort_key = { from = {"[Ąą]", "[Ćć]", "[Ęę]", "[Łł]", "[Ńń]", "[Óó]", "[Śś]", "[Żż]", "[Źź]"}, to = { "a" .. u(0x10FFFF), "c" .. u(0x10FFFF), "e" .. u(0x10FFFF), "l" .. u(0x10FFFF), "n" .. u(0x10FFFF), "o" .. u(0x10FFFF), "s" .. u(0x10FFFF), "z" .. u(0x10FFFF), "z" .. u(0x10FFFE)}} , } m["ps"] = { "ပါသတုန်", "Q58680", "ira-pat", aliases = {"Pashtun", "Pushto", "Pashtu", "Afghani"}, varieties = {"Central Pashto", "Northern Pashto", "Southern Pashto", {"Pukhto", "Pakhto", "Pakkhto"}}, scripts = {"ps-Arab"}, ancestors = {"ira-pat-pro"}, } m["pt"] = { canonicalName = "ပဝ်တူဂြဳ", otherNames = {"Portuguese", "Modern Portuguese"}, scripts = {"Latn", "Brai"}, family = "roa", ancestors = {"ine-pro", "itc-pro", "itc-ola", "la", "roa-opt"}, sort_key = { from = {"[àãáâä]", "[èẽéêë]", "[ìĩíï]", "[òóôõö]", "[üúùũ]", "ç", "ñ"}, to = {"a" , "e" , "i" , "o" , "u" , "c", "n"}} , } m["qu"] = { canonicalName = "ခေန်ချူဝါ", scripts = {"Latn"}, family = "qwe", wikipedia_article = "ဘာသာခေန်ချူဝါ", } m["rm"] = { canonicalName = "ရဝ်မာန်", otherNames = {"Romansch","Romansh", "Rumantsch", "Romanche"}, scripts = {"Latn"}, family = "roa", wikipedia_article = "Romansh language", } m["ro"] = { canonicalName = "ရဝ်မေနဳယျာ", otherNames = {"Romanian", "Daco-Romanian", "Roumanian", "Rumanian"}, scripts = {"Latn", "Cyrl"}, family = "roa", sort_key = { from = {"ă" , "â" , "î" , "ș" , "ț" }, to = {"a~", "a~~", "i~", "s~", "t~"}}, } m["ru"] = { canonicalName = "ရုဿျှာ", otherNames = {"Russian"}, scripts = {"Cyrl", "Brai"}, family = "zle", translit_module = "ru-translit", sort_key = { from = {"ё"}, to = {"е" .. mw.ustring.char(0x10FFFF)}}, entry_name = { from = {"Ѐ", "ѐ", "Ѝ", "ѝ", GRAVE, ACUTE}, to = {"Е", "е", "И", "и"}}, standardChars = "ЁІА-яёі0-9—" .. PUNCTUATION, } m["rw"] = { canonicalName = "ရဝမ်ဒါ ရမ်ဒဳ", otherNames = {"Rwanda-Rundi", "Rwanda", "Kinyarwanda", "Rundi", "Kirundi", "Ha", "Giha", "Hangaza", "Vinza", "Shubi", "Subi"}, scripts = {"Latn"}, family = "bnt", wikipedia_article = "Rwanda-Rundi", } m["sa"] = { canonicalName = "သံသကြိုတ်", otherNames = {"Sanskrit"}, scripts = {"Deva", "Bali", "as-Beng", "Beng", "Bhks", "Brah", "Gran", "Gujr", "Guru", "Java", "Khar", "Khmr", "Knda", "Lana", "Laoo", "Mlym", "Modi", "Mymr", "Nand", "Newa", "Orya", "Saur", "Shrd", "Sidd", "Sinh", "Taml", "Telu", "Thai", "Tibt", "Tirh"}, family = "inc-old", sort_key = { from = {"ā", "ī", "ū", "ḍ", "ḷ", "ḹ", "[ṁṃ]", "ṅ", "ñ", "ṇ", "ṛ", "ṝ", "ś", "ṣ", "ṭ", "([เโไ])([ก-ฮ])", "([ເໂໄ])([ກ-ຮ])", "ᩔ", "ᩕ", "ᩖ", "ᩘ", "([ᨭ-ᨱ])ᩛ", "([ᨷ-ᨾ])ᩛ", "ᩤ", u(0xFE00), u(0x200D)}, to = {"a~", "i~", "u~", "d~", "l~", "l~~", "m~", "n~", "n~~", "n~~~", "r~", "r~~", "s~", "s~~", "t~", "%2%1", "%2%1", "ᩈ᩠ᩈ", "᩠ᩁ", "᩠ᩃ", "ᨦ᩠", "%1᩠ᨮ", "%1᩠ᨻ", "ᩣ"}}, entry_name = { from = {"ึ", u(0xF700), u(0xF70F), u(0xFE00)}, to = {"ิํ", "ฐ", "ญ"}}, translit_module = "translit-redirect", ancestors = {"iir-pro", "inc-pro"}, } m["sc"] = { canonicalName = "သာဒဳနဳယာန်", otherNames = {"Sardinian", "Campidanese", "Campidanese Sardinian", "Logudorese", "Logudorese Sardinian", "Nuorese", "Nuorese Sardinian"}, scripts = {"Latn"}, family = "roa", } m["sd"] = { "သိန္ဓိ", 33997, "inc-snd", scripts = {"sd-Arab", "Deva", "Sind", "Khoj"}, entry_name = { from = {u(0x0671), u(0x064B), u(0x064C), u(0x064D), u(0x064E), u(0x064F), u(0x0650), u(0x0651), u(0x0652), u(0x0670), u(0x0640)}, to = {u(0x0627)}}, ancestors = {"inc-vra"}, translit_module = "translit-redirect", } m["se"] = { canonicalName = "သာမိ သၟဝ်ကျာ", otherNames = {"Northern Sami", "North Sami", "Northern Saami", "North Saami"}, scripts = {"Latn"}, family = "smi", entry_name = { from = {"([đflmnŋrsšŧv])'%1"}, to = {"%1%1"} }, wikipedia_article = "Northern Sami", } m["sg"] = { canonicalName = "သင်ဂဝ်", otherNames = {"Sango"}, scripts = {"Latn"}, family = "crp", } m["sh"] = { canonicalName = "သာဗ်ခြဝ်ဨရှဳယာန်", otherNames = {"Serbo-Croatian", "BCS", "Croato-Serbian", "Serbocroatian", "Bosnian", "Croatian", "Montenegrin", "Serbian"}, scripts = {"Latn", "Cyrl"}, family = "zls", ancestors = {"ine-pro", "ine-bsl-pro", "sla-pro"}, entry_name = { from = {"[ȀÀȂÁĀÃ]", "[ȁàȃáāã]", "[ȄÈȆÉĒẼ]", "[ȅèȇéēẽ]", "[ȈÌȊÍĪĨ]", "[ȉìȋíīĩ]", "[ȌÒȎÓŌÕ]", "[ȍòȏóōõ]", "[ȐȒŔ]", "[ȑȓŕ]", "[ȔÙȖÚŪŨ]", "[ȕùȗúūũ]", "Ѐ", "ѐ", "[ӢЍ]", "[ӣѝ]", "[Ӯ]", "[ӯ]", GRAVE, ACUTE, DGRAVE, INVBREVE, MACRON, TILDE}, to = {"A" , "a" , "E" , "e" , "I" , "i" , "O" , "o" , "R" , "r" , "U" , "u" , "Е", "е", "И" , "и", "У", "у" }}, wikimedia_codes = {"sh", "bs", "hr", "sr"}, wikipedia_article = "Serbo-Croatian", } m["si"] = { canonicalName = "သိၚ်္ဃဵုရ်", otherNames = {"Sinhalese", "Singhalese", "Sinhala"}, scripts = {"Sinh"}, family = "inc", ancestors = {"elu-prk"}, translit_module = "si-translit", override_translit = true, } m["sk"] = { canonicalName = "သလဝ်ဝေန်နဳယျာ", otherNames = {"Slovak"}, scripts = {"Latn"}, family = "zlw", ancestors = {"ine-pro", "ine-bsl-pro", "sla-pro", "zlw-osk"}, sort_key = { from = {"[áä]", "é", "í", "[óô]", "ú", "ý", "ŕ", "ĺ", "[" .. DIAER .. ACUTE .. CIRC .. "]"}, to = {"a" , "e", "i", "o" , "u", "y", "r", "l", ""}} , } m["sl"] = { canonicalName = "သၠဝ်ဝေနဳ", otherNames = {"Slovene", "Slovenian"}, scripts = {"Latn"}, family = "zls", entry_name = { from = {"[ÁÀÂȂȀ]", "[áàâȃȁ]", "[ÉÈÊȆȄỆẸ]", "[éèêȇȅệẹə]", "[ÍÌÎȊȈ]", "[íìîȋȉ]", "[ÓÒÔȎȌỘỌ]", "[óòôȏȍộọ]", "[ŔȒȐ]", "[ŕȓȑ]", "[ÚÙÛȖȔ]", "[úùûȗȕ]", "ł", GRAVE, ACUTE, DGRAVE, INVBREVE, CIRC, DOTBELOW}, to = {"A" , "a" , "E" , "e" , "I" , "i" , "O" , "o" , "R" , "r" , "U" , "u" , "l"}} , } m["sm"] = { canonicalName = "သမဝ်အာန်", otherNames = {"Samoan"}, scripts = {"Latn"}, family = "poz-pol", } m["sn"] = { canonicalName = "သျှိနာ", otherNames = {"Shona"}, scripts = {"Latn"}, family = "bnt", } m["so"] = { canonicalName = "ဆဝ်မာလဳ", otherNames = {"Somali"}, scripts = {"Latn", "Arab", "Osma"}, family = "cus", entry_name = { from = {"[ÁÀÂ]", "[áàâ]", "[ÉÈÊ]", "[éèê]", "[ÍÌÎ]", "[íìî]", "[ÓÒÔ]", "[óòô]", "[ÚÙÛ]", "[úùû]", "[ÝỲ]", "[ýỳ]"}, to = {"A" , "a" , "E" , "e" , "I" , "i" , "O" , "o" , "U" , "u", "Y", "y"}} , } m["sq"] = { canonicalName = "အလ်ဗနဳယာန်", otherNames = {"Albanian"}, scripts = {"Latn", "Elba"}, family = "sqj", ancestors = {"ine-pro", "sqj-pro"}, sort_key = { from = { '[âãä]', '[ÂÃÄ]', '[êẽë]', '[ÊẼË]', 'ĩ', 'Ĩ', 'õ', 'Õ', 'ũ', 'Ũ', 'ỹ', 'Ỹ', 'ç', 'Ç' }, to = { 'a', 'A', 'e', 'E', 'i', 'I', 'o', 'O', 'u', 'U', 'y', 'Y', 'c', 'C' } } , } m["ss"] = { canonicalName = "သဝါဇြဳ", otherNames = {"Swazi", "Swati"}, scripts = {"Latn"}, family = "bnt-ngu", entry_name = { from = {"[āàáâǎ]", "[ēèéêě]", "[īìíîǐ]", "[ōòóôǒ]", "[ūùúûǔ]", "ḿ", "[ǹńň]", MACRON, ACUTE, GRAVE, CIRC, CARON}, to = {"a" , "e" , "i" , "o" , "u" , "m", "n" }}, ancestors = {"bnt-pro"}, } m["st"] = { canonicalName = "သူထူ", otherNames = {"Sotho", "Sesotho", "Southern Sesotho", "Southern Sotho"}, scripts = {"Latn"}, family = "bnt", } m["su"] = { canonicalName = "သာန်ဓနဳ", otherNames = {"Sundanese"}, scripts = {"Sund", "Latn"}, family = "poz-msa", ancestors = {"map-pro", "poz-pro", "poz-sus-pro", "poz-msa-pro", "osn"}, translit_module = "su-translit", } m["sv"] = { canonicalName = "သွဳဒေန်", otherNames = {"Swedish"}, scripts = {"Latn"}, family = "gmq", ancestors = {"gmq-osw", "gem-pro", "ine-pro"}, sort_key = { from = {"ö", "å", "ä"}, to = {"o", "a", "a"}} , } m["sw"] = { canonicalName = "သဝါတ်ဟဳလဳ", otherNames = {"Swahili", "Settler Swahili", "KiSetla", "KiSettla", "Setla", "Settla", "Kitchen Swahili", "Kihindi", "Indian Swahili", "KiShamba", "Kishamba", "Field Swahili", "Kibabu", "Asian Swahili", "Kimanga", "Arab Swahili", "Kitvita", "Army Swahili"}, scripts = {"Latn", "Arab"}, family = "bnt", sort_key = { from = {"ng'", "^-"}, to = {"ngz"}} , } m["ta"] = { canonicalName = "တမဳလ်", otherNames = {"Tamil"}, scripts = {"Taml"}, family = "dra", ancestors = {"oty"}, translit_module = "ta-translit", override_translit = true, } m["te"] = { canonicalName = "တေလုဂု", otherNames = {"Telugu"}, scripts = {"Telu"}, family = "dra", ancestors = {"dra-pro", "dra-sou-pro", "dra-sdt-pro", "dra-ote"}, translit_module = "te-translit", override_translit = true, } m["tg"] = { canonicalName = "တာဇိက်", otherNames = {"Tajik", "Tadjik", "Tadzhik", "Tajiki", "Tajik Persian"}, scripts = {"Cyrl", "fa-Arab", "Latn"}, family = "ira-wes", ancestors = {"fa"}, translit_module = "tg-translit", override_translit = true, sort_key = { from = {"Ё", "ё"}, to = {"Е" , "е"}} , entry_name = { from = {ACUTE}, to = {}} , } m["th"] = { "သေံ", 9217, family = "tai-swe", scripts = {"Thai", "Brai"}, translit_module = "th-translit", sort_key = { from = {"[%pๆ]", "[็-๎]", "([เแโใไ])([ก-ฮ])"}, to = {"", "", "%2%1"}}, ancestors = {"qfa-tak-pro", "qfa-bet-pro", "tai-pro", "tai-swe-pro"}, } m["ti"] = { canonicalName = "တဳဂျရေဝ်ယျာ", otherNames = {"Tigrinya"}, scripts = {"Ethi"}, family = "sem-eth", translit_module = "Ethi-translit", } m["tk"] = { canonicalName = "တာခ်မေန်", otherNames = {"Turkmen"}, scripts = {"Latn", "Cyrl"}, family = "trk-ogz", entry_name = { from = {"ā", "ē", "ī", "ō", "ū", "ȳ", "ȫ", "ǖ", MACRON}, to = {"a", "e", "i", "o", "u", "y", "ö", "ü", ""}}, } m["tl"] = { canonicalName = "တာဂါလံက်", otherNames = {"Tagalog"}, scripts = {"Latn", "Tglg"}, family = "phi", entry_name = { from = {"[áàâ]", "[éèê]", "[íìî]", "[óòô]", "[úùû]", ACUTE, GRAVE, CIRC}, to = {"a" , "e" , "i" , "o" , "u" }}, translit_module = "tl-translit", override_translit = true } m["tn"] = { canonicalName = "သွာနာ", otherNames = {"Tswana", "Setswana"}, scripts = {"Latn"}, family = "bnt", } m["to"] = { canonicalName = "ထံင်ဂံင်", otherNames = {"Tongan"}, scripts = {"Latn"}, family = "poz-pol", } m["tr"] = { canonicalName = "တူရကဳ", otherNames = {"Turkish"}, scripts = {"Latn"}, family = "trk-ogz", ancestors = {"ota"}, } m["ts"] = { canonicalName = "သွေန်ဂါ", otherNames = {"Tsonga"}, scripts = {"Latn"}, family = "bnt", ancestors = {"nic-pro", "alv-pro", "nic-vco-pro", "nic-bco-pro", "nic-bod-pro", "bnt-pro"}, } m["tt"] = { canonicalName = "တာတာ", otherNames = {"Tatar"}, scripts = {"Cyrl", "Latn", "Arab", "tt-Arab"}, family = "trk-kip", translit_module = "tt-translit", override_translit = true, } -- "tw" IS TREATED AS "ak", SEE WT:LT m["ty"] = { canonicalName = "တဟဳတဳဃှေန်", otherNames = {"Tahitian"}, scripts = {"Latn"}, family = "poz-pol", } m["ug"] = { canonicalName = "ဥူဃူရ်", otherNames = {"Uigur", "Uighur", "Uygur"}, scripts = {"ug-Arab", "Latn", "Cyrl"}, family = "trk", ancestors = {"chg"}, translit_module = "ug-translit", override_translit = true, } m["uk"] = { canonicalName = "ယူကရိန်", otherNames = {"Ukrainian"}, scripts = {"Cyrl"}, family = "zle", ancestors = {"ine-pro", "ine-bsl-pro", "sla-pro", "orv", "zle-ouk"}, translit_module = "uk-translit", entry_name = { from = {"Ѐ", "ѐ", "Ѝ", "ѝ", GRAVE, ACUTE}, to = {"Е", "е", "И", "и"}}, standardChars = "ЄІЇА-ЩЫЬЮ-щыьюяєії" .. PUNCTUATION } m["ur"] = { "အူရဒူ", "Q1617", "inc-hnd", scripts = {"ur-Arab"}, ancestors = {"inc-ohi"}, entry_name = { from = {u(0x064B), u(0x064C), u(0x064D), u(0x064E), u(0x064F), u(0x0650), u(0x0651), u(0x0652)}, to = {}} , } m["uz"] = { canonicalName = "ဥုသဗဝ်", otherNames = {"Uzbek", "Northern Uzbek", "Southern Uzbek"}, scripts = {"Latn", "Cyrl", "fa-Arab"}, family = "trk", ancestors = {"chg"}, translit_module = "uz-translit" } m["ve"] = { canonicalName = "ဗါန်ဒါ", otherNames = {"Venda"}, scripts = {"Latn"}, family = "bnt", } m["vi"] = { canonicalName = "ဗဳယေတ်နာမ်", otherNames = {"Vietnamese", "Annamese", "Annamite"}, scripts = {"Latn", "Hani"}, family = "mkh-vie", ancestors = {"mkh-mvi"}, sort_key = "vi-sortkey", } m["vo"] = { canonicalName = "ဝဝ်လပုက်", otherNames = {"Volapük"}, scripts = {"Latn"}, family = "art", wikipedia_article = "Volapük", } m["wa"] = { canonicalName = "ဝါဠူ", otherNames = {"Walloon", "Liégeois", "Namurois", "Wallo-Picard", "Wallo-Lorrain"}, scripts = {"Latn"}, family = "roa-oil", ancestors = {"fro"}, sort_key = { from = {"[áàâäå]", "[éèêë]", "[íìîï]", "[óòôö]", "[úùûü]", "[ýỳŷÿ]", "ç", "'"}, to = {"a" , "e" , "i" , "o" , "u" , "y" , "c"}} , } m["wo"] = { canonicalName = "ဝဝ်လံက်", otherNames = {"Wolof", "Gambian Wolof"}, -- the subsumed dialect 'wof' scripts = {"Latn", "Arab"}, family = "alv-sng", } m["xh"] = { canonicalName = "ခါဝ်သာ", otherNames = {"Xhosa"}, scripts = {"Latn"}, family = "bnt-ngu", entry_name = { from = {"[āàáâǎ]", "[ēèéêě]", "[īìíîǐ]", "[ōòóôǒ]", "[ūùúûǔ]", "ḿ", "[ǹńň]", MACRON, ACUTE, GRAVE, CIRC, CARON}, to = {"a" , "e" , "i" , "o" , "u" , "m", "n" }}, ancestors = {"bnt-pro"}, } m["yi"] = { canonicalName = "ယိဒ်ဒိသ်", otherNames = {"Yiddish"}, scripts = {"Hebr"}, family = "gmw", ancestors = {"gmh"}, translit_module = "yi-translit", wikipedia_article = "Yiddish", } m["yo"] = { canonicalName = "ရိုရုဗာ", otherNames = {"Yoruba"}, scripts = {"Latn"}, family = "alv-von", ancestors = {"alv-yor-pro", "alv-edk-pro", "alv-yrd-pro"}, } m["za"] = { canonicalName = "ဇြုန်", otherNames = {"Standard Zhuang"}, scripts = {"Latn", "Hani"}, family = "tai", wikipedia_article = "Zhuang languages", } m["zh"] = { canonicalName = "ကြုက်", otherNames = {"Chinese"}, scripts = {"Hani", "Brai"}, family = "sit", ancestors = {"ltc", "sit-pro"}, sort_key = "zh-sortkey", } m["zu"] = { canonicalName = "သြူဠူ", otherNames = {"Zulu", "isiZulu"}, scripts = {"Latn"}, family = "bnt-ngu", entry_name = { from = {"[āàáâǎ]", "[ēèéêě]", "[īìíîǐ]", "[ōòóôǒ]", "[ūùúûǔ]", "ḿ", "[ǹńň]", MACRON, ACUTE, GRAVE, CIRC, CARON}, to = {"a" , "e" , "i" , "o" , "u" , "m", "n" }}, ancestors = {"bnt-pro"}, } return m 6gax4jytm65lsyxahzgzbzolvgufcjb 103865 103863 2024-11-01T08:37:35Z 咽頭べさ 33 မကလေၚ်ပလီုထောံ[[Special:Diff/103863|103863]]နူကဵု[[Special:Contributions/咽頭べさ|咽頭べさ]] ([[User talk:咽頭べさ|ဓရီုကျာ]])မပလေဝ်ဒါန်လဝ် 103865 Scribunto text/plain local u = mw.ustring.char -- UTF-8 encoded strings for some commonly-used diacritics local GRAVE = u(0x0300) local ACUTE = u(0x0301) local CIRC = u(0x0302) local TILDE = u(0x0303) local MACRON = u(0x0304) local BREVE = u(0x0306) local DOTABOVE = u(0x0307) local DIAER = u(0x0308) local CARON = u(0x030C) local DGRAVE = u(0x030F) local INVBREVE = u(0x0311) local DOTBELOW = u(0x0323) local RINGBELOW = u(0x0325) local CEDILLA = u(0x0327) local OGONEK = u(0x0328) local DOUBLEINVBREVE = u(0x0361) -- Punctuation to be used for standardChars field local PUNCTUATION = ' !#%&*+,-./:;<=>?@^_`|~\'()' local Cyrl = {"Cyrl"} local Latn = {"Latn"} local LatnArab = {"Latn", "Arab"} local m = {} m["aa"] = { canonicalName = "အဖှာင်", otherNames = {"Qafar"}, scripts = {"Latn"}, family = "cus", } m["ab"] = { canonicalName = "အာပ်ဟန်", otherNames = {"Abkhaz", "Abkhazian", "Abxazo"}, scripts = {"Cyrl", "Geor", "Latn"}, family = "cau-abz", translit_module = "ab-translit", override_translit = true, entry_name = { from = {GRAVE, ACUTE}, to = {}} , } m["ae"] = { "အဗါတ်သတေန်", 29572, "ira-cen", scripts = {"Avst", "Gujr"}, translit_module = "Avst-translit", wikipedia_article = "Avestan", } m["af"] = { canonicalName = "အေက်ဖရိကာန်", scripts = {"Latn", "Arab"}, family = "gmw", ancestors = {"nl"}, sort_key = { from = {"[äáâà]", "[ëéêè]", "[ïíîì]", "[öóôò]", "[üúûù]", "[ÿýŷỳ]", "^-", "'"}, to = {"a" , "e" , "i" , "o" , "u" , "y" }} , wikipedia_article = "Afrikaans", } m["ak"] = { canonicalName = "အကာန်", otherNames = {"Akan", "Twi-Fante", "Twi", "Fante", "Fanti", "Asante", "Akuapem"}, scripts = {"Latn"}, family = "alv-kwa", } m["am"] = { canonicalName = "အာန်ဟာရိစ်", otherNames = {"Amharic"}, scripts = {"Ethi"}, family = "sem-eth", translit_module = "Ethi-translit", wikipedia_article = "Amharic", } m["an"] = { canonicalName = "အာဒါဂေန်", otherNames = {"Aragonese"}, scripts = {"Latn"}, family = "roa", ancestors = {"ine-pro", "itc-pro", "itc-ola", "la", "roa-oan"}, } m["ar"] = { canonicalName = "အာရဗဳ", otherNames = {"Modern Standard Arabic", "Standard Arabic", "Literary Arabic", "Classical Arabic", "Arabic", "အာရက်လ်"}, scripts = {"Arab", "Brai"}, family = "sem-arb", -- alif waṣl to alif, remove diacritics entry_name = { from = {u(0x0671), u(0x064B), u(0x064C), u(0x064D), u(0x064E), u(0x064F), u(0x0650), u(0x0651), u(0x0652), u(0x0670), u(0x0640)}, to = {u(0x0627)}}, translit_module = "ar-translit", wikipedia_article = "Arabic", ancestors = {"sem-pro"}, } m["as"] = { canonicalName = "အိသ်ဇြာံမဳ", otherNames ={"Assamese"}, scripts = {"Beng"}, family = "inc", ancestors = {"inc-mgd"}, translit_module = "as-translit", } m["av"] = { "အာဗာ", "Q29561", "cau-nec", aliases = {"Avaric"}, scripts = Cyrl, ancestors = {"oav"}, translit_module = "translit-redirect", override_translit = true, entry_name = { from = {GRAVE, ACUTE}, to = {}} , } m["ay"] = { canonicalName = "အိုင်မာရ", otherNames = {"Aymara", "Southern Aymara", "Central Aymara"}, scripts = {"Latn"}, family = "sai-aym", } m["az"] = { "အာက်သေတ်ဗါဲဇြေနဳ", 9292, "trk-ogz", {"Latn", "Cyrl", "fa-Arab"}, ancestors = {"trk-oat"}, dotted_dotless_i = true, } m["ba"] = { canonicalName = "ဗေတ်ခဳ", otherNames = {"Bashkir"}, scripts = {"Cyrl"}, family = "trk-kip", translit_module = "ba-translit", override_translit = true, } m["be"] = { canonicalName = "ဗါလာရုဇ်", otherNames = {"Belarusian", "Belorussian", "Belarusan", "Bielorussian", "Byelorussian", "Belarussian", "White Russian"}, scripts = {"Cyrl"}, family = "zle", ancestors = {"orv"}, translit_module = "be-translit", sort_key = { from = {"Ё", "ё"}, to = {"Е" , "е"}}, entry_name = { from = {"Ѐ", "ѐ", GRAVE, ACUTE}, to = {"Е", "е"}}, } m["bg"] = { canonicalName = "ဗူလ်ဂရဳယာန်", otherNames = {"Bulgarian"}, scripts = {"Cyrl"}, family = "zls", translit_module = "bg-translit", entry_name = { from = {"Ѐ", "ѐ", "Ѝ", "ѝ", GRAVE, ACUTE}, to = {"Е", "е", "И", "и"}}, } m["bh"] = { canonicalName = "ဘဳဟာရဳ", otherNames = {"Bihari"}, scripts = {"Deva"}, family = "inc", ancestors = {"inc-mgd"}, wikipedia_article = "ဘာသာဘဳဟာရဳ", } m["bi"] = { canonicalName = "ဗဳသလာမာ", otherNames = {"Bislama"}, scripts = {"Latn"}, family = "crp", ancestors = {"ine-pro", "gem-pro", "gmw-pro", "ang", "enm", "en-ear", "en"}, wikipedia_article = "Bislama", } m["bm"] = { canonicalName = "ဗီုဗရာ", otherNames = {"Bamanankan"}, scripts = {"Latn"}, family = "dmn", } m["bn"] = { canonicalName = "ဘင်္ဂါလဳ", otherNames = {"Bangla", "Bengali"}, scripts = {"Beng"}, family = "inc", ancestors = {"inc-mgd"}, translit_module = "bn-translit", } m["bo"] = { canonicalName = "တဳဗဝ်", otherNames = {"Tibetan", "Ü", "Dbus", "Lhasa", "Lhasa Tibetan", "Amdo Tibetan", "Amdo", "Panang", "Khams", "Khams Tibetan", "Khamba", "Tseku", "Dolpo", "Humla", "Limi", "Lhomi", "Shing Saapa", "Mugom", "Mugu", "Nubri", "Walungge", "Gola", "Thudam", "Lowa", "Loke", "Mustang", "Tichurong", "တိဗက်"}, scripts = {"Tibt"}, family = "tbq", ancestors = {"xct"}, translit_module = "bo-translit", override_translit = true, wikipedia_article = "Standard Tibetan", -- may need verification } m["br"] = { canonicalName = "ဗရဳတေန်", otherNames = {"Breton"}, scripts = {"Latn"}, family = "cel-bry", ancestors = {"xbm"}, } m["ca"] = { canonicalName = "ကတလာန်", otherNames = {"Valencian", "Catalan"}, scripts = {"Latn"}, family = "roa", ancestors = {"roa-oca"}, sort_key = { from = {"à", "[èé]", "[íï]", "[òó]", "[úü]", "ç", "l·l"}, to = {"a", "e" , "i" , "o" , "u" , "c", "ll" }} , } m["ce"] = { canonicalName = "ချက်ခ်ချေင်", otherNames = {"Chechen"}, scripts = {"Cyrl", "Latn", "Arab"}, family = "cau-nkh", translit_module = "translit-redirect", override_translit = true, ancestors = {"ccn-pro", "cau-nec-pro", "cau-nkh-pro"}, entry_name = { from = {MACRON}, to = {}}, } m["ch"] = { canonicalName = "ချာမဝ်ရဝ်", otherNames = {"Chamorro", "Chamoru"}, scripts = {"Latn"}, family = "poz-sus", } m["co"] = { canonicalName = "ခဝ်သဳကာန်", otherNames = {"Corsican", "Corsu"}, scripts = {"Latn"}, family = "roa", } m["cr"] = { canonicalName = "ခရေဝ်", scripts = {"Cree", "Cans", "Latn"}, family = "alg", translit_module = "cr-translit", } m["cs"] = { canonicalName = "ချက်ခ်", otherNames = {"Czech"}, scripts = {"Latn"}, family = "zlw", ancestors = {"zlw-ocs", "sla-pro"}, sort_key = { from = {"á", "é", "í", "ó", "[úů]", "ý"}, to = {"a", "e", "i", "o", "u" , "y"}} , } m["cu"] = { "ခရေတ်သလာဗဝ်နေတ်တြေံ", "Q35499", "zls", aliases = {"Old Church Slavic"}, scripts = {"Cyrs", "Glag"}, translit_module = "Cyrs-Glag-translit", ancestors = {"ine-pro", "ine-bsl-pro", "sla-pro"}, entry_name = { from = {u(0x0484)}, -- kamora to = {}}, sort_key = { from = {"оу", "є"}, to = {"у" , "е"}} , } m["cv"] = { "ချူဝါတ်", "Q33348", "trk-ogr", scripts = Cyrl, ancestors = {"xbo"}, translit_module = "cv-translit", sort_key = { from = {"ӑ", "ё", "ӗ", "ҫ", "ӳ"}, to = { "а" .. u(0xF000), "е" .. u(0xF000), "е" .. u(0xF001), "с" .. u(0xF000), "у" .. u(0xF000) } }, override_translit = true, } m["cy"] = { canonicalName = "ဝေလ", otherNames ={"Welsh"}, scripts = {"Latn"}, family = "cel-bry", ancestors = {"wlm"}, sort_key = { from = {"[âáàä]", "[êéèë]", "[îíìï]", "[ôóòö]", "[ûúùü]", "[ŵẃẁẅ]", "[ŷýỳÿ]", "'"}, to = {"a" , "e" , "i" , "o" , "u" , "w" , "y" }} , } m["da"] = { canonicalName = "ဒိန်နေတ်", otherNames ={"Danish"}, scripts = {"Latn"}, family = "gmq", ancestors = {"gmq-oda"}, } m["de"] = { canonicalName = "ဂျာမာန်", otherNames = {"High German", "New High German", "Deutsch", "German", "ဂျာမနဳ"}, scripts = {"Latn", "Latf"}, family = "gmw", ancestors = {"gmh"}, sort_key = { from = {"[äàáâå]", "[ëèéê]", "[ïìíî]", "[öòóô]", "[üùúû]", "ß" }, to = {"a" , "e" , "i" , "o" , "u" , "ss"}} , } m["dv"] = { canonicalName = "ဒိဝေဟဳ", otherNames = {"Dhivehi", "Divehi", "Mahal", "Mahl", "Maldivian"}, scripts = {"Thaa"}, family = "inc", ancestors = {"pmh"}, -- or Helu? translit_module = "dv-translit", override_translit = true, wikipedia_article = "ဘာသာမောဝ်ဒိုက်", } m["dz"] = { canonicalName = "သောင်ခါ", otherNames = {"Dzongkha"}, scripts = {"Tibt"}, family = "tbq", ancestors = {"xct"}, translit_module = "bo-translit", override_translit = true, wikipedia_article = "Dzongkha", } m["ee"] = { canonicalName = "အဳဝါ", otherNames = {"Ewe"}, scripts = {"Latn"}, family = "alv-von", } m["el"] = { canonicalName = "ဂရေတ်", otherNames = {"Greek", "Modern Greek", "Neo-Hellenic"}, scripts = {"Grek", "Brai", "Polyt", "Latn"}, family = "grk", ancestors = {"ine-pro", "grk-pro", "grc-att", "grc-koi", "gkm-med", "el-kth", "grc"}, translit_module = "el-translit", override_translit = true, sort_key = { -- Keep this synchronized with grc, cpg, pnt from = {"[ᾳάᾴὰᾲᾶᾷἀᾀἄᾄἂᾂἆᾆἁᾁἅᾅἃᾃἇᾇ]", "[έὲἐἔἒἑἕἓ]", "[ῃήῄὴῂῆῇἠᾐἤᾔἢᾒἦᾖἡᾑἥᾕἣᾓἧᾗ]", "[ίὶῖἰἴἲἶἱἵἳἷϊΐῒῗ]", "[όὸὀὄὂὁὅὃ]", "[ύὺῦὐὔὒὖὑὕὓὗϋΰῢῧ]", "[ῳώῴὼῲῶῷὠᾠὤᾤὢᾢὦᾦὡᾡὥᾥὣᾣὧᾧ]", "ῥ", "ς"}, to = {"α" , "ε" , "η" , "ι" , "ο" , "υ" , "ω" , "ρ", "σ"}} , standardChars = "ͺ;΄-ώϜϝ" .. PUNCTUATION .. "ἀ-῾" } m["en"] = { canonicalName = "အင်္ဂလိက်", otherNames = {"English", "Modern English", "New English", "Hawaiian Creole English", "Hawai'ian Creole English", "Hawaiian Creole", "Hawai'ian Creole", "Polari", "Yinglish"}, -- all but the first three are names of subsumed dialects which once had codes scripts = {"Latn", "Brai", "Shaw", "Dsrt"}, -- entries in Shaw or Dsrt might require prior discussion family = "gmw", ancestors = {"enm"}, wikipedia_article = "ဘာသာအင်္ဂလိက်", sort_key = { from = {"[äàáâåā]", "[ëèéêē]", "[ïìíîī]", "[öòóôō]", "[üùúûū]", "æ" , "œ" , "[çč]", "ñ", "['9]", "1", "[23]", "[45]", "[67]", "0", "+", "."}, to = {"a" , "e" , "i" , "o" , "u" , "ae", "oe", "c" , "n" , "o" , "t" , "s" , "z" , "p" , "q"}}, wikimedia_codes = {"en", "simple"}, standardChars = "A-Za-z0-9" .. PUNCTUATION .. u(0x2800) .. "-" .. u(0x28FF) } m["eo"] = { canonicalName = "အေက်သပရေန်တဝ်", otherNames = {"Esperanto"}, scripts = {"Latn"}, family = "art", sort_key = { from = {"[áà]", "[éè]", "[íì]", "[óò]", "[úù]", "[ĉ]", "[ĝ]", "[ĥ]", "[ĵ]", "[ŝ]", "[ŭ]"}, to = {"a" , "e" , "i" , "o" , "u", "cĉ", "gĉ", "hĉ", "jĉ", "sĉ", "uĉ"}} , wikipedia_article = "Esperanto", } m["es"] = { "သပုင်", 1321, "roa-ibe", {"Latn", "Brai"}, ancestors = {"ine-pro", "itc-pro", "itc-ola", "la", "osp"}, sort_key = { from = {"á", "é", "í", "ó", "[úü]", "ç", "ñ"}, to = {"a", "e", "i", "o", "u" , "c", "n"}}, standardChars = "A-VXYZa-vxyz0-9ÁáÉéÍíÓóÚúÑñ¿¡" .. PUNCTUATION, } m["et"] = { canonicalName = "အေက်သတဝ်နဳယာန်", otherNames = {"Estonian"}, scripts = {"Latn"}, family = "urj-fin", } m["eu"] = { canonicalName = "ဗက်ခ်", otherNames = {"Basque", "Euskara"}, scripts = {"Latn"}, family = "euq", } m["fa"] = { canonicalName = "ပါရှေန်", otherNames = {"ပါရှာ", "ဖာသဳ", "ဖာစဳ", "Persian", "Farsi", "New Persian", "Modern Persian", "Western Persian", "Iranian Persian", "Eastern Persian", "Dari", "Aimaq", "Aimak", "Aymaq", "Eimak"}, scripts = {"fa-Arab"}, family = "ira-wes", ancestors = {"pal", "ira-pro", "iir-pro", "ine-pro"}, entry_name = { from = {u(0x064E), u(0x064F), u(0x0650), u(0x0651), u(0x0652)}, to = {}} , } m["ff"] = { canonicalName = "ဖှောတ်လာ", otherNames = {"Fula", "Adamawa Fulfulde", "Bagirmi Fulfulde", "Borgu Fulfulde", "Central-Eastern Niger Fulfulde", "Fulani", "Fulfulde", "Maasina Fulfulde", "Nigerian Fulfulde", "Pular", "Pulaar", "Western Niger Fulfulde"}, -- Maasina, etc are dialects, subsumed into this code scripts = {"Latn"}, family = "alv-sng", } m["fi"] = { "ဖေန်လာန်", "Q1412", "urj-fin", aliases = {"Suomi"}, scripts = Latn, entry_name = { from = {"ˣ"}, -- Used to indicate gemination of the next consonant to = {}}, sort_key = { from = {"[áàâã]", "[éèêẽ]", "[íìîĩ]", "[óòôõ]", "[úùûũ]", "[ýỳŷüű]", "[øõő]", "æ" , "œ" , "[čç]", "š", "ž", "ß" , "[':]"}, to = {"a" , "e" , "i" , "o" , "u" , "y" , "ö" , "ae", "oe", "c" , "s", "z", "ss"}} , } m["fj"] = { canonicalName = "ဖရဳဂျိ", otherNames = {"Fijian"}, scripts = {"Latn"}, family = "poz-occ", } m["fo"] = { canonicalName = "ဖာရဝ်သဳ", otherNames = {"Faroese"}, scripts = {"Latn"}, family = "gmq", ancestors = {"non"}, } m["fr"] = { canonicalName = "ပြင်သေတ်", otherNames = {"French", "Modern French"}, scripts = {"Latn", "Brai"}, family = "roa-oil", ancestors = {"frm", "la"}, sort_key = { from = {"[áàâä]", "[éèêë]", "[íìîï]", "[óòôö]", "[úùûü]", "[ýỳŷÿ]", "ç", "æ" , "œ" , "'"}, to = {"a" , "e" , "i" , "o" , "u" , "y" , "c", "ae", "oe"}}, standardChars = "A-Za-z0-9ÀÂÇÉÈÊËÎÏÔŒÛÙÜàâçéèêëîïôœûùü«»" .. PUNCTUATION } m["fy"] = { canonicalName = "ဖရေဝ်သဳယာန်လက္ကရဴ", otherNames = {"West Frisian", "Western Frisian", "Frisian"}, scripts = {"Latn"}, family = "gmw-fri", ancestors = {"ofs"}, } m["ga"] = { canonicalName = "အာဲယျာလာန်", otherNames = {"Irish", "Irish Gaelic", "အိုင်ရစ်ရှ်"}, scripts = {"Latn"}, family = "cel-gae", ancestors = {"mga"}, sort_key = { from = {"á", "é", "í", "ó", "ú", "ý", "ḃ" , "ċ" , "ḋ" , "ḟ" , "ġ" , "ṁ" , "ṗ" , "ṡ" , "ṫ" }, to = {"a", "e", "i", "o", "u", "y", "bh", "ch", "dh", "fh", "gh", "mh", "ph", "sh", "th"}} , } m["gd"] = { canonicalName = "သကတ်ဂဴလိစ်", otherNames = {"Scottish Gaelic", "Gàidhlig", "Highland Gaelic", "Scots Gaelic", "Scottish"}, scripts = {"Latn"}, family = "cel-gae", ancestors = {"mga"}, sort_key = { from = {"[áà]", "[éè]", "[íì]", "[óò]", "[úù]", "[ýỳ]"}, to = {"a" , "e" , "i" , "o" , "u" , "y" }} , wikipedia_article = "Scottish Gaelic", } m["gl"] = { canonicalName = "ဂလဳသဳယာန်", otherNames = {"Galician"}, scripts = {"Latn"}, family = "roa", ancestors = {"ine-pro", "itc-pro", "inc-pro", "itc-ola", "la", "roa-opt"}, sort_key = { from = {"á", "é", "í", "ó", "ú"}, to = {"a", "e", "i", "o", "u"}} , } m["gn"] = { canonicalName = "ဂူရာန်နဳ", otherNames = {"Guaraní"}, scripts = {"Latn"}, family = "tup-gua", wikipedia_article = "ဘာသာဂူရာန်နဳ", } m["gu"] = { canonicalName = "ဂုဂျာရတဳ", otherNames = {"Gujarati"}, scripts = {"Gujr"}, family = "inc", ancestors = {"inc-ogu"}, translit_module = "gu-translit", } m["gv"] = { canonicalName = "မာက်", otherNames = {"Manx", "Manx Gaelic"}, scripts = {"Latn"}, family = "cel-gae", ancestors = {"mga"}, sort_key = { from = {"ç", "-"}, to = {"c"}} , } m["ha"] = { canonicalName = "ဟဴသာ", otherNames = {"Hausa"}, scripts = {"Latn", "Arab"}, family = "cdc-wst", sort_key = { from = {"ɓ", "ɗ", "ƙ", "'y", "ƴ", "'" }, to = {"b~" , "d~" , "k~", "y~", "y~", "" }}, entry_name = { from = {"R̃", "r̃", "À", "à", "È", "è", "Ì", "ì", "Ò", "ò", "Ù", "ù", "Â", "â", "Ê", "ê", "Î", "î", "Ô", "ô", "Û", "û", "Ā", "ā", "Ē", "ē", "Ī", "ī", "Ō", "ō", "Ū", "ū", "Á", "á", "É", "é", "Í", "í", "Ó", "ó", "Ú", "ú", "Ā̀", "ā̀", "Ḕ", "ḕ", "Ī̀", "ī̀", "Ṑ", "ṑ", "Ū̀", "ū̀", GRAVE, ACUTE}, to = {"R", "r", "A", "a", "E", "e", "I", "i", "O", "o", "U", "u", "A", "a", "E", "e", "I", "i", "O", "o", "U", "u", "A", "a", "E", "e", "I", "i", "O", "o", "U", "u", "A", "a", "E", "e", "I", "i", "O", "o", "U", "u", "A", "a", "E", "e", "I", "i", "O", "o", "U", "u"}}, } m["he"] = { canonicalName = "ဟဳဘရဝ်", otherNames = {"Hebrew", "Ivrit"}, scripts = {"Hebr", "Phnx", "Brai"}, family = "sem-can", ancestors = {"afa-pro", "sem-pro", "sem-wes-pro", "hbo", "he-mis", "he-med"}, translit_module = "he-translit", entry_name = { from = {"[" .. u(0x0591) .. "-" .. u(0x05BD) .. u(0x05BF) .. "-" .. u(0x05C5) .. u(0x05C7) .. "]"}, to = {}} , } m["hi"] = { canonicalName = "ဟိန္ဒဳ", otherNames = {"ဟိန္ဒဳ", "Hindi", "Braj", "Brij Bhasha", "Braj Bhasha", "Braj Bhāshā", "Braj Bhakha", "Dehaati Zabaan"}, scripts = {"Deva", "Guru"}, -- Guru for the subsumed variety Braj family = "inc-hnd", ancestors = {"inc-ohi"}, translit_module = "hi-translit", wikipedia_article = "Hindi", } m["ho"] = { canonicalName = "ဟဳရဳမိုတု", otherNames = {"Hiri Motu", "Pidgin Motu", "Police Motu"}, scripts = {"Latn"}, family = "crp", ancestors = {"meu"}, wikipedia_article = "Hiri Motu", } m["ht"] = { "ဟေဲယှေန် ခရေဝ်အဝ်လ်", 33491, "crp", Latn, ancestors = {"fr"}, } m["hu"] = { canonicalName = "ဟာန်ဂါရေဝ်", otherNames = {"Hungarian", "Magyar"}, scripts = {"Latn", "Hung"}, family = "urj-ugr", ancestors = {"urj-pro", "urj-ugr-pro", "ohu"}, sort_key = { from = {"é", "í", "ó", "ú", "ő", "ö", "ü", "á"}, to = {"e", "i", "o", "u", "o", "o", "u", "a"}} , } m["hy"] = { canonicalName = "အာမေနဳယျာ", otherNames = {"Armenian", "Modern Armenian", "Eastern Armenian", "Western Armenian", "အမေရိကာန်ဗၟံက်", "အမေရိကာန်ပလိုတ်", "အမေရိကာန်အခေတ်တၟိ"}, scripts = {"Armn", "Brai"}, family = "hyx", ancestors = {"axm"}, translit_module = "Armn-translit", override_translit = true, sort_key = { from = {"ու", "և", "եւ"}, to = {"ւ", "եվ", "եվ"}}, entry_name = { from = {"՞", "՜", "՛", "՟", "և", "<sup>յ</sup>", "<sup>ի</sup>"}, to = {"", "", "", "", "եւ", "յ", "ի"}} , } m["hz"] = { canonicalName = "ဟဳရဲရို", otherNames = {"Herero"}, scripts = {"Latn"}, family = "bnt", } m["ia"] = { canonicalName = "အေန်တာလိင်ဂဝ်", otherNames = {"Interlingua"}, scripts = {"Latn"}, family = "art", wikipedia_article = "Interlingua", } m["id"] = { canonicalName = "အိန်ဒဝ်နဳသဳယျာ", otherNames = {"Indonesian"}, scripts = {"Latn"}, family = "poz-mly", ancestors = {"map-pro", "poz-pro", "poz-sus-pro", "poz-msa-pro", "poz-mcm-pro", "poz-mly-pro", "ms-old", "ms-cla", "ms"}, } m["ie"] = { canonicalName = "အေန်တာလိင်ဂဝေ", otherNames = {"Interlingue", "Occidental"}, scripts = {"Latn"}, family = "art", wikipedia_article = "Occidental language", } m["ig"] = { canonicalName = "အေတ်ဗါဝ်", otherNames = {"Igbo", "အစ္ဂဘို"}, scripts = {"Latn"}, family = "nic-bco", } m["ii"] = { canonicalName = "သေဲဆိုန်ယဳ", otherNames = {"Sichuan Yi", "Nuosu", "Nosu", "Northern Yi", "Liangshan Yi"}, scripts = {"Yiii"}, family = "tbq-lol", wikipedia_article = "Nuosu language", translit_module = "ii-translit", override_translit = true, } m["ik"] = { canonicalName = "အဳနုဗဳယာတ်", otherNames = {"Inupiak", "Inupiaq", "Iñupiaq", "Inupiatun"}, scripts = {"Latn"}, family = "esx-inu", wikipedia_article = "Inupiaq", } m["io"] = { canonicalName = "ဣဒဝ်", otherNames = {"Ido"}, scripts = {"Latn"}, family = "art", } m["is"] = { canonicalName = "အာက်သလာန်", otherNames = {"Icelandic", "အာက်သလာန်"}, scripts = {"Latn"}, family = "gmq", ancestors = {"non", "gem-pro", "ine-pro"}, sort_key = { from = {"ð", "ö", "ó", "æ", "á", "í", "ú"}, to = {"o", "o", "o", "ae", "a", "i", "u"}} , } m["it"] = { canonicalName = "အဳတခ်လဳ", otherNames = {"Italian"}, scripts = {"Latn"}, family = "roa", sort_key = { from = {"[àáâäå]", "[èéêë]", "[ìíîï]", "[òóôö]", "[ùúûü]"}, to = {"a" , "e" , "i" , "o" , "u" }} , } m["iu"] = { canonicalName = "ဣနုက်တိတုတ်", otherNames = {"Inuktitut", "Eastern Canadian Inuktitut", "Eastern Canadian Inuit", "Western Canadian Inuktitut", "Western Canadian Inuit", "Western Canadian Inuktun", "Inuinnaq", "Inuinnaqtun", "Inuvialuk", "Inuvialuktun", "Nunavimmiutit", "Nunatsiavummiut", "Aivilimmiut", "Natsilingmiut", "Kivallirmiut", "Siglit", "Siglitun"}, scripts = {"Cans", "Latn"}, family = "esx-inu", translit_module = "iu-translit", override_translit = true, wikipedia_article = "Inuktitut", } m["ja"] = { canonicalName = "ဂျပါန်", otherNames = {"Japanese", "Modern Japanese", "Nipponese", "Nihongo"}, scripts = {"Jpan", "Latn", "Hira", "Brai"}, family = "jpx", ancestors = {"ojp"}, --[[ sort_key = { from = {"[ぁァア]", "[ぃィイ]", "[ぅゔゥウヴ]", "[ぇェエ]", "[ぉォオ]", "[がゕカガヵ]", "[ぎキギ]", "[ぐクグㇰ]", "[げゖケゲヶ]", "[ごコゴ]", "[ざサザ]", "[じシジㇱ]", "[ずスズㇲ]", "[ぜセゼ]", "[ぞソゾ]", "[だタダ]", "[ぢチヂ]", "[っづッツヅ]", "[でテデ]", "[どトドㇳ]", "ナ", "ニ", "[ヌㇴ]", "ネ", "ノ", "[ばぱハバパㇵ]", "[びぴヒビピㇶ]", "[ぶぷフブプㇷ]", "[べぺヘベペㇸ]", "[ぼぽホボポㇹ]", "マ", "ミ", "[ムㇺ]", "メ", "モ", "[ゃャヤ]", "[ゅュユ]", "[ょョヨ]", "[ラㇻ]", "[リㇼ]", "[ルㇽ]", "[レㇾ]", "[ロㇿ]", "[ゎヮワヷ]", "[ヰヸ]", "[ヱヹ]", "[ヲヺ]", "ン", "[゙゚゛゜ゝゞ・ヽヾ]", "𛀀", "1", "2", "3", "4", "5", "6", "7", "8", "9", "0"}, to = {"あ", "い", "う", "え", "お", "か", "き", "く", "け", "こ", "さ", "し", "す", "せ", "そ", "た", "ち", "つ", "て", "と", "な", "に", "ぬ", "ね", "の", "は", "ひ", "ふ", "へ", "ほ", "ま", "み", "む", "め", "も", "や", "ゆ", "よ", "ら", "り", "る", "れ", "ろ", "わ", "ゐ", "ゑ", "を", "ん", "", "え", "い", "に", "み", "よ", "ご", "ろ", "な", "は", "き", "れ"}}, ]] } m["jv"] = { canonicalName = "ဂျာဗာ", otherNames = {"Javanese"}, scripts = {"Latn", "Java"}, family = "poz-sus", translit_module = "jv-translit", ancestors = {"kaw"}, link_tr = true, } m["ka"] = { canonicalName = "ဂျဝ်ဂျဳယျာ", otherNames = {"Georgian", "Kartvelian", "Judeo-Georgian", "Kivruli", "Gruzinic"}, scripts = {"Geor", "Geok", "Hebr"}, -- Hebr is used to write Judeo-Georgian family = "ccs-gzn", ancestors = {"oge"}, translit_module = "Geor-translit", override_translit = true, entry_name = { from = {"̂"}, to = {""}}, } m["kg"] = { canonicalName = "ခါမ်ဂဝ်", otherNames = {"Kongo", "Kikongo", "Koongo", "Laari", "San Salvador Kongo", "Yombe"}, scripts = {"Latn"}, family = "bnt", } m["ki"] = { canonicalName = "ခဳခူယူ", otherNames = {"Kikuyu", "Gikuyu", "Gĩkũyũ"}, scripts = {"Latn"}, family = "bnt", } m["kj"] = { canonicalName = "ကောန်ယာမာ", otherNames = {"Kwanyama", "Kuanyama", "Oshikwanyama"}, scripts = {"Latn"}, family = "bnt", wikipedia_article = "Kwanyama dialect", } m["kk"] = { canonicalName = "ကဇက်", scripts = {"Kazakh", "Cyrl", "Latn", "Arab", "kk-Arab"}, family = "trk-kip", ancestors = {"trk-pro"}, translit_module = "kk-translit", override_translit = true, } m["kl"] = { canonicalName = "ဂရိန်လာန်", otherNames = {"Greenlandic", "Kalaallisut"}, scripts = {"Latn"}, family = "esx-inu", } m["km"] = { "ခမေန်", "Q9205", family = "mkh-kmr", aliases = {"Khmer", "Cambodian"}, scripts = {"Khmr"}, ancestors = {"aav-pro", "mkh-pro", "mkh-kmr-pro", "okz", "xhm"}, translit_module = "km-translit", } m["kn"] = { canonicalName = "ကာန်နဒါ", otherNames = {"Kannada", "ကန္နာဒါ"}, scripts = {"Knda"}, family = "dra", translit_module = "kn-translit", wikipedia_article = "Kannada", ancestors = {"dra-mkn"}, } m["ko"] = { "ကိုဝ်ရဳယျာ", "Q9176", "qfa-kor", aliases = {"Korean", "Modern Korean"}, scripts = {"Kore", "Brai"}, ancestors = {"ko-ear"}, -- 20210122 trial idea: strip parenthesized hanja from entry link -- Hani regex is a reasonable subset of Hani from [[Module:scripts/data]], -- last updated on 20210203. entry_name = { from = { "%([一-鿿㐀-䶿𠀀-𮯯"..u(0x2F800).."-𯨟𰀀-𱍏﨎﨏﨑﨓﨔﨟﨡﨣﨤﨧﨨﨩]+%)", }, to = { "", }}, translit_module = "ko-translit", } m["kr"] = { canonicalName = "ကနူရဳ", otherNames = {"Kanuri", "Kanembu", "Bilma Kanuri", "Central Kanuri", "Manga Kanuri", "Tumari Kanuri"}, scripts = {"Latn", "Arab"}, family = "ssa-sah", sort_key = { from = {"ny", "ǝ", "sh"}, to = {"n~", "e~", "s~"}} , -- the sortkey and entry_name are only for standard Kanuri; when dialectal entries get added, someone will have to work out how the dialects should be represented orthographically entry_name = { from = {"À", "à", "È", "è", "Ǝ̀", "ǝ̀", "Ì", "ì", "Ò", "ò", "Ù", "ù", "Â", "â", "Ê", "ê", "Ǝ̂", "ǝ̂", "Î", "î", "Ô", "ô", "Û", "û", "Ă", "ă", "Ĕ", "ĕ", "Ǝ̆", "ǝ̆", "Ĭ", "ĭ", "Ŏ", "ŏ", "Ŭ", "ŭ", "Á", "á", "É", "é", "Ǝ́", "ǝ́", "Í", "í", "Ó", "ó", "Ú", "ú", GRAVE, ACUTE}, to = {"A", "a", "E", "e", "Ǝ", "ǝ", "I", "i", "O", "o", "U", "u", "A", "a", "E", "e", "Ǝ", "ǝ", "I", "i", "O", "o", "U", "u", "A", "a", "E", "e", "Ǝ", "ǝ", "I", "i", "O", "o", "U", "u", "A", "a", "E", "e", "Ǝ", "ǝ", "I", "i", "O", "o", "U", "u"}}, } m["ks"] = { "ကာဒ်ရှ်မဳယျာ", 33552, "inc-dar", {"ks-Arab", "Deva", "Shrd", "Latn"}, translit_module = "translit-redirect", ancestors = {"sa"}, } m["ku"] = { canonicalName = "ကာဒဳ", otherNames = {"Kurdish"}, scripts = {"Latn", "ku-Arab", "Armn", "Cyrl"}, family = "ira-wes", wikipedia_article = "Kurdish languages", } -- "kv" IS TREATED AS "koi", "kpv", SEE WT:LT m["kw"] = { canonicalName = "ခမ်နေတ်", otherNames = {"Cornish"}, scripts = {"Latn"}, family = "cel-bry", ancestors = {"ine-pro", "cel-pro", "cel-bry-pro", "oco", "cnx"}, } m["ky"] = { canonicalName = "ကာဇေတ်", otherNames = {"Kyrgyz", "Kirghiz", "Kirgiz"}, scripts = {"Cyrl", "Latn", "Arab"}, family = "trk-kip", translit_module = "ky-translit", override_translit = true, ancestors = {"trk-pro", "qwm"}, } m["la"] = { canonicalName = "လပ်တေန်", otherNames = {"Latin"}, scripts = {"Latn"}, family = "itc", ancestors = {"itc-ola"}, entry_name = { from = {"[ĀĂ]", "[āă]", "[ĒĔ]", "[ēĕë]", "[ĪĬÏ]", "[īĭï]", "[ŌŎ]", "[ōŏ]", "[ŪŬÜ]", "[ūŭü]", "Ȳ", "ȳ", MACRON, BREVE, DIAER}, to = {"A", "a", "E", "e", "I", "i", "O", "o", "U", "u", "Y", "y"}}, wikipedia_article = "Latin", standardChars = "A-Za-zÆæŒœĀ-ăĒ-ĕĪ-ĭŌ-ŏŪ-ŭȲȳ" .. MACRON .. BREVE .. PUNCTUATION } m["lb"] = { canonicalName = "လူဇေန်ဘာဂျ်", otherNames = {"Luxembourgish"}, scripts = {"Latn"}, family = "gmw", ancestors = {"gmh"}, wikipedia_article = "Luxembourgish", } m["lg"] = { canonicalName = "လုဂန်ဒါ", otherNames = {"ဂန်ဒါ", "Luganda", "Ganda", "Oluganda"}, scripts = {"Latn"}, family = "bnt", entry_name = { from = {"á", "Á", "é", "É", "í", "Í", "ó", "Ó", "ú", "Ú", "ń", "Ń", "ḿ", "Ḿ", "â", "Â", "ê", "Ê", "î", "Î", "ô", "Ô", "û", "Û" }, to = {"a", "A", "e", "E", "i", "I", "o", "O", "u", "U", "n", "N", "m", "M", "a", "A", "e", "E", "i", "I", "o", "O", "u", "U",}}, sort_key = { from = {"ŋ"}, to = {"n"}} , wikipedia_article = "Luganda", } m["li"] = { canonicalName = "လိမ်ဗူရ်ဂိသ်", otherNames = {"Limburgish", "Limburgan", "Limburgian", "Limburgic"}, scripts = {"Latn"}, family = "gmw", ancestors = {"dum"}, } m["ln"] = { canonicalName = "လေန်ဂါလာ", otherNames = {"Lingala", "Ngala"}, scripts = {"Latn"}, family = "bnt", wikipedia_article = "Lingala", } m["lo"] = { canonicalName = "သေံလဴ", otherNames = {"သေံလဴ", "Lao", "Laotian"}, scripts = {"Laoo"}, family = "tai-swe", translit_module = "lo-translit", sort_key = { from = {"ຼ", "ຽ", "ໜ", "ໝ", "([ເແໂໃໄ])([ກ-ຮ])"}, to = {"ລ", "ຍ", "ຫນ", "ຫມ", "%2%1"}}, ancestors = {"qfa-tak-pro", "qfa-bet-pro", "tai-pro", "tai-swe-pro"}, } m["lt"] = { canonicalName = "လေတ်တူယဵုနဳယျာ", otherNames = {"Lithuanian", "လေတ်တူယဵုနဳယျာ"}, scripts = {"Latn"}, family = "bat", ancestors = {"ine-pro", "ine-bsl-pro", "bat-pro", "olt"}, entry_name = { from = {"[áãà]", "[ÁÃÀ]", "[éẽè]", "[ÉẼÈ]", "[íĩì]", "[ÍĨÌ]", "[ýỹ]", "[ÝỸ]", "ñ", "[óõò]", "[ÓÕÒ]", "[úũù]", "[ÚŨÙ]", ACUTE, GRAVE, TILDE}, to = {"a", "A", "e", "E", "i", "I", "y", "Y", "n", "o", "O", "u", "U"}} , } m["lu"] = { canonicalName = "ဠူဘ-ကာတေန်ဂါ", scripts = {"Latn"}, family = "bnt", } m["lv"] = { canonicalName = "လပ်ဗဳယာ", otherNames = {"Latvian", "Lettish", "Lett"}, scripts = {"Latn"}, family = "bat", ancestors = {"ine-bsl-pro", "bat-pro"}, entry_name = { -- This attempts to convert vowels with tone marks to vowels either with -- or without macrons. Specifically, there should be no macrons if the -- vowel is part of a diphthong (including resonant diphthongs such -- pìrksts -> pirksts not #pīrksts). What we do is first convert the -- vowel + tone mark to a vowel + tilde in a decomposed fashion, -- then remove the tilde in diphthongs, then convert the remaining -- vowel + tilde sequences to macroned vowels, then delete any other -- tilde. We leave already-macroned vowels alone: Both e.g. ar and ār -- occur before consonants. FIXME: This still might not be sufficient. from = {"Ȩ", "ȩ", "[ÂÃÀ]", "[âãà]", "[ÊẼÈ]", "[êẽè]", "[ÎĨÌ]", "[îĩì]", "[ÔÕÒ]", "[ôõò]", "[ÛŨÙ]", "[ûũù]", "[ÑǸ]", "[ñǹ]", "[" .. CIRC .. TILDE ..GRAVE .."]", "([aAeEiIoOuU])" .. TILDE .."?([lrnmuiLRNMUI])" .. TILDE .. "?([^aAeEiIoOuUāĀēĒīĪūŪ])", "([aAeEiIoOuU])" .. TILDE .."?([lrnmuiLRNMUI])" .. TILDE .."?$", "([iI])" .. TILDE .. "?([eE])" .. TILDE .. "?", "A" .. TILDE, "a" .. TILDE, "E" .. TILDE, "e" .. TILDE, "I" .. TILDE, "i" .. TILDE, "U" .. TILDE, "u" .. TILDE, TILDE}, to = {"E", "e", "A" .. TILDE, "a" .. TILDE, "E" .. TILDE, "e" .. TILDE, "I" .. TILDE, "i" .. TILDE, "O", "o", "U" .. TILDE, "u" .. TILDE, "N", "n", TILDE, "%1%2%3", "%1%2", "%1%2", "Ā", "ā", "Ē", "ē", "Ī", "ī", "Ū", "ū", ""}}, } m["mg"] = { canonicalName = "မာလာဂါသဳ", otherNames = {"Malagasy", "Betsimisaraka Malagasy", "Betsimisaraka", "Northern Betsimisaraka Malagasy", "Northern Betsimisaraka", "Southern Betsimisaraka Malagasy", "Southern Betsimisaraka", "Bara Malagasy", "Bara", "Masikoro Malagasy", "Masikoro", "Antankarana", "Antankarana Malagasy", "Plateau Malagasy", "Sakalava", "Tandroy Malagasy", "Tandroy", "Tanosy", "Tanosy Malagasy", "Tesaka", "Tsimihety", "Tsimihety Malagasy", "Bushi", "Shibushi", "Kibushi", "Sakalava"}, scripts = {"Latn"}, family = "poz-bre", } m["mh"] = { canonicalName = "မာချဲလဳ", otherNames = {"Marshallese"}, scripts = {"Latn"}, family = "poz-mic", sort_key = { from = {"ā" , "ļ" , "m̧" , "ņ" , "n̄" , "o̧" , "ō" , "ū" }, to = {"a~", "l~", "m~", "n~", "n~~", "o~", "o~~", "u~"}} , } m["mi"] = { canonicalName = "မဝ်ရဳ", otherNames = {"Maori", "Māori"}, scripts = {"Latn"}, family = "poz-pol", wikipedia_article = "Māori language", sort_key = { from = {"ā" , "ļ" , "m̧" , "ņ" , "n̄" , "o̧" , "ō" , "ū" }, to = {"a~", "l~", "m~", "n~", "n~~", "o~", "o~~", "u~"}} , } m["mk"] = { canonicalName = "မက်သဳဒဝ်နဳယျာ", otherNames = {"Macedonian"}, scripts = {"Cyrl"}, family = "zls", translit_module = "mk-translit", ancestors = {"ine-pro", "ine-bsl-pro", "sla-pro"}, entry_name = { from = {ACUTE}, to = {}}, } m["ml"] = { canonicalName = "မလေဝ်ယျလာမ်", otherNames = {"Malayalam"}, scripts = {"Mlym"}, family = "dra", translit_module = "ml-translit", override_translit = true, wikipedia_article = "Malayalam", } m["mn"] = { canonicalName = "မန်ဂဝ်လဳယျာ", otherNames = {"မန်ဂဝ်လဳယျာ", "ခန်ခါ မန်ဂဝ်လဳယျာ"}, scripts = {"Cyrl", "Mong", "Soyo", "Zanb"}, -- entries in Soyo or Zanb might require prior discussion family = "xgn", ancestors = {"cmg"}, translit_module = "mn-translit", override_translit = true, } -- "mo" IS TREATED AS "ro", SEE WT:LT m["mr"] = { canonicalName = "မာရဒဳ", otherNames = {"Marathi"}, scripts = {"Deva", "Modi"}, family = "inc", ancestors = {"omr"}, translit_module = "hi-translit", } m["ms"] = { canonicalName = "မလေဝ်", otherNames = {"Malay", "Malaysian", "Standard Malay", "Orang Seletar", "Orang Kanaq", "Jakun", "Temuan"}, scripts = {"Latn", "ms-Arab"}, family = "poz-mly", ancestors = {"map-pro", "poz-pro", "poz-sus-pro", "poz-msa-pro", "poz-mcm-pro", "poz-mly-pro", "ms-old", "ms-cla"}, } m["mt"] = { canonicalName = "မာလ်တဳ", otherNames = {"Maltese"}, scripts = {"Latn"}, family = "sem-arb", ancestors = {"sqr"}, } m["my"] = { canonicalName = "ဗၟာ", otherNames = {"Burmese", "Myanmar", "ဗၟာ"}, scripts = {"Mymr"}, family = "tbq-brm", ancestors = {"obr", "sit-pro", "tbq-pro"}, wikipedia_article = "ဘာသာဗၟာ", translit_module = "my-translit", override_translit = true, } m["na"] = { canonicalName = "နာဥူလောန်", otherNames = {"Nauruan","Nauru"}, scripts = {"Latn"}, family = "poz-mic", } m["nb"] = { canonicalName = "နဝ်ဝေ ဗော်ခ်မဝ်", otherNames = {"Norwegian Bokmål", "Bokmål"}, scripts = {"Latn"}, family = "gmq", ancestors = {"gmq-mno", "gem-pro"}, wikimedia_codes = {"no"}, wikipedia_article = "Bokmål", } m["nd"] = { canonicalName = "Northern Ndebele", otherNames = {"North Ndebele"}, scripts = {"Latn"}, family = "bnt-ngu", entry_name = { from = {"[āàáâǎ]", "[ēèéêě]", "[īìíîǐ]", "[ōòóôǒ]", "[ūùúûǔ]", "ḿ", "[ǹńň]", MACRON, ACUTE, GRAVE, CIRC, CARON}, to = {"a" , "e" , "i" , "o" , "u" , "m", "n" }}, } m["ne"] = { "နဳပဝ်", 33823, "inc-pah", scripts = {"Deva", "Newa"}, ancestors = {"ine-pro", "iir-pro", "inc-pro", "sa", "inc-ash", "pra-kha"}, translit_module = "ne-translit", } m["ng"] = { canonicalName = "အွန်ဒွန်ဂါ", otherNames = {"Ndonga"}, scripts = {"Latn"}, family = "bnt", wikipedia_article = "Ndonga dialect", } m["nl"] = { canonicalName = "ဒါတ်", otherNames = {"Dutch", "Netherlandic", "Flemish"}, scripts = {"Latn"}, family = "gmw", ancestors = {"dum"}, sort_key = { from = {"[äáâå]", "[ëéê]", "[ïíî]", "[öóô]", "[üúû]", "ç", "ñ", "^-"}, to = {"a" , "e" , "i" , "o" , "u" , "c", "n"}} , standardChars = "A-Za-z0-9" .. PUNCTUATION .. u(0x2800) .. "-" .. u(0x28FF), } m["nn"] = { canonicalName = "နဝ်ဝေ နဳနိုတ်", otherNames = {"Norwegian Nynorsk", "New Norwegian", "Nynorsk"}, scripts = {"Latn"}, family = "gmq", ancestors = {"gmq-mno"}, wikipedia_article = "Nynorsk", } m["no"] = { canonicalName = "နဝ်ဝေ", otherNames = {"Norwegian"}, scripts = {"Latn"}, family = "gmq", ancestors = {"gmq-mno"}, } m["nr"] = { canonicalName = "အာန်ဒေဗေလေဝ် လ္ပာ်ဒိုဟ်သမၠုင်ကျာ", otherNames = {"South Ndebele"}, scripts = {"Latn"}, family = "bnt-ngu", entry_name = { from = {"[āàáâǎ]", "[ēèéêě]", "[īìíîǐ]", "[ōòóôǒ]", "[ūùúûǔ]", "ḿ", "[ǹńň]", MACRON, ACUTE, GRAVE, CIRC, CARON}, to = {"a" , "e" , "i" , "o" , "u" , "m", "n" }}, } m["nv"] = { "နာဝါဟဝ်", 13310, "apa", Latn, sort_key = { from = {"[áą]", "[éę]", "[íį]", "[óǫ]", "ń", "^n([djlt])", "ł" , "[ʼ’']", ACUTE}, to = {"a" , "e" , "i" , "o" , "n", "ni%1" , "l~"}}, -- the tilde is used to guarantee that ł will always be sorted after all other words with l } m["ny"] = { canonicalName = "ချဳချေန်ဝါ", otherNames = {"နရန်ဂျာ", "Chichewa", "Chicheŵa", "Chinyanja", "Nyanja", "Chewa", "Cicewa", "Cewa", "Cinyanja"}, scripts = {"Latn"}, family = "bnt", entry_name = { from = {"ŵ", "Ŵ", "á", "Á", "é", "É", "í", "Í", "ó", "Ó", "ú", "Ú", "ń", "Ń", "ḿ", "Ḿ" }, to = {"w", "W", "a", "A", "e", "E", "i", "I", "o", "O", "u", "U", "n", "N", "m", "M"}}, sort_key = { from = {"ng'"}, to = {"ng"}} , wikipedia_article = "Chewa language", } m["oc"] = { "အောက်စဳတာန်", "Q14185", "roa-ocr", aliases = {"အောက်စဳတာန်"}, -- don't list varieties here that are in [[Module:etymology languages/data]] scripts = {"Latn", "Hebr"}, ancestors = {"pro"}, sort_key = { from = {"[àá]", "[èé]", "[íï]", "[òó]", "[úü]", "ç", "([lns])·h"}, to = {"a" , "e" , "i" , "o" , "u" , "c", "%1h" }} , } m["oj"] = { canonicalName = "အဝ်ဂျဳဗဝေ", otherNames = {"Ojibwe", "Chippewa", "Ojibway", "Ojibwemowin", "Southwestern Ojibwa"}, scripts = {"Cans", "Latn"}, family = "alg", } m["om"] = { canonicalName = "အဝ်ရဝ်မဝ်", otherNames = {"Oromo", "Orma", "Borana-Arsi-Guji Oromo", "West Central Oromo"}, scripts = {"Latn", "Ethi"}, family = "cus-eas", } m["or"] = { canonicalName = "အဝ်ရေဝ်ယာ", otherNames = {"Oriya", "Odia", "Oorya"}, scripts = {"Orya"}, family = "inc", ancestors = {"inc-mgd"}, translit_module = "or-translit", wikipedia_article = "Odia language", } m["os"] = { canonicalName = "အဝ်ဇြဳယာန်", otherNames = {"Ossetian", "Ossete", "Ossetic", "Digor", "Iron"}, scripts = {"Cyrl", "Geor", "Latn"}, family = "ira", ancestors = {"oos"}, translit_module = "os-translit", override_translit = true, entry_name = { from = {GRAVE, ACUTE}, to = {}} , } m["pa"] = { canonicalName = "ပါန်ချာပဳ", otherNames = {"Punjabi", "Panjabi"}, scripts = {"Guru", "pa-Arab"}, family = "inc-opa", ancestors = {"inc-opa"}, translit_module = "translit-redirect", entry_name = { from = {u(0x064B), u(0x064C), u(0x064D), u(0x064E), u(0x064F), u(0x0650), u(0x0651), u(0x0652), u(0x0658), u(0x08C7), u(0x0768)}, to = {"", "", "", "", "", "", "", "", "", "ل", "ن"}} , } m["pi"] = { "ပါဠိ", "Q36727", "inc-mid", scripts = {"Latn", "Brah", "Deva", "Beng", "Sinh", "Mymr", "Thai", "Lana", "Laoo", "Khmr"}, ancestors = {"sa"}, translit_module = "pi-translit", sort_key = { from = {"ā", "ī", "ū", "ḍ", "ḷ", "[ṁṃ]", "ṅ", "ñ", "ṇ", "ṭ", "([เโ])([ก-ฮ])", "([ເໂ])([ກ-ຮ])", "ᩔ", "ᩕ", "ᩖ", "ᩘ", "([ᨭ-ᨱ])ᩛ", "([ᨷ-ᨾ])ᩛ", "ᩤ", u(0xFE00), u(0x200D)}, to = {"a~", "i~", "u~", "d~", "l~", "m~", "n~", "n~~", "n~~~", "t~", "%2%1", "%2%1", "ᩈ᩠ᩈ", "᩠ᩁ", "᩠ᩃ", "ᨦ᩠", "%1᩠ᨮ", "%1᩠ᨻ", "ᩣ"}} , entry_name = { from = {u(0xFE00)}, to = {}}, } m["pl"] = { canonicalName = "ပဝ်လာန်", otherNames = {"Polish"}, scripts = {"Latn"}, family = "zlw", ancestors = {"zlw-opl", "sla-pro"}, sort_key = { from = {"[Ąą]", "[Ćć]", "[Ęę]", "[Łł]", "[Ńń]", "[Óó]", "[Śś]", "[Żż]", "[Źź]"}, to = { "a" .. u(0x10FFFF), "c" .. u(0x10FFFF), "e" .. u(0x10FFFF), "l" .. u(0x10FFFF), "n" .. u(0x10FFFF), "o" .. u(0x10FFFF), "s" .. u(0x10FFFF), "z" .. u(0x10FFFF), "z" .. u(0x10FFFE)}} , } m["ps"] = { "ပါသတုန်", "Q58680", "ira-pat", aliases = {"Pashtun", "Pushto", "Pashtu", "Afghani"}, varieties = {"Central Pashto", "Northern Pashto", "Southern Pashto", {"Pukhto", "Pakhto", "Pakkhto"}}, scripts = {"ps-Arab"}, ancestors = {"ira-pat-pro"}, } m["pt"] = { canonicalName = "ပဝ်တူဂြဳ", otherNames = {"Portuguese", "Modern Portuguese"}, scripts = {"Latn", "Brai"}, family = "roa", ancestors = {"ine-pro", "itc-pro", "itc-ola", "la", "roa-opt"}, sort_key = { from = {"[àãáâä]", "[èẽéêë]", "[ìĩíï]", "[òóôõö]", "[üúùũ]", "ç", "ñ"}, to = {"a" , "e" , "i" , "o" , "u" , "c", "n"}} , } m["qu"] = { canonicalName = "ခေန်ချူဝါ", scripts = {"Latn"}, family = "qwe", wikipedia_article = "ဘာသာခေန်ချူဝါ", } m["rm"] = { canonicalName = "ရဝ်မာန်", otherNames = {"Romansch","Romansh", "Rumantsch", "Romanche"}, scripts = {"Latn"}, family = "roa", wikipedia_article = "Romansh language", } m["ro"] = { canonicalName = "ရဝ်မေနဳယျာ", otherNames = {"Romanian", "Daco-Romanian", "Roumanian", "Rumanian"}, scripts = {"Latn", "Cyrl"}, family = "roa", sort_key = { from = {"ă" , "â" , "î" , "ș" , "ț" }, to = {"a~", "a~~", "i~", "s~", "t~"}}, } m["ru"] = { canonicalName = "ရုဿျှာ", otherNames = {"Russian"}, scripts = {"Cyrl", "Brai"}, family = "zle", translit_module = "ru-translit", sort_key = { from = {"ё"}, to = {"е" .. mw.ustring.char(0x10FFFF)}}, entry_name = { from = {"Ѐ", "ѐ", "Ѝ", "ѝ", GRAVE, ACUTE}, to = {"Е", "е", "И", "и"}}, standardChars = "ЁІА-яёі0-9—" .. PUNCTUATION, } m["rw"] = { canonicalName = "ရဝမ်ဒါ ရမ်ဒဳ", otherNames = {"Rwanda-Rundi", "Rwanda", "Kinyarwanda", "Rundi", "Kirundi", "Ha", "Giha", "Hangaza", "Vinza", "Shubi", "Subi"}, scripts = {"Latn"}, family = "bnt", wikipedia_article = "Rwanda-Rundi", } m["sa"] = { canonicalName = "သံသကြိုတ်", otherNames = {"Sanskrit"}, scripts = {"Deva", "Bali", "as-Beng", "Beng", "Bhks", "Brah", "Gran", "Gujr", "Guru", "Java", "Khar", "Khmr", "Knda", "Lana", "Laoo", "Mlym", "Modi", "Mymr", "Nand", "Newa", "Orya", "Saur", "Shrd", "Sidd", "Sinh", "Taml", "Telu", "Thai", "Tibt", "Tirh"}, family = "inc-old", sort_key = { from = {"ā", "ī", "ū", "ḍ", "ḷ", "ḹ", "[ṁṃ]", "ṅ", "ñ", "ṇ", "ṛ", "ṝ", "ś", "ṣ", "ṭ", "([เโไ])([ก-ฮ])", "([ເໂໄ])([ກ-ຮ])", "ᩔ", "ᩕ", "ᩖ", "ᩘ", "([ᨭ-ᨱ])ᩛ", "([ᨷ-ᨾ])ᩛ", "ᩤ", u(0xFE00), u(0x200D)}, to = {"a~", "i~", "u~", "d~", "l~", "l~~", "m~", "n~", "n~~", "n~~~", "r~", "r~~", "s~", "s~~", "t~", "%2%1", "%2%1", "ᩈ᩠ᩈ", "᩠ᩁ", "᩠ᩃ", "ᨦ᩠", "%1᩠ᨮ", "%1᩠ᨻ", "ᩣ"}}, entry_name = { from = {"ึ", u(0xF700), u(0xF70F), u(0xFE00)}, to = {"ิํ", "ฐ", "ญ"}}, translit_module = "translit-redirect", ancestors = {"iir-pro", "inc-pro"}, } m["sc"] = { canonicalName = "သာဒဳနဳယာန်", otherNames = {"Sardinian", "Campidanese", "Campidanese Sardinian", "Logudorese", "Logudorese Sardinian", "Nuorese", "Nuorese Sardinian"}, scripts = {"Latn"}, family = "roa", } m["sd"] = { "သိန္ဓိ", 33997, "inc-snd", scripts = {"sd-Arab", "Deva", "Sind", "Khoj"}, entry_name = { from = {u(0x0671), u(0x064B), u(0x064C), u(0x064D), u(0x064E), u(0x064F), u(0x0650), u(0x0651), u(0x0652), u(0x0670), u(0x0640)}, to = {u(0x0627)}}, ancestors = {"inc-vra"}, translit_module = "translit-redirect", } m["se"] = { canonicalName = "သာမိ သၟဝ်ကျာ", otherNames = {"Northern Sami", "North Sami", "Northern Saami", "North Saami"}, scripts = {"Latn"}, family = "smi", entry_name = { from = {"([đflmnŋrsšŧv])'%1"}, to = {"%1%1"} }, wikipedia_article = "Northern Sami", } m["sg"] = { canonicalName = "သင်ဂဝ်", otherNames = {"Sango"}, scripts = {"Latn"}, family = "crp", } m["sh"] = { canonicalName = "သာဗ်ခြဝ်ဨရှဳယာန်", otherNames = {"Serbo-Croatian", "BCS", "Croato-Serbian", "Serbocroatian", "Bosnian", "Croatian", "Montenegrin", "Serbian"}, scripts = {"Latn", "Cyrl"}, family = "zls", ancestors = {"ine-pro", "ine-bsl-pro", "sla-pro"}, entry_name = { from = {"[ȀÀȂÁĀÃ]", "[ȁàȃáāã]", "[ȄÈȆÉĒẼ]", "[ȅèȇéēẽ]", "[ȈÌȊÍĪĨ]", "[ȉìȋíīĩ]", "[ȌÒȎÓŌÕ]", "[ȍòȏóōõ]", "[ȐȒŔ]", "[ȑȓŕ]", "[ȔÙȖÚŪŨ]", "[ȕùȗúūũ]", "Ѐ", "ѐ", "[ӢЍ]", "[ӣѝ]", "[Ӯ]", "[ӯ]", GRAVE, ACUTE, DGRAVE, INVBREVE, MACRON, TILDE}, to = {"A" , "a" , "E" , "e" , "I" , "i" , "O" , "o" , "R" , "r" , "U" , "u" , "Е", "е", "И" , "и", "У", "у" }}, wikimedia_codes = {"sh", "bs", "hr", "sr"}, wikipedia_article = "Serbo-Croatian", } m["si"] = { canonicalName = "သိၚ်္ဃဵုရ်", otherNames = {"Sinhalese", "Singhalese", "Sinhala"}, scripts = {"Sinh"}, family = "inc", ancestors = {"elu-prk"}, translit_module = "si-translit", override_translit = true, } m["sk"] = { canonicalName = "သလဝ်ဝေန်နဳယျာ", otherNames = {"Slovak"}, scripts = {"Latn"}, family = "zlw", ancestors = {"ine-pro", "ine-bsl-pro", "sla-pro", "zlw-osk"}, sort_key = { from = {"[áä]", "é", "í", "[óô]", "ú", "ý", "ŕ", "ĺ", "[" .. DIAER .. ACUTE .. CIRC .. "]"}, to = {"a" , "e", "i", "o" , "u", "y", "r", "l", ""}} , } m["sl"] = { canonicalName = "သၠဝ်ဝေနဳ", otherNames = {"Slovene", "Slovenian"}, scripts = {"Latn"}, family = "zls", entry_name = { from = {"[ÁÀÂȂȀ]", "[áàâȃȁ]", "[ÉÈÊȆȄỆẸ]", "[éèêȇȅệẹə]", "[ÍÌÎȊȈ]", "[íìîȋȉ]", "[ÓÒÔȎȌỘỌ]", "[óòôȏȍộọ]", "[ŔȒȐ]", "[ŕȓȑ]", "[ÚÙÛȖȔ]", "[úùûȗȕ]", "ł", GRAVE, ACUTE, DGRAVE, INVBREVE, CIRC, DOTBELOW}, to = {"A" , "a" , "E" , "e" , "I" , "i" , "O" , "o" , "R" , "r" , "U" , "u" , "l"}} , } m["sm"] = { canonicalName = "သမဝ်အာန်", otherNames = {"Samoan"}, scripts = {"Latn"}, family = "poz-pol", } m["sn"] = { canonicalName = "သျှိနာ", otherNames = {"Shona"}, scripts = {"Latn"}, family = "bnt", } m["so"] = { canonicalName = "ဆဝ်မာလဳ", otherNames = {"Somali"}, scripts = {"Latn", "Arab", "Osma"}, family = "cus", entry_name = { from = {"[ÁÀÂ]", "[áàâ]", "[ÉÈÊ]", "[éèê]", "[ÍÌÎ]", "[íìî]", "[ÓÒÔ]", "[óòô]", "[ÚÙÛ]", "[úùû]", "[ÝỲ]", "[ýỳ]"}, to = {"A" , "a" , "E" , "e" , "I" , "i" , "O" , "o" , "U" , "u", "Y", "y"}} , } m["sq"] = { canonicalName = "အလ်ဗနဳယာန်", otherNames = {"Albanian"}, scripts = {"Latn", "Elba"}, family = "sqj", ancestors = {"ine-pro", "sqj-pro"}, sort_key = { from = { '[âãä]', '[ÂÃÄ]', '[êẽë]', '[ÊẼË]', 'ĩ', 'Ĩ', 'õ', 'Õ', 'ũ', 'Ũ', 'ỹ', 'Ỹ', 'ç', 'Ç' }, to = { 'a', 'A', 'e', 'E', 'i', 'I', 'o', 'O', 'u', 'U', 'y', 'Y', 'c', 'C' } } , } m["ss"] = { canonicalName = "သဝါဇြဳ", otherNames = {"Swazi", "Swati"}, scripts = {"Latn"}, family = "bnt-ngu", entry_name = { from = {"[āàáâǎ]", "[ēèéêě]", "[īìíîǐ]", "[ōòóôǒ]", "[ūùúûǔ]", "ḿ", "[ǹńň]", MACRON, ACUTE, GRAVE, CIRC, CARON}, to = {"a" , "e" , "i" , "o" , "u" , "m", "n" }}, ancestors = {"bnt-pro"}, } m["st"] = { canonicalName = "သူထူ", otherNames = {"Sotho", "Sesotho", "Southern Sesotho", "Southern Sotho"}, scripts = {"Latn"}, family = "bnt", } m["su"] = { canonicalName = "သာန်ဓနဳ", otherNames = {"Sundanese"}, scripts = {"Sund", "Latn"}, family = "poz-msa", ancestors = {"map-pro", "poz-pro", "poz-sus-pro", "poz-msa-pro", "osn"}, translit_module = "su-translit", } m["sv"] = { canonicalName = "သွဳဒေန်", otherNames = {"Swedish"}, scripts = {"Latn"}, family = "gmq", ancestors = {"gmq-osw", "gem-pro", "ine-pro"}, sort_key = { from = {"ö", "å", "ä"}, to = {"o", "a", "a"}} , } m["sw"] = { canonicalName = "သဝါတ်ဟဳလဳ", otherNames = {"Swahili", "Settler Swahili", "KiSetla", "KiSettla", "Setla", "Settla", "Kitchen Swahili", "Kihindi", "Indian Swahili", "KiShamba", "Kishamba", "Field Swahili", "Kibabu", "Asian Swahili", "Kimanga", "Arab Swahili", "Kitvita", "Army Swahili"}, scripts = {"Latn", "Arab"}, family = "bnt", sort_key = { from = {"ng'", "^-"}, to = {"ngz"}} , } m["ta"] = { canonicalName = "တမဳလ်", otherNames = {"Tamil"}, scripts = {"Taml"}, family = "dra", ancestors = {"oty"}, translit_module = "ta-translit", override_translit = true, } m["te"] = { canonicalName = "တေလုဂု", otherNames = {"Telugu"}, scripts = {"Telu"}, family = "dra", ancestors = {"dra-pro", "dra-sou-pro", "dra-sdt-pro", "dra-ote"}, translit_module = "te-translit", override_translit = true, } m["tg"] = { canonicalName = "တာဇိက်", otherNames = {"Tajik", "Tadjik", "Tadzhik", "Tajiki", "Tajik Persian"}, scripts = {"Cyrl", "fa-Arab", "Latn"}, family = "ira-wes", ancestors = {"fa"}, translit_module = "tg-translit", override_translit = true, sort_key = { from = {"Ё", "ё"}, to = {"Е" , "е"}} , entry_name = { from = {ACUTE}, to = {}} , } m["th"] = { "သေံ", 9217, family = "tai-swe", scripts = {"Thai", "Brai"}, translit_module = "th-translit", sort_key = { from = {"[%pๆ]", "[็-๎]", "([เแโใไ])([ก-ฮ])"}, to = {"", "", "%2%1"}}, ancestors = {"qfa-tak-pro", "qfa-bet-pro", "tai-pro", "tai-swe-pro"}, } m["ti"] = { canonicalName = "တဳဂျရေဝ်ယျာ", otherNames = {"Tigrinya"}, scripts = {"Ethi"}, family = "sem-eth", translit_module = "Ethi-translit", } m["tk"] = { canonicalName = "တာခ်မေန်", otherNames = {"Turkmen"}, scripts = {"Latn", "Cyrl"}, family = "trk-ogz", entry_name = { from = {"ā", "ē", "ī", "ō", "ū", "ȳ", "ȫ", "ǖ", MACRON}, to = {"a", "e", "i", "o", "u", "y", "ö", "ü", ""}}, } m["tl"] = { canonicalName = "တာဂါလံက်", otherNames = {"Tagalog"}, scripts = {"Latn", "Tglg"}, family = "phi", entry_name = { from = {"[áàâ]", "[éèê]", "[íìî]", "[óòô]", "[úùû]", ACUTE, GRAVE, CIRC}, to = {"a" , "e" , "i" , "o" , "u" }}, translit_module = "tl-translit", override_translit = true } m["tn"] = { canonicalName = "သွာနာ", otherNames = {"Tswana", "Setswana"}, scripts = {"Latn"}, family = "bnt", } m["to"] = { canonicalName = "ထံင်ဂံင်", otherNames = {"Tongan"}, scripts = {"Latn"}, family = "poz-pol", } m["tr"] = { canonicalName = "တူရကဳ", otherNames = {"Turkish"}, scripts = {"Latn"}, family = "trk-ogz", ancestors = {"ota"}, } m["ts"] = { canonicalName = "သွေန်ဂါ", otherNames = {"Tsonga"}, scripts = {"Latn"}, family = "bnt", ancestors = {"nic-pro", "alv-pro", "nic-vco-pro", "nic-bco-pro", "nic-bod-pro", "bnt-pro"}, } m["tt"] = { canonicalName = "တာတာ", otherNames = {"Tatar"}, scripts = {"Cyrl", "Latn", "Arab", "tt-Arab"}, family = "trk-kip", translit_module = "tt-translit", override_translit = true, } -- "tw" IS TREATED AS "ak", SEE WT:LT m["ty"] = { canonicalName = "တဟဳတဳဃှေန်", otherNames = {"Tahitian"}, scripts = {"Latn"}, family = "poz-pol", } m["ug"] = { canonicalName = "ဥူဃူရ်", otherNames = {"Uigur", "Uighur", "Uygur"}, scripts = {"ug-Arab", "Latn", "Cyrl"}, family = "trk", ancestors = {"chg"}, translit_module = "ug-translit", override_translit = true, } m["uk"] = { canonicalName = "ယူကရိန်", otherNames = {"Ukrainian"}, scripts = {"Cyrl"}, family = "zle", ancestors = {"ine-pro", "ine-bsl-pro", "sla-pro", "orv", "zle-ouk"}, translit_module = "uk-translit", entry_name = { from = {"Ѐ", "ѐ", "Ѝ", "ѝ", GRAVE, ACUTE}, to = {"Е", "е", "И", "и"}}, standardChars = "ЄІЇА-ЩЫЬЮ-щыьюяєії" .. PUNCTUATION } m["ur"] = { "အူရဒူ", "Q1617", "inc-hnd", scripts = {"ur-Arab"}, ancestors = {"inc-ohi"}, entry_name = { from = {u(0x064B), u(0x064C), u(0x064D), u(0x064E), u(0x064F), u(0x0650), u(0x0651), u(0x0652)}, to = {}} , } m["uz"] = { canonicalName = "ဥုသဗဝ်", otherNames = {"Uzbek", "Northern Uzbek", "Southern Uzbek"}, scripts = {"Latn", "Cyrl", "fa-Arab"}, family = "trk", ancestors = {"chg"}, translit_module = "uz-translit" } m["ve"] = { canonicalName = "ဗါန်ဒါ", otherNames = {"Venda"}, scripts = {"Latn"}, family = "bnt", } m["vi"] = { canonicalName = "ဗဳယေတ်နာမ်", otherNames = {"Vietnamese", "Annamese", "Annamite"}, scripts = {"Latn", "Hani"}, family = "mkh-vie", ancestors = {"mkh-mvi"}, sort_key = "vi-sortkey", } m["vo"] = { canonicalName = "ဝဝ်လပုက်", otherNames = {"Volapük"}, scripts = {"Latn"}, family = "art", wikipedia_article = "Volapük", } m["wa"] = { canonicalName = "ဝါဠူ", otherNames = {"Walloon", "Liégeois", "Namurois", "Wallo-Picard", "Wallo-Lorrain"}, scripts = {"Latn"}, family = "roa-oil", ancestors = {"fro"}, sort_key = { from = {"[áàâäå]", "[éèêë]", "[íìîï]", "[óòôö]", "[úùûü]", "[ýỳŷÿ]", "ç", "'"}, to = {"a" , "e" , "i" , "o" , "u" , "y" , "c"}} , } m["wo"] = { canonicalName = "ဝဝ်လံက်", otherNames = {"Wolof", "Gambian Wolof"}, -- the subsumed dialect 'wof' scripts = {"Latn", "Arab"}, family = "alv-sng", } m["xh"] = { canonicalName = "ခါဝ်သာ", otherNames = {"Xhosa"}, scripts = {"Latn"}, family = "bnt-ngu", entry_name = { from = {"[āàáâǎ]", "[ēèéêě]", "[īìíîǐ]", "[ōòóôǒ]", "[ūùúûǔ]", "ḿ", "[ǹńň]", MACRON, ACUTE, GRAVE, CIRC, CARON}, to = {"a" , "e" , "i" , "o" , "u" , "m", "n" }}, ancestors = {"bnt-pro"}, } m["yi"] = { canonicalName = "ယိဒ်ဒိသ်", otherNames = {"Yiddish"}, scripts = {"Hebr"}, family = "gmw", ancestors = {"gmh"}, translit_module = "yi-translit", wikipedia_article = "Yiddish", } m["yo"] = { canonicalName = "ရိုရုဗာ", otherNames = {"Yoruba"}, scripts = {"Latn"}, family = "alv-von", ancestors = {"alv-yor-pro", "alv-edk-pro", "alv-yrd-pro"}, } m["za"] = { canonicalName = "ဇြုန်", otherNames = {"Standard Zhuang"}, scripts = {"Latn", "Hani"}, family = "tai", wikipedia_article = "Zhuang languages", } m["zh"] = { canonicalName = "ကြုက်", otherNames = {"Chinese"}, scripts = {"Hani", "Brai"}, family = "sit", ancestors = {"ltc", "sit-pro"}, sort_key = "zh-sortkey", } m["zu"] = { canonicalName = "သြူဠူ", otherNames = {"Zulu", "isiZulu"}, scripts = {"Latn"}, family = "bnt-ngu", entry_name = { from = {"[āàáâǎ]", "[ēèéêě]", "[īìíîǐ]", "[ōòóôǒ]", "[ūùúûǔ]", "ḿ", "[ǹńň]", MACRON, ACUTE, GRAVE, CIRC, CARON}, to = {"a" , "e" , "i" , "o" , "u" , "m", "n" }}, ancestors = {"bnt-pro"}, } return m eevgscnrbg90ex2detbd1jnyf2xirgj 103866 103865 2024-11-01T08:41:33Z 咽頭べさ 33 103866 Scribunto text/plain local u = mw.ustring.char -- UTF-8 encoded strings for some commonly-used diacritics local GRAVE = u(0x0300) local ACUTE = u(0x0301) local CIRC = u(0x0302) local TILDE = u(0x0303) local MACRON = u(0x0304) local BREVE = u(0x0306) local DOTABOVE = u(0x0307) local DIAER = u(0x0308) local CARON = u(0x030C) local DGRAVE = u(0x030F) local INVBREVE = u(0x0311) local DOTBELOW = u(0x0323) local RINGBELOW = u(0x0325) local CEDILLA = u(0x0327) local OGONEK = u(0x0328) local DOUBLEINVBREVE = u(0x0361) -- Punctuation to be used for standardChars field local PUNCTUATION = ' !#%&*+,-./:;<=>?@^_`|~\'()' local Cyrl = {"Cyrl"} local Latn = {"Latn"} local LatnArab = {"Latn", "Arab"} local m = {} m["aa"] = { canonicalName = "အဖှာင်", otherNames = {"Qafar"}, scripts = {"Latn"}, family = "cus", } m["ab"] = { canonicalName = "အာပ်ဟန်", otherNames = {"Abkhaz", "Abkhazian", "Abxazo"}, scripts = {"Cyrl", "Geor", "Latn"}, family = "cau-abz", translit_module = "ab-translit", override_translit = true, entry_name = { from = {GRAVE, ACUTE}, to = {}} , } m["ae"] = { "အဗါတ်သတေန်", 29572, "ira-cen", scripts = {"Avst", "Gujr"}, translit_module = "Avst-translit", wikipedia_article = "Avestan", } m["af"] = { canonicalName = "အေက်ဖရိကာန်", scripts = {"Latn", "Arab"}, family = "gmw", ancestors = {"nl"}, sort_key = { from = {"[äáâà]", "[ëéêè]", "[ïíîì]", "[öóôò]", "[üúûù]", "[ÿýŷỳ]", "^-", "'"}, to = {"a" , "e" , "i" , "o" , "u" , "y" }} , wikipedia_article = "Afrikaans", } m["ak"] = { canonicalName = "အကာန်", otherNames = {"Akan", "Twi-Fante", "Twi", "Fante", "Fanti", "Asante", "Akuapem"}, scripts = {"Latn"}, family = "alv-kwa", } m["am"] = { canonicalName = "အာန်ဟာရိစ်", otherNames = {"Amharic"}, scripts = {"Ethi"}, family = "sem-eth", translit_module = "Ethi-translit", wikipedia_article = "Amharic", } m["an"] = { canonicalName = "အာဒါဂေန်", otherNames = {"Aragonese"}, scripts = {"Latn"}, family = "roa", ancestors = {"ine-pro", "itc-pro", "itc-ola", "la", "roa-oan"}, } m["ar"] = { canonicalName = "အာရဗဳ", otherNames = {"Modern Standard Arabic", "Standard Arabic", "Literary Arabic", "Classical Arabic", "Arabic", "အာရက်လ်"}, scripts = {"Arab", "Brai"}, family = "sem-arb", -- alif waṣl to alif, remove diacritics entry_name = { from = {u(0x0671), u(0x064B), u(0x064C), u(0x064D), u(0x064E), u(0x064F), u(0x0650), u(0x0651), u(0x0652), u(0x0670), u(0x0640)}, to = {u(0x0627)}}, translit_module = "ar-translit", wikipedia_article = "Arabic", ancestors = {"sem-pro"}, } m["as"] = { canonicalName = "အိသ်ဇြာံမဳ", otherNames ={"Assamese"}, scripts = {"Beng"}, family = "inc", ancestors = {"inc-mgd"}, translit_module = "as-translit", } m["av"] = { "အာဗာ", "Q29561", "cau-nec", aliases = {"Avaric"}, scripts = Cyrl, ancestors = {"oav"}, translit_module = "translit-redirect", override_translit = true, entry_name = { from = {GRAVE, ACUTE}, to = {}} , } m["ay"] = { canonicalName = "အိုင်မာရ", otherNames = {"Aymara", "Southern Aymara", "Central Aymara"}, scripts = {"Latn"}, family = "sai-aym", } m["az"] = { "အာက်သေတ်ဗါဲဇြေနဳ", 9292, "trk-ogz", {"Latn", "Cyrl", "fa-Arab"}, ancestors = {"trk-oat"}, dotted_dotless_i = true, } m["ba"] = { canonicalName = "ဗေတ်ခဳ", otherNames = {"Bashkir"}, scripts = {"Cyrl"}, family = "trk-kip", translit_module = "ba-translit", override_translit = true, } m["be"] = { canonicalName = "ဗါလာရုဇ်", otherNames = {"Belarusian", "Belorussian", "Belarusan", "Bielorussian", "Byelorussian", "Belarussian", "White Russian"}, scripts = {"Cyrl"}, family = "zle", ancestors = {"orv"}, translit_module = "be-translit", sort_key = { from = {"Ё", "ё"}, to = {"Е" , "е"}}, entry_name = { from = {"Ѐ", "ѐ", GRAVE, ACUTE}, to = {"Е", "е"}}, } m["bg"] = { canonicalName = "ဗူလ်ဂရဳယာန်", otherNames = {"Bulgarian"}, scripts = {"Cyrl"}, family = "zls", translit_module = "bg-translit", entry_name = { from = {"Ѐ", "ѐ", "Ѝ", "ѝ", GRAVE, ACUTE}, to = {"Е", "е", "И", "и"}}, } m["bh"] = { canonicalName = "ဘဳဟာရဳ", otherNames = {"Bihari"}, scripts = {"Deva"}, family = "inc", ancestors = {"inc-mgd"}, wikipedia_article = "ဘာသာဘဳဟာရဳ", } m["bi"] = { canonicalName = "ဗဳသလာမာ", otherNames = {"Bislama"}, scripts = {"Latn"}, family = "crp", ancestors = {"ine-pro", "gem-pro", "gmw-pro", "ang", "enm", "en-ear", "en"}, wikipedia_article = "Bislama", } m["bm"] = { canonicalName = "ဗီုဗရာ", otherNames = {"Bamanankan"}, scripts = {"Latn"}, family = "dmn", } m["bn"] = { canonicalName = "ဘင်္ဂါလဳ", otherNames = {"Bangla", "Bengali"}, scripts = {"Beng"}, family = "inc", ancestors = {"inc-mgd"}, translit_module = "bn-translit", } m["bo"] = { canonicalName = "တဳဗဝ်", otherNames = {"Tibetan", "Ü", "Dbus", "Lhasa", "Lhasa Tibetan", "Amdo Tibetan", "Amdo", "Panang", "Khams", "Khams Tibetan", "Khamba", "Tseku", "Dolpo", "Humla", "Limi", "Lhomi", "Shing Saapa", "Mugom", "Mugu", "Nubri", "Walungge", "Gola", "Thudam", "Lowa", "Loke", "Mustang", "Tichurong", "တိဗက်"}, scripts = {"Tibt"}, family = "tbq", ancestors = {"xct"}, translit_module = "bo-translit", override_translit = true, wikipedia_article = "Standard Tibetan", -- may need verification } m["br"] = { canonicalName = "ဗရဳတေန်", otherNames = {"Breton"}, scripts = {"Latn"}, family = "cel-bry", ancestors = {"xbm"}, } m["ca"] = { canonicalName = "ကတလာန်", otherNames = {"Valencian", "Catalan"}, scripts = {"Latn"}, family = "roa", ancestors = {"roa-oca"}, sort_key = { from = {"à", "[èé]", "[íï]", "[òó]", "[úü]", "ç", "l·l"}, to = {"a", "e" , "i" , "o" , "u" , "c", "ll" }} , } m["ce"] = { canonicalName = "ချက်ခ်ချေင်", otherNames = {"Chechen"}, scripts = {"Cyrl", "Latn", "Arab"}, family = "cau-nkh", translit_module = "translit-redirect", override_translit = true, ancestors = {"ccn-pro", "cau-nec-pro", "cau-nkh-pro"}, entry_name = { from = {MACRON}, to = {}}, } m["ch"] = { canonicalName = "ချာမဝ်ရဝ်", otherNames = {"Chamorro", "Chamoru"}, scripts = {"Latn"}, family = "poz-sus", } m["co"] = { canonicalName = "ခဝ်သဳကာန်", otherNames = {"Corsican", "Corsu"}, scripts = {"Latn"}, family = "roa", } m["cr"] = { canonicalName = "ခရေဝ်", scripts = {"Cree", "Cans", "Latn"}, family = "alg", translit_module = "cr-translit", } m["cs"] = { canonicalName = "ချက်ခ်", otherNames = {"Czech"}, scripts = {"Latn"}, family = "zlw", ancestors = {"zlw-ocs", "sla-pro"}, sort_key = { from = {"á", "é", "í", "ó", "[úů]", "ý"}, to = {"a", "e", "i", "o", "u" , "y"}} , } m["cu"] = { "ခရေတ်သလာဗဝ်နေတ်တြေံ", "Q35499", "zls", aliases = {"Old Church Slavic"}, scripts = {"Cyrs", "Glag"}, translit_module = "Cyrs-Glag-translit", ancestors = {"ine-pro", "ine-bsl-pro", "sla-pro"}, entry_name = { from = {u(0x0484)}, -- kamora to = {}}, sort_key = { from = {"оу", "є"}, to = {"у" , "е"}} , } m["cv"] = { "ချူဝါတ်", "Q33348", "trk-ogr", scripts = Cyrl, ancestors = {"xbo"}, translit_module = "cv-translit", sort_key = { from = {"ӑ", "ё", "ӗ", "ҫ", "ӳ"}, to = { "а" .. u(0xF000), "е" .. u(0xF000), "е" .. u(0xF001), "с" .. u(0xF000), "у" .. u(0xF000) } }, override_translit = true, } m["cy"] = { canonicalName = "ဝေလ", otherNames ={"Welsh"}, scripts = {"Latn"}, family = "cel-bry", ancestors = {"wlm"}, sort_key = { from = {"[âáàä]", "[êéèë]", "[îíìï]", "[ôóòö]", "[ûúùü]", "[ŵẃẁẅ]", "[ŷýỳÿ]", "'"}, to = {"a" , "e" , "i" , "o" , "u" , "w" , "y" }} , } m["da"] = { canonicalName = "ဒိန်နေတ်", otherNames ={"Danish"}, scripts = {"Latn"}, family = "gmq", ancestors = {"gmq-oda"}, } m["de"] = { canonicalName = "ဂျာမာန်", otherNames = {"High German", "New High German", "Deutsch", "German", "ဂျာမနဳ"}, scripts = {"Latn", "Latf"}, family = "gmw", ancestors = {"gmh"}, sort_key = { from = {"[äàáâå]", "[ëèéê]", "[ïìíî]", "[öòóô]", "[üùúû]", "ß" }, to = {"a" , "e" , "i" , "o" , "u" , "ss"}} , } m["dv"] = { canonicalName = "ဒိဝေဟဳ", otherNames = {"Dhivehi", "Divehi", "Mahal", "Mahl", "Maldivian"}, scripts = {"Thaa"}, family = "inc", ancestors = {"pmh"}, -- or Helu? translit_module = "dv-translit", override_translit = true, wikipedia_article = "ဘာသာမောဝ်ဒိုက်", } m["dz"] = { canonicalName = "သောင်ခါ", otherNames = {"Dzongkha"}, scripts = {"Tibt"}, family = "tbq", ancestors = {"xct"}, translit_module = "bo-translit", override_translit = true, wikipedia_article = "Dzongkha", } m["ee"] = { canonicalName = "အဳဝါ", otherNames = {"Ewe"}, scripts = {"Latn"}, family = "alv-von", } m["el"] = { canonicalName = "ဂရေတ်", otherNames = {"Greek", "Modern Greek", "Neo-Hellenic"}, scripts = {"Grek", "Brai", "Polyt", "Latn"}, family = "grk", ancestors = {"ine-pro", "grk-pro", "grc-att", "grc-koi", "gkm-med", "el-kth", "grc"}, translit_module = "el-translit", override_translit = true, sort_key = { -- Keep this synchronized with grc, cpg, pnt from = {"[ᾳάᾴὰᾲᾶᾷἀᾀἄᾄἂᾂἆᾆἁᾁἅᾅἃᾃἇᾇ]", "[έὲἐἔἒἑἕἓ]", "[ῃήῄὴῂῆῇἠᾐἤᾔἢᾒἦᾖἡᾑἥᾕἣᾓἧᾗ]", "[ίὶῖἰἴἲἶἱἵἳἷϊΐῒῗ]", "[όὸὀὄὂὁὅὃ]", "[ύὺῦὐὔὒὖὑὕὓὗϋΰῢῧ]", "[ῳώῴὼῲῶῷὠᾠὤᾤὢᾢὦᾦὡᾡὥᾥὣᾣὧᾧ]", "ῥ", "ς"}, to = {"α" , "ε" , "η" , "ι" , "ο" , "υ" , "ω" , "ρ", "σ"}} , standardChars = "ͺ;΄-ώϜϝ" .. PUNCTUATION .. "ἀ-῾" } m["en"] = { canonicalName = "အင်္ဂလိက်", otherNames = {"English", "Modern English", "New English", "Hawaiian Creole English", "Hawai'ian Creole English", "Hawaiian Creole", "Hawai'ian Creole", "Polari", "Yinglish"}, -- all but the first three are names of subsumed dialects which once had codes scripts = {"Latn", "Brai", "Shaw", "Dsrt"}, -- entries in Shaw or Dsrt might require prior discussion family = "gmw", ancestors = {"enm"}, wikipedia_article = "ဘာသာအင်္ဂလိက်", sort_key = { from = {"æ", "🅱", "[¢©ᴄ]", "[ðđ]", "[əǝ]", "[ħʜ]", "ɨ", "ł", "[ŋɲ]", "[øɔ]", "œ", "ꝓ", "ß", "ʋ"}, to = {"ae", "b", "c", "d", "e", "h", "i", "l", "n", "o", "oe", "p", "ss", "v"}} , wikimedia_codes = {"en", "simple"}, standardChars = "AaBbCcDdEeFfGgHhIiJjKkLlMmNnOoPpQqRrSsTtUuVvWwXxYyZz", } m["eo"] = { canonicalName = "အေက်သပရေန်တဝ်", otherNames = {"Esperanto"}, scripts = {"Latn"}, family = "art", sort_key = { from = {"[áà]", "[éè]", "[íì]", "[óò]", "[úù]", "[ĉ]", "[ĝ]", "[ĥ]", "[ĵ]", "[ŝ]", "[ŭ]"}, to = {"a" , "e" , "i" , "o" , "u", "cĉ", "gĉ", "hĉ", "jĉ", "sĉ", "uĉ"}} , wikipedia_article = "Esperanto", } m["es"] = { "သပုင်", 1321, "roa-ibe", {"Latn", "Brai"}, ancestors = {"ine-pro", "itc-pro", "itc-ola", "la", "osp"}, sort_key = { from = {"á", "é", "í", "ó", "[úü]", "ç", "ñ"}, to = {"a", "e", "i", "o", "u" , "c", "n"}}, standardChars = "A-VXYZa-vxyz0-9ÁáÉéÍíÓóÚúÑñ¿¡" .. PUNCTUATION, } m["et"] = { canonicalName = "အေက်သတဝ်နဳယာန်", otherNames = {"Estonian"}, scripts = {"Latn"}, family = "urj-fin", } m["eu"] = { canonicalName = "ဗက်ခ်", otherNames = {"Basque", "Euskara"}, scripts = {"Latn"}, family = "euq", } m["fa"] = { canonicalName = "ပါရှေန်", otherNames = {"ပါရှာ", "ဖာသဳ", "ဖာစဳ", "Persian", "Farsi", "New Persian", "Modern Persian", "Western Persian", "Iranian Persian", "Eastern Persian", "Dari", "Aimaq", "Aimak", "Aymaq", "Eimak"}, scripts = {"fa-Arab"}, family = "ira-wes", ancestors = {"pal", "ira-pro", "iir-pro", "ine-pro"}, entry_name = { from = {u(0x064E), u(0x064F), u(0x0650), u(0x0651), u(0x0652)}, to = {}} , } m["ff"] = { canonicalName = "ဖှောတ်လာ", otherNames = {"Fula", "Adamawa Fulfulde", "Bagirmi Fulfulde", "Borgu Fulfulde", "Central-Eastern Niger Fulfulde", "Fulani", "Fulfulde", "Maasina Fulfulde", "Nigerian Fulfulde", "Pular", "Pulaar", "Western Niger Fulfulde"}, -- Maasina, etc are dialects, subsumed into this code scripts = {"Latn"}, family = "alv-sng", } m["fi"] = { "ဖေန်လာန်", "Q1412", "urj-fin", aliases = {"Suomi"}, scripts = Latn, entry_name = { from = {"ˣ"}, -- Used to indicate gemination of the next consonant to = {}}, sort_key = { from = {"[áàâã]", "[éèêẽ]", "[íìîĩ]", "[óòôõ]", "[úùûũ]", "[ýỳŷüű]", "[øõő]", "æ" , "œ" , "[čç]", "š", "ž", "ß" , "[':]"}, to = {"a" , "e" , "i" , "o" , "u" , "y" , "ö" , "ae", "oe", "c" , "s", "z", "ss"}} , } m["fj"] = { canonicalName = "ဖရဳဂျိ", otherNames = {"Fijian"}, scripts = {"Latn"}, family = "poz-occ", } m["fo"] = { canonicalName = "ဖာရဝ်သဳ", otherNames = {"Faroese"}, scripts = {"Latn"}, family = "gmq", ancestors = {"non"}, } m["fr"] = { canonicalName = "ပြင်သေတ်", otherNames = {"French", "Modern French"}, scripts = {"Latn", "Brai"}, family = "roa-oil", ancestors = {"frm", "la"}, sort_key = { from = {"[áàâä]", "[éèêë]", "[íìîï]", "[óòôö]", "[úùûü]", "[ýỳŷÿ]", "ç", "æ" , "œ" , "'"}, to = {"a" , "e" , "i" , "o" , "u" , "y" , "c", "ae", "oe"}}, standardChars = "A-Za-z0-9ÀÂÇÉÈÊËÎÏÔŒÛÙÜàâçéèêëîïôœûùü«»" .. PUNCTUATION } m["fy"] = { canonicalName = "ဖရေဝ်သဳယာန်လက္ကရဴ", otherNames = {"West Frisian", "Western Frisian", "Frisian"}, scripts = {"Latn"}, family = "gmw-fri", ancestors = {"ofs"}, } m["ga"] = { canonicalName = "အာဲယျာလာန်", otherNames = {"Irish", "Irish Gaelic", "အိုင်ရစ်ရှ်"}, scripts = {"Latn"}, family = "cel-gae", ancestors = {"mga"}, sort_key = { from = {"á", "é", "í", "ó", "ú", "ý", "ḃ" , "ċ" , "ḋ" , "ḟ" , "ġ" , "ṁ" , "ṗ" , "ṡ" , "ṫ" }, to = {"a", "e", "i", "o", "u", "y", "bh", "ch", "dh", "fh", "gh", "mh", "ph", "sh", "th"}} , } m["gd"] = { canonicalName = "သကတ်ဂဴလိစ်", otherNames = {"Scottish Gaelic", "Gàidhlig", "Highland Gaelic", "Scots Gaelic", "Scottish"}, scripts = {"Latn"}, family = "cel-gae", ancestors = {"mga"}, sort_key = { from = {"[áà]", "[éè]", "[íì]", "[óò]", "[úù]", "[ýỳ]"}, to = {"a" , "e" , "i" , "o" , "u" , "y" }} , wikipedia_article = "Scottish Gaelic", } m["gl"] = { canonicalName = "ဂလဳသဳယာန်", otherNames = {"Galician"}, scripts = {"Latn"}, family = "roa", ancestors = {"ine-pro", "itc-pro", "inc-pro", "itc-ola", "la", "roa-opt"}, sort_key = { from = {"á", "é", "í", "ó", "ú"}, to = {"a", "e", "i", "o", "u"}} , } m["gn"] = { canonicalName = "ဂူရာန်နဳ", otherNames = {"Guaraní"}, scripts = {"Latn"}, family = "tup-gua", wikipedia_article = "ဘာသာဂူရာန်နဳ", } m["gu"] = { canonicalName = "ဂုဂျာရတဳ", otherNames = {"Gujarati"}, scripts = {"Gujr"}, family = "inc", ancestors = {"inc-ogu"}, translit_module = "gu-translit", } m["gv"] = { canonicalName = "မာက်", otherNames = {"Manx", "Manx Gaelic"}, scripts = {"Latn"}, family = "cel-gae", ancestors = {"mga"}, sort_key = { from = {"ç", "-"}, to = {"c"}} , } m["ha"] = { canonicalName = "ဟဴသာ", otherNames = {"Hausa"}, scripts = {"Latn", "Arab"}, family = "cdc-wst", sort_key = { from = {"ɓ", "ɗ", "ƙ", "'y", "ƴ", "'" }, to = {"b~" , "d~" , "k~", "y~", "y~", "" }}, entry_name = { from = {"R̃", "r̃", "À", "à", "È", "è", "Ì", "ì", "Ò", "ò", "Ù", "ù", "Â", "â", "Ê", "ê", "Î", "î", "Ô", "ô", "Û", "û", "Ā", "ā", "Ē", "ē", "Ī", "ī", "Ō", "ō", "Ū", "ū", "Á", "á", "É", "é", "Í", "í", "Ó", "ó", "Ú", "ú", "Ā̀", "ā̀", "Ḕ", "ḕ", "Ī̀", "ī̀", "Ṑ", "ṑ", "Ū̀", "ū̀", GRAVE, ACUTE}, to = {"R", "r", "A", "a", "E", "e", "I", "i", "O", "o", "U", "u", "A", "a", "E", "e", "I", "i", "O", "o", "U", "u", "A", "a", "E", "e", "I", "i", "O", "o", "U", "u", "A", "a", "E", "e", "I", "i", "O", "o", "U", "u", "A", "a", "E", "e", "I", "i", "O", "o", "U", "u"}}, } m["he"] = { canonicalName = "ဟဳဘရဝ်", otherNames = {"Hebrew", "Ivrit"}, scripts = {"Hebr", "Phnx", "Brai"}, family = "sem-can", ancestors = {"afa-pro", "sem-pro", "sem-wes-pro", "hbo", "he-mis", "he-med"}, translit_module = "he-translit", entry_name = { from = {"[" .. u(0x0591) .. "-" .. u(0x05BD) .. u(0x05BF) .. "-" .. u(0x05C5) .. u(0x05C7) .. "]"}, to = {}} , } m["hi"] = { canonicalName = "ဟိန္ဒဳ", otherNames = {"ဟိန္ဒဳ", "Hindi", "Braj", "Brij Bhasha", "Braj Bhasha", "Braj Bhāshā", "Braj Bhakha", "Dehaati Zabaan"}, scripts = {"Deva", "Guru"}, -- Guru for the subsumed variety Braj family = "inc-hnd", ancestors = {"inc-ohi"}, translit_module = "hi-translit", wikipedia_article = "Hindi", } m["ho"] = { canonicalName = "ဟဳရဳမိုတု", otherNames = {"Hiri Motu", "Pidgin Motu", "Police Motu"}, scripts = {"Latn"}, family = "crp", ancestors = {"meu"}, wikipedia_article = "Hiri Motu", } m["ht"] = { "ဟေဲယှေန် ခရေဝ်အဝ်လ်", 33491, "crp", Latn, ancestors = {"fr"}, } m["hu"] = { canonicalName = "ဟာန်ဂါရေဝ်", otherNames = {"Hungarian", "Magyar"}, scripts = {"Latn", "Hung"}, family = "urj-ugr", ancestors = {"urj-pro", "urj-ugr-pro", "ohu"}, sort_key = { from = {"é", "í", "ó", "ú", "ő", "ö", "ü", "á"}, to = {"e", "i", "o", "u", "o", "o", "u", "a"}} , } m["hy"] = { canonicalName = "အာမေနဳယျာ", otherNames = {"Armenian", "Modern Armenian", "Eastern Armenian", "Western Armenian", "အမေရိကာန်ဗၟံက်", "အမေရိကာန်ပလိုတ်", "အမေရိကာန်အခေတ်တၟိ"}, scripts = {"Armn", "Brai"}, family = "hyx", ancestors = {"axm"}, translit_module = "Armn-translit", override_translit = true, sort_key = { from = {"ու", "և", "եւ"}, to = {"ւ", "եվ", "եվ"}}, entry_name = { from = {"՞", "՜", "՛", "՟", "և", "<sup>յ</sup>", "<sup>ի</sup>"}, to = {"", "", "", "", "եւ", "յ", "ի"}} , } m["hz"] = { canonicalName = "ဟဳရဲရို", otherNames = {"Herero"}, scripts = {"Latn"}, family = "bnt", } m["ia"] = { canonicalName = "အေန်တာလိင်ဂဝ်", otherNames = {"Interlingua"}, scripts = {"Latn"}, family = "art", wikipedia_article = "Interlingua", } m["id"] = { canonicalName = "အိန်ဒဝ်နဳသဳယျာ", otherNames = {"Indonesian"}, scripts = {"Latn"}, family = "poz-mly", ancestors = {"map-pro", "poz-pro", "poz-sus-pro", "poz-msa-pro", "poz-mcm-pro", "poz-mly-pro", "ms-old", "ms-cla", "ms"}, } m["ie"] = { canonicalName = "အေန်တာလိင်ဂဝေ", otherNames = {"Interlingue", "Occidental"}, scripts = {"Latn"}, family = "art", wikipedia_article = "Occidental language", } m["ig"] = { canonicalName = "အေတ်ဗါဝ်", otherNames = {"Igbo", "အစ္ဂဘို"}, scripts = {"Latn"}, family = "nic-bco", } m["ii"] = { canonicalName = "သေဲဆိုန်ယဳ", otherNames = {"Sichuan Yi", "Nuosu", "Nosu", "Northern Yi", "Liangshan Yi"}, scripts = {"Yiii"}, family = "tbq-lol", wikipedia_article = "Nuosu language", translit_module = "ii-translit", override_translit = true, } m["ik"] = { canonicalName = "အဳနုဗဳယာတ်", otherNames = {"Inupiak", "Inupiaq", "Iñupiaq", "Inupiatun"}, scripts = {"Latn"}, family = "esx-inu", wikipedia_article = "Inupiaq", } m["io"] = { canonicalName = "ဣဒဝ်", otherNames = {"Ido"}, scripts = {"Latn"}, family = "art", } m["is"] = { canonicalName = "အာက်သလာန်", otherNames = {"Icelandic", "အာက်သလာန်"}, scripts = {"Latn"}, family = "gmq", ancestors = {"non", "gem-pro", "ine-pro"}, sort_key = { from = {"ð", "ö", "ó", "æ", "á", "í", "ú"}, to = {"o", "o", "o", "ae", "a", "i", "u"}} , } m["it"] = { canonicalName = "အဳတခ်လဳ", otherNames = {"Italian"}, scripts = {"Latn"}, family = "roa", sort_key = { from = {"[àáâäå]", "[èéêë]", "[ìíîï]", "[òóôö]", "[ùúûü]"}, to = {"a" , "e" , "i" , "o" , "u" }} , } m["iu"] = { canonicalName = "ဣနုက်တိတုတ်", otherNames = {"Inuktitut", "Eastern Canadian Inuktitut", "Eastern Canadian Inuit", "Western Canadian Inuktitut", "Western Canadian Inuit", "Western Canadian Inuktun", "Inuinnaq", "Inuinnaqtun", "Inuvialuk", "Inuvialuktun", "Nunavimmiutit", "Nunatsiavummiut", "Aivilimmiut", "Natsilingmiut", "Kivallirmiut", "Siglit", "Siglitun"}, scripts = {"Cans", "Latn"}, family = "esx-inu", translit_module = "iu-translit", override_translit = true, wikipedia_article = "Inuktitut", } m["ja"] = { canonicalName = "ဂျပါန်", otherNames = {"Japanese", "Modern Japanese", "Nipponese", "Nihongo"}, scripts = {"Jpan", "Latn", "Hira", "Brai"}, family = "jpx", ancestors = {"ojp"}, --[[ sort_key = { from = {"[ぁァア]", "[ぃィイ]", "[ぅゔゥウヴ]", "[ぇェエ]", "[ぉォオ]", "[がゕカガヵ]", "[ぎキギ]", "[ぐクグㇰ]", "[げゖケゲヶ]", "[ごコゴ]", "[ざサザ]", "[じシジㇱ]", "[ずスズㇲ]", "[ぜセゼ]", "[ぞソゾ]", "[だタダ]", "[ぢチヂ]", "[っづッツヅ]", "[でテデ]", "[どトドㇳ]", "ナ", "ニ", "[ヌㇴ]", "ネ", "ノ", "[ばぱハバパㇵ]", "[びぴヒビピㇶ]", "[ぶぷフブプㇷ]", "[べぺヘベペㇸ]", "[ぼぽホボポㇹ]", "マ", "ミ", "[ムㇺ]", "メ", "モ", "[ゃャヤ]", "[ゅュユ]", "[ょョヨ]", "[ラㇻ]", "[リㇼ]", "[ルㇽ]", "[レㇾ]", "[ロㇿ]", "[ゎヮワヷ]", "[ヰヸ]", "[ヱヹ]", "[ヲヺ]", "ン", "[゙゚゛゜ゝゞ・ヽヾ]", "𛀀", "1", "2", "3", "4", "5", "6", "7", "8", "9", "0"}, to = {"あ", "い", "う", "え", "お", "か", "き", "く", "け", "こ", "さ", "し", "す", "せ", "そ", "た", "ち", "つ", "て", "と", "な", "に", "ぬ", "ね", "の", "は", "ひ", "ふ", "へ", "ほ", "ま", "み", "む", "め", "も", "や", "ゆ", "よ", "ら", "り", "る", "れ", "ろ", "わ", "ゐ", "ゑ", "を", "ん", "", "え", "い", "に", "み", "よ", "ご", "ろ", "な", "は", "き", "れ"}}, ]] } m["jv"] = { canonicalName = "ဂျာဗာ", otherNames = {"Javanese"}, scripts = {"Latn", "Java"}, family = "poz-sus", translit_module = "jv-translit", ancestors = {"kaw"}, link_tr = true, } m["ka"] = { canonicalName = "ဂျဝ်ဂျဳယျာ", otherNames = {"Georgian", "Kartvelian", "Judeo-Georgian", "Kivruli", "Gruzinic"}, scripts = {"Geor", "Geok", "Hebr"}, -- Hebr is used to write Judeo-Georgian family = "ccs-gzn", ancestors = {"oge"}, translit_module = "Geor-translit", override_translit = true, entry_name = { from = {"̂"}, to = {""}}, } m["kg"] = { canonicalName = "ခါမ်ဂဝ်", otherNames = {"Kongo", "Kikongo", "Koongo", "Laari", "San Salvador Kongo", "Yombe"}, scripts = {"Latn"}, family = "bnt", } m["ki"] = { canonicalName = "ခဳခူယူ", otherNames = {"Kikuyu", "Gikuyu", "Gĩkũyũ"}, scripts = {"Latn"}, family = "bnt", } m["kj"] = { canonicalName = "ကောန်ယာမာ", otherNames = {"Kwanyama", "Kuanyama", "Oshikwanyama"}, scripts = {"Latn"}, family = "bnt", wikipedia_article = "Kwanyama dialect", } m["kk"] = { canonicalName = "ကဇက်", scripts = {"Kazakh", "Cyrl", "Latn", "Arab", "kk-Arab"}, family = "trk-kip", ancestors = {"trk-pro"}, translit_module = "kk-translit", override_translit = true, } m["kl"] = { canonicalName = "ဂရိန်လာန်", otherNames = {"Greenlandic", "Kalaallisut"}, scripts = {"Latn"}, family = "esx-inu", } m["km"] = { "ခမေန်", "Q9205", family = "mkh-kmr", aliases = {"Khmer", "Cambodian"}, scripts = {"Khmr"}, ancestors = {"aav-pro", "mkh-pro", "mkh-kmr-pro", "okz", "xhm"}, translit_module = "km-translit", } m["kn"] = { canonicalName = "ကာန်နဒါ", otherNames = {"Kannada", "ကန္နာဒါ"}, scripts = {"Knda"}, family = "dra", translit_module = "kn-translit", wikipedia_article = "Kannada", ancestors = {"dra-mkn"}, } m["ko"] = { "ကိုဝ်ရဳယျာ", "Q9176", "qfa-kor", aliases = {"Korean", "Modern Korean"}, scripts = {"Kore", "Brai"}, ancestors = {"ko-ear"}, -- 20210122 trial idea: strip parenthesized hanja from entry link -- Hani regex is a reasonable subset of Hani from [[Module:scripts/data]], -- last updated on 20210203. entry_name = { from = { "%([一-鿿㐀-䶿𠀀-𮯯"..u(0x2F800).."-𯨟𰀀-𱍏﨎﨏﨑﨓﨔﨟﨡﨣﨤﨧﨨﨩]+%)", }, to = { "", }}, translit_module = "ko-translit", } m["kr"] = { canonicalName = "ကနူရဳ", otherNames = {"Kanuri", "Kanembu", "Bilma Kanuri", "Central Kanuri", "Manga Kanuri", "Tumari Kanuri"}, scripts = {"Latn", "Arab"}, family = "ssa-sah", sort_key = { from = {"ny", "ǝ", "sh"}, to = {"n~", "e~", "s~"}} , -- the sortkey and entry_name are only for standard Kanuri; when dialectal entries get added, someone will have to work out how the dialects should be represented orthographically entry_name = { from = {"À", "à", "È", "è", "Ǝ̀", "ǝ̀", "Ì", "ì", "Ò", "ò", "Ù", "ù", "Â", "â", "Ê", "ê", "Ǝ̂", "ǝ̂", "Î", "î", "Ô", "ô", "Û", "û", "Ă", "ă", "Ĕ", "ĕ", "Ǝ̆", "ǝ̆", "Ĭ", "ĭ", "Ŏ", "ŏ", "Ŭ", "ŭ", "Á", "á", "É", "é", "Ǝ́", "ǝ́", "Í", "í", "Ó", "ó", "Ú", "ú", GRAVE, ACUTE}, to = {"A", "a", "E", "e", "Ǝ", "ǝ", "I", "i", "O", "o", "U", "u", "A", "a", "E", "e", "Ǝ", "ǝ", "I", "i", "O", "o", "U", "u", "A", "a", "E", "e", "Ǝ", "ǝ", "I", "i", "O", "o", "U", "u", "A", "a", "E", "e", "Ǝ", "ǝ", "I", "i", "O", "o", "U", "u"}}, } m["ks"] = { "ကာဒ်ရှ်မဳယျာ", 33552, "inc-dar", {"ks-Arab", "Deva", "Shrd", "Latn"}, translit_module = "translit-redirect", ancestors = {"sa"}, } m["ku"] = { canonicalName = "ကာဒဳ", otherNames = {"Kurdish"}, scripts = {"Latn", "ku-Arab", "Armn", "Cyrl"}, family = "ira-wes", wikipedia_article = "Kurdish languages", } -- "kv" IS TREATED AS "koi", "kpv", SEE WT:LT m["kw"] = { canonicalName = "ခမ်နေတ်", otherNames = {"Cornish"}, scripts = {"Latn"}, family = "cel-bry", ancestors = {"ine-pro", "cel-pro", "cel-bry-pro", "oco", "cnx"}, } m["ky"] = { canonicalName = "ကာဇေတ်", otherNames = {"Kyrgyz", "Kirghiz", "Kirgiz"}, scripts = {"Cyrl", "Latn", "Arab"}, family = "trk-kip", translit_module = "ky-translit", override_translit = true, ancestors = {"trk-pro", "qwm"}, } m["la"] = { canonicalName = "လပ်တေန်", otherNames = {"Latin"}, scripts = {"Latn"}, family = "itc", ancestors = {"itc-ola"}, entry_name = { from = {"[ĀĂ]", "[āă]", "[ĒĔ]", "[ēĕë]", "[ĪĬÏ]", "[īĭï]", "[ŌŎ]", "[ōŏ]", "[ŪŬÜ]", "[ūŭü]", "Ȳ", "ȳ", MACRON, BREVE, DIAER}, to = {"A", "a", "E", "e", "I", "i", "O", "o", "U", "u", "Y", "y"}}, wikipedia_article = "Latin", standardChars = "A-Za-zÆæŒœĀ-ăĒ-ĕĪ-ĭŌ-ŏŪ-ŭȲȳ" .. MACRON .. BREVE .. PUNCTUATION } m["lb"] = { canonicalName = "လူဇေန်ဘာဂျ်", otherNames = {"Luxembourgish"}, scripts = {"Latn"}, family = "gmw", ancestors = {"gmh"}, wikipedia_article = "Luxembourgish", } m["lg"] = { canonicalName = "လုဂန်ဒါ", otherNames = {"ဂန်ဒါ", "Luganda", "Ganda", "Oluganda"}, scripts = {"Latn"}, family = "bnt", entry_name = { from = {"á", "Á", "é", "É", "í", "Í", "ó", "Ó", "ú", "Ú", "ń", "Ń", "ḿ", "Ḿ", "â", "Â", "ê", "Ê", "î", "Î", "ô", "Ô", "û", "Û" }, to = {"a", "A", "e", "E", "i", "I", "o", "O", "u", "U", "n", "N", "m", "M", "a", "A", "e", "E", "i", "I", "o", "O", "u", "U",}}, sort_key = { from = {"ŋ"}, to = {"n"}} , wikipedia_article = "Luganda", } m["li"] = { canonicalName = "လိမ်ဗူရ်ဂိသ်", otherNames = {"Limburgish", "Limburgan", "Limburgian", "Limburgic"}, scripts = {"Latn"}, family = "gmw", ancestors = {"dum"}, } m["ln"] = { canonicalName = "လေန်ဂါလာ", otherNames = {"Lingala", "Ngala"}, scripts = {"Latn"}, family = "bnt", wikipedia_article = "Lingala", } m["lo"] = { canonicalName = "သေံလဴ", otherNames = {"သေံလဴ", "Lao", "Laotian"}, scripts = {"Laoo"}, family = "tai-swe", translit_module = "lo-translit", sort_key = { from = {"ຼ", "ຽ", "ໜ", "ໝ", "([ເແໂໃໄ])([ກ-ຮ])"}, to = {"ລ", "ຍ", "ຫນ", "ຫມ", "%2%1"}}, ancestors = {"qfa-tak-pro", "qfa-bet-pro", "tai-pro", "tai-swe-pro"}, } m["lt"] = { canonicalName = "လေတ်တူယဵုနဳယျာ", otherNames = {"Lithuanian", "လေတ်တူယဵုနဳယျာ"}, scripts = {"Latn"}, family = "bat", ancestors = {"ine-pro", "ine-bsl-pro", "bat-pro", "olt"}, entry_name = { from = {"[áãà]", "[ÁÃÀ]", "[éẽè]", "[ÉẼÈ]", "[íĩì]", "[ÍĨÌ]", "[ýỹ]", "[ÝỸ]", "ñ", "[óõò]", "[ÓÕÒ]", "[úũù]", "[ÚŨÙ]", ACUTE, GRAVE, TILDE}, to = {"a", "A", "e", "E", "i", "I", "y", "Y", "n", "o", "O", "u", "U"}} , } m["lu"] = { canonicalName = "ဠူဘ-ကာတေန်ဂါ", scripts = {"Latn"}, family = "bnt", } m["lv"] = { canonicalName = "လပ်ဗဳယာ", otherNames = {"Latvian", "Lettish", "Lett"}, scripts = {"Latn"}, family = "bat", ancestors = {"ine-bsl-pro", "bat-pro"}, entry_name = { -- This attempts to convert vowels with tone marks to vowels either with -- or without macrons. Specifically, there should be no macrons if the -- vowel is part of a diphthong (including resonant diphthongs such -- pìrksts -> pirksts not #pīrksts). What we do is first convert the -- vowel + tone mark to a vowel + tilde in a decomposed fashion, -- then remove the tilde in diphthongs, then convert the remaining -- vowel + tilde sequences to macroned vowels, then delete any other -- tilde. We leave already-macroned vowels alone: Both e.g. ar and ār -- occur before consonants. FIXME: This still might not be sufficient. from = {"Ȩ", "ȩ", "[ÂÃÀ]", "[âãà]", "[ÊẼÈ]", "[êẽè]", "[ÎĨÌ]", "[îĩì]", "[ÔÕÒ]", "[ôõò]", "[ÛŨÙ]", "[ûũù]", "[ÑǸ]", "[ñǹ]", "[" .. CIRC .. TILDE ..GRAVE .."]", "([aAeEiIoOuU])" .. TILDE .."?([lrnmuiLRNMUI])" .. TILDE .. "?([^aAeEiIoOuUāĀēĒīĪūŪ])", "([aAeEiIoOuU])" .. TILDE .."?([lrnmuiLRNMUI])" .. TILDE .."?$", "([iI])" .. TILDE .. "?([eE])" .. TILDE .. "?", "A" .. TILDE, "a" .. TILDE, "E" .. TILDE, "e" .. TILDE, "I" .. TILDE, "i" .. TILDE, "U" .. TILDE, "u" .. TILDE, TILDE}, to = {"E", "e", "A" .. TILDE, "a" .. TILDE, "E" .. TILDE, "e" .. TILDE, "I" .. TILDE, "i" .. TILDE, "O", "o", "U" .. TILDE, "u" .. TILDE, "N", "n", TILDE, "%1%2%3", "%1%2", "%1%2", "Ā", "ā", "Ē", "ē", "Ī", "ī", "Ū", "ū", ""}}, } m["mg"] = { canonicalName = "မာလာဂါသဳ", otherNames = {"Malagasy", "Betsimisaraka Malagasy", "Betsimisaraka", "Northern Betsimisaraka Malagasy", "Northern Betsimisaraka", "Southern Betsimisaraka Malagasy", "Southern Betsimisaraka", "Bara Malagasy", "Bara", "Masikoro Malagasy", "Masikoro", "Antankarana", "Antankarana Malagasy", "Plateau Malagasy", "Sakalava", "Tandroy Malagasy", "Tandroy", "Tanosy", "Tanosy Malagasy", "Tesaka", "Tsimihety", "Tsimihety Malagasy", "Bushi", "Shibushi", "Kibushi", "Sakalava"}, scripts = {"Latn"}, family = "poz-bre", } m["mh"] = { canonicalName = "မာချဲလဳ", otherNames = {"Marshallese"}, scripts = {"Latn"}, family = "poz-mic", sort_key = { from = {"ā" , "ļ" , "m̧" , "ņ" , "n̄" , "o̧" , "ō" , "ū" }, to = {"a~", "l~", "m~", "n~", "n~~", "o~", "o~~", "u~"}} , } m["mi"] = { canonicalName = "မဝ်ရဳ", otherNames = {"Maori", "Māori"}, scripts = {"Latn"}, family = "poz-pol", wikipedia_article = "Māori language", sort_key = { from = {"ā" , "ļ" , "m̧" , "ņ" , "n̄" , "o̧" , "ō" , "ū" }, to = {"a~", "l~", "m~", "n~", "n~~", "o~", "o~~", "u~"}} , } m["mk"] = { canonicalName = "မက်သဳဒဝ်နဳယျာ", otherNames = {"Macedonian"}, scripts = {"Cyrl"}, family = "zls", translit_module = "mk-translit", ancestors = {"ine-pro", "ine-bsl-pro", "sla-pro"}, entry_name = { from = {ACUTE}, to = {}}, } m["ml"] = { canonicalName = "မလေဝ်ယျလာမ်", otherNames = {"Malayalam"}, scripts = {"Mlym"}, family = "dra", translit_module = "ml-translit", override_translit = true, wikipedia_article = "Malayalam", } m["mn"] = { canonicalName = "မန်ဂဝ်လဳယျာ", otherNames = {"မန်ဂဝ်လဳယျာ", "ခန်ခါ မန်ဂဝ်လဳယျာ"}, scripts = {"Cyrl", "Mong", "Soyo", "Zanb"}, -- entries in Soyo or Zanb might require prior discussion family = "xgn", ancestors = {"cmg"}, translit_module = "mn-translit", override_translit = true, } -- "mo" IS TREATED AS "ro", SEE WT:LT m["mr"] = { canonicalName = "မာရဒဳ", otherNames = {"Marathi"}, scripts = {"Deva", "Modi"}, family = "inc", ancestors = {"omr"}, translit_module = "hi-translit", } m["ms"] = { canonicalName = "မလေဝ်", otherNames = {"Malay", "Malaysian", "Standard Malay", "Orang Seletar", "Orang Kanaq", "Jakun", "Temuan"}, scripts = {"Latn", "ms-Arab"}, family = "poz-mly", ancestors = {"map-pro", "poz-pro", "poz-sus-pro", "poz-msa-pro", "poz-mcm-pro", "poz-mly-pro", "ms-old", "ms-cla"}, } m["mt"] = { canonicalName = "မာလ်တဳ", otherNames = {"Maltese"}, scripts = {"Latn"}, family = "sem-arb", ancestors = {"sqr"}, } m["my"] = { canonicalName = "ဗၟာ", otherNames = {"Burmese", "Myanmar", "ဗၟာ"}, scripts = {"Mymr"}, family = "tbq-brm", ancestors = {"obr", "sit-pro", "tbq-pro"}, wikipedia_article = "ဘာသာဗၟာ", translit_module = "my-translit", override_translit = true, } m["na"] = { canonicalName = "နာဥူလောန်", otherNames = {"Nauruan","Nauru"}, scripts = {"Latn"}, family = "poz-mic", } m["nb"] = { canonicalName = "နဝ်ဝေ ဗော်ခ်မဝ်", otherNames = {"Norwegian Bokmål", "Bokmål"}, scripts = {"Latn"}, family = "gmq", ancestors = {"gmq-mno", "gem-pro"}, wikimedia_codes = {"no"}, wikipedia_article = "Bokmål", } m["nd"] = { canonicalName = "Northern Ndebele", otherNames = {"North Ndebele"}, scripts = {"Latn"}, family = "bnt-ngu", entry_name = { from = {"[āàáâǎ]", "[ēèéêě]", "[īìíîǐ]", "[ōòóôǒ]", "[ūùúûǔ]", "ḿ", "[ǹńň]", MACRON, ACUTE, GRAVE, CIRC, CARON}, to = {"a" , "e" , "i" , "o" , "u" , "m", "n" }}, } m["ne"] = { "နဳပဝ်", 33823, "inc-pah", scripts = {"Deva", "Newa"}, ancestors = {"ine-pro", "iir-pro", "inc-pro", "sa", "inc-ash", "pra-kha"}, translit_module = "ne-translit", } m["ng"] = { canonicalName = "အွန်ဒွန်ဂါ", otherNames = {"Ndonga"}, scripts = {"Latn"}, family = "bnt", wikipedia_article = "Ndonga dialect", } m["nl"] = { canonicalName = "ဒါတ်", otherNames = {"Dutch", "Netherlandic", "Flemish"}, scripts = {"Latn"}, family = "gmw", ancestors = {"dum"}, sort_key = { from = {"[äáâå]", "[ëéê]", "[ïíî]", "[öóô]", "[üúû]", "ç", "ñ", "^-"}, to = {"a" , "e" , "i" , "o" , "u" , "c", "n"}} , standardChars = "A-Za-z0-9" .. PUNCTUATION .. u(0x2800) .. "-" .. u(0x28FF), } m["nn"] = { canonicalName = "နဝ်ဝေ နဳနိုတ်", otherNames = {"Norwegian Nynorsk", "New Norwegian", "Nynorsk"}, scripts = {"Latn"}, family = "gmq", ancestors = {"gmq-mno"}, wikipedia_article = "Nynorsk", } m["no"] = { canonicalName = "နဝ်ဝေ", otherNames = {"Norwegian"}, scripts = {"Latn"}, family = "gmq", ancestors = {"gmq-mno"}, } m["nr"] = { canonicalName = "အာန်ဒေဗေလေဝ် လ္ပာ်ဒိုဟ်သမၠုင်ကျာ", otherNames = {"South Ndebele"}, scripts = {"Latn"}, family = "bnt-ngu", entry_name = { from = {"[āàáâǎ]", "[ēèéêě]", "[īìíîǐ]", "[ōòóôǒ]", "[ūùúûǔ]", "ḿ", "[ǹńň]", MACRON, ACUTE, GRAVE, CIRC, CARON}, to = {"a" , "e" , "i" , "o" , "u" , "m", "n" }}, } m["nv"] = { "နာဝါဟဝ်", 13310, "apa", Latn, sort_key = { from = {"[áą]", "[éę]", "[íį]", "[óǫ]", "ń", "^n([djlt])", "ł" , "[ʼ’']", ACUTE}, to = {"a" , "e" , "i" , "o" , "n", "ni%1" , "l~"}}, -- the tilde is used to guarantee that ł will always be sorted after all other words with l } m["ny"] = { canonicalName = "ချဳချေန်ဝါ", otherNames = {"နရန်ဂျာ", "Chichewa", "Chicheŵa", "Chinyanja", "Nyanja", "Chewa", "Cicewa", "Cewa", "Cinyanja"}, scripts = {"Latn"}, family = "bnt", entry_name = { from = {"ŵ", "Ŵ", "á", "Á", "é", "É", "í", "Í", "ó", "Ó", "ú", "Ú", "ń", "Ń", "ḿ", "Ḿ" }, to = {"w", "W", "a", "A", "e", "E", "i", "I", "o", "O", "u", "U", "n", "N", "m", "M"}}, sort_key = { from = {"ng'"}, to = {"ng"}} , wikipedia_article = "Chewa language", } m["oc"] = { "အောက်စဳတာန်", "Q14185", "roa-ocr", aliases = {"အောက်စဳတာန်"}, -- don't list varieties here that are in [[Module:etymology languages/data]] scripts = {"Latn", "Hebr"}, ancestors = {"pro"}, sort_key = { from = {"[àá]", "[èé]", "[íï]", "[òó]", "[úü]", "ç", "([lns])·h"}, to = {"a" , "e" , "i" , "o" , "u" , "c", "%1h" }} , } m["oj"] = { canonicalName = "အဝ်ဂျဳဗဝေ", otherNames = {"Ojibwe", "Chippewa", "Ojibway", "Ojibwemowin", "Southwestern Ojibwa"}, scripts = {"Cans", "Latn"}, family = "alg", } m["om"] = { canonicalName = "အဝ်ရဝ်မဝ်", otherNames = {"Oromo", "Orma", "Borana-Arsi-Guji Oromo", "West Central Oromo"}, scripts = {"Latn", "Ethi"}, family = "cus-eas", } m["or"] = { canonicalName = "အဝ်ရေဝ်ယာ", otherNames = {"Oriya", "Odia", "Oorya"}, scripts = {"Orya"}, family = "inc", ancestors = {"inc-mgd"}, translit_module = "or-translit", wikipedia_article = "Odia language", } m["os"] = { canonicalName = "အဝ်ဇြဳယာန်", otherNames = {"Ossetian", "Ossete", "Ossetic", "Digor", "Iron"}, scripts = {"Cyrl", "Geor", "Latn"}, family = "ira", ancestors = {"oos"}, translit_module = "os-translit", override_translit = true, entry_name = { from = {GRAVE, ACUTE}, to = {}} , } m["pa"] = { canonicalName = "ပါန်ချာပဳ", otherNames = {"Punjabi", "Panjabi"}, scripts = {"Guru", "pa-Arab"}, family = "inc-opa", ancestors = {"inc-opa"}, translit_module = "translit-redirect", entry_name = { from = {u(0x064B), u(0x064C), u(0x064D), u(0x064E), u(0x064F), u(0x0650), u(0x0651), u(0x0652), u(0x0658), u(0x08C7), u(0x0768)}, to = {"", "", "", "", "", "", "", "", "", "ل", "ن"}} , } m["pi"] = { "ပါဠိ", "Q36727", "inc-mid", scripts = {"Latn", "Brah", "Deva", "Beng", "Sinh", "Mymr", "Thai", "Lana", "Laoo", "Khmr"}, ancestors = {"sa"}, translit_module = "pi-translit", sort_key = { from = {"ā", "ī", "ū", "ḍ", "ḷ", "[ṁṃ]", "ṅ", "ñ", "ṇ", "ṭ", "([เโ])([ก-ฮ])", "([ເໂ])([ກ-ຮ])", "ᩔ", "ᩕ", "ᩖ", "ᩘ", "([ᨭ-ᨱ])ᩛ", "([ᨷ-ᨾ])ᩛ", "ᩤ", u(0xFE00), u(0x200D)}, to = {"a~", "i~", "u~", "d~", "l~", "m~", "n~", "n~~", "n~~~", "t~", "%2%1", "%2%1", "ᩈ᩠ᩈ", "᩠ᩁ", "᩠ᩃ", "ᨦ᩠", "%1᩠ᨮ", "%1᩠ᨻ", "ᩣ"}} , entry_name = { from = {u(0xFE00)}, to = {}}, } m["pl"] = { canonicalName = "ပဝ်လာန်", otherNames = {"Polish"}, scripts = {"Latn"}, family = "zlw", ancestors = {"zlw-opl", "sla-pro"}, sort_key = { from = {"[Ąą]", "[Ćć]", "[Ęę]", "[Łł]", "[Ńń]", "[Óó]", "[Śś]", "[Żż]", "[Źź]"}, to = { "a" .. u(0x10FFFF), "c" .. u(0x10FFFF), "e" .. u(0x10FFFF), "l" .. u(0x10FFFF), "n" .. u(0x10FFFF), "o" .. u(0x10FFFF), "s" .. u(0x10FFFF), "z" .. u(0x10FFFF), "z" .. u(0x10FFFE)}} , } m["ps"] = { "ပါသတုန်", "Q58680", "ira-pat", aliases = {"Pashtun", "Pushto", "Pashtu", "Afghani"}, varieties = {"Central Pashto", "Northern Pashto", "Southern Pashto", {"Pukhto", "Pakhto", "Pakkhto"}}, scripts = {"ps-Arab"}, ancestors = {"ira-pat-pro"}, } m["pt"] = { canonicalName = "ပဝ်တူဂြဳ", otherNames = {"Portuguese", "Modern Portuguese"}, scripts = {"Latn", "Brai"}, family = "roa", ancestors = {"ine-pro", "itc-pro", "itc-ola", "la", "roa-opt"}, sort_key = { from = {"[àãáâä]", "[èẽéêë]", "[ìĩíï]", "[òóôõö]", "[üúùũ]", "ç", "ñ"}, to = {"a" , "e" , "i" , "o" , "u" , "c", "n"}} , } m["qu"] = { canonicalName = "ခေန်ချူဝါ", scripts = {"Latn"}, family = "qwe", wikipedia_article = "ဘာသာခေန်ချူဝါ", } m["rm"] = { canonicalName = "ရဝ်မာန်", otherNames = {"Romansch","Romansh", "Rumantsch", "Romanche"}, scripts = {"Latn"}, family = "roa", wikipedia_article = "Romansh language", } m["ro"] = { canonicalName = "ရဝ်မေနဳယျာ", otherNames = {"Romanian", "Daco-Romanian", "Roumanian", "Rumanian"}, scripts = {"Latn", "Cyrl"}, family = "roa", sort_key = { from = {"ă" , "â" , "î" , "ș" , "ț" }, to = {"a~", "a~~", "i~", "s~", "t~"}}, } m["ru"] = { canonicalName = "ရုဿျှာ", otherNames = {"Russian"}, scripts = {"Cyrl", "Brai"}, family = "zle", translit_module = "ru-translit", sort_key = { from = {"ё"}, to = {"е" .. mw.ustring.char(0x10FFFF)}}, entry_name = { from = {"Ѐ", "ѐ", "Ѝ", "ѝ", GRAVE, ACUTE}, to = {"Е", "е", "И", "и"}}, standardChars = "ЁІА-яёі0-9—" .. PUNCTUATION, } m["rw"] = { canonicalName = "ရဝမ်ဒါ ရမ်ဒဳ", otherNames = {"Rwanda-Rundi", "Rwanda", "Kinyarwanda", "Rundi", "Kirundi", "Ha", "Giha", "Hangaza", "Vinza", "Shubi", "Subi"}, scripts = {"Latn"}, family = "bnt", wikipedia_article = "Rwanda-Rundi", } m["sa"] = { canonicalName = "သံသကြိုတ်", otherNames = {"Sanskrit"}, scripts = {"Deva", "Bali", "as-Beng", "Beng", "Bhks", "Brah", "Gran", "Gujr", "Guru", "Java", "Khar", "Khmr", "Knda", "Lana", "Laoo", "Mlym", "Modi", "Mymr", "Nand", "Newa", "Orya", "Saur", "Shrd", "Sidd", "Sinh", "Taml", "Telu", "Thai", "Tibt", "Tirh"}, family = "inc-old", sort_key = { from = {"ā", "ī", "ū", "ḍ", "ḷ", "ḹ", "[ṁṃ]", "ṅ", "ñ", "ṇ", "ṛ", "ṝ", "ś", "ṣ", "ṭ", "([เโไ])([ก-ฮ])", "([ເໂໄ])([ກ-ຮ])", "ᩔ", "ᩕ", "ᩖ", "ᩘ", "([ᨭ-ᨱ])ᩛ", "([ᨷ-ᨾ])ᩛ", "ᩤ", u(0xFE00), u(0x200D)}, to = {"a~", "i~", "u~", "d~", "l~", "l~~", "m~", "n~", "n~~", "n~~~", "r~", "r~~", "s~", "s~~", "t~", "%2%1", "%2%1", "ᩈ᩠ᩈ", "᩠ᩁ", "᩠ᩃ", "ᨦ᩠", "%1᩠ᨮ", "%1᩠ᨻ", "ᩣ"}}, entry_name = { from = {"ึ", u(0xF700), u(0xF70F), u(0xFE00)}, to = {"ิํ", "ฐ", "ญ"}}, translit_module = "translit-redirect", ancestors = {"iir-pro", "inc-pro"}, } m["sc"] = { canonicalName = "သာဒဳနဳယာန်", otherNames = {"Sardinian", "Campidanese", "Campidanese Sardinian", "Logudorese", "Logudorese Sardinian", "Nuorese", "Nuorese Sardinian"}, scripts = {"Latn"}, family = "roa", } m["sd"] = { "သိန္ဓိ", 33997, "inc-snd", scripts = {"sd-Arab", "Deva", "Sind", "Khoj"}, entry_name = { from = {u(0x0671), u(0x064B), u(0x064C), u(0x064D), u(0x064E), u(0x064F), u(0x0650), u(0x0651), u(0x0652), u(0x0670), u(0x0640)}, to = {u(0x0627)}}, ancestors = {"inc-vra"}, translit_module = "translit-redirect", } m["se"] = { canonicalName = "သာမိ သၟဝ်ကျာ", otherNames = {"Northern Sami", "North Sami", "Northern Saami", "North Saami"}, scripts = {"Latn"}, family = "smi", entry_name = { from = {"([đflmnŋrsšŧv])'%1"}, to = {"%1%1"} }, wikipedia_article = "Northern Sami", } m["sg"] = { canonicalName = "သင်ဂဝ်", otherNames = {"Sango"}, scripts = {"Latn"}, family = "crp", } m["sh"] = { canonicalName = "သာဗ်ခြဝ်ဨရှဳယာန်", otherNames = {"Serbo-Croatian", "BCS", "Croato-Serbian", "Serbocroatian", "Bosnian", "Croatian", "Montenegrin", "Serbian"}, scripts = {"Latn", "Cyrl"}, family = "zls", ancestors = {"ine-pro", "ine-bsl-pro", "sla-pro"}, entry_name = { from = {"[ȀÀȂÁĀÃ]", "[ȁàȃáāã]", "[ȄÈȆÉĒẼ]", "[ȅèȇéēẽ]", "[ȈÌȊÍĪĨ]", "[ȉìȋíīĩ]", "[ȌÒȎÓŌÕ]", "[ȍòȏóōõ]", "[ȐȒŔ]", "[ȑȓŕ]", "[ȔÙȖÚŪŨ]", "[ȕùȗúūũ]", "Ѐ", "ѐ", "[ӢЍ]", "[ӣѝ]", "[Ӯ]", "[ӯ]", GRAVE, ACUTE, DGRAVE, INVBREVE, MACRON, TILDE}, to = {"A" , "a" , "E" , "e" , "I" , "i" , "O" , "o" , "R" , "r" , "U" , "u" , "Е", "е", "И" , "и", "У", "у" }}, wikimedia_codes = {"sh", "bs", "hr", "sr"}, wikipedia_article = "Serbo-Croatian", } m["si"] = { canonicalName = "သိၚ်္ဃဵုရ်", otherNames = {"Sinhalese", "Singhalese", "Sinhala"}, scripts = {"Sinh"}, family = "inc", ancestors = {"elu-prk"}, translit_module = "si-translit", override_translit = true, } m["sk"] = { canonicalName = "သလဝ်ဝေန်နဳယျာ", otherNames = {"Slovak"}, scripts = {"Latn"}, family = "zlw", ancestors = {"ine-pro", "ine-bsl-pro", "sla-pro", "zlw-osk"}, sort_key = { from = {"[áä]", "é", "í", "[óô]", "ú", "ý", "ŕ", "ĺ", "[" .. DIAER .. ACUTE .. CIRC .. "]"}, to = {"a" , "e", "i", "o" , "u", "y", "r", "l", ""}} , } m["sl"] = { canonicalName = "သၠဝ်ဝေနဳ", otherNames = {"Slovene", "Slovenian"}, scripts = {"Latn"}, family = "zls", entry_name = { from = {"[ÁÀÂȂȀ]", "[áàâȃȁ]", "[ÉÈÊȆȄỆẸ]", "[éèêȇȅệẹə]", "[ÍÌÎȊȈ]", "[íìîȋȉ]", "[ÓÒÔȎȌỘỌ]", "[óòôȏȍộọ]", "[ŔȒȐ]", "[ŕȓȑ]", "[ÚÙÛȖȔ]", "[úùûȗȕ]", "ł", GRAVE, ACUTE, DGRAVE, INVBREVE, CIRC, DOTBELOW}, to = {"A" , "a" , "E" , "e" , "I" , "i" , "O" , "o" , "R" , "r" , "U" , "u" , "l"}} , } m["sm"] = { canonicalName = "သမဝ်အာန်", otherNames = {"Samoan"}, scripts = {"Latn"}, family = "poz-pol", } m["sn"] = { canonicalName = "သျှိနာ", otherNames = {"Shona"}, scripts = {"Latn"}, family = "bnt", } m["so"] = { canonicalName = "ဆဝ်မာလဳ", otherNames = {"Somali"}, scripts = {"Latn", "Arab", "Osma"}, family = "cus", entry_name = { from = {"[ÁÀÂ]", "[áàâ]", "[ÉÈÊ]", "[éèê]", "[ÍÌÎ]", "[íìî]", "[ÓÒÔ]", "[óòô]", "[ÚÙÛ]", "[úùû]", "[ÝỲ]", "[ýỳ]"}, to = {"A" , "a" , "E" , "e" , "I" , "i" , "O" , "o" , "U" , "u", "Y", "y"}} , } m["sq"] = { canonicalName = "အလ်ဗနဳယာန်", otherNames = {"Albanian"}, scripts = {"Latn", "Elba"}, family = "sqj", ancestors = {"ine-pro", "sqj-pro"}, sort_key = { from = { '[âãä]', '[ÂÃÄ]', '[êẽë]', '[ÊẼË]', 'ĩ', 'Ĩ', 'õ', 'Õ', 'ũ', 'Ũ', 'ỹ', 'Ỹ', 'ç', 'Ç' }, to = { 'a', 'A', 'e', 'E', 'i', 'I', 'o', 'O', 'u', 'U', 'y', 'Y', 'c', 'C' } } , } m["ss"] = { canonicalName = "သဝါဇြဳ", otherNames = {"Swazi", "Swati"}, scripts = {"Latn"}, family = "bnt-ngu", entry_name = { from = {"[āàáâǎ]", "[ēèéêě]", "[īìíîǐ]", "[ōòóôǒ]", "[ūùúûǔ]", "ḿ", "[ǹńň]", MACRON, ACUTE, GRAVE, CIRC, CARON}, to = {"a" , "e" , "i" , "o" , "u" , "m", "n" }}, ancestors = {"bnt-pro"}, } m["st"] = { canonicalName = "သူထူ", otherNames = {"Sotho", "Sesotho", "Southern Sesotho", "Southern Sotho"}, scripts = {"Latn"}, family = "bnt", } m["su"] = { canonicalName = "သာန်ဓနဳ", otherNames = {"Sundanese"}, scripts = {"Sund", "Latn"}, family = "poz-msa", ancestors = {"map-pro", "poz-pro", "poz-sus-pro", "poz-msa-pro", "osn"}, translit_module = "su-translit", } m["sv"] = { canonicalName = "သွဳဒေန်", otherNames = {"Swedish"}, scripts = {"Latn"}, family = "gmq", ancestors = {"gmq-osw", "gem-pro", "ine-pro"}, sort_key = { from = {"ö", "å", "ä"}, to = {"o", "a", "a"}} , } m["sw"] = { canonicalName = "သဝါတ်ဟဳလဳ", otherNames = {"Swahili", "Settler Swahili", "KiSetla", "KiSettla", "Setla", "Settla", "Kitchen Swahili", "Kihindi", "Indian Swahili", "KiShamba", "Kishamba", "Field Swahili", "Kibabu", "Asian Swahili", "Kimanga", "Arab Swahili", "Kitvita", "Army Swahili"}, scripts = {"Latn", "Arab"}, family = "bnt", sort_key = { from = {"ng'", "^-"}, to = {"ngz"}} , } m["ta"] = { canonicalName = "တမဳလ်", otherNames = {"Tamil"}, scripts = {"Taml"}, family = "dra", ancestors = {"oty"}, translit_module = "ta-translit", override_translit = true, } m["te"] = { canonicalName = "တေလုဂု", otherNames = {"Telugu"}, scripts = {"Telu"}, family = "dra", ancestors = {"dra-pro", "dra-sou-pro", "dra-sdt-pro", "dra-ote"}, translit_module = "te-translit", override_translit = true, } m["tg"] = { canonicalName = "တာဇိက်", otherNames = {"Tajik", "Tadjik", "Tadzhik", "Tajiki", "Tajik Persian"}, scripts = {"Cyrl", "fa-Arab", "Latn"}, family = "ira-wes", ancestors = {"fa"}, translit_module = "tg-translit", override_translit = true, sort_key = { from = {"Ё", "ё"}, to = {"Е" , "е"}} , entry_name = { from = {ACUTE}, to = {}} , } m["th"] = { "သေံ", 9217, family = "tai-swe", scripts = {"Thai", "Brai"}, translit_module = "th-translit", sort_key = { from = {"[%pๆ]", "[็-๎]", "([เแโใไ])([ก-ฮ])"}, to = {"", "", "%2%1"}}, ancestors = {"qfa-tak-pro", "qfa-bet-pro", "tai-pro", "tai-swe-pro"}, } m["ti"] = { canonicalName = "တဳဂျရေဝ်ယျာ", otherNames = {"Tigrinya"}, scripts = {"Ethi"}, family = "sem-eth", translit_module = "Ethi-translit", } m["tk"] = { canonicalName = "တာခ်မေန်", otherNames = {"Turkmen"}, scripts = {"Latn", "Cyrl"}, family = "trk-ogz", entry_name = { from = {"ā", "ē", "ī", "ō", "ū", "ȳ", "ȫ", "ǖ", MACRON}, to = {"a", "e", "i", "o", "u", "y", "ö", "ü", ""}}, } m["tl"] = { canonicalName = "တာဂါလံက်", otherNames = {"Tagalog"}, scripts = {"Latn", "Tglg"}, family = "phi", entry_name = { from = {"[áàâ]", "[éèê]", "[íìî]", "[óòô]", "[úùû]", ACUTE, GRAVE, CIRC}, to = {"a" , "e" , "i" , "o" , "u" }}, translit_module = "tl-translit", override_translit = true } m["tn"] = { canonicalName = "သွာနာ", otherNames = {"Tswana", "Setswana"}, scripts = {"Latn"}, family = "bnt", } m["to"] = { canonicalName = "ထံင်ဂံင်", otherNames = {"Tongan"}, scripts = {"Latn"}, family = "poz-pol", } m["tr"] = { canonicalName = "တူရကဳ", otherNames = {"Turkish"}, scripts = {"Latn"}, family = "trk-ogz", ancestors = {"ota"}, } m["ts"] = { canonicalName = "သွေန်ဂါ", otherNames = {"Tsonga"}, scripts = {"Latn"}, family = "bnt", ancestors = {"nic-pro", "alv-pro", "nic-vco-pro", "nic-bco-pro", "nic-bod-pro", "bnt-pro"}, } m["tt"] = { canonicalName = "တာတာ", otherNames = {"Tatar"}, scripts = {"Cyrl", "Latn", "Arab", "tt-Arab"}, family = "trk-kip", translit_module = "tt-translit", override_translit = true, } -- "tw" IS TREATED AS "ak", SEE WT:LT m["ty"] = { canonicalName = "တဟဳတဳဃှေန်", otherNames = {"Tahitian"}, scripts = {"Latn"}, family = "poz-pol", } m["ug"] = { canonicalName = "ဥူဃူရ်", otherNames = {"Uigur", "Uighur", "Uygur"}, scripts = {"ug-Arab", "Latn", "Cyrl"}, family = "trk", ancestors = {"chg"}, translit_module = "ug-translit", override_translit = true, } m["uk"] = { canonicalName = "ယူကရိန်", otherNames = {"Ukrainian"}, scripts = {"Cyrl"}, family = "zle", ancestors = {"ine-pro", "ine-bsl-pro", "sla-pro", "orv", "zle-ouk"}, translit_module = "uk-translit", entry_name = { from = {"Ѐ", "ѐ", "Ѝ", "ѝ", GRAVE, ACUTE}, to = {"Е", "е", "И", "и"}}, standardChars = "ЄІЇА-ЩЫЬЮ-щыьюяєії" .. PUNCTUATION } m["ur"] = { "အူရဒူ", "Q1617", "inc-hnd", scripts = {"ur-Arab"}, ancestors = {"inc-ohi"}, entry_name = { from = {u(0x064B), u(0x064C), u(0x064D), u(0x064E), u(0x064F), u(0x0650), u(0x0651), u(0x0652)}, to = {}} , } m["uz"] = { canonicalName = "ဥုသဗဝ်", otherNames = {"Uzbek", "Northern Uzbek", "Southern Uzbek"}, scripts = {"Latn", "Cyrl", "fa-Arab"}, family = "trk", ancestors = {"chg"}, translit_module = "uz-translit" } m["ve"] = { canonicalName = "ဗါန်ဒါ", otherNames = {"Venda"}, scripts = {"Latn"}, family = "bnt", } m["vi"] = { canonicalName = "ဗဳယေတ်နာမ်", otherNames = {"Vietnamese", "Annamese", "Annamite"}, scripts = {"Latn", "Hani"}, family = "mkh-vie", ancestors = {"mkh-mvi"}, sort_key = "vi-sortkey", } m["vo"] = { canonicalName = "ဝဝ်လပုက်", otherNames = {"Volapük"}, scripts = {"Latn"}, family = "art", wikipedia_article = "Volapük", } m["wa"] = { canonicalName = "ဝါဠူ", otherNames = {"Walloon", "Liégeois", "Namurois", "Wallo-Picard", "Wallo-Lorrain"}, scripts = {"Latn"}, family = "roa-oil", ancestors = {"fro"}, sort_key = { from = {"[áàâäå]", "[éèêë]", "[íìîï]", "[óòôö]", "[úùûü]", "[ýỳŷÿ]", "ç", "'"}, to = {"a" , "e" , "i" , "o" , "u" , "y" , "c"}} , } m["wo"] = { canonicalName = "ဝဝ်လံက်", otherNames = {"Wolof", "Gambian Wolof"}, -- the subsumed dialect 'wof' scripts = {"Latn", "Arab"}, family = "alv-sng", } m["xh"] = { canonicalName = "ခါဝ်သာ", otherNames = {"Xhosa"}, scripts = {"Latn"}, family = "bnt-ngu", entry_name = { from = {"[āàáâǎ]", "[ēèéêě]", "[īìíîǐ]", "[ōòóôǒ]", "[ūùúûǔ]", "ḿ", "[ǹńň]", MACRON, ACUTE, GRAVE, CIRC, CARON}, to = {"a" , "e" , "i" , "o" , "u" , "m", "n" }}, ancestors = {"bnt-pro"}, } m["yi"] = { canonicalName = "ယိဒ်ဒိသ်", otherNames = {"Yiddish"}, scripts = {"Hebr"}, family = "gmw", ancestors = {"gmh"}, translit_module = "yi-translit", wikipedia_article = "Yiddish", } m["yo"] = { canonicalName = "ရိုရုဗာ", otherNames = {"Yoruba"}, scripts = {"Latn"}, family = "alv-von", ancestors = {"alv-yor-pro", "alv-edk-pro", "alv-yrd-pro"}, } m["za"] = { canonicalName = "ဇြုန်", otherNames = {"Standard Zhuang"}, scripts = {"Latn", "Hani"}, family = "tai", wikipedia_article = "Zhuang languages", } m["zh"] = { canonicalName = "ကြုက်", otherNames = {"Chinese"}, scripts = {"Hani", "Brai"}, family = "sit", ancestors = {"ltc", "sit-pro"}, sort_key = "zh-sortkey", } m["zu"] = { canonicalName = "သြူဠူ", otherNames = {"Zulu", "isiZulu"}, scripts = {"Latn"}, family = "bnt-ngu", entry_name = { from = {"[āàáâǎ]", "[ēèéêě]", "[īìíîǐ]", "[ōòóôǒ]", "[ūùúûǔ]", "ḿ", "[ǹńň]", MACRON, ACUTE, GRAVE, CIRC, CARON}, to = {"a" , "e" , "i" , "o" , "u" , "m", "n" }}, ancestors = {"bnt-pro"}, } return m 2zyx2d98ngk1l7u3yapn4h2ghkwd8x3 103872 103866 2024-11-01T08:59:54Z 咽頭べさ 33 မကလေၚ်ပလီုထောံ[[Special:Diff/103866|103866]]နူကဵု[[Special:Contributions/咽頭べさ|咽頭べさ]] ([[User talk:咽頭べさ|ဓရီုကျာ]])မပလေဝ်ဒါန်လဝ် 103872 Scribunto text/plain local u = mw.ustring.char -- UTF-8 encoded strings for some commonly-used diacritics local GRAVE = u(0x0300) local ACUTE = u(0x0301) local CIRC = u(0x0302) local TILDE = u(0x0303) local MACRON = u(0x0304) local BREVE = u(0x0306) local DOTABOVE = u(0x0307) local DIAER = u(0x0308) local CARON = u(0x030C) local DGRAVE = u(0x030F) local INVBREVE = u(0x0311) local DOTBELOW = u(0x0323) local RINGBELOW = u(0x0325) local CEDILLA = u(0x0327) local OGONEK = u(0x0328) local DOUBLEINVBREVE = u(0x0361) -- Punctuation to be used for standardChars field local PUNCTUATION = ' !#%&*+,-./:;<=>?@^_`|~\'()' local Cyrl = {"Cyrl"} local Latn = {"Latn"} local LatnArab = {"Latn", "Arab"} local m = {} m["aa"] = { canonicalName = "အဖှာင်", otherNames = {"Qafar"}, scripts = {"Latn"}, family = "cus", } m["ab"] = { canonicalName = "အာပ်ဟန်", otherNames = {"Abkhaz", "Abkhazian", "Abxazo"}, scripts = {"Cyrl", "Geor", "Latn"}, family = "cau-abz", translit_module = "ab-translit", override_translit = true, entry_name = { from = {GRAVE, ACUTE}, to = {}} , } m["ae"] = { "အဗါတ်သတေန်", 29572, "ira-cen", scripts = {"Avst", "Gujr"}, translit_module = "Avst-translit", wikipedia_article = "Avestan", } m["af"] = { canonicalName = "အေက်ဖရိကာန်", scripts = {"Latn", "Arab"}, family = "gmw", ancestors = {"nl"}, sort_key = { from = {"[äáâà]", "[ëéêè]", "[ïíîì]", "[öóôò]", "[üúûù]", "[ÿýŷỳ]", "^-", "'"}, to = {"a" , "e" , "i" , "o" , "u" , "y" }} , wikipedia_article = "Afrikaans", } m["ak"] = { canonicalName = "အကာန်", otherNames = {"Akan", "Twi-Fante", "Twi", "Fante", "Fanti", "Asante", "Akuapem"}, scripts = {"Latn"}, family = "alv-kwa", } m["am"] = { canonicalName = "အာန်ဟာရိစ်", otherNames = {"Amharic"}, scripts = {"Ethi"}, family = "sem-eth", translit_module = "Ethi-translit", wikipedia_article = "Amharic", } m["an"] = { canonicalName = "အာဒါဂေန်", otherNames = {"Aragonese"}, scripts = {"Latn"}, family = "roa", ancestors = {"ine-pro", "itc-pro", "itc-ola", "la", "roa-oan"}, } m["ar"] = { canonicalName = "အာရဗဳ", otherNames = {"Modern Standard Arabic", "Standard Arabic", "Literary Arabic", "Classical Arabic", "Arabic", "အာရက်လ်"}, scripts = {"Arab", "Brai"}, family = "sem-arb", -- alif waṣl to alif, remove diacritics entry_name = { from = {u(0x0671), u(0x064B), u(0x064C), u(0x064D), u(0x064E), u(0x064F), u(0x0650), u(0x0651), u(0x0652), u(0x0670), u(0x0640)}, to = {u(0x0627)}}, translit_module = "ar-translit", wikipedia_article = "Arabic", ancestors = {"sem-pro"}, } m["as"] = { canonicalName = "အိသ်ဇြာံမဳ", otherNames ={"Assamese"}, scripts = {"Beng"}, family = "inc", ancestors = {"inc-mgd"}, translit_module = "as-translit", } m["av"] = { "အာဗာ", "Q29561", "cau-nec", aliases = {"Avaric"}, scripts = Cyrl, ancestors = {"oav"}, translit_module = "translit-redirect", override_translit = true, entry_name = { from = {GRAVE, ACUTE}, to = {}} , } m["ay"] = { canonicalName = "အိုင်မာရ", otherNames = {"Aymara", "Southern Aymara", "Central Aymara"}, scripts = {"Latn"}, family = "sai-aym", } m["az"] = { "အာက်သေတ်ဗါဲဇြေနဳ", 9292, "trk-ogz", {"Latn", "Cyrl", "fa-Arab"}, ancestors = {"trk-oat"}, dotted_dotless_i = true, } m["ba"] = { canonicalName = "ဗေတ်ခဳ", otherNames = {"Bashkir"}, scripts = {"Cyrl"}, family = "trk-kip", translit_module = "ba-translit", override_translit = true, } m["be"] = { canonicalName = "ဗါလာရုဇ်", otherNames = {"Belarusian", "Belorussian", "Belarusan", "Bielorussian", "Byelorussian", "Belarussian", "White Russian"}, scripts = {"Cyrl"}, family = "zle", ancestors = {"orv"}, translit_module = "be-translit", sort_key = { from = {"Ё", "ё"}, to = {"Е" , "е"}}, entry_name = { from = {"Ѐ", "ѐ", GRAVE, ACUTE}, to = {"Е", "е"}}, } m["bg"] = { canonicalName = "ဗူလ်ဂရဳယာန်", otherNames = {"Bulgarian"}, scripts = {"Cyrl"}, family = "zls", translit_module = "bg-translit", entry_name = { from = {"Ѐ", "ѐ", "Ѝ", "ѝ", GRAVE, ACUTE}, to = {"Е", "е", "И", "и"}}, } m["bh"] = { canonicalName = "ဘဳဟာရဳ", otherNames = {"Bihari"}, scripts = {"Deva"}, family = "inc", ancestors = {"inc-mgd"}, wikipedia_article = "ဘာသာဘဳဟာရဳ", } m["bi"] = { canonicalName = "ဗဳသလာမာ", otherNames = {"Bislama"}, scripts = {"Latn"}, family = "crp", ancestors = {"ine-pro", "gem-pro", "gmw-pro", "ang", "enm", "en-ear", "en"}, wikipedia_article = "Bislama", } m["bm"] = { canonicalName = "ဗီုဗရာ", otherNames = {"Bamanankan"}, scripts = {"Latn"}, family = "dmn", } m["bn"] = { canonicalName = "ဘင်္ဂါလဳ", otherNames = {"Bangla", "Bengali"}, scripts = {"Beng"}, family = "inc", ancestors = {"inc-mgd"}, translit_module = "bn-translit", } m["bo"] = { canonicalName = "တဳဗဝ်", otherNames = {"Tibetan", "Ü", "Dbus", "Lhasa", "Lhasa Tibetan", "Amdo Tibetan", "Amdo", "Panang", "Khams", "Khams Tibetan", "Khamba", "Tseku", "Dolpo", "Humla", "Limi", "Lhomi", "Shing Saapa", "Mugom", "Mugu", "Nubri", "Walungge", "Gola", "Thudam", "Lowa", "Loke", "Mustang", "Tichurong", "တိဗက်"}, scripts = {"Tibt"}, family = "tbq", ancestors = {"xct"}, translit_module = "bo-translit", override_translit = true, wikipedia_article = "Standard Tibetan", -- may need verification } m["br"] = { canonicalName = "ဗရဳတေန်", otherNames = {"Breton"}, scripts = {"Latn"}, family = "cel-bry", ancestors = {"xbm"}, } m["ca"] = { canonicalName = "ကတလာန်", otherNames = {"Valencian", "Catalan"}, scripts = {"Latn"}, family = "roa", ancestors = {"roa-oca"}, sort_key = { from = {"à", "[èé]", "[íï]", "[òó]", "[úü]", "ç", "l·l"}, to = {"a", "e" , "i" , "o" , "u" , "c", "ll" }} , } m["ce"] = { canonicalName = "ချက်ခ်ချေင်", otherNames = {"Chechen"}, scripts = {"Cyrl", "Latn", "Arab"}, family = "cau-nkh", translit_module = "translit-redirect", override_translit = true, ancestors = {"ccn-pro", "cau-nec-pro", "cau-nkh-pro"}, entry_name = { from = {MACRON}, to = {}}, } m["ch"] = { canonicalName = "ချာမဝ်ရဝ်", otherNames = {"Chamorro", "Chamoru"}, scripts = {"Latn"}, family = "poz-sus", } m["co"] = { canonicalName = "ခဝ်သဳကာန်", otherNames = {"Corsican", "Corsu"}, scripts = {"Latn"}, family = "roa", } m["cr"] = { canonicalName = "ခရေဝ်", scripts = {"Cree", "Cans", "Latn"}, family = "alg", translit_module = "cr-translit", } m["cs"] = { canonicalName = "ချက်ခ်", otherNames = {"Czech"}, scripts = {"Latn"}, family = "zlw", ancestors = {"zlw-ocs", "sla-pro"}, sort_key = { from = {"á", "é", "í", "ó", "[úů]", "ý"}, to = {"a", "e", "i", "o", "u" , "y"}} , } m["cu"] = { "ခရေတ်သလာဗဝ်နေတ်တြေံ", "Q35499", "zls", aliases = {"Old Church Slavic"}, scripts = {"Cyrs", "Glag"}, translit_module = "Cyrs-Glag-translit", ancestors = {"ine-pro", "ine-bsl-pro", "sla-pro"}, entry_name = { from = {u(0x0484)}, -- kamora to = {}}, sort_key = { from = {"оу", "є"}, to = {"у" , "е"}} , } m["cv"] = { "ချူဝါတ်", "Q33348", "trk-ogr", scripts = Cyrl, ancestors = {"xbo"}, translit_module = "cv-translit", sort_key = { from = {"ӑ", "ё", "ӗ", "ҫ", "ӳ"}, to = { "а" .. u(0xF000), "е" .. u(0xF000), "е" .. u(0xF001), "с" .. u(0xF000), "у" .. u(0xF000) } }, override_translit = true, } m["cy"] = { canonicalName = "ဝေလ", otherNames ={"Welsh"}, scripts = {"Latn"}, family = "cel-bry", ancestors = {"wlm"}, sort_key = { from = {"[âáàä]", "[êéèë]", "[îíìï]", "[ôóòö]", "[ûúùü]", "[ŵẃẁẅ]", "[ŷýỳÿ]", "'"}, to = {"a" , "e" , "i" , "o" , "u" , "w" , "y" }} , } m["da"] = { canonicalName = "ဒိန်နေတ်", otherNames ={"Danish"}, scripts = {"Latn"}, family = "gmq", ancestors = {"gmq-oda"}, } m["de"] = { canonicalName = "ဂျာမာန်", otherNames = {"High German", "New High German", "Deutsch", "German", "ဂျာမနဳ"}, scripts = {"Latn", "Latf"}, family = "gmw", ancestors = {"gmh"}, sort_key = { from = {"[äàáâå]", "[ëèéê]", "[ïìíî]", "[öòóô]", "[üùúû]", "ß" }, to = {"a" , "e" , "i" , "o" , "u" , "ss"}} , } m["dv"] = { canonicalName = "ဒိဝေဟဳ", otherNames = {"Dhivehi", "Divehi", "Mahal", "Mahl", "Maldivian"}, scripts = {"Thaa"}, family = "inc", ancestors = {"pmh"}, -- or Helu? translit_module = "dv-translit", override_translit = true, wikipedia_article = "ဘာသာမောဝ်ဒိုက်", } m["dz"] = { canonicalName = "သောင်ခါ", otherNames = {"Dzongkha"}, scripts = {"Tibt"}, family = "tbq", ancestors = {"xct"}, translit_module = "bo-translit", override_translit = true, wikipedia_article = "Dzongkha", } m["ee"] = { canonicalName = "အဳဝါ", otherNames = {"Ewe"}, scripts = {"Latn"}, family = "alv-von", } m["el"] = { canonicalName = "ဂရေတ်", otherNames = {"Greek", "Modern Greek", "Neo-Hellenic"}, scripts = {"Grek", "Brai", "Polyt", "Latn"}, family = "grk", ancestors = {"ine-pro", "grk-pro", "grc-att", "grc-koi", "gkm-med", "el-kth", "grc"}, translit_module = "el-translit", override_translit = true, sort_key = { -- Keep this synchronized with grc, cpg, pnt from = {"[ᾳάᾴὰᾲᾶᾷἀᾀἄᾄἂᾂἆᾆἁᾁἅᾅἃᾃἇᾇ]", "[έὲἐἔἒἑἕἓ]", "[ῃήῄὴῂῆῇἠᾐἤᾔἢᾒἦᾖἡᾑἥᾕἣᾓἧᾗ]", "[ίὶῖἰἴἲἶἱἵἳἷϊΐῒῗ]", "[όὸὀὄὂὁὅὃ]", "[ύὺῦὐὔὒὖὑὕὓὗϋΰῢῧ]", "[ῳώῴὼῲῶῷὠᾠὤᾤὢᾢὦᾦὡᾡὥᾥὣᾣὧᾧ]", "ῥ", "ς"}, to = {"α" , "ε" , "η" , "ι" , "ο" , "υ" , "ω" , "ρ", "σ"}} , standardChars = "ͺ;΄-ώϜϝ" .. PUNCTUATION .. "ἀ-῾" } m["en"] = { canonicalName = "အင်္ဂလိက်", otherNames = {"English", "Modern English", "New English", "Hawaiian Creole English", "Hawai'ian Creole English", "Hawaiian Creole", "Hawai'ian Creole", "Polari", "Yinglish"}, -- all but the first three are names of subsumed dialects which once had codes scripts = {"Latn", "Brai", "Shaw", "Dsrt"}, -- entries in Shaw or Dsrt might require prior discussion family = "gmw", ancestors = {"enm"}, wikipedia_article = "ဘာသာအင်္ဂလိက်", sort_key = { from = {"[äàáâåā]", "[ëèéêē]", "[ïìíîī]", "[öòóôō]", "[üùúûū]", "æ" , "œ" , "[çč]", "ñ", "['9]", "1", "[23]", "[45]", "[67]", "0", "+", "."}, to = {"a" , "e" , "i" , "o" , "u" , "ae", "oe", "c" , "n" , "o" , "t" , "s" , "z" , "p" , "q"}}, wikimedia_codes = {"en", "simple"}, standardChars = "A-Za-z0-9" .. PUNCTUATION .. u(0x2800) .. "-" .. u(0x28FF) } m["eo"] = { canonicalName = "အေက်သပရေန်တဝ်", otherNames = {"Esperanto"}, scripts = {"Latn"}, family = "art", sort_key = { from = {"[áà]", "[éè]", "[íì]", "[óò]", "[úù]", "[ĉ]", "[ĝ]", "[ĥ]", "[ĵ]", "[ŝ]", "[ŭ]"}, to = {"a" , "e" , "i" , "o" , "u", "cĉ", "gĉ", "hĉ", "jĉ", "sĉ", "uĉ"}} , wikipedia_article = "Esperanto", } m["es"] = { "သပုင်", 1321, "roa-ibe", {"Latn", "Brai"}, ancestors = {"ine-pro", "itc-pro", "itc-ola", "la", "osp"}, sort_key = { from = {"á", "é", "í", "ó", "[úü]", "ç", "ñ"}, to = {"a", "e", "i", "o", "u" , "c", "n"}}, standardChars = "A-VXYZa-vxyz0-9ÁáÉéÍíÓóÚúÑñ¿¡" .. PUNCTUATION, } m["et"] = { canonicalName = "အေက်သတဝ်နဳယာန်", otherNames = {"Estonian"}, scripts = {"Latn"}, family = "urj-fin", } m["eu"] = { canonicalName = "ဗက်ခ်", otherNames = {"Basque", "Euskara"}, scripts = {"Latn"}, family = "euq", } m["fa"] = { canonicalName = "ပါရှေန်", otherNames = {"ပါရှာ", "ဖာသဳ", "ဖာစဳ", "Persian", "Farsi", "New Persian", "Modern Persian", "Western Persian", "Iranian Persian", "Eastern Persian", "Dari", "Aimaq", "Aimak", "Aymaq", "Eimak"}, scripts = {"fa-Arab"}, family = "ira-wes", ancestors = {"pal", "ira-pro", "iir-pro", "ine-pro"}, entry_name = { from = {u(0x064E), u(0x064F), u(0x0650), u(0x0651), u(0x0652)}, to = {}} , } m["ff"] = { canonicalName = "ဖှောတ်လာ", otherNames = {"Fula", "Adamawa Fulfulde", "Bagirmi Fulfulde", "Borgu Fulfulde", "Central-Eastern Niger Fulfulde", "Fulani", "Fulfulde", "Maasina Fulfulde", "Nigerian Fulfulde", "Pular", "Pulaar", "Western Niger Fulfulde"}, -- Maasina, etc are dialects, subsumed into this code scripts = {"Latn"}, family = "alv-sng", } m["fi"] = { "ဖေန်လာန်", "Q1412", "urj-fin", aliases = {"Suomi"}, scripts = Latn, entry_name = { from = {"ˣ"}, -- Used to indicate gemination of the next consonant to = {}}, sort_key = { from = {"[áàâã]", "[éèêẽ]", "[íìîĩ]", "[óòôõ]", "[úùûũ]", "[ýỳŷüű]", "[øõő]", "æ" , "œ" , "[čç]", "š", "ž", "ß" , "[':]"}, to = {"a" , "e" , "i" , "o" , "u" , "y" , "ö" , "ae", "oe", "c" , "s", "z", "ss"}} , } m["fj"] = { canonicalName = "ဖရဳဂျိ", otherNames = {"Fijian"}, scripts = {"Latn"}, family = "poz-occ", } m["fo"] = { canonicalName = "ဖာရဝ်သဳ", otherNames = {"Faroese"}, scripts = {"Latn"}, family = "gmq", ancestors = {"non"}, } m["fr"] = { canonicalName = "ပြင်သေတ်", otherNames = {"French", "Modern French"}, scripts = {"Latn", "Brai"}, family = "roa-oil", ancestors = {"frm", "la"}, sort_key = { from = {"[áàâä]", "[éèêë]", "[íìîï]", "[óòôö]", "[úùûü]", "[ýỳŷÿ]", "ç", "æ" , "œ" , "'"}, to = {"a" , "e" , "i" , "o" , "u" , "y" , "c", "ae", "oe"}}, standardChars = "A-Za-z0-9ÀÂÇÉÈÊËÎÏÔŒÛÙÜàâçéèêëîïôœûùü«»" .. PUNCTUATION } m["fy"] = { canonicalName = "ဖရေဝ်သဳယာန်လက္ကရဴ", otherNames = {"West Frisian", "Western Frisian", "Frisian"}, scripts = {"Latn"}, family = "gmw-fri", ancestors = {"ofs"}, } m["ga"] = { canonicalName = "အာဲယျာလာန်", otherNames = {"Irish", "Irish Gaelic", "အိုင်ရစ်ရှ်"}, scripts = {"Latn"}, family = "cel-gae", ancestors = {"mga"}, sort_key = { from = {"á", "é", "í", "ó", "ú", "ý", "ḃ" , "ċ" , "ḋ" , "ḟ" , "ġ" , "ṁ" , "ṗ" , "ṡ" , "ṫ" }, to = {"a", "e", "i", "o", "u", "y", "bh", "ch", "dh", "fh", "gh", "mh", "ph", "sh", "th"}} , } m["gd"] = { canonicalName = "သကတ်ဂဴလိစ်", otherNames = {"Scottish Gaelic", "Gàidhlig", "Highland Gaelic", "Scots Gaelic", "Scottish"}, scripts = {"Latn"}, family = "cel-gae", ancestors = {"mga"}, sort_key = { from = {"[áà]", "[éè]", "[íì]", "[óò]", "[úù]", "[ýỳ]"}, to = {"a" , "e" , "i" , "o" , "u" , "y" }} , wikipedia_article = "Scottish Gaelic", } m["gl"] = { canonicalName = "ဂလဳသဳယာန်", otherNames = {"Galician"}, scripts = {"Latn"}, family = "roa", ancestors = {"ine-pro", "itc-pro", "inc-pro", "itc-ola", "la", "roa-opt"}, sort_key = { from = {"á", "é", "í", "ó", "ú"}, to = {"a", "e", "i", "o", "u"}} , } m["gn"] = { canonicalName = "ဂူရာန်နဳ", otherNames = {"Guaraní"}, scripts = {"Latn"}, family = "tup-gua", wikipedia_article = "ဘာသာဂူရာန်နဳ", } m["gu"] = { canonicalName = "ဂုဂျာရတဳ", otherNames = {"Gujarati"}, scripts = {"Gujr"}, family = "inc", ancestors = {"inc-ogu"}, translit_module = "gu-translit", } m["gv"] = { canonicalName = "မာက်", otherNames = {"Manx", "Manx Gaelic"}, scripts = {"Latn"}, family = "cel-gae", ancestors = {"mga"}, sort_key = { from = {"ç", "-"}, to = {"c"}} , } m["ha"] = { canonicalName = "ဟဴသာ", otherNames = {"Hausa"}, scripts = {"Latn", "Arab"}, family = "cdc-wst", sort_key = { from = {"ɓ", "ɗ", "ƙ", "'y", "ƴ", "'" }, to = {"b~" , "d~" , "k~", "y~", "y~", "" }}, entry_name = { from = {"R̃", "r̃", "À", "à", "È", "è", "Ì", "ì", "Ò", "ò", "Ù", "ù", "Â", "â", "Ê", "ê", "Î", "î", "Ô", "ô", "Û", "û", "Ā", "ā", "Ē", "ē", "Ī", "ī", "Ō", "ō", "Ū", "ū", "Á", "á", "É", "é", "Í", "í", "Ó", "ó", "Ú", "ú", "Ā̀", "ā̀", "Ḕ", "ḕ", "Ī̀", "ī̀", "Ṑ", "ṑ", "Ū̀", "ū̀", GRAVE, ACUTE}, to = {"R", "r", "A", "a", "E", "e", "I", "i", "O", "o", "U", "u", "A", "a", "E", "e", "I", "i", "O", "o", "U", "u", "A", "a", "E", "e", "I", "i", "O", "o", "U", "u", "A", "a", "E", "e", "I", "i", "O", "o", "U", "u", "A", "a", "E", "e", "I", "i", "O", "o", "U", "u"}}, } m["he"] = { canonicalName = "ဟဳဘရဝ်", otherNames = {"Hebrew", "Ivrit"}, scripts = {"Hebr", "Phnx", "Brai"}, family = "sem-can", ancestors = {"afa-pro", "sem-pro", "sem-wes-pro", "hbo", "he-mis", "he-med"}, translit_module = "he-translit", entry_name = { from = {"[" .. u(0x0591) .. "-" .. u(0x05BD) .. u(0x05BF) .. "-" .. u(0x05C5) .. u(0x05C7) .. "]"}, to = {}} , } m["hi"] = { canonicalName = "ဟိန္ဒဳ", otherNames = {"ဟိန္ဒဳ", "Hindi", "Braj", "Brij Bhasha", "Braj Bhasha", "Braj Bhāshā", "Braj Bhakha", "Dehaati Zabaan"}, scripts = {"Deva", "Guru"}, -- Guru for the subsumed variety Braj family = "inc-hnd", ancestors = {"inc-ohi"}, translit_module = "hi-translit", wikipedia_article = "Hindi", } m["ho"] = { canonicalName = "ဟဳရဳမိုတု", otherNames = {"Hiri Motu", "Pidgin Motu", "Police Motu"}, scripts = {"Latn"}, family = "crp", ancestors = {"meu"}, wikipedia_article = "Hiri Motu", } m["ht"] = { "ဟေဲယှေန် ခရေဝ်အဝ်လ်", 33491, "crp", Latn, ancestors = {"fr"}, } m["hu"] = { canonicalName = "ဟာန်ဂါရေဝ်", otherNames = {"Hungarian", "Magyar"}, scripts = {"Latn", "Hung"}, family = "urj-ugr", ancestors = {"urj-pro", "urj-ugr-pro", "ohu"}, sort_key = { from = {"é", "í", "ó", "ú", "ő", "ö", "ü", "á"}, to = {"e", "i", "o", "u", "o", "o", "u", "a"}} , } m["hy"] = { canonicalName = "အာမေနဳယျာ", otherNames = {"Armenian", "Modern Armenian", "Eastern Armenian", "Western Armenian", "အမေရိကာန်ဗၟံက်", "အမေရိကာန်ပလိုတ်", "အမေရိကာန်အခေတ်တၟိ"}, scripts = {"Armn", "Brai"}, family = "hyx", ancestors = {"axm"}, translit_module = "Armn-translit", override_translit = true, sort_key = { from = {"ու", "և", "եւ"}, to = {"ւ", "եվ", "եվ"}}, entry_name = { from = {"՞", "՜", "՛", "՟", "և", "<sup>յ</sup>", "<sup>ի</sup>"}, to = {"", "", "", "", "եւ", "յ", "ի"}} , } m["hz"] = { canonicalName = "ဟဳရဲရို", otherNames = {"Herero"}, scripts = {"Latn"}, family = "bnt", } m["ia"] = { canonicalName = "အေန်တာလိင်ဂဝ်", otherNames = {"Interlingua"}, scripts = {"Latn"}, family = "art", wikipedia_article = "Interlingua", } m["id"] = { canonicalName = "အိန်ဒဝ်နဳသဳယျာ", otherNames = {"Indonesian"}, scripts = {"Latn"}, family = "poz-mly", ancestors = {"map-pro", "poz-pro", "poz-sus-pro", "poz-msa-pro", "poz-mcm-pro", "poz-mly-pro", "ms-old", "ms-cla", "ms"}, } m["ie"] = { canonicalName = "အေန်တာလိင်ဂဝေ", otherNames = {"Interlingue", "Occidental"}, scripts = {"Latn"}, family = "art", wikipedia_article = "Occidental language", } m["ig"] = { canonicalName = "အေတ်ဗါဝ်", otherNames = {"Igbo", "အစ္ဂဘို"}, scripts = {"Latn"}, family = "nic-bco", } m["ii"] = { canonicalName = "သေဲဆိုန်ယဳ", otherNames = {"Sichuan Yi", "Nuosu", "Nosu", "Northern Yi", "Liangshan Yi"}, scripts = {"Yiii"}, family = "tbq-lol", wikipedia_article = "Nuosu language", translit_module = "ii-translit", override_translit = true, } m["ik"] = { canonicalName = "အဳနုဗဳယာတ်", otherNames = {"Inupiak", "Inupiaq", "Iñupiaq", "Inupiatun"}, scripts = {"Latn"}, family = "esx-inu", wikipedia_article = "Inupiaq", } m["io"] = { canonicalName = "ဣဒဝ်", otherNames = {"Ido"}, scripts = {"Latn"}, family = "art", } m["is"] = { canonicalName = "အာက်သလာန်", otherNames = {"Icelandic", "အာက်သလာန်"}, scripts = {"Latn"}, family = "gmq", ancestors = {"non", "gem-pro", "ine-pro"}, sort_key = { from = {"ð", "ö", "ó", "æ", "á", "í", "ú"}, to = {"o", "o", "o", "ae", "a", "i", "u"}} , } m["it"] = { canonicalName = "အဳတခ်လဳ", otherNames = {"Italian"}, scripts = {"Latn"}, family = "roa", sort_key = { from = {"[àáâäå]", "[èéêë]", "[ìíîï]", "[òóôö]", "[ùúûü]"}, to = {"a" , "e" , "i" , "o" , "u" }} , } m["iu"] = { canonicalName = "ဣနုက်တိတုတ်", otherNames = {"Inuktitut", "Eastern Canadian Inuktitut", "Eastern Canadian Inuit", "Western Canadian Inuktitut", "Western Canadian Inuit", "Western Canadian Inuktun", "Inuinnaq", "Inuinnaqtun", "Inuvialuk", "Inuvialuktun", "Nunavimmiutit", "Nunatsiavummiut", "Aivilimmiut", "Natsilingmiut", "Kivallirmiut", "Siglit", "Siglitun"}, scripts = {"Cans", "Latn"}, family = "esx-inu", translit_module = "iu-translit", override_translit = true, wikipedia_article = "Inuktitut", } m["ja"] = { canonicalName = "ဂျပါန်", otherNames = {"Japanese", "Modern Japanese", "Nipponese", "Nihongo"}, scripts = {"Jpan", "Latn", "Hira", "Brai"}, family = "jpx", ancestors = {"ojp"}, --[[ sort_key = { from = {"[ぁァア]", "[ぃィイ]", "[ぅゔゥウヴ]", "[ぇェエ]", "[ぉォオ]", "[がゕカガヵ]", "[ぎキギ]", "[ぐクグㇰ]", "[げゖケゲヶ]", "[ごコゴ]", "[ざサザ]", "[じシジㇱ]", "[ずスズㇲ]", "[ぜセゼ]", "[ぞソゾ]", "[だタダ]", "[ぢチヂ]", "[っづッツヅ]", "[でテデ]", "[どトドㇳ]", "ナ", "ニ", "[ヌㇴ]", "ネ", "ノ", "[ばぱハバパㇵ]", "[びぴヒビピㇶ]", "[ぶぷフブプㇷ]", "[べぺヘベペㇸ]", "[ぼぽホボポㇹ]", "マ", "ミ", "[ムㇺ]", "メ", "モ", "[ゃャヤ]", "[ゅュユ]", "[ょョヨ]", "[ラㇻ]", "[リㇼ]", "[ルㇽ]", "[レㇾ]", "[ロㇿ]", "[ゎヮワヷ]", "[ヰヸ]", "[ヱヹ]", "[ヲヺ]", "ン", "[゙゚゛゜ゝゞ・ヽヾ]", "𛀀", "1", "2", "3", "4", "5", "6", "7", "8", "9", "0"}, to = {"あ", "い", "う", "え", "お", "か", "き", "く", "け", "こ", "さ", "し", "す", "せ", "そ", "た", "ち", "つ", "て", "と", "な", "に", "ぬ", "ね", "の", "は", "ひ", "ふ", "へ", "ほ", "ま", "み", "む", "め", "も", "や", "ゆ", "よ", "ら", "り", "る", "れ", "ろ", "わ", "ゐ", "ゑ", "を", "ん", "", "え", "い", "に", "み", "よ", "ご", "ろ", "な", "は", "き", "れ"}}, ]] } m["jv"] = { canonicalName = "ဂျာဗာ", otherNames = {"Javanese"}, scripts = {"Latn", "Java"}, family = "poz-sus", translit_module = "jv-translit", ancestors = {"kaw"}, link_tr = true, } m["ka"] = { canonicalName = "ဂျဝ်ဂျဳယျာ", otherNames = {"Georgian", "Kartvelian", "Judeo-Georgian", "Kivruli", "Gruzinic"}, scripts = {"Geor", "Geok", "Hebr"}, -- Hebr is used to write Judeo-Georgian family = "ccs-gzn", ancestors = {"oge"}, translit_module = "Geor-translit", override_translit = true, entry_name = { from = {"̂"}, to = {""}}, } m["kg"] = { canonicalName = "ခါမ်ဂဝ်", otherNames = {"Kongo", "Kikongo", "Koongo", "Laari", "San Salvador Kongo", "Yombe"}, scripts = {"Latn"}, family = "bnt", } m["ki"] = { canonicalName = "ခဳခူယူ", otherNames = {"Kikuyu", "Gikuyu", "Gĩkũyũ"}, scripts = {"Latn"}, family = "bnt", } m["kj"] = { canonicalName = "ကောန်ယာမာ", otherNames = {"Kwanyama", "Kuanyama", "Oshikwanyama"}, scripts = {"Latn"}, family = "bnt", wikipedia_article = "Kwanyama dialect", } m["kk"] = { canonicalName = "ကဇက်", scripts = {"Kazakh", "Cyrl", "Latn", "Arab", "kk-Arab"}, family = "trk-kip", ancestors = {"trk-pro"}, translit_module = "kk-translit", override_translit = true, } m["kl"] = { canonicalName = "ဂရိန်လာန်", otherNames = {"Greenlandic", "Kalaallisut"}, scripts = {"Latn"}, family = "esx-inu", } m["km"] = { "ခမေန်", "Q9205", family = "mkh-kmr", aliases = {"Khmer", "Cambodian"}, scripts = {"Khmr"}, ancestors = {"aav-pro", "mkh-pro", "mkh-kmr-pro", "okz", "xhm"}, translit_module = "km-translit", } m["kn"] = { canonicalName = "ကာန်နဒါ", otherNames = {"Kannada", "ကန္နာဒါ"}, scripts = {"Knda"}, family = "dra", translit_module = "kn-translit", wikipedia_article = "Kannada", ancestors = {"dra-mkn"}, } m["ko"] = { "ကိုဝ်ရဳယျာ", "Q9176", "qfa-kor", aliases = {"Korean", "Modern Korean"}, scripts = {"Kore", "Brai"}, ancestors = {"ko-ear"}, -- 20210122 trial idea: strip parenthesized hanja from entry link -- Hani regex is a reasonable subset of Hani from [[Module:scripts/data]], -- last updated on 20210203. entry_name = { from = { "%([一-鿿㐀-䶿𠀀-𮯯"..u(0x2F800).."-𯨟𰀀-𱍏﨎﨏﨑﨓﨔﨟﨡﨣﨤﨧﨨﨩]+%)", }, to = { "", }}, translit_module = "ko-translit", } m["kr"] = { canonicalName = "ကနူရဳ", otherNames = {"Kanuri", "Kanembu", "Bilma Kanuri", "Central Kanuri", "Manga Kanuri", "Tumari Kanuri"}, scripts = {"Latn", "Arab"}, family = "ssa-sah", sort_key = { from = {"ny", "ǝ", "sh"}, to = {"n~", "e~", "s~"}} , -- the sortkey and entry_name are only for standard Kanuri; when dialectal entries get added, someone will have to work out how the dialects should be represented orthographically entry_name = { from = {"À", "à", "È", "è", "Ǝ̀", "ǝ̀", "Ì", "ì", "Ò", "ò", "Ù", "ù", "Â", "â", "Ê", "ê", "Ǝ̂", "ǝ̂", "Î", "î", "Ô", "ô", "Û", "û", "Ă", "ă", "Ĕ", "ĕ", "Ǝ̆", "ǝ̆", "Ĭ", "ĭ", "Ŏ", "ŏ", "Ŭ", "ŭ", "Á", "á", "É", "é", "Ǝ́", "ǝ́", "Í", "í", "Ó", "ó", "Ú", "ú", GRAVE, ACUTE}, to = {"A", "a", "E", "e", "Ǝ", "ǝ", "I", "i", "O", "o", "U", "u", "A", "a", "E", "e", "Ǝ", "ǝ", "I", "i", "O", "o", "U", "u", "A", "a", "E", "e", "Ǝ", "ǝ", "I", "i", "O", "o", "U", "u", "A", "a", "E", "e", "Ǝ", "ǝ", "I", "i", "O", "o", "U", "u"}}, } m["ks"] = { "ကာဒ်ရှ်မဳယျာ", 33552, "inc-dar", {"ks-Arab", "Deva", "Shrd", "Latn"}, translit_module = "translit-redirect", ancestors = {"sa"}, } m["ku"] = { canonicalName = "ကာဒဳ", otherNames = {"Kurdish"}, scripts = {"Latn", "ku-Arab", "Armn", "Cyrl"}, family = "ira-wes", wikipedia_article = "Kurdish languages", } -- "kv" IS TREATED AS "koi", "kpv", SEE WT:LT m["kw"] = { canonicalName = "ခမ်နေတ်", otherNames = {"Cornish"}, scripts = {"Latn"}, family = "cel-bry", ancestors = {"ine-pro", "cel-pro", "cel-bry-pro", "oco", "cnx"}, } m["ky"] = { canonicalName = "ကာဇေတ်", otherNames = {"Kyrgyz", "Kirghiz", "Kirgiz"}, scripts = {"Cyrl", "Latn", "Arab"}, family = "trk-kip", translit_module = "ky-translit", override_translit = true, ancestors = {"trk-pro", "qwm"}, } m["la"] = { canonicalName = "လပ်တေန်", otherNames = {"Latin"}, scripts = {"Latn"}, family = "itc", ancestors = {"itc-ola"}, entry_name = { from = {"[ĀĂ]", "[āă]", "[ĒĔ]", "[ēĕë]", "[ĪĬÏ]", "[īĭï]", "[ŌŎ]", "[ōŏ]", "[ŪŬÜ]", "[ūŭü]", "Ȳ", "ȳ", MACRON, BREVE, DIAER}, to = {"A", "a", "E", "e", "I", "i", "O", "o", "U", "u", "Y", "y"}}, wikipedia_article = "Latin", standardChars = "A-Za-zÆæŒœĀ-ăĒ-ĕĪ-ĭŌ-ŏŪ-ŭȲȳ" .. MACRON .. BREVE .. PUNCTUATION } m["lb"] = { canonicalName = "လူဇေန်ဘာဂျ်", otherNames = {"Luxembourgish"}, scripts = {"Latn"}, family = "gmw", ancestors = {"gmh"}, wikipedia_article = "Luxembourgish", } m["lg"] = { canonicalName = "လုဂန်ဒါ", otherNames = {"ဂန်ဒါ", "Luganda", "Ganda", "Oluganda"}, scripts = {"Latn"}, family = "bnt", entry_name = { from = {"á", "Á", "é", "É", "í", "Í", "ó", "Ó", "ú", "Ú", "ń", "Ń", "ḿ", "Ḿ", "â", "Â", "ê", "Ê", "î", "Î", "ô", "Ô", "û", "Û" }, to = {"a", "A", "e", "E", "i", "I", "o", "O", "u", "U", "n", "N", "m", "M", "a", "A", "e", "E", "i", "I", "o", "O", "u", "U",}}, sort_key = { from = {"ŋ"}, to = {"n"}} , wikipedia_article = "Luganda", } m["li"] = { canonicalName = "လိမ်ဗူရ်ဂိသ်", otherNames = {"Limburgish", "Limburgan", "Limburgian", "Limburgic"}, scripts = {"Latn"}, family = "gmw", ancestors = {"dum"}, } m["ln"] = { canonicalName = "လေန်ဂါလာ", otherNames = {"Lingala", "Ngala"}, scripts = {"Latn"}, family = "bnt", wikipedia_article = "Lingala", } m["lo"] = { canonicalName = "သေံလဴ", otherNames = {"သေံလဴ", "Lao", "Laotian"}, scripts = {"Laoo"}, family = "tai-swe", translit_module = "lo-translit", sort_key = { from = {"ຼ", "ຽ", "ໜ", "ໝ", "([ເແໂໃໄ])([ກ-ຮ])"}, to = {"ລ", "ຍ", "ຫນ", "ຫມ", "%2%1"}}, ancestors = {"qfa-tak-pro", "qfa-bet-pro", "tai-pro", "tai-swe-pro"}, } m["lt"] = { canonicalName = "လေတ်တူယဵုနဳယျာ", otherNames = {"Lithuanian", "လေတ်တူယဵုနဳယျာ"}, scripts = {"Latn"}, family = "bat", ancestors = {"ine-pro", "ine-bsl-pro", "bat-pro", "olt"}, entry_name = { from = {"[áãà]", "[ÁÃÀ]", "[éẽè]", "[ÉẼÈ]", "[íĩì]", "[ÍĨÌ]", "[ýỹ]", "[ÝỸ]", "ñ", "[óõò]", "[ÓÕÒ]", "[úũù]", "[ÚŨÙ]", ACUTE, GRAVE, TILDE}, to = {"a", "A", "e", "E", "i", "I", "y", "Y", "n", "o", "O", "u", "U"}} , } m["lu"] = { canonicalName = "ဠူဘ-ကာတေန်ဂါ", scripts = {"Latn"}, family = "bnt", } m["lv"] = { canonicalName = "လပ်ဗဳယာ", otherNames = {"Latvian", "Lettish", "Lett"}, scripts = {"Latn"}, family = "bat", ancestors = {"ine-bsl-pro", "bat-pro"}, entry_name = { -- This attempts to convert vowels with tone marks to vowels either with -- or without macrons. Specifically, there should be no macrons if the -- vowel is part of a diphthong (including resonant diphthongs such -- pìrksts -> pirksts not #pīrksts). What we do is first convert the -- vowel + tone mark to a vowel + tilde in a decomposed fashion, -- then remove the tilde in diphthongs, then convert the remaining -- vowel + tilde sequences to macroned vowels, then delete any other -- tilde. We leave already-macroned vowels alone: Both e.g. ar and ār -- occur before consonants. FIXME: This still might not be sufficient. from = {"Ȩ", "ȩ", "[ÂÃÀ]", "[âãà]", "[ÊẼÈ]", "[êẽè]", "[ÎĨÌ]", "[îĩì]", "[ÔÕÒ]", "[ôõò]", "[ÛŨÙ]", "[ûũù]", "[ÑǸ]", "[ñǹ]", "[" .. CIRC .. TILDE ..GRAVE .."]", "([aAeEiIoOuU])" .. TILDE .."?([lrnmuiLRNMUI])" .. TILDE .. "?([^aAeEiIoOuUāĀēĒīĪūŪ])", "([aAeEiIoOuU])" .. TILDE .."?([lrnmuiLRNMUI])" .. TILDE .."?$", "([iI])" .. TILDE .. "?([eE])" .. TILDE .. "?", "A" .. TILDE, "a" .. TILDE, "E" .. TILDE, "e" .. TILDE, "I" .. TILDE, "i" .. TILDE, "U" .. TILDE, "u" .. TILDE, TILDE}, to = {"E", "e", "A" .. TILDE, "a" .. TILDE, "E" .. TILDE, "e" .. TILDE, "I" .. TILDE, "i" .. TILDE, "O", "o", "U" .. TILDE, "u" .. TILDE, "N", "n", TILDE, "%1%2%3", "%1%2", "%1%2", "Ā", "ā", "Ē", "ē", "Ī", "ī", "Ū", "ū", ""}}, } m["mg"] = { canonicalName = "မာလာဂါသဳ", otherNames = {"Malagasy", "Betsimisaraka Malagasy", "Betsimisaraka", "Northern Betsimisaraka Malagasy", "Northern Betsimisaraka", "Southern Betsimisaraka Malagasy", "Southern Betsimisaraka", "Bara Malagasy", "Bara", "Masikoro Malagasy", "Masikoro", "Antankarana", "Antankarana Malagasy", "Plateau Malagasy", "Sakalava", "Tandroy Malagasy", "Tandroy", "Tanosy", "Tanosy Malagasy", "Tesaka", "Tsimihety", "Tsimihety Malagasy", "Bushi", "Shibushi", "Kibushi", "Sakalava"}, scripts = {"Latn"}, family = "poz-bre", } m["mh"] = { canonicalName = "မာချဲလဳ", otherNames = {"Marshallese"}, scripts = {"Latn"}, family = "poz-mic", sort_key = { from = {"ā" , "ļ" , "m̧" , "ņ" , "n̄" , "o̧" , "ō" , "ū" }, to = {"a~", "l~", "m~", "n~", "n~~", "o~", "o~~", "u~"}} , } m["mi"] = { canonicalName = "မဝ်ရဳ", otherNames = {"Maori", "Māori"}, scripts = {"Latn"}, family = "poz-pol", wikipedia_article = "Māori language", sort_key = { from = {"ā" , "ļ" , "m̧" , "ņ" , "n̄" , "o̧" , "ō" , "ū" }, to = {"a~", "l~", "m~", "n~", "n~~", "o~", "o~~", "u~"}} , } m["mk"] = { canonicalName = "မက်သဳဒဝ်နဳယျာ", otherNames = {"Macedonian"}, scripts = {"Cyrl"}, family = "zls", translit_module = "mk-translit", ancestors = {"ine-pro", "ine-bsl-pro", "sla-pro"}, entry_name = { from = {ACUTE}, to = {}}, } m["ml"] = { canonicalName = "မလေဝ်ယျလာမ်", otherNames = {"Malayalam"}, scripts = {"Mlym"}, family = "dra", translit_module = "ml-translit", override_translit = true, wikipedia_article = "Malayalam", } m["mn"] = { canonicalName = "မန်ဂဝ်လဳယျာ", otherNames = {"မန်ဂဝ်လဳယျာ", "ခန်ခါ မန်ဂဝ်လဳယျာ"}, scripts = {"Cyrl", "Mong", "Soyo", "Zanb"}, -- entries in Soyo or Zanb might require prior discussion family = "xgn", ancestors = {"cmg"}, translit_module = "mn-translit", override_translit = true, } -- "mo" IS TREATED AS "ro", SEE WT:LT m["mr"] = { canonicalName = "မာရဒဳ", otherNames = {"Marathi"}, scripts = {"Deva", "Modi"}, family = "inc", ancestors = {"omr"}, translit_module = "hi-translit", } m["ms"] = { canonicalName = "မလေဝ်", otherNames = {"Malay", "Malaysian", "Standard Malay", "Orang Seletar", "Orang Kanaq", "Jakun", "Temuan"}, scripts = {"Latn", "ms-Arab"}, family = "poz-mly", ancestors = {"map-pro", "poz-pro", "poz-sus-pro", "poz-msa-pro", "poz-mcm-pro", "poz-mly-pro", "ms-old", "ms-cla"}, } m["mt"] = { canonicalName = "မာလ်တဳ", otherNames = {"Maltese"}, scripts = {"Latn"}, family = "sem-arb", ancestors = {"sqr"}, } m["my"] = { canonicalName = "ဗၟာ", otherNames = {"Burmese", "Myanmar", "ဗၟာ"}, scripts = {"Mymr"}, family = "tbq-brm", ancestors = {"obr", "sit-pro", "tbq-pro"}, wikipedia_article = "ဘာသာဗၟာ", translit_module = "my-translit", override_translit = true, } m["na"] = { canonicalName = "နာဥူလောန်", otherNames = {"Nauruan","Nauru"}, scripts = {"Latn"}, family = "poz-mic", } m["nb"] = { canonicalName = "နဝ်ဝေ ဗော်ခ်မဝ်", otherNames = {"Norwegian Bokmål", "Bokmål"}, scripts = {"Latn"}, family = "gmq", ancestors = {"gmq-mno", "gem-pro"}, wikimedia_codes = {"no"}, wikipedia_article = "Bokmål", } m["nd"] = { canonicalName = "Northern Ndebele", otherNames = {"North Ndebele"}, scripts = {"Latn"}, family = "bnt-ngu", entry_name = { from = {"[āàáâǎ]", "[ēèéêě]", "[īìíîǐ]", "[ōòóôǒ]", "[ūùúûǔ]", "ḿ", "[ǹńň]", MACRON, ACUTE, GRAVE, CIRC, CARON}, to = {"a" , "e" , "i" , "o" , "u" , "m", "n" }}, } m["ne"] = { "နဳပဝ်", 33823, "inc-pah", scripts = {"Deva", "Newa"}, ancestors = {"ine-pro", "iir-pro", "inc-pro", "sa", "inc-ash", "pra-kha"}, translit_module = "ne-translit", } m["ng"] = { canonicalName = "အွန်ဒွန်ဂါ", otherNames = {"Ndonga"}, scripts = {"Latn"}, family = "bnt", wikipedia_article = "Ndonga dialect", } m["nl"] = { canonicalName = "ဒါတ်", otherNames = {"Dutch", "Netherlandic", "Flemish"}, scripts = {"Latn"}, family = "gmw", ancestors = {"dum"}, sort_key = { from = {"[äáâå]", "[ëéê]", "[ïíî]", "[öóô]", "[üúû]", "ç", "ñ", "^-"}, to = {"a" , "e" , "i" , "o" , "u" , "c", "n"}} , standardChars = "A-Za-z0-9" .. PUNCTUATION .. u(0x2800) .. "-" .. u(0x28FF), } m["nn"] = { canonicalName = "နဝ်ဝေ နဳနိုတ်", otherNames = {"Norwegian Nynorsk", "New Norwegian", "Nynorsk"}, scripts = {"Latn"}, family = "gmq", ancestors = {"gmq-mno"}, wikipedia_article = "Nynorsk", } m["no"] = { canonicalName = "နဝ်ဝေ", otherNames = {"Norwegian"}, scripts = {"Latn"}, family = "gmq", ancestors = {"gmq-mno"}, } m["nr"] = { canonicalName = "အာန်ဒေဗေလေဝ် လ္ပာ်ဒိုဟ်သမၠုင်ကျာ", otherNames = {"South Ndebele"}, scripts = {"Latn"}, family = "bnt-ngu", entry_name = { from = {"[āàáâǎ]", "[ēèéêě]", "[īìíîǐ]", "[ōòóôǒ]", "[ūùúûǔ]", "ḿ", "[ǹńň]", MACRON, ACUTE, GRAVE, CIRC, CARON}, to = {"a" , "e" , "i" , "o" , "u" , "m", "n" }}, } m["nv"] = { "နာဝါဟဝ်", 13310, "apa", Latn, sort_key = { from = {"[áą]", "[éę]", "[íį]", "[óǫ]", "ń", "^n([djlt])", "ł" , "[ʼ’']", ACUTE}, to = {"a" , "e" , "i" , "o" , "n", "ni%1" , "l~"}}, -- the tilde is used to guarantee that ł will always be sorted after all other words with l } m["ny"] = { canonicalName = "ချဳချေန်ဝါ", otherNames = {"နရန်ဂျာ", "Chichewa", "Chicheŵa", "Chinyanja", "Nyanja", "Chewa", "Cicewa", "Cewa", "Cinyanja"}, scripts = {"Latn"}, family = "bnt", entry_name = { from = {"ŵ", "Ŵ", "á", "Á", "é", "É", "í", "Í", "ó", "Ó", "ú", "Ú", "ń", "Ń", "ḿ", "Ḿ" }, to = {"w", "W", "a", "A", "e", "E", "i", "I", "o", "O", "u", "U", "n", "N", "m", "M"}}, sort_key = { from = {"ng'"}, to = {"ng"}} , wikipedia_article = "Chewa language", } m["oc"] = { "အောက်စဳတာန်", "Q14185", "roa-ocr", aliases = {"အောက်စဳတာန်"}, -- don't list varieties here that are in [[Module:etymology languages/data]] scripts = {"Latn", "Hebr"}, ancestors = {"pro"}, sort_key = { from = {"[àá]", "[èé]", "[íï]", "[òó]", "[úü]", "ç", "([lns])·h"}, to = {"a" , "e" , "i" , "o" , "u" , "c", "%1h" }} , } m["oj"] = { canonicalName = "အဝ်ဂျဳဗဝေ", otherNames = {"Ojibwe", "Chippewa", "Ojibway", "Ojibwemowin", "Southwestern Ojibwa"}, scripts = {"Cans", "Latn"}, family = "alg", } m["om"] = { canonicalName = "အဝ်ရဝ်မဝ်", otherNames = {"Oromo", "Orma", "Borana-Arsi-Guji Oromo", "West Central Oromo"}, scripts = {"Latn", "Ethi"}, family = "cus-eas", } m["or"] = { canonicalName = "အဝ်ရေဝ်ယာ", otherNames = {"Oriya", "Odia", "Oorya"}, scripts = {"Orya"}, family = "inc", ancestors = {"inc-mgd"}, translit_module = "or-translit", wikipedia_article = "Odia language", } m["os"] = { canonicalName = "အဝ်ဇြဳယာန်", otherNames = {"Ossetian", "Ossete", "Ossetic", "Digor", "Iron"}, scripts = {"Cyrl", "Geor", "Latn"}, family = "ira", ancestors = {"oos"}, translit_module = "os-translit", override_translit = true, entry_name = { from = {GRAVE, ACUTE}, to = {}} , } m["pa"] = { canonicalName = "ပါန်ချာပဳ", otherNames = {"Punjabi", "Panjabi"}, scripts = {"Guru", "pa-Arab"}, family = "inc-opa", ancestors = {"inc-opa"}, translit_module = "translit-redirect", entry_name = { from = {u(0x064B), u(0x064C), u(0x064D), u(0x064E), u(0x064F), u(0x0650), u(0x0651), u(0x0652), u(0x0658), u(0x08C7), u(0x0768)}, to = {"", "", "", "", "", "", "", "", "", "ل", "ن"}} , } m["pi"] = { "ပါဠိ", "Q36727", "inc-mid", scripts = {"Latn", "Brah", "Deva", "Beng", "Sinh", "Mymr", "Thai", "Lana", "Laoo", "Khmr"}, ancestors = {"sa"}, translit_module = "pi-translit", sort_key = { from = {"ā", "ī", "ū", "ḍ", "ḷ", "[ṁṃ]", "ṅ", "ñ", "ṇ", "ṭ", "([เโ])([ก-ฮ])", "([ເໂ])([ກ-ຮ])", "ᩔ", "ᩕ", "ᩖ", "ᩘ", "([ᨭ-ᨱ])ᩛ", "([ᨷ-ᨾ])ᩛ", "ᩤ", u(0xFE00), u(0x200D)}, to = {"a~", "i~", "u~", "d~", "l~", "m~", "n~", "n~~", "n~~~", "t~", "%2%1", "%2%1", "ᩈ᩠ᩈ", "᩠ᩁ", "᩠ᩃ", "ᨦ᩠", "%1᩠ᨮ", "%1᩠ᨻ", "ᩣ"}} , entry_name = { from = {u(0xFE00)}, to = {}}, } m["pl"] = { canonicalName = "ပဝ်လာန်", otherNames = {"Polish"}, scripts = {"Latn"}, family = "zlw", ancestors = {"zlw-opl", "sla-pro"}, sort_key = { from = {"[Ąą]", "[Ćć]", "[Ęę]", "[Łł]", "[Ńń]", "[Óó]", "[Śś]", "[Żż]", "[Źź]"}, to = { "a" .. u(0x10FFFF), "c" .. u(0x10FFFF), "e" .. u(0x10FFFF), "l" .. u(0x10FFFF), "n" .. u(0x10FFFF), "o" .. u(0x10FFFF), "s" .. u(0x10FFFF), "z" .. u(0x10FFFF), "z" .. u(0x10FFFE)}} , } m["ps"] = { "ပါသတုန်", "Q58680", "ira-pat", aliases = {"Pashtun", "Pushto", "Pashtu", "Afghani"}, varieties = {"Central Pashto", "Northern Pashto", "Southern Pashto", {"Pukhto", "Pakhto", "Pakkhto"}}, scripts = {"ps-Arab"}, ancestors = {"ira-pat-pro"}, } m["pt"] = { canonicalName = "ပဝ်တူဂြဳ", otherNames = {"Portuguese", "Modern Portuguese"}, scripts = {"Latn", "Brai"}, family = "roa", ancestors = {"ine-pro", "itc-pro", "itc-ola", "la", "roa-opt"}, sort_key = { from = {"[àãáâä]", "[èẽéêë]", "[ìĩíï]", "[òóôõö]", "[üúùũ]", "ç", "ñ"}, to = {"a" , "e" , "i" , "o" , "u" , "c", "n"}} , } m["qu"] = { canonicalName = "ခေန်ချူဝါ", scripts = {"Latn"}, family = "qwe", wikipedia_article = "ဘာသာခေန်ချူဝါ", } m["rm"] = { canonicalName = "ရဝ်မာန်", otherNames = {"Romansch","Romansh", "Rumantsch", "Romanche"}, scripts = {"Latn"}, family = "roa", wikipedia_article = "Romansh language", } m["ro"] = { canonicalName = "ရဝ်မေနဳယျာ", otherNames = {"Romanian", "Daco-Romanian", "Roumanian", "Rumanian"}, scripts = {"Latn", "Cyrl"}, family = "roa", sort_key = { from = {"ă" , "â" , "î" , "ș" , "ț" }, to = {"a~", "a~~", "i~", "s~", "t~"}}, } m["ru"] = { canonicalName = "ရုဿျှာ", otherNames = {"Russian"}, scripts = {"Cyrl", "Brai"}, family = "zle", translit_module = "ru-translit", sort_key = { from = {"ё"}, to = {"е" .. mw.ustring.char(0x10FFFF)}}, entry_name = { from = {"Ѐ", "ѐ", "Ѝ", "ѝ", GRAVE, ACUTE}, to = {"Е", "е", "И", "и"}}, standardChars = "ЁІА-яёі0-9—" .. PUNCTUATION, } m["rw"] = { canonicalName = "ရဝမ်ဒါ ရမ်ဒဳ", otherNames = {"Rwanda-Rundi", "Rwanda", "Kinyarwanda", "Rundi", "Kirundi", "Ha", "Giha", "Hangaza", "Vinza", "Shubi", "Subi"}, scripts = {"Latn"}, family = "bnt", wikipedia_article = "Rwanda-Rundi", } m["sa"] = { canonicalName = "သံသကြိုတ်", otherNames = {"Sanskrit"}, scripts = {"Deva", "Bali", "as-Beng", "Beng", "Bhks", "Brah", "Gran", "Gujr", "Guru", "Java", "Khar", "Khmr", "Knda", "Lana", "Laoo", "Mlym", "Modi", "Mymr", "Nand", "Newa", "Orya", "Saur", "Shrd", "Sidd", "Sinh", "Taml", "Telu", "Thai", "Tibt", "Tirh"}, family = "inc-old", sort_key = { from = {"ā", "ī", "ū", "ḍ", "ḷ", "ḹ", "[ṁṃ]", "ṅ", "ñ", "ṇ", "ṛ", "ṝ", "ś", "ṣ", "ṭ", "([เโไ])([ก-ฮ])", "([ເໂໄ])([ກ-ຮ])", "ᩔ", "ᩕ", "ᩖ", "ᩘ", "([ᨭ-ᨱ])ᩛ", "([ᨷ-ᨾ])ᩛ", "ᩤ", u(0xFE00), u(0x200D)}, to = {"a~", "i~", "u~", "d~", "l~", "l~~", "m~", "n~", "n~~", "n~~~", "r~", "r~~", "s~", "s~~", "t~", "%2%1", "%2%1", "ᩈ᩠ᩈ", "᩠ᩁ", "᩠ᩃ", "ᨦ᩠", "%1᩠ᨮ", "%1᩠ᨻ", "ᩣ"}}, entry_name = { from = {"ึ", u(0xF700), u(0xF70F), u(0xFE00)}, to = {"ิํ", "ฐ", "ญ"}}, translit_module = "translit-redirect", ancestors = {"iir-pro", "inc-pro"}, } m["sc"] = { canonicalName = "သာဒဳနဳယာန်", otherNames = {"Sardinian", "Campidanese", "Campidanese Sardinian", "Logudorese", "Logudorese Sardinian", "Nuorese", "Nuorese Sardinian"}, scripts = {"Latn"}, family = "roa", } m["sd"] = { "သိန္ဓိ", 33997, "inc-snd", scripts = {"sd-Arab", "Deva", "Sind", "Khoj"}, entry_name = { from = {u(0x0671), u(0x064B), u(0x064C), u(0x064D), u(0x064E), u(0x064F), u(0x0650), u(0x0651), u(0x0652), u(0x0670), u(0x0640)}, to = {u(0x0627)}}, ancestors = {"inc-vra"}, translit_module = "translit-redirect", } m["se"] = { canonicalName = "သာမိ သၟဝ်ကျာ", otherNames = {"Northern Sami", "North Sami", "Northern Saami", "North Saami"}, scripts = {"Latn"}, family = "smi", entry_name = { from = {"([đflmnŋrsšŧv])'%1"}, to = {"%1%1"} }, wikipedia_article = "Northern Sami", } m["sg"] = { canonicalName = "သင်ဂဝ်", otherNames = {"Sango"}, scripts = {"Latn"}, family = "crp", } m["sh"] = { canonicalName = "သာဗ်ခြဝ်ဨရှဳယာန်", otherNames = {"Serbo-Croatian", "BCS", "Croato-Serbian", "Serbocroatian", "Bosnian", "Croatian", "Montenegrin", "Serbian"}, scripts = {"Latn", "Cyrl"}, family = "zls", ancestors = {"ine-pro", "ine-bsl-pro", "sla-pro"}, entry_name = { from = {"[ȀÀȂÁĀÃ]", "[ȁàȃáāã]", "[ȄÈȆÉĒẼ]", "[ȅèȇéēẽ]", "[ȈÌȊÍĪĨ]", "[ȉìȋíīĩ]", "[ȌÒȎÓŌÕ]", "[ȍòȏóōõ]", "[ȐȒŔ]", "[ȑȓŕ]", "[ȔÙȖÚŪŨ]", "[ȕùȗúūũ]", "Ѐ", "ѐ", "[ӢЍ]", "[ӣѝ]", "[Ӯ]", "[ӯ]", GRAVE, ACUTE, DGRAVE, INVBREVE, MACRON, TILDE}, to = {"A" , "a" , "E" , "e" , "I" , "i" , "O" , "o" , "R" , "r" , "U" , "u" , "Е", "е", "И" , "и", "У", "у" }}, wikimedia_codes = {"sh", "bs", "hr", "sr"}, wikipedia_article = "Serbo-Croatian", } m["si"] = { canonicalName = "သိၚ်္ဃဵုရ်", otherNames = {"Sinhalese", "Singhalese", "Sinhala"}, scripts = {"Sinh"}, family = "inc", ancestors = {"elu-prk"}, translit_module = "si-translit", override_translit = true, } m["sk"] = { canonicalName = "သလဝ်ဝေန်နဳယျာ", otherNames = {"Slovak"}, scripts = {"Latn"}, family = "zlw", ancestors = {"ine-pro", "ine-bsl-pro", "sla-pro", "zlw-osk"}, sort_key = { from = {"[áä]", "é", "í", "[óô]", "ú", "ý", "ŕ", "ĺ", "[" .. DIAER .. ACUTE .. CIRC .. "]"}, to = {"a" , "e", "i", "o" , "u", "y", "r", "l", ""}} , } m["sl"] = { canonicalName = "သၠဝ်ဝေနဳ", otherNames = {"Slovene", "Slovenian"}, scripts = {"Latn"}, family = "zls", entry_name = { from = {"[ÁÀÂȂȀ]", "[áàâȃȁ]", "[ÉÈÊȆȄỆẸ]", "[éèêȇȅệẹə]", "[ÍÌÎȊȈ]", "[íìîȋȉ]", "[ÓÒÔȎȌỘỌ]", "[óòôȏȍộọ]", "[ŔȒȐ]", "[ŕȓȑ]", "[ÚÙÛȖȔ]", "[úùûȗȕ]", "ł", GRAVE, ACUTE, DGRAVE, INVBREVE, CIRC, DOTBELOW}, to = {"A" , "a" , "E" , "e" , "I" , "i" , "O" , "o" , "R" , "r" , "U" , "u" , "l"}} , } m["sm"] = { canonicalName = "သမဝ်အာန်", otherNames = {"Samoan"}, scripts = {"Latn"}, family = "poz-pol", } m["sn"] = { canonicalName = "သျှိနာ", otherNames = {"Shona"}, scripts = {"Latn"}, family = "bnt", } m["so"] = { canonicalName = "ဆဝ်မာလဳ", otherNames = {"Somali"}, scripts = {"Latn", "Arab", "Osma"}, family = "cus", entry_name = { from = {"[ÁÀÂ]", "[áàâ]", "[ÉÈÊ]", "[éèê]", "[ÍÌÎ]", "[íìî]", "[ÓÒÔ]", "[óòô]", "[ÚÙÛ]", "[úùû]", "[ÝỲ]", "[ýỳ]"}, to = {"A" , "a" , "E" , "e" , "I" , "i" , "O" , "o" , "U" , "u", "Y", "y"}} , } m["sq"] = { canonicalName = "အလ်ဗနဳယာန်", otherNames = {"Albanian"}, scripts = {"Latn", "Elba"}, family = "sqj", ancestors = {"ine-pro", "sqj-pro"}, sort_key = { from = { '[âãä]', '[ÂÃÄ]', '[êẽë]', '[ÊẼË]', 'ĩ', 'Ĩ', 'õ', 'Õ', 'ũ', 'Ũ', 'ỹ', 'Ỹ', 'ç', 'Ç' }, to = { 'a', 'A', 'e', 'E', 'i', 'I', 'o', 'O', 'u', 'U', 'y', 'Y', 'c', 'C' } } , } m["ss"] = { canonicalName = "သဝါဇြဳ", otherNames = {"Swazi", "Swati"}, scripts = {"Latn"}, family = "bnt-ngu", entry_name = { from = {"[āàáâǎ]", "[ēèéêě]", "[īìíîǐ]", "[ōòóôǒ]", "[ūùúûǔ]", "ḿ", "[ǹńň]", MACRON, ACUTE, GRAVE, CIRC, CARON}, to = {"a" , "e" , "i" , "o" , "u" , "m", "n" }}, ancestors = {"bnt-pro"}, } m["st"] = { canonicalName = "သူထူ", otherNames = {"Sotho", "Sesotho", "Southern Sesotho", "Southern Sotho"}, scripts = {"Latn"}, family = "bnt", } m["su"] = { canonicalName = "သာန်ဓနဳ", otherNames = {"Sundanese"}, scripts = {"Sund", "Latn"}, family = "poz-msa", ancestors = {"map-pro", "poz-pro", "poz-sus-pro", "poz-msa-pro", "osn"}, translit_module = "su-translit", } m["sv"] = { canonicalName = "သွဳဒေန်", otherNames = {"Swedish"}, scripts = {"Latn"}, family = "gmq", ancestors = {"gmq-osw", "gem-pro", "ine-pro"}, sort_key = { from = {"ö", "å", "ä"}, to = {"o", "a", "a"}} , } m["sw"] = { canonicalName = "သဝါတ်ဟဳလဳ", otherNames = {"Swahili", "Settler Swahili", "KiSetla", "KiSettla", "Setla", "Settla", "Kitchen Swahili", "Kihindi", "Indian Swahili", "KiShamba", "Kishamba", "Field Swahili", "Kibabu", "Asian Swahili", "Kimanga", "Arab Swahili", "Kitvita", "Army Swahili"}, scripts = {"Latn", "Arab"}, family = "bnt", sort_key = { from = {"ng'", "^-"}, to = {"ngz"}} , } m["ta"] = { canonicalName = "တမဳလ်", otherNames = {"Tamil"}, scripts = {"Taml"}, family = "dra", ancestors = {"oty"}, translit_module = "ta-translit", override_translit = true, } m["te"] = { canonicalName = "တေလုဂု", otherNames = {"Telugu"}, scripts = {"Telu"}, family = "dra", ancestors = {"dra-pro", "dra-sou-pro", "dra-sdt-pro", "dra-ote"}, translit_module = "te-translit", override_translit = true, } m["tg"] = { canonicalName = "တာဇိက်", otherNames = {"Tajik", "Tadjik", "Tadzhik", "Tajiki", "Tajik Persian"}, scripts = {"Cyrl", "fa-Arab", "Latn"}, family = "ira-wes", ancestors = {"fa"}, translit_module = "tg-translit", override_translit = true, sort_key = { from = {"Ё", "ё"}, to = {"Е" , "е"}} , entry_name = { from = {ACUTE}, to = {}} , } m["th"] = { "သေံ", 9217, family = "tai-swe", scripts = {"Thai", "Brai"}, translit_module = "th-translit", sort_key = { from = {"[%pๆ]", "[็-๎]", "([เแโใไ])([ก-ฮ])"}, to = {"", "", "%2%1"}}, ancestors = {"qfa-tak-pro", "qfa-bet-pro", "tai-pro", "tai-swe-pro"}, } m["ti"] = { canonicalName = "တဳဂျရေဝ်ယျာ", otherNames = {"Tigrinya"}, scripts = {"Ethi"}, family = "sem-eth", translit_module = "Ethi-translit", } m["tk"] = { canonicalName = "တာခ်မေန်", otherNames = {"Turkmen"}, scripts = {"Latn", "Cyrl"}, family = "trk-ogz", entry_name = { from = {"ā", "ē", "ī", "ō", "ū", "ȳ", "ȫ", "ǖ", MACRON}, to = {"a", "e", "i", "o", "u", "y", "ö", "ü", ""}}, } m["tl"] = { canonicalName = "တာဂါလံက်", otherNames = {"Tagalog"}, scripts = {"Latn", "Tglg"}, family = "phi", entry_name = { from = {"[áàâ]", "[éèê]", "[íìî]", "[óòô]", "[úùû]", ACUTE, GRAVE, CIRC}, to = {"a" , "e" , "i" , "o" , "u" }}, translit_module = "tl-translit", override_translit = true } m["tn"] = { canonicalName = "သွာနာ", otherNames = {"Tswana", "Setswana"}, scripts = {"Latn"}, family = "bnt", } m["to"] = { canonicalName = "ထံင်ဂံင်", otherNames = {"Tongan"}, scripts = {"Latn"}, family = "poz-pol", } m["tr"] = { canonicalName = "တူရကဳ", otherNames = {"Turkish"}, scripts = {"Latn"}, family = "trk-ogz", ancestors = {"ota"}, } m["ts"] = { canonicalName = "သွေန်ဂါ", otherNames = {"Tsonga"}, scripts = {"Latn"}, family = "bnt", ancestors = {"nic-pro", "alv-pro", "nic-vco-pro", "nic-bco-pro", "nic-bod-pro", "bnt-pro"}, } m["tt"] = { canonicalName = "တာတာ", otherNames = {"Tatar"}, scripts = {"Cyrl", "Latn", "Arab", "tt-Arab"}, family = "trk-kip", translit_module = "tt-translit", override_translit = true, } -- "tw" IS TREATED AS "ak", SEE WT:LT m["ty"] = { canonicalName = "တဟဳတဳဃှေန်", otherNames = {"Tahitian"}, scripts = {"Latn"}, family = "poz-pol", } m["ug"] = { canonicalName = "ဥူဃူရ်", otherNames = {"Uigur", "Uighur", "Uygur"}, scripts = {"ug-Arab", "Latn", "Cyrl"}, family = "trk", ancestors = {"chg"}, translit_module = "ug-translit", override_translit = true, } m["uk"] = { canonicalName = "ယူကရိန်", otherNames = {"Ukrainian"}, scripts = {"Cyrl"}, family = "zle", ancestors = {"ine-pro", "ine-bsl-pro", "sla-pro", "orv", "zle-ouk"}, translit_module = "uk-translit", entry_name = { from = {"Ѐ", "ѐ", "Ѝ", "ѝ", GRAVE, ACUTE}, to = {"Е", "е", "И", "и"}}, standardChars = "ЄІЇА-ЩЫЬЮ-щыьюяєії" .. PUNCTUATION } m["ur"] = { "အူရဒူ", "Q1617", "inc-hnd", scripts = {"ur-Arab"}, ancestors = {"inc-ohi"}, entry_name = { from = {u(0x064B), u(0x064C), u(0x064D), u(0x064E), u(0x064F), u(0x0650), u(0x0651), u(0x0652)}, to = {}} , } m["uz"] = { canonicalName = "ဥုသဗဝ်", otherNames = {"Uzbek", "Northern Uzbek", "Southern Uzbek"}, scripts = {"Latn", "Cyrl", "fa-Arab"}, family = "trk", ancestors = {"chg"}, translit_module = "uz-translit" } m["ve"] = { canonicalName = "ဗါန်ဒါ", otherNames = {"Venda"}, scripts = {"Latn"}, family = "bnt", } m["vi"] = { canonicalName = "ဗဳယေတ်နာမ်", otherNames = {"Vietnamese", "Annamese", "Annamite"}, scripts = {"Latn", "Hani"}, family = "mkh-vie", ancestors = {"mkh-mvi"}, sort_key = "vi-sortkey", } m["vo"] = { canonicalName = "ဝဝ်လပုက်", otherNames = {"Volapük"}, scripts = {"Latn"}, family = "art", wikipedia_article = "Volapük", } m["wa"] = { canonicalName = "ဝါဠူ", otherNames = {"Walloon", "Liégeois", "Namurois", "Wallo-Picard", "Wallo-Lorrain"}, scripts = {"Latn"}, family = "roa-oil", ancestors = {"fro"}, sort_key = { from = {"[áàâäå]", "[éèêë]", "[íìîï]", "[óòôö]", "[úùûü]", "[ýỳŷÿ]", "ç", "'"}, to = {"a" , "e" , "i" , "o" , "u" , "y" , "c"}} , } m["wo"] = { canonicalName = "ဝဝ်လံက်", otherNames = {"Wolof", "Gambian Wolof"}, -- the subsumed dialect 'wof' scripts = {"Latn", "Arab"}, family = "alv-sng", } m["xh"] = { canonicalName = "ခါဝ်သာ", otherNames = {"Xhosa"}, scripts = {"Latn"}, family = "bnt-ngu", entry_name = { from = {"[āàáâǎ]", "[ēèéêě]", "[īìíîǐ]", "[ōòóôǒ]", "[ūùúûǔ]", "ḿ", "[ǹńň]", MACRON, ACUTE, GRAVE, CIRC, CARON}, to = {"a" , "e" , "i" , "o" , "u" , "m", "n" }}, ancestors = {"bnt-pro"}, } m["yi"] = { canonicalName = "ယိဒ်ဒိသ်", otherNames = {"Yiddish"}, scripts = {"Hebr"}, family = "gmw", ancestors = {"gmh"}, translit_module = "yi-translit", wikipedia_article = "Yiddish", } m["yo"] = { canonicalName = "ရိုရုဗာ", otherNames = {"Yoruba"}, scripts = {"Latn"}, family = "alv-von", ancestors = {"alv-yor-pro", "alv-edk-pro", "alv-yrd-pro"}, } m["za"] = { canonicalName = "ဇြုန်", otherNames = {"Standard Zhuang"}, scripts = {"Latn", "Hani"}, family = "tai", wikipedia_article = "Zhuang languages", } m["zh"] = { canonicalName = "ကြုက်", otherNames = {"Chinese"}, scripts = {"Hani", "Brai"}, family = "sit", ancestors = {"ltc", "sit-pro"}, sort_key = "zh-sortkey", } m["zu"] = { canonicalName = "သြူဠူ", otherNames = {"Zulu", "isiZulu"}, scripts = {"Latn"}, family = "bnt-ngu", entry_name = { from = {"[āàáâǎ]", "[ēèéêě]", "[īìíîǐ]", "[ōòóôǒ]", "[ūùúûǔ]", "ḿ", "[ǹńň]", MACRON, ACUTE, GRAVE, CIRC, CARON}, to = {"a" , "e" , "i" , "o" , "u" , "m", "n" }}, ancestors = {"bnt-pro"}, } return m eevgscnrbg90ex2detbd1jnyf2xirgj 103874 103872 2024-11-01T09:09:15Z 咽頭べさ 33 103874 Scribunto text/plain local u = mw.ustring.char -- UTF-8 encoded strings for some commonly-used diacritics local GRAVE = u(0x0300) local ACUTE = u(0x0301) local CIRC = u(0x0302) local TILDE = u(0x0303) local MACRON = u(0x0304) local BREVE = u(0x0306) local DOTABOVE = u(0x0307) local DIAER = u(0x0308) local CARON = u(0x030C) local DGRAVE = u(0x030F) local INVBREVE = u(0x0311) local DOTBELOW = u(0x0323) local RINGBELOW = u(0x0325) local CEDILLA = u(0x0327) local OGONEK = u(0x0328) local DOUBLEINVBREVE = u(0x0361) -- Punctuation to be used for standardChars field local PUNCTUATION = ' !#%&*+,-./:;<=>?@^_`|~\'()' local Cyrl = {"Cyrl"} local Latn = {"Latn"} local LatnArab = {"Latn", "Arab"} local m = {} m["aa"] = { canonicalName = "အဖှာင်", otherNames = {"Qafar"}, scripts = {"Latn"}, family = "cus", } m["ab"] = { canonicalName = "အာပ်ဟန်", otherNames = {"Abkhaz", "Abkhazian", "Abxazo"}, scripts = {"Cyrl", "Geor", "Latn"}, family = "cau-abz", translit_module = "ab-translit", override_translit = true, entry_name = { from = {GRAVE, ACUTE}, to = {}} , } m["ae"] = { "အဗါတ်သတေန်", 29572, "ira-cen", scripts = {"Avst", "Gujr"}, translit_module = "Avst-translit", wikipedia_article = "Avestan", } m["af"] = { canonicalName = "အေက်ဖရိကာန်", scripts = {"Latn", "Arab"}, family = "gmw", ancestors = {"nl"}, sort_key = { from = {"[äáâà]", "[ëéêè]", "[ïíîì]", "[öóôò]", "[üúûù]", "[ÿýŷỳ]", "^-", "'"}, to = {"a" , "e" , "i" , "o" , "u" , "y" }} , wikipedia_article = "Afrikaans", } m["ak"] = { canonicalName = "အကာန်", otherNames = {"Akan", "Twi-Fante", "Twi", "Fante", "Fanti", "Asante", "Akuapem"}, scripts = {"Latn"}, family = "alv-kwa", } m["am"] = { canonicalName = "အာန်ဟာရိစ်", otherNames = {"Amharic"}, scripts = {"Ethi"}, family = "sem-eth", translit_module = "Ethi-translit", wikipedia_article = "Amharic", } m["an"] = { canonicalName = "အာဒါဂေန်", otherNames = {"Aragonese"}, scripts = {"Latn"}, family = "roa", ancestors = {"ine-pro", "itc-pro", "itc-ola", "la", "roa-oan"}, } m["ar"] = { canonicalName = "အာရဗဳ", otherNames = {"Modern Standard Arabic", "Standard Arabic", "Literary Arabic", "Classical Arabic", "Arabic", "အာရက်လ်"}, scripts = {"Arab", "Brai"}, family = "sem-arb", -- alif waṣl to alif, remove diacritics entry_name = { from = {u(0x0671), u(0x064B), u(0x064C), u(0x064D), u(0x064E), u(0x064F), u(0x0650), u(0x0651), u(0x0652), u(0x0670), u(0x0640)}, to = {u(0x0627)}}, translit_module = "ar-translit", wikipedia_article = "Arabic", ancestors = {"sem-pro"}, } m["as"] = { canonicalName = "အိသ်ဇြာံမဳ", otherNames ={"Assamese"}, scripts = {"Beng"}, family = "inc", ancestors = {"inc-mgd"}, translit_module = "as-translit", } m["av"] = { "အာဗာ", "Q29561", "cau-nec", aliases = {"Avaric"}, scripts = Cyrl, ancestors = {"oav"}, translit_module = "translit-redirect", override_translit = true, entry_name = { from = {GRAVE, ACUTE}, to = {}} , } m["ay"] = { canonicalName = "အိုင်မာရ", otherNames = {"Aymara", "Southern Aymara", "Central Aymara"}, scripts = {"Latn"}, family = "sai-aym", } m["az"] = { "အာက်သေတ်ဗါဲဇြေနဳ", 9292, "trk-ogz", {"Latn", "Cyrl", "fa-Arab"}, ancestors = {"trk-oat"}, dotted_dotless_i = true, } m["ba"] = { canonicalName = "ဗေတ်ခဳ", otherNames = {"Bashkir"}, scripts = {"Cyrl"}, family = "trk-kip", translit_module = "ba-translit", override_translit = true, } m["be"] = { canonicalName = "ဗါလာရုဇ်", otherNames = {"Belarusian", "Belorussian", "Belarusan", "Bielorussian", "Byelorussian", "Belarussian", "White Russian"}, scripts = {"Cyrl"}, family = "zle", ancestors = {"orv"}, translit_module = "be-translit", sort_key = { from = {"Ё", "ё"}, to = {"Е" , "е"}}, entry_name = { from = {"Ѐ", "ѐ", GRAVE, ACUTE}, to = {"Е", "е"}}, } m["bg"] = { canonicalName = "ဗူလ်ဂရဳယာန်", otherNames = {"Bulgarian"}, scripts = {"Cyrl"}, family = "zls", translit_module = "bg-translit", entry_name = { from = {"Ѐ", "ѐ", "Ѝ", "ѝ", GRAVE, ACUTE}, to = {"Е", "е", "И", "и"}}, } m["bh"] = { canonicalName = "ဘဳဟာရဳ", otherNames = {"Bihari"}, scripts = {"Deva"}, family = "inc", ancestors = {"inc-mgd"}, wikipedia_article = "ဘာသာဘဳဟာရဳ", } m["bi"] = { canonicalName = "ဗဳသလာမာ", otherNames = {"Bislama"}, scripts = {"Latn"}, family = "crp", ancestors = {"ine-pro", "gem-pro", "gmw-pro", "ang", "enm", "en-ear", "en"}, wikipedia_article = "Bislama", } m["bm"] = { canonicalName = "ဗီုဗရာ", otherNames = {"Bamanankan"}, scripts = {"Latn"}, family = "dmn", } m["bn"] = { canonicalName = "ဘင်္ဂါလဳ", otherNames = {"Bangla", "Bengali"}, scripts = {"Beng"}, family = "inc", ancestors = {"inc-mgd"}, translit_module = "bn-translit", } m["bo"] = { canonicalName = "တဳဗဝ်", otherNames = {"Tibetan", "Ü", "Dbus", "Lhasa", "Lhasa Tibetan", "Amdo Tibetan", "Amdo", "Panang", "Khams", "Khams Tibetan", "Khamba", "Tseku", "Dolpo", "Humla", "Limi", "Lhomi", "Shing Saapa", "Mugom", "Mugu", "Nubri", "Walungge", "Gola", "Thudam", "Lowa", "Loke", "Mustang", "Tichurong", "တိဗက်"}, scripts = {"Tibt"}, family = "tbq", ancestors = {"xct"}, translit_module = "bo-translit", override_translit = true, wikipedia_article = "Standard Tibetan", -- may need verification } m["br"] = { canonicalName = "ဗရဳတေန်", otherNames = {"Breton"}, scripts = {"Latn"}, family = "cel-bry", ancestors = {"xbm"}, } m["ca"] = { canonicalName = "ကတလာန်", otherNames = {"Valencian", "Catalan"}, scripts = {"Latn"}, family = "roa", ancestors = {"roa-oca"}, sort_key = { from = {"à", "[èé]", "[íï]", "[òó]", "[úü]", "ç", "l·l"}, to = {"a", "e" , "i" , "o" , "u" , "c", "ll" }} , } m["ce"] = { canonicalName = "ချက်ခ်ချေင်", otherNames = {"Chechen"}, scripts = {"Cyrl", "Latn", "Arab"}, family = "cau-nkh", translit_module = "translit-redirect", override_translit = true, ancestors = {"ccn-pro", "cau-nec-pro", "cau-nkh-pro"}, entry_name = { from = {MACRON}, to = {}}, } m["ch"] = { canonicalName = "ချာမဝ်ရဝ်", otherNames = {"Chamorro", "Chamoru"}, scripts = {"Latn"}, family = "poz-sus", } m["co"] = { canonicalName = "ခဝ်သဳကာန်", otherNames = {"Corsican", "Corsu"}, scripts = {"Latn"}, family = "roa", } m["cr"] = { canonicalName = "ခရေဝ်", scripts = {"Cree", "Cans", "Latn"}, family = "alg", translit_module = "cr-translit", } m["cs"] = { canonicalName = "ချက်ခ်", otherNames = {"Czech"}, scripts = {"Latn"}, family = "zlw", ancestors = {"zlw-ocs", "sla-pro"}, sort_key = { from = {"á", "é", "í", "ó", "[úů]", "ý"}, to = {"a", "e", "i", "o", "u" , "y"}} , } m["cu"] = { "ခရေတ်သလာဗဝ်နေတ်တြေံ", "Q35499", "zls", aliases = {"Old Church Slavic"}, scripts = {"Cyrs", "Glag"}, translit_module = "Cyrs-Glag-translit", ancestors = {"ine-pro", "ine-bsl-pro", "sla-pro"}, entry_name = { from = {u(0x0484)}, -- kamora to = {}}, sort_key = { from = {"оу", "є"}, to = {"у" , "е"}} , } m["cv"] = { "ချူဝါတ်", "Q33348", "trk-ogr", scripts = Cyrl, ancestors = {"xbo"}, translit_module = "cv-translit", sort_key = { from = {"ӑ", "ё", "ӗ", "ҫ", "ӳ"}, to = { "а" .. u(0xF000), "е" .. u(0xF000), "е" .. u(0xF001), "с" .. u(0xF000), "у" .. u(0xF000) } }, override_translit = true, } m["cy"] = { canonicalName = "ဝေလ", otherNames ={"Welsh"}, scripts = {"Latn"}, family = "cel-bry", ancestors = {"wlm"}, sort_key = { from = {"[âáàä]", "[êéèë]", "[îíìï]", "[ôóòö]", "[ûúùü]", "[ŵẃẁẅ]", "[ŷýỳÿ]", "'"}, to = {"a" , "e" , "i" , "o" , "u" , "w" , "y" }} , } m["da"] = { canonicalName = "ဒိန်နေတ်", otherNames ={"Danish"}, scripts = {"Latn"}, family = "gmq", ancestors = {"gmq-oda"}, } m["de"] = { canonicalName = "ဂျာမာန်", otherNames = {"High German", "New High German", "Deutsch", "German", "ဂျာမနဳ"}, scripts = {"Latn", "Latf"}, family = "gmw", ancestors = {"gmh"}, sort_key = { from = {"[äàáâå]", "[ëèéê]", "[ïìíî]", "[öòóô]", "[üùúû]", "ß" }, to = {"a" , "e" , "i" , "o" , "u" , "ss"}} , } m["dv"] = { canonicalName = "ဒိဝေဟဳ", otherNames = {"Dhivehi", "Divehi", "Mahal", "Mahl", "Maldivian"}, scripts = {"Thaa"}, family = "inc", ancestors = {"pmh"}, -- or Helu? translit_module = "dv-translit", override_translit = true, wikipedia_article = "ဘာသာမောဝ်ဒိုက်", } m["dz"] = { canonicalName = "သောင်ခါ", otherNames = {"Dzongkha"}, scripts = {"Tibt"}, family = "tbq", ancestors = {"xct"}, translit_module = "bo-translit", override_translit = true, wikipedia_article = "Dzongkha", } m["ee"] = { canonicalName = "အဳဝါ", otherNames = {"Ewe"}, scripts = {"Latn"}, family = "alv-von", } m["el"] = { canonicalName = "ဂရေတ်", otherNames = {"Greek", "Modern Greek", "Neo-Hellenic"}, scripts = {"Grek", "Brai", "Polyt", "Latn"}, family = "grk", ancestors = {"ine-pro", "grk-pro", "grc-att", "grc-koi", "gkm-med", "el-kth", "grc"}, translit_module = "el-translit", override_translit = true, sort_key = { -- Keep this synchronized with grc, cpg, pnt from = {"[ᾳάᾴὰᾲᾶᾷἀᾀἄᾄἂᾂἆᾆἁᾁἅᾅἃᾃἇᾇ]", "[έὲἐἔἒἑἕἓ]", "[ῃήῄὴῂῆῇἠᾐἤᾔἢᾒἦᾖἡᾑἥᾕἣᾓἧᾗ]", "[ίὶῖἰἴἲἶἱἵἳἷϊΐῒῗ]", "[όὸὀὄὂὁὅὃ]", "[ύὺῦὐὔὒὖὑὕὓὗϋΰῢῧ]", "[ῳώῴὼῲῶῷὠᾠὤᾤὢᾢὦᾦὡᾡὥᾥὣᾣὧᾧ]", "ῥ", "ς"}, to = {"α" , "ε" , "η" , "ι" , "ο" , "υ" , "ω" , "ρ", "σ"}} , standardChars = "ͺ;΄-ώϜϝ" .. PUNCTUATION .. "ἀ-῾" } m["en"] = { canonicalName = "အင်္ဂလိက်", otherNames = {"English", "Modern English", "New English", "Hawaiian Creole English", "Hawai'ian Creole English", "Hawaiian Creole", "Hawai'ian Creole", "Polari", "Yinglish"}, -- all but the first three are names of subsumed dialects which once had codes scripts = {"Latn", "Brai", "Shaw", "Dsrt"}, -- entries in Shaw or Dsrt might require prior discussion family = "gmw", ancestors = {"enm"}, wikipedia_article = "ဘာသာအင်္ဂလိက်", sort_key = { from = {"[äàáâåā]", "[ëèéêē]", "[ïìíîī]", "[öòóôō]", "[üùúûū]", "æ" , "œ" , "[çč]", "ñ", "['9]", "1", "[23]", "[45]", "[67]", "0", "+", ".", "'", "-"}, to = {"a" , "e" , "i" , "o" , "u" , "ae", "oe", "c" , "n" , "o" , "t" , "s" , "z" , "p" , "q" , "s" , "t"}}, wikimedia_codes = {"en", "simple"}, standardChars = "A-Za-z0-9" .. PUNCTUATION .. u(0x2800) .. "-" .. u(0x28FF) } m["eo"] = { canonicalName = "အေက်သပရေန်တဝ်", otherNames = {"Esperanto"}, scripts = {"Latn"}, family = "art", sort_key = { from = {"[áà]", "[éè]", "[íì]", "[óò]", "[úù]", "[ĉ]", "[ĝ]", "[ĥ]", "[ĵ]", "[ŝ]", "[ŭ]"}, to = {"a" , "e" , "i" , "o" , "u", "cĉ", "gĉ", "hĉ", "jĉ", "sĉ", "uĉ"}} , wikipedia_article = "Esperanto", } m["es"] = { "သပုင်", 1321, "roa-ibe", {"Latn", "Brai"}, ancestors = {"ine-pro", "itc-pro", "itc-ola", "la", "osp"}, sort_key = { from = {"á", "é", "í", "ó", "[úü]", "ç", "ñ"}, to = {"a", "e", "i", "o", "u" , "c", "n"}}, standardChars = "A-VXYZa-vxyz0-9ÁáÉéÍíÓóÚúÑñ¿¡" .. PUNCTUATION, } m["et"] = { canonicalName = "အေက်သတဝ်နဳယာန်", otherNames = {"Estonian"}, scripts = {"Latn"}, family = "urj-fin", } m["eu"] = { canonicalName = "ဗက်ခ်", otherNames = {"Basque", "Euskara"}, scripts = {"Latn"}, family = "euq", } m["fa"] = { canonicalName = "ပါရှေန်", otherNames = {"ပါရှာ", "ဖာသဳ", "ဖာစဳ", "Persian", "Farsi", "New Persian", "Modern Persian", "Western Persian", "Iranian Persian", "Eastern Persian", "Dari", "Aimaq", "Aimak", "Aymaq", "Eimak"}, scripts = {"fa-Arab"}, family = "ira-wes", ancestors = {"pal", "ira-pro", "iir-pro", "ine-pro"}, entry_name = { from = {u(0x064E), u(0x064F), u(0x0650), u(0x0651), u(0x0652)}, to = {}} , } m["ff"] = { canonicalName = "ဖှောတ်လာ", otherNames = {"Fula", "Adamawa Fulfulde", "Bagirmi Fulfulde", "Borgu Fulfulde", "Central-Eastern Niger Fulfulde", "Fulani", "Fulfulde", "Maasina Fulfulde", "Nigerian Fulfulde", "Pular", "Pulaar", "Western Niger Fulfulde"}, -- Maasina, etc are dialects, subsumed into this code scripts = {"Latn"}, family = "alv-sng", } m["fi"] = { "ဖေန်လာန်", "Q1412", "urj-fin", aliases = {"Suomi"}, scripts = Latn, entry_name = { from = {"ˣ"}, -- Used to indicate gemination of the next consonant to = {}}, sort_key = { from = {"[áàâã]", "[éèêẽ]", "[íìîĩ]", "[óòôõ]", "[úùûũ]", "[ýỳŷüű]", "[øõő]", "æ" , "œ" , "[čç]", "š", "ž", "ß" , "[':]"}, to = {"a" , "e" , "i" , "o" , "u" , "y" , "ö" , "ae", "oe", "c" , "s", "z", "ss"}} , } m["fj"] = { canonicalName = "ဖရဳဂျိ", otherNames = {"Fijian"}, scripts = {"Latn"}, family = "poz-occ", } m["fo"] = { canonicalName = "ဖာရဝ်သဳ", otherNames = {"Faroese"}, scripts = {"Latn"}, family = "gmq", ancestors = {"non"}, } m["fr"] = { canonicalName = "ပြင်သေတ်", otherNames = {"French", "Modern French"}, scripts = {"Latn", "Brai"}, family = "roa-oil", ancestors = {"frm", "la"}, sort_key = { from = {"[áàâä]", "[éèêë]", "[íìîï]", "[óòôö]", "[úùûü]", "[ýỳŷÿ]", "ç", "æ" , "œ" , "'"}, to = {"a" , "e" , "i" , "o" , "u" , "y" , "c", "ae", "oe"}}, standardChars = "A-Za-z0-9ÀÂÇÉÈÊËÎÏÔŒÛÙÜàâçéèêëîïôœûùü«»" .. PUNCTUATION } m["fy"] = { canonicalName = "ဖရေဝ်သဳယာန်လက္ကရဴ", otherNames = {"West Frisian", "Western Frisian", "Frisian"}, scripts = {"Latn"}, family = "gmw-fri", ancestors = {"ofs"}, } m["ga"] = { canonicalName = "အာဲယျာလာန်", otherNames = {"Irish", "Irish Gaelic", "အိုင်ရစ်ရှ်"}, scripts = {"Latn"}, family = "cel-gae", ancestors = {"mga"}, sort_key = { from = {"á", "é", "í", "ó", "ú", "ý", "ḃ" , "ċ" , "ḋ" , "ḟ" , "ġ" , "ṁ" , "ṗ" , "ṡ" , "ṫ" }, to = {"a", "e", "i", "o", "u", "y", "bh", "ch", "dh", "fh", "gh", "mh", "ph", "sh", "th"}} , } m["gd"] = { canonicalName = "သကတ်ဂဴလိစ်", otherNames = {"Scottish Gaelic", "Gàidhlig", "Highland Gaelic", "Scots Gaelic", "Scottish"}, scripts = {"Latn"}, family = "cel-gae", ancestors = {"mga"}, sort_key = { from = {"[áà]", "[éè]", "[íì]", "[óò]", "[úù]", "[ýỳ]"}, to = {"a" , "e" , "i" , "o" , "u" , "y" }} , wikipedia_article = "Scottish Gaelic", } m["gl"] = { canonicalName = "ဂလဳသဳယာန်", otherNames = {"Galician"}, scripts = {"Latn"}, family = "roa", ancestors = {"ine-pro", "itc-pro", "inc-pro", "itc-ola", "la", "roa-opt"}, sort_key = { from = {"á", "é", "í", "ó", "ú"}, to = {"a", "e", "i", "o", "u"}} , } m["gn"] = { canonicalName = "ဂူရာန်နဳ", otherNames = {"Guaraní"}, scripts = {"Latn"}, family = "tup-gua", wikipedia_article = "ဘာသာဂူရာန်နဳ", } m["gu"] = { canonicalName = "ဂုဂျာရတဳ", otherNames = {"Gujarati"}, scripts = {"Gujr"}, family = "inc", ancestors = {"inc-ogu"}, translit_module = "gu-translit", } m["gv"] = { canonicalName = "မာက်", otherNames = {"Manx", "Manx Gaelic"}, scripts = {"Latn"}, family = "cel-gae", ancestors = {"mga"}, sort_key = { from = {"ç", "-"}, to = {"c"}} , } m["ha"] = { canonicalName = "ဟဴသာ", otherNames = {"Hausa"}, scripts = {"Latn", "Arab"}, family = "cdc-wst", sort_key = { from = {"ɓ", "ɗ", "ƙ", "'y", "ƴ", "'" }, to = {"b~" , "d~" , "k~", "y~", "y~", "" }}, entry_name = { from = {"R̃", "r̃", "À", "à", "È", "è", "Ì", "ì", "Ò", "ò", "Ù", "ù", "Â", "â", "Ê", "ê", "Î", "î", "Ô", "ô", "Û", "û", "Ā", "ā", "Ē", "ē", "Ī", "ī", "Ō", "ō", "Ū", "ū", "Á", "á", "É", "é", "Í", "í", "Ó", "ó", "Ú", "ú", "Ā̀", "ā̀", "Ḕ", "ḕ", "Ī̀", "ī̀", "Ṑ", "ṑ", "Ū̀", "ū̀", GRAVE, ACUTE}, to = {"R", "r", "A", "a", "E", "e", "I", "i", "O", "o", "U", "u", "A", "a", "E", "e", "I", "i", "O", "o", "U", "u", "A", "a", "E", "e", "I", "i", "O", "o", "U", "u", "A", "a", "E", "e", "I", "i", "O", "o", "U", "u", "A", "a", "E", "e", "I", "i", "O", "o", "U", "u"}}, } m["he"] = { canonicalName = "ဟဳဘရဝ်", otherNames = {"Hebrew", "Ivrit"}, scripts = {"Hebr", "Phnx", "Brai"}, family = "sem-can", ancestors = {"afa-pro", "sem-pro", "sem-wes-pro", "hbo", "he-mis", "he-med"}, translit_module = "he-translit", entry_name = { from = {"[" .. u(0x0591) .. "-" .. u(0x05BD) .. u(0x05BF) .. "-" .. u(0x05C5) .. u(0x05C7) .. "]"}, to = {}} , } m["hi"] = { canonicalName = "ဟိန္ဒဳ", otherNames = {"ဟိန္ဒဳ", "Hindi", "Braj", "Brij Bhasha", "Braj Bhasha", "Braj Bhāshā", "Braj Bhakha", "Dehaati Zabaan"}, scripts = {"Deva", "Guru"}, -- Guru for the subsumed variety Braj family = "inc-hnd", ancestors = {"inc-ohi"}, translit_module = "hi-translit", wikipedia_article = "Hindi", } m["ho"] = { canonicalName = "ဟဳရဳမိုတု", otherNames = {"Hiri Motu", "Pidgin Motu", "Police Motu"}, scripts = {"Latn"}, family = "crp", ancestors = {"meu"}, wikipedia_article = "Hiri Motu", } m["ht"] = { "ဟေဲယှေန် ခရေဝ်အဝ်လ်", 33491, "crp", Latn, ancestors = {"fr"}, } m["hu"] = { canonicalName = "ဟာန်ဂါရေဝ်", otherNames = {"Hungarian", "Magyar"}, scripts = {"Latn", "Hung"}, family = "urj-ugr", ancestors = {"urj-pro", "urj-ugr-pro", "ohu"}, sort_key = { from = {"é", "í", "ó", "ú", "ő", "ö", "ü", "á"}, to = {"e", "i", "o", "u", "o", "o", "u", "a"}} , } m["hy"] = { canonicalName = "အာမေနဳယျာ", otherNames = {"Armenian", "Modern Armenian", "Eastern Armenian", "Western Armenian", "အမေရိကာန်ဗၟံက်", "အမေရိကာန်ပလိုတ်", "အမေရိကာန်အခေတ်တၟိ"}, scripts = {"Armn", "Brai"}, family = "hyx", ancestors = {"axm"}, translit_module = "Armn-translit", override_translit = true, sort_key = { from = {"ու", "և", "եւ"}, to = {"ւ", "եվ", "եվ"}}, entry_name = { from = {"՞", "՜", "՛", "՟", "և", "<sup>յ</sup>", "<sup>ի</sup>"}, to = {"", "", "", "", "եւ", "յ", "ի"}} , } m["hz"] = { canonicalName = "ဟဳရဲရို", otherNames = {"Herero"}, scripts = {"Latn"}, family = "bnt", } m["ia"] = { canonicalName = "အေန်တာလိင်ဂဝ်", otherNames = {"Interlingua"}, scripts = {"Latn"}, family = "art", wikipedia_article = "Interlingua", } m["id"] = { canonicalName = "အိန်ဒဝ်နဳသဳယျာ", otherNames = {"Indonesian"}, scripts = {"Latn"}, family = "poz-mly", ancestors = {"map-pro", "poz-pro", "poz-sus-pro", "poz-msa-pro", "poz-mcm-pro", "poz-mly-pro", "ms-old", "ms-cla", "ms"}, } m["ie"] = { canonicalName = "အေန်တာလိင်ဂဝေ", otherNames = {"Interlingue", "Occidental"}, scripts = {"Latn"}, family = "art", wikipedia_article = "Occidental language", } m["ig"] = { canonicalName = "အေတ်ဗါဝ်", otherNames = {"Igbo", "အစ္ဂဘို"}, scripts = {"Latn"}, family = "nic-bco", } m["ii"] = { canonicalName = "သေဲဆိုန်ယဳ", otherNames = {"Sichuan Yi", "Nuosu", "Nosu", "Northern Yi", "Liangshan Yi"}, scripts = {"Yiii"}, family = "tbq-lol", wikipedia_article = "Nuosu language", translit_module = "ii-translit", override_translit = true, } m["ik"] = { canonicalName = "အဳနုဗဳယာတ်", otherNames = {"Inupiak", "Inupiaq", "Iñupiaq", "Inupiatun"}, scripts = {"Latn"}, family = "esx-inu", wikipedia_article = "Inupiaq", } m["io"] = { canonicalName = "ဣဒဝ်", otherNames = {"Ido"}, scripts = {"Latn"}, family = "art", } m["is"] = { canonicalName = "အာက်သလာန်", otherNames = {"Icelandic", "အာက်သလာန်"}, scripts = {"Latn"}, family = "gmq", ancestors = {"non", "gem-pro", "ine-pro"}, sort_key = { from = {"ð", "ö", "ó", "æ", "á", "í", "ú"}, to = {"o", "o", "o", "ae", "a", "i", "u"}} , } m["it"] = { canonicalName = "အဳတခ်လဳ", otherNames = {"Italian"}, scripts = {"Latn"}, family = "roa", sort_key = { from = {"[àáâäå]", "[èéêë]", "[ìíîï]", "[òóôö]", "[ùúûü]"}, to = {"a" , "e" , "i" , "o" , "u" }} , } m["iu"] = { canonicalName = "ဣနုက်တိတုတ်", otherNames = {"Inuktitut", "Eastern Canadian Inuktitut", "Eastern Canadian Inuit", "Western Canadian Inuktitut", "Western Canadian Inuit", "Western Canadian Inuktun", "Inuinnaq", "Inuinnaqtun", "Inuvialuk", "Inuvialuktun", "Nunavimmiutit", "Nunatsiavummiut", "Aivilimmiut", "Natsilingmiut", "Kivallirmiut", "Siglit", "Siglitun"}, scripts = {"Cans", "Latn"}, family = "esx-inu", translit_module = "iu-translit", override_translit = true, wikipedia_article = "Inuktitut", } m["ja"] = { canonicalName = "ဂျပါန်", otherNames = {"Japanese", "Modern Japanese", "Nipponese", "Nihongo"}, scripts = {"Jpan", "Latn", "Hira", "Brai"}, family = "jpx", ancestors = {"ojp"}, --[[ sort_key = { from = {"[ぁァア]", "[ぃィイ]", "[ぅゔゥウヴ]", "[ぇェエ]", "[ぉォオ]", "[がゕカガヵ]", "[ぎキギ]", "[ぐクグㇰ]", "[げゖケゲヶ]", "[ごコゴ]", "[ざサザ]", "[じシジㇱ]", "[ずスズㇲ]", "[ぜセゼ]", "[ぞソゾ]", "[だタダ]", "[ぢチヂ]", "[っづッツヅ]", "[でテデ]", "[どトドㇳ]", "ナ", "ニ", "[ヌㇴ]", "ネ", "ノ", "[ばぱハバパㇵ]", "[びぴヒビピㇶ]", "[ぶぷフブプㇷ]", "[べぺヘベペㇸ]", "[ぼぽホボポㇹ]", "マ", "ミ", "[ムㇺ]", "メ", "モ", "[ゃャヤ]", "[ゅュユ]", "[ょョヨ]", "[ラㇻ]", "[リㇼ]", "[ルㇽ]", "[レㇾ]", "[ロㇿ]", "[ゎヮワヷ]", "[ヰヸ]", "[ヱヹ]", "[ヲヺ]", "ン", "[゙゚゛゜ゝゞ・ヽヾ]", "𛀀", "1", "2", "3", "4", "5", "6", "7", "8", "9", "0"}, to = {"あ", "い", "う", "え", "お", "か", "き", "く", "け", "こ", "さ", "し", "す", "せ", "そ", "た", "ち", "つ", "て", "と", "な", "に", "ぬ", "ね", "の", "は", "ひ", "ふ", "へ", "ほ", "ま", "み", "む", "め", "も", "や", "ゆ", "よ", "ら", "り", "る", "れ", "ろ", "わ", "ゐ", "ゑ", "を", "ん", "", "え", "い", "に", "み", "よ", "ご", "ろ", "な", "は", "き", "れ"}}, ]] } m["jv"] = { canonicalName = "ဂျာဗာ", otherNames = {"Javanese"}, scripts = {"Latn", "Java"}, family = "poz-sus", translit_module = "jv-translit", ancestors = {"kaw"}, link_tr = true, } m["ka"] = { canonicalName = "ဂျဝ်ဂျဳယျာ", otherNames = {"Georgian", "Kartvelian", "Judeo-Georgian", "Kivruli", "Gruzinic"}, scripts = {"Geor", "Geok", "Hebr"}, -- Hebr is used to write Judeo-Georgian family = "ccs-gzn", ancestors = {"oge"}, translit_module = "Geor-translit", override_translit = true, entry_name = { from = {"̂"}, to = {""}}, } m["kg"] = { canonicalName = "ခါမ်ဂဝ်", otherNames = {"Kongo", "Kikongo", "Koongo", "Laari", "San Salvador Kongo", "Yombe"}, scripts = {"Latn"}, family = "bnt", } m["ki"] = { canonicalName = "ခဳခူယူ", otherNames = {"Kikuyu", "Gikuyu", "Gĩkũyũ"}, scripts = {"Latn"}, family = "bnt", } m["kj"] = { canonicalName = "ကောန်ယာမာ", otherNames = {"Kwanyama", "Kuanyama", "Oshikwanyama"}, scripts = {"Latn"}, family = "bnt", wikipedia_article = "Kwanyama dialect", } m["kk"] = { canonicalName = "ကဇက်", scripts = {"Kazakh", "Cyrl", "Latn", "Arab", "kk-Arab"}, family = "trk-kip", ancestors = {"trk-pro"}, translit_module = "kk-translit", override_translit = true, } m["kl"] = { canonicalName = "ဂရိန်လာန်", otherNames = {"Greenlandic", "Kalaallisut"}, scripts = {"Latn"}, family = "esx-inu", } m["km"] = { "ခမေန်", "Q9205", family = "mkh-kmr", aliases = {"Khmer", "Cambodian"}, scripts = {"Khmr"}, ancestors = {"aav-pro", "mkh-pro", "mkh-kmr-pro", "okz", "xhm"}, translit_module = "km-translit", } m["kn"] = { canonicalName = "ကာန်နဒါ", otherNames = {"Kannada", "ကန္နာဒါ"}, scripts = {"Knda"}, family = "dra", translit_module = "kn-translit", wikipedia_article = "Kannada", ancestors = {"dra-mkn"}, } m["ko"] = { "ကိုဝ်ရဳယျာ", "Q9176", "qfa-kor", aliases = {"Korean", "Modern Korean"}, scripts = {"Kore", "Brai"}, ancestors = {"ko-ear"}, -- 20210122 trial idea: strip parenthesized hanja from entry link -- Hani regex is a reasonable subset of Hani from [[Module:scripts/data]], -- last updated on 20210203. entry_name = { from = { "%([一-鿿㐀-䶿𠀀-𮯯"..u(0x2F800).."-𯨟𰀀-𱍏﨎﨏﨑﨓﨔﨟﨡﨣﨤﨧﨨﨩]+%)", }, to = { "", }}, translit_module = "ko-translit", } m["kr"] = { canonicalName = "ကနူရဳ", otherNames = {"Kanuri", "Kanembu", "Bilma Kanuri", "Central Kanuri", "Manga Kanuri", "Tumari Kanuri"}, scripts = {"Latn", "Arab"}, family = "ssa-sah", sort_key = { from = {"ny", "ǝ", "sh"}, to = {"n~", "e~", "s~"}} , -- the sortkey and entry_name are only for standard Kanuri; when dialectal entries get added, someone will have to work out how the dialects should be represented orthographically entry_name = { from = {"À", "à", "È", "è", "Ǝ̀", "ǝ̀", "Ì", "ì", "Ò", "ò", "Ù", "ù", "Â", "â", "Ê", "ê", "Ǝ̂", "ǝ̂", "Î", "î", "Ô", "ô", "Û", "û", "Ă", "ă", "Ĕ", "ĕ", "Ǝ̆", "ǝ̆", "Ĭ", "ĭ", "Ŏ", "ŏ", "Ŭ", "ŭ", "Á", "á", "É", "é", "Ǝ́", "ǝ́", "Í", "í", "Ó", "ó", "Ú", "ú", GRAVE, ACUTE}, to = {"A", "a", "E", "e", "Ǝ", "ǝ", "I", "i", "O", "o", "U", "u", "A", "a", "E", "e", "Ǝ", "ǝ", "I", "i", "O", "o", "U", "u", "A", "a", "E", "e", "Ǝ", "ǝ", "I", "i", "O", "o", "U", "u", "A", "a", "E", "e", "Ǝ", "ǝ", "I", "i", "O", "o", "U", "u"}}, } m["ks"] = { "ကာဒ်ရှ်မဳယျာ", 33552, "inc-dar", {"ks-Arab", "Deva", "Shrd", "Latn"}, translit_module = "translit-redirect", ancestors = {"sa"}, } m["ku"] = { canonicalName = "ကာဒဳ", otherNames = {"Kurdish"}, scripts = {"Latn", "ku-Arab", "Armn", "Cyrl"}, family = "ira-wes", wikipedia_article = "Kurdish languages", } -- "kv" IS TREATED AS "koi", "kpv", SEE WT:LT m["kw"] = { canonicalName = "ခမ်နေတ်", otherNames = {"Cornish"}, scripts = {"Latn"}, family = "cel-bry", ancestors = {"ine-pro", "cel-pro", "cel-bry-pro", "oco", "cnx"}, } m["ky"] = { canonicalName = "ကာဇေတ်", otherNames = {"Kyrgyz", "Kirghiz", "Kirgiz"}, scripts = {"Cyrl", "Latn", "Arab"}, family = "trk-kip", translit_module = "ky-translit", override_translit = true, ancestors = {"trk-pro", "qwm"}, } m["la"] = { canonicalName = "လပ်တေန်", otherNames = {"Latin"}, scripts = {"Latn"}, family = "itc", ancestors = {"itc-ola"}, entry_name = { from = {"[ĀĂ]", "[āă]", "[ĒĔ]", "[ēĕë]", "[ĪĬÏ]", "[īĭï]", "[ŌŎ]", "[ōŏ]", "[ŪŬÜ]", "[ūŭü]", "Ȳ", "ȳ", MACRON, BREVE, DIAER}, to = {"A", "a", "E", "e", "I", "i", "O", "o", "U", "u", "Y", "y"}}, wikipedia_article = "Latin", standardChars = "A-Za-zÆæŒœĀ-ăĒ-ĕĪ-ĭŌ-ŏŪ-ŭȲȳ" .. MACRON .. BREVE .. PUNCTUATION } m["lb"] = { canonicalName = "လူဇေန်ဘာဂျ်", otherNames = {"Luxembourgish"}, scripts = {"Latn"}, family = "gmw", ancestors = {"gmh"}, wikipedia_article = "Luxembourgish", } m["lg"] = { canonicalName = "လုဂန်ဒါ", otherNames = {"ဂန်ဒါ", "Luganda", "Ganda", "Oluganda"}, scripts = {"Latn"}, family = "bnt", entry_name = { from = {"á", "Á", "é", "É", "í", "Í", "ó", "Ó", "ú", "Ú", "ń", "Ń", "ḿ", "Ḿ", "â", "Â", "ê", "Ê", "î", "Î", "ô", "Ô", "û", "Û" }, to = {"a", "A", "e", "E", "i", "I", "o", "O", "u", "U", "n", "N", "m", "M", "a", "A", "e", "E", "i", "I", "o", "O", "u", "U",}}, sort_key = { from = {"ŋ"}, to = {"n"}} , wikipedia_article = "Luganda", } m["li"] = { canonicalName = "လိမ်ဗူရ်ဂိသ်", otherNames = {"Limburgish", "Limburgan", "Limburgian", "Limburgic"}, scripts = {"Latn"}, family = "gmw", ancestors = {"dum"}, } m["ln"] = { canonicalName = "လေန်ဂါလာ", otherNames = {"Lingala", "Ngala"}, scripts = {"Latn"}, family = "bnt", wikipedia_article = "Lingala", } m["lo"] = { canonicalName = "သေံလဴ", otherNames = {"သေံလဴ", "Lao", "Laotian"}, scripts = {"Laoo"}, family = "tai-swe", translit_module = "lo-translit", sort_key = { from = {"ຼ", "ຽ", "ໜ", "ໝ", "([ເແໂໃໄ])([ກ-ຮ])"}, to = {"ລ", "ຍ", "ຫນ", "ຫມ", "%2%1"}}, ancestors = {"qfa-tak-pro", "qfa-bet-pro", "tai-pro", "tai-swe-pro"}, } m["lt"] = { canonicalName = "လေတ်တူယဵုနဳယျာ", otherNames = {"Lithuanian", "လေတ်တူယဵုနဳယျာ"}, scripts = {"Latn"}, family = "bat", ancestors = {"ine-pro", "ine-bsl-pro", "bat-pro", "olt"}, entry_name = { from = {"[áãà]", "[ÁÃÀ]", "[éẽè]", "[ÉẼÈ]", "[íĩì]", "[ÍĨÌ]", "[ýỹ]", "[ÝỸ]", "ñ", "[óõò]", "[ÓÕÒ]", "[úũù]", "[ÚŨÙ]", ACUTE, GRAVE, TILDE}, to = {"a", "A", "e", "E", "i", "I", "y", "Y", "n", "o", "O", "u", "U"}} , } m["lu"] = { canonicalName = "ဠူဘ-ကာတေန်ဂါ", scripts = {"Latn"}, family = "bnt", } m["lv"] = { canonicalName = "လပ်ဗဳယာ", otherNames = {"Latvian", "Lettish", "Lett"}, scripts = {"Latn"}, family = "bat", ancestors = {"ine-bsl-pro", "bat-pro"}, entry_name = { -- This attempts to convert vowels with tone marks to vowels either with -- or without macrons. Specifically, there should be no macrons if the -- vowel is part of a diphthong (including resonant diphthongs such -- pìrksts -> pirksts not #pīrksts). What we do is first convert the -- vowel + tone mark to a vowel + tilde in a decomposed fashion, -- then remove the tilde in diphthongs, then convert the remaining -- vowel + tilde sequences to macroned vowels, then delete any other -- tilde. We leave already-macroned vowels alone: Both e.g. ar and ār -- occur before consonants. FIXME: This still might not be sufficient. from = {"Ȩ", "ȩ", "[ÂÃÀ]", "[âãà]", "[ÊẼÈ]", "[êẽè]", "[ÎĨÌ]", "[îĩì]", "[ÔÕÒ]", "[ôõò]", "[ÛŨÙ]", "[ûũù]", "[ÑǸ]", "[ñǹ]", "[" .. CIRC .. TILDE ..GRAVE .."]", "([aAeEiIoOuU])" .. TILDE .."?([lrnmuiLRNMUI])" .. TILDE .. "?([^aAeEiIoOuUāĀēĒīĪūŪ])", "([aAeEiIoOuU])" .. TILDE .."?([lrnmuiLRNMUI])" .. TILDE .."?$", "([iI])" .. TILDE .. "?([eE])" .. TILDE .. "?", "A" .. TILDE, "a" .. TILDE, "E" .. TILDE, "e" .. TILDE, "I" .. TILDE, "i" .. TILDE, "U" .. TILDE, "u" .. TILDE, TILDE}, to = {"E", "e", "A" .. TILDE, "a" .. TILDE, "E" .. TILDE, "e" .. TILDE, "I" .. TILDE, "i" .. TILDE, "O", "o", "U" .. TILDE, "u" .. TILDE, "N", "n", TILDE, "%1%2%3", "%1%2", "%1%2", "Ā", "ā", "Ē", "ē", "Ī", "ī", "Ū", "ū", ""}}, } m["mg"] = { canonicalName = "မာလာဂါသဳ", otherNames = {"Malagasy", "Betsimisaraka Malagasy", "Betsimisaraka", "Northern Betsimisaraka Malagasy", "Northern Betsimisaraka", "Southern Betsimisaraka Malagasy", "Southern Betsimisaraka", "Bara Malagasy", "Bara", "Masikoro Malagasy", "Masikoro", "Antankarana", "Antankarana Malagasy", "Plateau Malagasy", "Sakalava", "Tandroy Malagasy", "Tandroy", "Tanosy", "Tanosy Malagasy", "Tesaka", "Tsimihety", "Tsimihety Malagasy", "Bushi", "Shibushi", "Kibushi", "Sakalava"}, scripts = {"Latn"}, family = "poz-bre", } m["mh"] = { canonicalName = "မာချဲလဳ", otherNames = {"Marshallese"}, scripts = {"Latn"}, family = "poz-mic", sort_key = { from = {"ā" , "ļ" , "m̧" , "ņ" , "n̄" , "o̧" , "ō" , "ū" }, to = {"a~", "l~", "m~", "n~", "n~~", "o~", "o~~", "u~"}} , } m["mi"] = { canonicalName = "မဝ်ရဳ", otherNames = {"Maori", "Māori"}, scripts = {"Latn"}, family = "poz-pol", wikipedia_article = "Māori language", sort_key = { from = {"ā" , "ļ" , "m̧" , "ņ" , "n̄" , "o̧" , "ō" , "ū" }, to = {"a~", "l~", "m~", "n~", "n~~", "o~", "o~~", "u~"}} , } m["mk"] = { canonicalName = "မက်သဳဒဝ်နဳယျာ", otherNames = {"Macedonian"}, scripts = {"Cyrl"}, family = "zls", translit_module = "mk-translit", ancestors = {"ine-pro", "ine-bsl-pro", "sla-pro"}, entry_name = { from = {ACUTE}, to = {}}, } m["ml"] = { canonicalName = "မလေဝ်ယျလာမ်", otherNames = {"Malayalam"}, scripts = {"Mlym"}, family = "dra", translit_module = "ml-translit", override_translit = true, wikipedia_article = "Malayalam", } m["mn"] = { canonicalName = "မန်ဂဝ်လဳယျာ", otherNames = {"မန်ဂဝ်လဳယျာ", "ခန်ခါ မန်ဂဝ်လဳယျာ"}, scripts = {"Cyrl", "Mong", "Soyo", "Zanb"}, -- entries in Soyo or Zanb might require prior discussion family = "xgn", ancestors = {"cmg"}, translit_module = "mn-translit", override_translit = true, } -- "mo" IS TREATED AS "ro", SEE WT:LT m["mr"] = { canonicalName = "မာရဒဳ", otherNames = {"Marathi"}, scripts = {"Deva", "Modi"}, family = "inc", ancestors = {"omr"}, translit_module = "hi-translit", } m["ms"] = { canonicalName = "မလေဝ်", otherNames = {"Malay", "Malaysian", "Standard Malay", "Orang Seletar", "Orang Kanaq", "Jakun", "Temuan"}, scripts = {"Latn", "ms-Arab"}, family = "poz-mly", ancestors = {"map-pro", "poz-pro", "poz-sus-pro", "poz-msa-pro", "poz-mcm-pro", "poz-mly-pro", "ms-old", "ms-cla"}, } m["mt"] = { canonicalName = "မာလ်တဳ", otherNames = {"Maltese"}, scripts = {"Latn"}, family = "sem-arb", ancestors = {"sqr"}, } m["my"] = { canonicalName = "ဗၟာ", otherNames = {"Burmese", "Myanmar", "ဗၟာ"}, scripts = {"Mymr"}, family = "tbq-brm", ancestors = {"obr", "sit-pro", "tbq-pro"}, wikipedia_article = "ဘာသာဗၟာ", translit_module = "my-translit", override_translit = true, } m["na"] = { canonicalName = "နာဥူလောန်", otherNames = {"Nauruan","Nauru"}, scripts = {"Latn"}, family = "poz-mic", } m["nb"] = { canonicalName = "နဝ်ဝေ ဗော်ခ်မဝ်", otherNames = {"Norwegian Bokmål", "Bokmål"}, scripts = {"Latn"}, family = "gmq", ancestors = {"gmq-mno", "gem-pro"}, wikimedia_codes = {"no"}, wikipedia_article = "Bokmål", } m["nd"] = { canonicalName = "Northern Ndebele", otherNames = {"North Ndebele"}, scripts = {"Latn"}, family = "bnt-ngu", entry_name = { from = {"[āàáâǎ]", "[ēèéêě]", "[īìíîǐ]", "[ōòóôǒ]", "[ūùúûǔ]", "ḿ", "[ǹńň]", MACRON, ACUTE, GRAVE, CIRC, CARON}, to = {"a" , "e" , "i" , "o" , "u" , "m", "n" }}, } m["ne"] = { "နဳပဝ်", 33823, "inc-pah", scripts = {"Deva", "Newa"}, ancestors = {"ine-pro", "iir-pro", "inc-pro", "sa", "inc-ash", "pra-kha"}, translit_module = "ne-translit", } m["ng"] = { canonicalName = "အွန်ဒွန်ဂါ", otherNames = {"Ndonga"}, scripts = {"Latn"}, family = "bnt", wikipedia_article = "Ndonga dialect", } m["nl"] = { canonicalName = "ဒါတ်", otherNames = {"Dutch", "Netherlandic", "Flemish"}, scripts = {"Latn"}, family = "gmw", ancestors = {"dum"}, sort_key = { from = {"[äáâå]", "[ëéê]", "[ïíî]", "[öóô]", "[üúû]", "ç", "ñ", "^-"}, to = {"a" , "e" , "i" , "o" , "u" , "c", "n"}} , standardChars = "A-Za-z0-9" .. PUNCTUATION .. u(0x2800) .. "-" .. u(0x28FF), } m["nn"] = { canonicalName = "နဝ်ဝေ နဳနိုတ်", otherNames = {"Norwegian Nynorsk", "New Norwegian", "Nynorsk"}, scripts = {"Latn"}, family = "gmq", ancestors = {"gmq-mno"}, wikipedia_article = "Nynorsk", } m["no"] = { canonicalName = "နဝ်ဝေ", otherNames = {"Norwegian"}, scripts = {"Latn"}, family = "gmq", ancestors = {"gmq-mno"}, } m["nr"] = { canonicalName = "အာန်ဒေဗေလေဝ် လ္ပာ်ဒိုဟ်သမၠုင်ကျာ", otherNames = {"South Ndebele"}, scripts = {"Latn"}, family = "bnt-ngu", entry_name = { from = {"[āàáâǎ]", "[ēèéêě]", "[īìíîǐ]", "[ōòóôǒ]", "[ūùúûǔ]", "ḿ", "[ǹńň]", MACRON, ACUTE, GRAVE, CIRC, CARON}, to = {"a" , "e" , "i" , "o" , "u" , "m", "n" }}, } m["nv"] = { "နာဝါဟဝ်", 13310, "apa", Latn, sort_key = { from = {"[áą]", "[éę]", "[íį]", "[óǫ]", "ń", "^n([djlt])", "ł" , "[ʼ’']", ACUTE}, to = {"a" , "e" , "i" , "o" , "n", "ni%1" , "l~"}}, -- the tilde is used to guarantee that ł will always be sorted after all other words with l } m["ny"] = { canonicalName = "ချဳချေန်ဝါ", otherNames = {"နရန်ဂျာ", "Chichewa", "Chicheŵa", "Chinyanja", "Nyanja", "Chewa", "Cicewa", "Cewa", "Cinyanja"}, scripts = {"Latn"}, family = "bnt", entry_name = { from = {"ŵ", "Ŵ", "á", "Á", "é", "É", "í", "Í", "ó", "Ó", "ú", "Ú", "ń", "Ń", "ḿ", "Ḿ" }, to = {"w", "W", "a", "A", "e", "E", "i", "I", "o", "O", "u", "U", "n", "N", "m", "M"}}, sort_key = { from = {"ng'"}, to = {"ng"}} , wikipedia_article = "Chewa language", } m["oc"] = { "အောက်စဳတာန်", "Q14185", "roa-ocr", aliases = {"အောက်စဳတာန်"}, -- don't list varieties here that are in [[Module:etymology languages/data]] scripts = {"Latn", "Hebr"}, ancestors = {"pro"}, sort_key = { from = {"[àá]", "[èé]", "[íï]", "[òó]", "[úü]", "ç", "([lns])·h"}, to = {"a" , "e" , "i" , "o" , "u" , "c", "%1h" }} , } m["oj"] = { canonicalName = "အဝ်ဂျဳဗဝေ", otherNames = {"Ojibwe", "Chippewa", "Ojibway", "Ojibwemowin", "Southwestern Ojibwa"}, scripts = {"Cans", "Latn"}, family = "alg", } m["om"] = { canonicalName = "အဝ်ရဝ်မဝ်", otherNames = {"Oromo", "Orma", "Borana-Arsi-Guji Oromo", "West Central Oromo"}, scripts = {"Latn", "Ethi"}, family = "cus-eas", } m["or"] = { canonicalName = "အဝ်ရေဝ်ယာ", otherNames = {"Oriya", "Odia", "Oorya"}, scripts = {"Orya"}, family = "inc", ancestors = {"inc-mgd"}, translit_module = "or-translit", wikipedia_article = "Odia language", } m["os"] = { canonicalName = "အဝ်ဇြဳယာန်", otherNames = {"Ossetian", "Ossete", "Ossetic", "Digor", "Iron"}, scripts = {"Cyrl", "Geor", "Latn"}, family = "ira", ancestors = {"oos"}, translit_module = "os-translit", override_translit = true, entry_name = { from = {GRAVE, ACUTE}, to = {}} , } m["pa"] = { canonicalName = "ပါန်ချာပဳ", otherNames = {"Punjabi", "Panjabi"}, scripts = {"Guru", "pa-Arab"}, family = "inc-opa", ancestors = {"inc-opa"}, translit_module = "translit-redirect", entry_name = { from = {u(0x064B), u(0x064C), u(0x064D), u(0x064E), u(0x064F), u(0x0650), u(0x0651), u(0x0652), u(0x0658), u(0x08C7), u(0x0768)}, to = {"", "", "", "", "", "", "", "", "", "ل", "ن"}} , } m["pi"] = { "ပါဠိ", "Q36727", "inc-mid", scripts = {"Latn", "Brah", "Deva", "Beng", "Sinh", "Mymr", "Thai", "Lana", "Laoo", "Khmr"}, ancestors = {"sa"}, translit_module = "pi-translit", sort_key = { from = {"ā", "ī", "ū", "ḍ", "ḷ", "[ṁṃ]", "ṅ", "ñ", "ṇ", "ṭ", "([เโ])([ก-ฮ])", "([ເໂ])([ກ-ຮ])", "ᩔ", "ᩕ", "ᩖ", "ᩘ", "([ᨭ-ᨱ])ᩛ", "([ᨷ-ᨾ])ᩛ", "ᩤ", u(0xFE00), u(0x200D)}, to = {"a~", "i~", "u~", "d~", "l~", "m~", "n~", "n~~", "n~~~", "t~", "%2%1", "%2%1", "ᩈ᩠ᩈ", "᩠ᩁ", "᩠ᩃ", "ᨦ᩠", "%1᩠ᨮ", "%1᩠ᨻ", "ᩣ"}} , entry_name = { from = {u(0xFE00)}, to = {}}, } m["pl"] = { canonicalName = "ပဝ်လာန်", otherNames = {"Polish"}, scripts = {"Latn"}, family = "zlw", ancestors = {"zlw-opl", "sla-pro"}, sort_key = { from = {"[Ąą]", "[Ćć]", "[Ęę]", "[Łł]", "[Ńń]", "[Óó]", "[Śś]", "[Żż]", "[Źź]"}, to = { "a" .. u(0x10FFFF), "c" .. u(0x10FFFF), "e" .. u(0x10FFFF), "l" .. u(0x10FFFF), "n" .. u(0x10FFFF), "o" .. u(0x10FFFF), "s" .. u(0x10FFFF), "z" .. u(0x10FFFF), "z" .. u(0x10FFFE)}} , } m["ps"] = { "ပါသတုန်", "Q58680", "ira-pat", aliases = {"Pashtun", "Pushto", "Pashtu", "Afghani"}, varieties = {"Central Pashto", "Northern Pashto", "Southern Pashto", {"Pukhto", "Pakhto", "Pakkhto"}}, scripts = {"ps-Arab"}, ancestors = {"ira-pat-pro"}, } m["pt"] = { canonicalName = "ပဝ်တူဂြဳ", otherNames = {"Portuguese", "Modern Portuguese"}, scripts = {"Latn", "Brai"}, family = "roa", ancestors = {"ine-pro", "itc-pro", "itc-ola", "la", "roa-opt"}, sort_key = { from = {"[àãáâä]", "[èẽéêë]", "[ìĩíï]", "[òóôõö]", "[üúùũ]", "ç", "ñ"}, to = {"a" , "e" , "i" , "o" , "u" , "c", "n"}} , } m["qu"] = { canonicalName = "ခေန်ချူဝါ", scripts = {"Latn"}, family = "qwe", wikipedia_article = "ဘာသာခေန်ချူဝါ", } m["rm"] = { canonicalName = "ရဝ်မာန်", otherNames = {"Romansch","Romansh", "Rumantsch", "Romanche"}, scripts = {"Latn"}, family = "roa", wikipedia_article = "Romansh language", } m["ro"] = { canonicalName = "ရဝ်မေနဳယျာ", otherNames = {"Romanian", "Daco-Romanian", "Roumanian", "Rumanian"}, scripts = {"Latn", "Cyrl"}, family = "roa", sort_key = { from = {"ă" , "â" , "î" , "ș" , "ț" }, to = {"a~", "a~~", "i~", "s~", "t~"}}, } m["ru"] = { canonicalName = "ရုဿျှာ", otherNames = {"Russian"}, scripts = {"Cyrl", "Brai"}, family = "zle", translit_module = "ru-translit", sort_key = { from = {"ё"}, to = {"е" .. mw.ustring.char(0x10FFFF)}}, entry_name = { from = {"Ѐ", "ѐ", "Ѝ", "ѝ", GRAVE, ACUTE}, to = {"Е", "е", "И", "и"}}, standardChars = "ЁІА-яёі0-9—" .. PUNCTUATION, } m["rw"] = { canonicalName = "ရဝမ်ဒါ ရမ်ဒဳ", otherNames = {"Rwanda-Rundi", "Rwanda", "Kinyarwanda", "Rundi", "Kirundi", "Ha", "Giha", "Hangaza", "Vinza", "Shubi", "Subi"}, scripts = {"Latn"}, family = "bnt", wikipedia_article = "Rwanda-Rundi", } m["sa"] = { canonicalName = "သံသကြိုတ်", otherNames = {"Sanskrit"}, scripts = {"Deva", "Bali", "as-Beng", "Beng", "Bhks", "Brah", "Gran", "Gujr", "Guru", "Java", "Khar", "Khmr", "Knda", "Lana", "Laoo", "Mlym", "Modi", "Mymr", "Nand", "Newa", "Orya", "Saur", "Shrd", "Sidd", "Sinh", "Taml", "Telu", "Thai", "Tibt", "Tirh"}, family = "inc-old", sort_key = { from = {"ā", "ī", "ū", "ḍ", "ḷ", "ḹ", "[ṁṃ]", "ṅ", "ñ", "ṇ", "ṛ", "ṝ", "ś", "ṣ", "ṭ", "([เโไ])([ก-ฮ])", "([ເໂໄ])([ກ-ຮ])", "ᩔ", "ᩕ", "ᩖ", "ᩘ", "([ᨭ-ᨱ])ᩛ", "([ᨷ-ᨾ])ᩛ", "ᩤ", u(0xFE00), u(0x200D)}, to = {"a~", "i~", "u~", "d~", "l~", "l~~", "m~", "n~", "n~~", "n~~~", "r~", "r~~", "s~", "s~~", "t~", "%2%1", "%2%1", "ᩈ᩠ᩈ", "᩠ᩁ", "᩠ᩃ", "ᨦ᩠", "%1᩠ᨮ", "%1᩠ᨻ", "ᩣ"}}, entry_name = { from = {"ึ", u(0xF700), u(0xF70F), u(0xFE00)}, to = {"ิํ", "ฐ", "ญ"}}, translit_module = "translit-redirect", ancestors = {"iir-pro", "inc-pro"}, } m["sc"] = { canonicalName = "သာဒဳနဳယာန်", otherNames = {"Sardinian", "Campidanese", "Campidanese Sardinian", "Logudorese", "Logudorese Sardinian", "Nuorese", "Nuorese Sardinian"}, scripts = {"Latn"}, family = "roa", } m["sd"] = { "သိန္ဓိ", 33997, "inc-snd", scripts = {"sd-Arab", "Deva", "Sind", "Khoj"}, entry_name = { from = {u(0x0671), u(0x064B), u(0x064C), u(0x064D), u(0x064E), u(0x064F), u(0x0650), u(0x0651), u(0x0652), u(0x0670), u(0x0640)}, to = {u(0x0627)}}, ancestors = {"inc-vra"}, translit_module = "translit-redirect", } m["se"] = { canonicalName = "သာမိ သၟဝ်ကျာ", otherNames = {"Northern Sami", "North Sami", "Northern Saami", "North Saami"}, scripts = {"Latn"}, family = "smi", entry_name = { from = {"([đflmnŋrsšŧv])'%1"}, to = {"%1%1"} }, wikipedia_article = "Northern Sami", } m["sg"] = { canonicalName = "သင်ဂဝ်", otherNames = {"Sango"}, scripts = {"Latn"}, family = "crp", } m["sh"] = { canonicalName = "သာဗ်ခြဝ်ဨရှဳယာန်", otherNames = {"Serbo-Croatian", "BCS", "Croato-Serbian", "Serbocroatian", "Bosnian", "Croatian", "Montenegrin", "Serbian"}, scripts = {"Latn", "Cyrl"}, family = "zls", ancestors = {"ine-pro", "ine-bsl-pro", "sla-pro"}, entry_name = { from = {"[ȀÀȂÁĀÃ]", "[ȁàȃáāã]", "[ȄÈȆÉĒẼ]", "[ȅèȇéēẽ]", "[ȈÌȊÍĪĨ]", "[ȉìȋíīĩ]", "[ȌÒȎÓŌÕ]", "[ȍòȏóōõ]", "[ȐȒŔ]", "[ȑȓŕ]", "[ȔÙȖÚŪŨ]", "[ȕùȗúūũ]", "Ѐ", "ѐ", "[ӢЍ]", "[ӣѝ]", "[Ӯ]", "[ӯ]", GRAVE, ACUTE, DGRAVE, INVBREVE, MACRON, TILDE}, to = {"A" , "a" , "E" , "e" , "I" , "i" , "O" , "o" , "R" , "r" , "U" , "u" , "Е", "е", "И" , "и", "У", "у" }}, wikimedia_codes = {"sh", "bs", "hr", "sr"}, wikipedia_article = "Serbo-Croatian", } m["si"] = { canonicalName = "သိၚ်္ဃဵုရ်", otherNames = {"Sinhalese", "Singhalese", "Sinhala"}, scripts = {"Sinh"}, family = "inc", ancestors = {"elu-prk"}, translit_module = "si-translit", override_translit = true, } m["sk"] = { canonicalName = "သလဝ်ဝေန်နဳယျာ", otherNames = {"Slovak"}, scripts = {"Latn"}, family = "zlw", ancestors = {"ine-pro", "ine-bsl-pro", "sla-pro", "zlw-osk"}, sort_key = { from = {"[áä]", "é", "í", "[óô]", "ú", "ý", "ŕ", "ĺ", "[" .. DIAER .. ACUTE .. CIRC .. "]"}, to = {"a" , "e", "i", "o" , "u", "y", "r", "l", ""}} , } m["sl"] = { canonicalName = "သၠဝ်ဝေနဳ", otherNames = {"Slovene", "Slovenian"}, scripts = {"Latn"}, family = "zls", entry_name = { from = {"[ÁÀÂȂȀ]", "[áàâȃȁ]", "[ÉÈÊȆȄỆẸ]", "[éèêȇȅệẹə]", "[ÍÌÎȊȈ]", "[íìîȋȉ]", "[ÓÒÔȎȌỘỌ]", "[óòôȏȍộọ]", "[ŔȒȐ]", "[ŕȓȑ]", "[ÚÙÛȖȔ]", "[úùûȗȕ]", "ł", GRAVE, ACUTE, DGRAVE, INVBREVE, CIRC, DOTBELOW}, to = {"A" , "a" , "E" , "e" , "I" , "i" , "O" , "o" , "R" , "r" , "U" , "u" , "l"}} , } m["sm"] = { canonicalName = "သမဝ်အာန်", otherNames = {"Samoan"}, scripts = {"Latn"}, family = "poz-pol", } m["sn"] = { canonicalName = "သျှိနာ", otherNames = {"Shona"}, scripts = {"Latn"}, family = "bnt", } m["so"] = { canonicalName = "ဆဝ်မာလဳ", otherNames = {"Somali"}, scripts = {"Latn", "Arab", "Osma"}, family = "cus", entry_name = { from = {"[ÁÀÂ]", "[áàâ]", "[ÉÈÊ]", "[éèê]", "[ÍÌÎ]", "[íìî]", "[ÓÒÔ]", "[óòô]", "[ÚÙÛ]", "[úùû]", "[ÝỲ]", "[ýỳ]"}, to = {"A" , "a" , "E" , "e" , "I" , "i" , "O" , "o" , "U" , "u", "Y", "y"}} , } m["sq"] = { canonicalName = "အလ်ဗနဳယာန်", otherNames = {"Albanian"}, scripts = {"Latn", "Elba"}, family = "sqj", ancestors = {"ine-pro", "sqj-pro"}, sort_key = { from = { '[âãä]', '[ÂÃÄ]', '[êẽë]', '[ÊẼË]', 'ĩ', 'Ĩ', 'õ', 'Õ', 'ũ', 'Ũ', 'ỹ', 'Ỹ', 'ç', 'Ç' }, to = { 'a', 'A', 'e', 'E', 'i', 'I', 'o', 'O', 'u', 'U', 'y', 'Y', 'c', 'C' } } , } m["ss"] = { canonicalName = "သဝါဇြဳ", otherNames = {"Swazi", "Swati"}, scripts = {"Latn"}, family = "bnt-ngu", entry_name = { from = {"[āàáâǎ]", "[ēèéêě]", "[īìíîǐ]", "[ōòóôǒ]", "[ūùúûǔ]", "ḿ", "[ǹńň]", MACRON, ACUTE, GRAVE, CIRC, CARON}, to = {"a" , "e" , "i" , "o" , "u" , "m", "n" }}, ancestors = {"bnt-pro"}, } m["st"] = { canonicalName = "သူထူ", otherNames = {"Sotho", "Sesotho", "Southern Sesotho", "Southern Sotho"}, scripts = {"Latn"}, family = "bnt", } m["su"] = { canonicalName = "သာန်ဓနဳ", otherNames = {"Sundanese"}, scripts = {"Sund", "Latn"}, family = "poz-msa", ancestors = {"map-pro", "poz-pro", "poz-sus-pro", "poz-msa-pro", "osn"}, translit_module = "su-translit", } m["sv"] = { canonicalName = "သွဳဒေန်", otherNames = {"Swedish"}, scripts = {"Latn"}, family = "gmq", ancestors = {"gmq-osw", "gem-pro", "ine-pro"}, sort_key = { from = {"ö", "å", "ä"}, to = {"o", "a", "a"}} , } m["sw"] = { canonicalName = "သဝါတ်ဟဳလဳ", otherNames = {"Swahili", "Settler Swahili", "KiSetla", "KiSettla", "Setla", "Settla", "Kitchen Swahili", "Kihindi", "Indian Swahili", "KiShamba", "Kishamba", "Field Swahili", "Kibabu", "Asian Swahili", "Kimanga", "Arab Swahili", "Kitvita", "Army Swahili"}, scripts = {"Latn", "Arab"}, family = "bnt", sort_key = { from = {"ng'", "^-"}, to = {"ngz"}} , } m["ta"] = { canonicalName = "တမဳလ်", otherNames = {"Tamil"}, scripts = {"Taml"}, family = "dra", ancestors = {"oty"}, translit_module = "ta-translit", override_translit = true, } m["te"] = { canonicalName = "တေလုဂု", otherNames = {"Telugu"}, scripts = {"Telu"}, family = "dra", ancestors = {"dra-pro", "dra-sou-pro", "dra-sdt-pro", "dra-ote"}, translit_module = "te-translit", override_translit = true, } m["tg"] = { canonicalName = "တာဇိက်", otherNames = {"Tajik", "Tadjik", "Tadzhik", "Tajiki", "Tajik Persian"}, scripts = {"Cyrl", "fa-Arab", "Latn"}, family = "ira-wes", ancestors = {"fa"}, translit_module = "tg-translit", override_translit = true, sort_key = { from = {"Ё", "ё"}, to = {"Е" , "е"}} , entry_name = { from = {ACUTE}, to = {}} , } m["th"] = { "သေံ", 9217, family = "tai-swe", scripts = {"Thai", "Brai"}, translit_module = "th-translit", sort_key = { from = {"[%pๆ]", "[็-๎]", "([เแโใไ])([ก-ฮ])"}, to = {"", "", "%2%1"}}, ancestors = {"qfa-tak-pro", "qfa-bet-pro", "tai-pro", "tai-swe-pro"}, } m["ti"] = { canonicalName = "တဳဂျရေဝ်ယျာ", otherNames = {"Tigrinya"}, scripts = {"Ethi"}, family = "sem-eth", translit_module = "Ethi-translit", } m["tk"] = { canonicalName = "တာခ်မေန်", otherNames = {"Turkmen"}, scripts = {"Latn", "Cyrl"}, family = "trk-ogz", entry_name = { from = {"ā", "ē", "ī", "ō", "ū", "ȳ", "ȫ", "ǖ", MACRON}, to = {"a", "e", "i", "o", "u", "y", "ö", "ü", ""}}, } m["tl"] = { canonicalName = "တာဂါလံက်", otherNames = {"Tagalog"}, scripts = {"Latn", "Tglg"}, family = "phi", entry_name = { from = {"[áàâ]", "[éèê]", "[íìî]", "[óòô]", "[úùû]", ACUTE, GRAVE, CIRC}, to = {"a" , "e" , "i" , "o" , "u" }}, translit_module = "tl-translit", override_translit = true } m["tn"] = { canonicalName = "သွာနာ", otherNames = {"Tswana", "Setswana"}, scripts = {"Latn"}, family = "bnt", } m["to"] = { canonicalName = "ထံင်ဂံင်", otherNames = {"Tongan"}, scripts = {"Latn"}, family = "poz-pol", } m["tr"] = { canonicalName = "တူရကဳ", otherNames = {"Turkish"}, scripts = {"Latn"}, family = "trk-ogz", ancestors = {"ota"}, } m["ts"] = { canonicalName = "သွေန်ဂါ", otherNames = {"Tsonga"}, scripts = {"Latn"}, family = "bnt", ancestors = {"nic-pro", "alv-pro", "nic-vco-pro", "nic-bco-pro", "nic-bod-pro", "bnt-pro"}, } m["tt"] = { canonicalName = "တာတာ", otherNames = {"Tatar"}, scripts = {"Cyrl", "Latn", "Arab", "tt-Arab"}, family = "trk-kip", translit_module = "tt-translit", override_translit = true, } -- "tw" IS TREATED AS "ak", SEE WT:LT m["ty"] = { canonicalName = "တဟဳတဳဃှေန်", otherNames = {"Tahitian"}, scripts = {"Latn"}, family = "poz-pol", } m["ug"] = { canonicalName = "ဥူဃူရ်", otherNames = {"Uigur", "Uighur", "Uygur"}, scripts = {"ug-Arab", "Latn", "Cyrl"}, family = "trk", ancestors = {"chg"}, translit_module = "ug-translit", override_translit = true, } m["uk"] = { canonicalName = "ယူကရိန်", otherNames = {"Ukrainian"}, scripts = {"Cyrl"}, family = "zle", ancestors = {"ine-pro", "ine-bsl-pro", "sla-pro", "orv", "zle-ouk"}, translit_module = "uk-translit", entry_name = { from = {"Ѐ", "ѐ", "Ѝ", "ѝ", GRAVE, ACUTE}, to = {"Е", "е", "И", "и"}}, standardChars = "ЄІЇА-ЩЫЬЮ-щыьюяєії" .. PUNCTUATION } m["ur"] = { "အူရဒူ", "Q1617", "inc-hnd", scripts = {"ur-Arab"}, ancestors = {"inc-ohi"}, entry_name = { from = {u(0x064B), u(0x064C), u(0x064D), u(0x064E), u(0x064F), u(0x0650), u(0x0651), u(0x0652)}, to = {}} , } m["uz"] = { canonicalName = "ဥုသဗဝ်", otherNames = {"Uzbek", "Northern Uzbek", "Southern Uzbek"}, scripts = {"Latn", "Cyrl", "fa-Arab"}, family = "trk", ancestors = {"chg"}, translit_module = "uz-translit" } m["ve"] = { canonicalName = "ဗါန်ဒါ", otherNames = {"Venda"}, scripts = {"Latn"}, family = "bnt", } m["vi"] = { canonicalName = "ဗဳယေတ်နာမ်", otherNames = {"Vietnamese", "Annamese", "Annamite"}, scripts = {"Latn", "Hani"}, family = "mkh-vie", ancestors = {"mkh-mvi"}, sort_key = "vi-sortkey", } m["vo"] = { canonicalName = "ဝဝ်လပုက်", otherNames = {"Volapük"}, scripts = {"Latn"}, family = "art", wikipedia_article = "Volapük", } m["wa"] = { canonicalName = "ဝါဠူ", otherNames = {"Walloon", "Liégeois", "Namurois", "Wallo-Picard", "Wallo-Lorrain"}, scripts = {"Latn"}, family = "roa-oil", ancestors = {"fro"}, sort_key = { from = {"[áàâäå]", "[éèêë]", "[íìîï]", "[óòôö]", "[úùûü]", "[ýỳŷÿ]", "ç", "'"}, to = {"a" , "e" , "i" , "o" , "u" , "y" , "c"}} , } m["wo"] = { canonicalName = "ဝဝ်လံက်", otherNames = {"Wolof", "Gambian Wolof"}, -- the subsumed dialect 'wof' scripts = {"Latn", "Arab"}, family = "alv-sng", } m["xh"] = { canonicalName = "ခါဝ်သာ", otherNames = {"Xhosa"}, scripts = {"Latn"}, family = "bnt-ngu", entry_name = { from = {"[āàáâǎ]", "[ēèéêě]", "[īìíîǐ]", "[ōòóôǒ]", "[ūùúûǔ]", "ḿ", "[ǹńň]", MACRON, ACUTE, GRAVE, CIRC, CARON}, to = {"a" , "e" , "i" , "o" , "u" , "m", "n" }}, ancestors = {"bnt-pro"}, } m["yi"] = { canonicalName = "ယိဒ်ဒိသ်", otherNames = {"Yiddish"}, scripts = {"Hebr"}, family = "gmw", ancestors = {"gmh"}, translit_module = "yi-translit", wikipedia_article = "Yiddish", } m["yo"] = { canonicalName = "ရိုရုဗာ", otherNames = {"Yoruba"}, scripts = {"Latn"}, family = "alv-von", ancestors = {"alv-yor-pro", "alv-edk-pro", "alv-yrd-pro"}, } m["za"] = { canonicalName = "ဇြုန်", otherNames = {"Standard Zhuang"}, scripts = {"Latn", "Hani"}, family = "tai", wikipedia_article = "Zhuang languages", } m["zh"] = { canonicalName = "ကြုက်", otherNames = {"Chinese"}, scripts = {"Hani", "Brai"}, family = "sit", ancestors = {"ltc", "sit-pro"}, sort_key = "zh-sortkey", } m["zu"] = { canonicalName = "သြူဠူ", otherNames = {"Zulu", "isiZulu"}, scripts = {"Latn"}, family = "bnt-ngu", entry_name = { from = {"[āàáâǎ]", "[ēèéêě]", "[īìíîǐ]", "[ōòóôǒ]", "[ūùúûǔ]", "ḿ", "[ǹńň]", MACRON, ACUTE, GRAVE, CIRC, CARON}, to = {"a" , "e" , "i" , "o" , "u" , "m", "n" }}, ancestors = {"bnt-pro"}, } return m 087vf9ffocjor0s08w7xedkzoyl6m5m မဝ်ဂျူ:languages/data/all 828 725 103864 73959 2024-11-01T08:35:54Z 咽頭べさ 33 103864 Scribunto text/plain local string = string local table = table local find = string.find local format = string.format local gsub = string.gsub local next = next local require = require local all_scripts do local scripts, n = {}, 0 for script in next, require("Module:scripts/data") do n = n + 1 scripts[n] = script end table.sort(scripts) all_scripts = table.concat(scripts, ",") end local modules = { "Module:languages/data/2", "Module:languages/data/exceptional" } local data = {} for i = 1, 28 do local mname = modules[i] or format("Module:languages/data/3/%c", 0x5E + i) for key, value in next, require(mname) do -- Handle the special script codes "All" and "Hants". local value4 = value[4] if value4 == "All" then value[4] = all_scripts elseif value4 and find(value4, "Hants", 1, true) then value[4] = gsub(value4, "Hants", "Hani,Hant,Hans") end data[key] = value end for lkey, lvalue in next, require(mname .. "/extra") do local lkey_data = data[lkey] if lkey_data then for key, value in next, lvalue do lkey_data[key] = value end end end end return data dp1mff68q486yy7e09r7l87j501y1uk 103875 103864 2024-11-01T09:17:24Z 咽頭べさ 33 103875 Scribunto text/plain local modules = { ["Module:languages/data/2"] = true, ["Module:languages/data/3/a"] = true, ["Module:languages/data/3/b"] = true, ["Module:languages/data/3/c"] = true, ["Module:languages/data/3/d"] = true, ["Module:languages/data/3/e"] = true, ["Module:languages/data/3/f"] = true, ["Module:languages/data/3/g"] = true, ["Module:languages/data/3/h"] = true, ["Module:languages/data/3/i"] = true, ["Module:languages/data/3/j"] = true, ["Module:languages/data/3/k"] = true, ["Module:languages/data/3/l"] = true, ["Module:languages/data/3/m"] = true, ["Module:languages/data/3/n"] = true, ["Module:languages/data/3/o"] = true, ["Module:languages/data/3/p"] = true, ["Module:languages/data/3/q"] = true, ["Module:languages/data/3/r"] = true, ["Module:languages/data/3/s"] = true, ["Module:languages/data/3/t"] = true, ["Module:languages/data/3/u"] = true, ["Module:languages/data/3/v"] = true, ["Module:languages/data/3/w"] = true, ["Module:languages/data/3/x"] = true, ["Module:languages/data/3/y"] = true, ["Module:languages/data/3/z"] = true, ["Module:languages/data/exceptional"] = true, } local m = {} for mname in pairs(modules) do for key, value in pairs(require(mname)) do if value[4] == "All" then local scripts = {} for script in pairs(require("Module:scripts/data")) do table.insert(scripts, script) end value[4] = scripts elseif type(value[4]) == "string" then value[4] = mw.text.split(value[4], "%s*,%s*") end if type(value.ancestors) == "string" then value.ancestors = mw.text.split(value.ancestors, "%s*,%s*") end if type(value.wikimedia_codes) == "string" then value.wikimedia_codes = mw.text.split(value.wikimedia_codes, "%s*,%s*") end m[key] = value end local xname = mname .. "/extra" for lkey, lvalue in pairs(require(xname)) do if m[lkey] then for key, value in pairs(lvalue) do m[lkey][key] = lvalue[key] end end end end return m 2qpyqnathwfcw3m1kwbugaikb8fzc6k တီ 0 79227 103876 103843 2024-11-01T09:52:04Z 咽頭べさ 33 103876 wikitext text/x-wiki {{also/auto}} =={{=mnw=}}== ===နိရုတ်=== ဝေါဟာကၠုၚ်နူ {{inh|mnw|omx|တမ်}} ===ဗွဟ်ရမ္သာင်=== * {{IPA|mnw|/tɛm/}} * {{audio|mnw|LL-Q13349 (mnw)-咽頭べさ-{{PAGENAME}}.wav|ရမျာင်}} * {{homophones|mnw|တမ်}} ===နာမ်=== {{mnw-noun}} # ကၠိုဟ်၊ ကၠိုဟ်စိုတ်။ # သ္ကဵုတီ၊ သ္ကဵုကၠိုဟ်ခၠၚ်၊ သ္ကဵုဒဒှ်ေဒယှ်။ # တီညာတ်၊ ဒဒှ်ေ၊ ဒဒှ်ေဒယှ်။ # ကၠိုဟ်ကၠုၚ်၊ ကၠိုဟ်တီကၠုၚ်။ # သ္ဂောံတီ၊ သ္ဒးဒုၚ်ကလိုဟ်၊ ကလိုဟ်သ္ကဵုတီ။ # ပဇၞောဝ်မတ်၊ ကၠိုဟ်စိုတ်တီညာတ်။ # ကၞာတ်သမ္တီ၊ စၟိန်ပြမာန်၊ စၟတ်ကေတ်၊ ကၞာတ်သမ္တီလ္ၚတ်ချိုတ်ချိုတ်ပၠိုတ်ပၠိုတ်။ =={{=my=}}== ===ဗွဟ်ရမ္သာင်=== * {{my-IPA}} * {{homophones|my|တည်}} ===သဗ္ဗနာမ်=== {{my-pronoun}} # သဗ္ဗနာမ်မစၟဳတၚ်သၟာန်ဇာန်မတဝ်ပတုပ်ရံၚ်မာန်အပ္ဍဲမရပ်စပ်ကြိယာဝိသေသန 'ၜိုတ်၊ ၜိုတ်လဵု၊ မူ၊ မု၊ မူဟိုတ်ရော' ဂမၠိုၚ်။ ===နိရုတ်=== {{bor+|my|zh|}} {{m|zh|第}} ===နာမ်=== {{my-noun}} # ဒါဝ်မဳနုဝ်မနွံကဵုဒလတ်မအရံၚ်ဍာဲၜါသာ်။ ===ကြိယာ=== {{my-verb}} # သကဵုသလးထောံဆဆဵုဖျေံစွံလဝ်သွက်ဇိက်တဵုလွဳ။ ===နိရုတ်=== ဝေါဟာကၠုၚ်နူ {{inh|my|tbq-pro|*zril}} ===နာမ် ၂=== {{my-noun}} # ပကောတ်တိ။ ===နာမ် ၃=== {{my-noun}} # ကောန်စဴကောန်စေက်။ ===={{See also}}==== * {{list:kinship generations/my}} ===ကြိယာ ၂=== {{my-verb}} # သကဵုသၠေံ၊ မဟီုဂလာန်ဆဆဵု။ ===နိရုတ်=== {{bor+|my|en|tee}} ===နာမ် ၄=== {{my-noun}} # မဆေၚ်စပ်ကဵုအက္ခရ်လပ်တေန်နကဵုဝေါဟာ [[T]]/[[t]] (တဳ)။ ===={{See also}}==== {{my-AtoZ}} f00kqctpg04pe3ie3msnl6jgfghqjsd 103877 103876 2024-11-01T09:52:19Z 咽頭べさ 33 /* နိရုတ် */ 103877 wikitext text/x-wiki {{also/auto}} =={{=mnw=}}== ===နိရုတ်=== ဝေါဟာကၠုၚ်နူ {{inh|mnw|omx|တမ်}} ===ဗွဟ်ရမ္သာင်=== * {{IPA|mnw|/tɛm/}} * {{audio|mnw|LL-Q13349 (mnw)-咽頭べさ-{{PAGENAME}}.wav|ရမျာင်}} * {{homophones|mnw|တမ်}} ===နာမ်=== {{mnw-noun}} # ကၠိုဟ်၊ ကၠိုဟ်စိုတ်။ # သ္ကဵုတီ၊ သ္ကဵုကၠိုဟ်ခၠၚ်၊ သ္ကဵုဒဒှ်ေဒယှ်။ # တီညာတ်၊ ဒဒှ်ေ၊ ဒဒှ်ေဒယှ်။ # ကၠိုဟ်ကၠုၚ်၊ ကၠိုဟ်တီကၠုၚ်။ # သ္ဂောံတီ၊ သ္ဒးဒုၚ်ကလိုဟ်၊ ကလိုဟ်သ္ကဵုတီ။ # ပဇၞောဝ်မတ်၊ ကၠိုဟ်စိုတ်တီညာတ်။ # ကၞာတ်သမ္တီ၊ စၟိန်ပြမာန်၊ စၟတ်ကေတ်၊ ကၞာတ်သမ္တီလ္ၚတ်ချိုတ်ချိုတ်ပၠိုတ်ပၠိုတ်။ =={{=my=}}== ===ဗွဟ်ရမ္သာင်=== * {{my-IPA}} * {{homophones|my|တည်}} ===သဗ္ဗနာမ်=== {{my-pronoun}} # သဗ္ဗနာမ်မစၟဳတၚ်သၟာန်ဇာန်မတဝ်ပတုပ်ရံၚ်မာန်အပ္ဍဲမရပ်စပ်ကြိယာဝိသေသန 'ၜိုတ်၊ ၜိုတ်လဵု၊ မူ၊ မု၊ မူဟိုတ်ရော' ဂမၠိုၚ်။ ===နိရုတ်=== {{bor+|my|zh|}} {{m|zh|第}} ===နာမ်=== {{my-noun}} # ဒါဝ်မဳနုဝ်မနွံကဵုဒလတ်မအရံၚ်ဍာဲၜါသာ်။ ===ကြိယာ=== {{my-verb}} # သကဵုသလးထောံဆဆဵုဖျေံစွံလဝ်သွက်ဇိက်တဵုလွဳ။ ===နိရုတ်=== ဝေါဟာကၠုၚ်နူ {inh|my|tbq-pro|*zril}} ===နာမ် ၂=== {{my-noun}} # ပကောတ်တိ။ ===နာမ် ၃=== {{my-noun}} # ကောန်စဴကောန်စေက်။ ===={{See also}}==== * {{list:kinship generations/my}} ===ကြိယာ ၂=== {{my-verb}} # သကဵုသၠေံ၊ မဟီုဂလာန်ဆဆဵု။ ===နိရုတ်=== {{bor+|my|en|tee}} ===နာမ် ၄=== {{my-noun}} # မဆေၚ်စပ်ကဵုအက္ခရ်လပ်တေန်နကဵုဝေါဟာ [[T]]/[[t]] (တဳ)။ ===={{See also}}==== {{my-AtoZ}} sip2ve7pahdg5p6dp88t1kmkpteuh6r 103880 103877 2024-11-01T10:01:36Z 咽頭べさ 33 103880 wikitext text/x-wiki {{also/auto}} =={{=mnw=}}== ===နိရုတ်=== ဝေါဟာကၠုၚ်နူ {{inh|mnw|omx|တမ်}} ===ဗွဟ်ရမ္သာင်=== * {{IPA|mnw|/tɛm/}} * {{audio|mnw|LL-Q13349 (mnw)-咽頭べさ-{{PAGENAME}}.wav|ရမျာင်}} * {{homophones|mnw|တမ်}} ===နာမ်=== {{mnw-noun}} # ကၠိုဟ်၊ ကၠိုဟ်စိုတ်။ # သ္ကဵုတီ၊ သ္ကဵုကၠိုဟ်ခၠၚ်၊ သ္ကဵုဒဒှ်ေဒယှ်။ # တီညာတ်၊ ဒဒှ်ေ၊ ဒဒှ်ေဒယှ်။ # ကၠိုဟ်ကၠုၚ်၊ ကၠိုဟ်တီကၠုၚ်။ # သ္ဂောံတီ၊ သ္ဒးဒုၚ်ကလိုဟ်၊ ကလိုဟ်သ္ကဵုတီ။ # ပဇၞောဝ်မတ်၊ ကၠိုဟ်စိုတ်တီညာတ်။ # ကၞာတ်သမ္တီ၊ စၟိန်ပြမာန်၊ စၟတ်ကေတ်၊ ကၞာတ်သမ္တီလ္ၚတ်ချိုတ်ချိုတ်ပၠိုတ်ပၠိုတ်။ =={{=my=}}== ===ဗွဟ်ရမ္သာင်=== * {{my-IPA}} * {{homophones|my|တည်}} ===သဗ္ဗနာမ်=== {{my-pronoun}} # သဗ္ဗနာမ်မစၟဳတၚ်သၟာန်ဇာန်မတဝ်ပတုပ်ရံၚ်မာန်အပ္ဍဲမရပ်စပ်ကြိယာဝိသေသန 'ၜိုတ်၊ ၜိုတ်လဵု၊ မူ၊ မု၊ မူဟိုတ်ရော' ဂမၠိုၚ်။ ===နိရုတ်=== {{bor+|my|zh|-}} {{m|zh|第}} ===နာမ်=== {{my-noun}} # ဒါဝ်မဳနုဝ်မနွံကဵုဒလတ်မအရံၚ်ဍာဲၜါသာ်။ ===ကြိယာ=== {{my-verb}} # သကဵုသလးထောံဆဆဵုဖျေံစွံလဝ်သွက်ဇိက်တဵုလွဳ။ ===နိရုတ်=== ဝေါဟာကၠုၚ်နူ {inh|my|tbq-pro|*zril}} ===နာမ် ၂=== {{my-noun}} # ပကောတ်တိ။ ===နာမ် ၃=== {{my-noun}} # ကောန်စဴကောန်စေက်။ ===={{See also}}==== * {{list:kinship generations/my}} ===ကြိယာ ၂=== {{my-verb}} # သကဵုသၠေံ၊ မဟီုဂလာန်ဆဆဵု။ ===နိရုတ်=== {{bor+|my|en|tee}} ===နာမ် ၄=== {{my-noun}} # မဆေၚ်စပ်ကဵုအက္ခရ်လပ်တေန်နကဵုဝေါဟာ [[T]]/[[t]] (တဳ)။ ===={{See also}}==== {{my-AtoZ}} n5bjmb1y9mjk5uzxw9tbavwni1h4vdf 103883 103880 2024-11-01T10:27:36Z 咽頭べさ 33 103883 wikitext text/x-wiki {{also/auto}} =={{=mnw=}}== ===နိရုတ်=== ဝေါဟာကၠုၚ်နူ {{inh|mnw|omx|တမ်}} ===ဗွဟ်ရမ္သာင်=== * {{IPA|mnw|/tɛm/}} * {{audio|mnw|LL-Q13349 (mnw)-咽頭べさ-{{PAGENAME}}.wav|ရမျာင်}} * {{homophones|mnw|တမ်}} ===နာမ်=== {{mnw-noun}} # ကၠိုဟ်၊ ကၠိုဟ်စိုတ်။ # သ္ကဵုတီ၊ သ္ကဵုကၠိုဟ်ခၠၚ်၊ သ္ကဵုဒဒှ်ေဒယှ်။ # တီညာတ်၊ ဒဒှ်ေ၊ ဒဒှ်ေဒယှ်။ # ကၠိုဟ်ကၠုၚ်၊ ကၠိုဟ်တီကၠုၚ်။ # သ္ဂောံတီ၊ သ္ဒးဒုၚ်ကလိုဟ်၊ ကလိုဟ်သ္ကဵုတီ။ # ပဇၞောဝ်မတ်၊ ကၠိုဟ်စိုတ်တီညာတ်။ # ကၞာတ်သမ္တီ၊ စၟိန်ပြမာန်၊ စၟတ်ကေတ်၊ ကၞာတ်သမ္တီလ္ၚတ်ချိုတ်ချိုတ်ပၠိုတ်ပၠိုတ်။ =={{=my=}}== ===ဗွဟ်ရမ္သာင်=== * {{my-IPA}} * {{homophones|my|တည်}} ===သဗ္ဗနာမ်=== {{my-pronoun}} # သဗ္ဗနာမ်မစၟဳတၚ်သၟာန်ဇာန်မတဝ်ပတုပ်ရံၚ်မာန်အပ္ဍဲမရပ်စပ်ကြိယာဝိသေသန 'ၜိုတ်၊ ၜိုတ်လဵု၊ မူ၊ မု၊ မူဟိုတ်ရော' ဂမၠိုၚ်။ ===နိရုတ်=== {{bor+|my|zh|-}} {{m|zh|第}} ===နာမ်=== {{my-noun}} # ဒါဝ်မဳနုဝ်မနွံကဵုဒလတ်မအရံၚ်ဍာဲၜါသာ်။ ===ကြိယာ=== {{my-verb}} # သကဵုသလးထောံဆဆဵုဖျေံစွံလဝ်သွက်ဇိက်တဵုလွဳ။ ===နိရုတ်=== ဝေါဟာကၠုၚ်နူ {inh|my|tbq-pro|*zril}} ===နာမ် ၂=== {{my-noun}} # ပကောတ်တိ။ ===နာမ် ၃=== {{my-noun}} # ကောန်စဴကောန်စေက်။ ===={{See also}}==== * {{list:kinship generations/my}} ===ကြိယာ ၂=== {{my-verb}} # သကဵုသၠေံ၊ မဟီုဂလာန်ဆဆဵု။ ===နိရုတ်=== {{bor+|my|en|tee}} ===နာမ် ၄=== {{my-noun}} # မဆေၚ်စပ်ကဵုအက္ခရ်လပ်တေန်နကဵုဝေါဟာ [[T]]/[[t]] (တဳ)။ ===={{See also}}==== {{my-AtoZ}} =={{=shn=}}== ===ဗွဟ်ရမ္သာင်=== {{shn-pron}} ===ကြိယာ=== {{shn-verb}} # မတက်သာက္ဍာ။ kh6qb86ks9eb1883jvsl4uyssynh6uz တဝ်ၜံၚ် 0 79228 103844 2024-11-01T07:46:55Z 咽頭べさ 33 ခၞံကၠောန်လဝ် မုက်လိက် နကဵု "=={{=mnw=}}== ===ဗွဟ်ရမ္သာင်=== {{IPA|mnw|/tɔpɔŋ/}} * {{audio|mnw|LL-Q13349 (mnw)-咽頭べさ-{{PAGENAME}}.wav|ရမျာင်}} ===နာမ်=== {{mnw-noun}} # ယာတ်သၟာ်မတ္ၜန်ကဝးလဝ်တုဲဗပ်ဗျပ်လဝ်ကၠေၚ်၊ စတ်စုတ်လဝ်သွက်သ္ဂောံရပ်တုဲ စံၚ်ဗဂဵု..." 103844 wikitext text/x-wiki =={{=mnw=}}== ===ဗွဟ်ရမ္သာင်=== {{IPA|mnw|/tɔpɔŋ/}} * {{audio|mnw|LL-Q13349 (mnw)-咽頭べさ-{{PAGENAME}}.wav|ရမျာင်}} ===နာမ်=== {{mnw-noun}} # ယာတ်သၟာ်မတ္ၜန်ကဝးလဝ်တုဲဗပ်ဗျပ်လဝ်ကၠေၚ်၊ စတ်စုတ်လဝ်သွက်သ္ဂောံရပ်တုဲ စံၚ်ဗဂဵုလဝ်ပၟတ်သွက်သ္ဂောံဂွံလျး အခါမအာကၠုၚ်စတရဴအခိၚ်ဗ္တံဒမၠု၊ တဝ်ၜံၚ်မိန်သော၊ မိန်ရှောတဝ်ၜံၚ်၊ မာဲသော၊ မာဲရှော။ jd5b2d5kwunuilduoohm86u3ybdjk07 great-great-grandchild 0 79229 103845 2024-11-01T08:04:39Z 咽頭べさ 33 ခၞံကၠောန်လဝ် မုက်လိက် နကဵု "{{also|great great grandchild}} =={{=en=}}== ===ပွံင်နဲတၞဟ်=== * {{alter|en|great great grandchild}} ===နာမ်=== {{en-noun|great-great-grandchildren|head=[[great-]][[great-grandchild]]}} # ကောန်စဴကောန်စေက်။" 103845 wikitext text/x-wiki {{also|great great grandchild}} =={{=en=}}== ===ပွံင်နဲတၞဟ်=== * {{alter|en|great great grandchild}} ===နာမ်=== {{en-noun|great-great-grandchildren|head=[[great-]][[great-grandchild]]}} # ကောန်စဴကောန်စေက်။ h5cangvmoc3d8syoo7v16wow1282vfs great great grandchild 0 79230 103846 2024-11-01T08:05:31Z 咽頭べさ 33 ခၞံကၠောန်လဝ် မုက်လိက် နကဵု "{{also|great-great-grandchild}} =={{=en=}}== ===နာမ်=== {{en-noun|head=[[great]] [[great]] [[grandchildren]]|great great grandchildren}} # {{alternative spelling of|en|great-great-grandchild}}" 103846 wikitext text/x-wiki {{also|great-great-grandchild}} =={{=en=}}== ===နာမ်=== {{en-noun|head=[[great]] [[great]] [[grandchildren]]|great great grandchildren}} # {{alternative spelling of|en|great-great-grandchild}} 3qlohqdl7q84vnfbjrabfp5l2n2hwf2 great great grandchildren 0 79231 103847 2024-11-01T08:06:35Z 咽頭べさ 33 ခၞံကၠောန်လဝ် မုက်လိက် နကဵု "{{also|great-great-grandchildren}} =={{=en=}}== ===နာမ်=== {{head|en|ဗီုပြင်နာမ်}} # {{plural of|en|great great grandchild|nodot=1}} ({{alternative spelling of|en|great-great-grandchildren|nocap=1|nodot=1}})" 103847 wikitext text/x-wiki {{also|great-great-grandchildren}} =={{=en=}}== ===နာမ်=== {{head|en|ဗီုပြင်နာမ်}} # {{plural of|en|great great grandchild|nodot=1}} ({{alternative spelling of|en|great-great-grandchildren|nocap=1|nodot=1}}) 2d82n2537k0dwc9aqxesw32490h5taq great-great-grandchildren 0 79232 103848 2024-11-01T08:07:30Z 咽頭べさ 33 ခၞံကၠောန်လဝ် မုက်လိက် နကဵု "{{also|great great grandchildren}} =={{=en=}}== ===နာမ်=== {{head|en|ဗီုပြင်နာမ်|head=[[great-]][[great-grandchildren]]}} # {{plural of|en|great-great-grandchild}}" 103848 wikitext text/x-wiki {{also|great great grandchildren}} =={{=en=}}== ===နာမ်=== {{head|en|ဗီုပြင်နာမ်|head=[[great-]][[great-grandchildren]]}} # {{plural of|en|great-great-grandchild}} 6u2g4aj3h6xjfs8vy8whkx4qr1jsn8t great-grandchildren 0 79233 103849 2024-11-01T08:08:38Z 咽頭べさ 33 ခၞံကၠောန်လဝ် မုက်လိက် နကဵု "{{also|greatgrandchildren|great grandchildren}} =={{=en=}}== ===နာမ်=== {{head|en|ဗီုပြင်နာမ်|head=[[great-]][[grandchildren]]}} # {{plural of|en|great-grandchild}}" 103849 wikitext text/x-wiki {{also|greatgrandchildren|great grandchildren}} =={{=en=}}== ===နာမ်=== {{head|en|ဗီုပြင်နာမ်|head=[[great-]][[grandchildren]]}} # {{plural of|en|great-grandchild}} a0cp1wegnb31t3yoedx8ja9hk4r6j9v great-grandchild 0 79234 103850 2024-11-01T08:10:21Z 咽頭べさ 33 ခၞံကၠောန်လဝ် မုက်လိက် နကဵု "{{also|greatgrandchild|great grandchild}} =={{=en=}}== ===ပွံင်နဲတၞဟ်=== * {{alter|en|great grandchild|greatgrandchild}} ===နာမ်=== {{en-noun|great-grandchildren|head=[[great-]][[grandchild]]}} # ကောန်စေက်။" 103850 wikitext text/x-wiki {{also|greatgrandchild|great grandchild}} =={{=en=}}== ===ပွံင်နဲတၞဟ်=== * {{alter|en|great grandchild|greatgrandchild}} ===နာမ်=== {{en-noun|great-grandchildren|head=[[great-]][[grandchild]]}} # ကောန်စေက်။ 7ic22jfv6rwy3oq67iz5cb3cwwpg1bz great grandchild 0 79235 103851 2024-11-01T08:11:18Z 咽頭べさ 33 ခၞံကၠောန်လဝ် မုက်လိက် နကဵု "{{also|greatgrandchild|great-grandchild}} =={{=en=}}== ===နာမ်=== {{en-noun|great grandchildren}} # {{alternative spelling of|en|great-grandchild}}" 103851 wikitext text/x-wiki {{also|greatgrandchild|great-grandchild}} =={{=en=}}== ===နာမ်=== {{en-noun|great grandchildren}} # {{alternative spelling of|en|great-grandchild}} 39hk7e7vpv0qb7htndvaey94qfi9jxe great grandchildren 0 79236 103852 2024-11-01T08:12:12Z 咽頭べさ 33 ခၞံကၠောန်လဝ် မုက်လိက် နကဵု "{{also|greatgrandchildren|great-grandchildren}} =={{=en=}}== ===နာမ်=== {{head|en|ဗီုပြင်နာမ်}} # {{plural of|en|great grandchild|nodot=1}} ({{alternative spelling of|en|great-grandchildren|nocap=1|nodot=1}})" 103852 wikitext text/x-wiki {{also|greatgrandchildren|great-grandchildren}} =={{=en=}}== ===နာမ်=== {{head|en|ဗီုပြင်နာမ်}} # {{plural of|en|great grandchild|nodot=1}} ({{alternative spelling of|en|great-grandchildren|nocap=1|nodot=1}}) 2xcmjjnzhz8h313dbm0685626pr1tk5 greatgrandchildren 0 79237 103853 2024-11-01T08:13:02Z 咽頭べさ 33 ခၞံကၠောန်လဝ် မုက်လိက် နကဵု "{{also|great-grandchildren|great grandchildren}} =={{=en=}}== ===နာမ်=== {{head|en|ဗီုပြင်နာမ်}} # {{plural of|en|greatgrandchild}}" 103853 wikitext text/x-wiki {{also|great-grandchildren|great grandchildren}} =={{=en=}}== ===နာမ်=== {{head|en|ဗီုပြင်နာမ်}} # {{plural of|en|greatgrandchild}} mfob8yeob6msjoabyiw6frqi50hukpn greatgrandchild 0 79238 103854 2024-11-01T08:13:44Z 咽頭べさ 33 ခၞံကၠောန်လဝ် မုက်လိက် နကဵု "{{also|great-grandchild|great grandchild}} =={{=en=}}== ===နာမ်=== {{en-noun|greatgrandchildren}} # {{alternative form of|en|great-grandchild}}" 103854 wikitext text/x-wiki {{also|great-grandchild|great grandchild}} =={{=en=}}== ===နာမ်=== {{en-noun|greatgrandchildren}} # {{alternative form of|en|great-grandchild}} 73xqkc0b1moyayynvrq4icq0nndaenc great-great-grandfather 0 79239 103855 2024-11-01T08:18:04Z 咽頭べさ 33 ခၞံကၠောန်လဝ် မုက်လိက် နကဵု "{{also|great great grandfather}} =={{=en=}}== ===ပွံင်နဲတၞဟ်=== * {{alter|en|great great grandfather}} ===နာမ်=== {{en-noun|head=[[great-]][[great-grandfather]]}} # ကောန်စဴကောန်စေက်လ္ပာ်အပါဇၞော်။" 103855 wikitext text/x-wiki {{also|great great grandfather}} =={{=en=}}== ===ပွံင်နဲတၞဟ်=== * {{alter|en|great great grandfather}} ===နာမ်=== {{en-noun|head=[[great-]][[great-grandfather]]}} # ကောန်စဴကောန်စေက်လ္ပာ်အပါဇၞော်။ 0fat6h4ggz4uer2xlxvp7u8w3zwmfeb great-great-grandfathers 0 79240 103856 2024-11-01T08:19:04Z 咽頭べさ 33 ခၞံကၠောန်လဝ် မုက်လိက် နကဵု "{{also|great great grandfathers}} =={{=en=}}== ===နာမ်=== {{head|en|ဗီုပြင်နာမ်|head=[[great-]][[great-grandfathers]]}} # {{plural of|en|great-great-grandfather}}" 103856 wikitext text/x-wiki {{also|great great grandfathers}} =={{=en=}}== ===နာမ်=== {{head|en|ဗီုပြင်နာမ်|head=[[great-]][[great-grandfathers]]}} # {{plural of|en|great-great-grandfather}} cg8q63f7zox4te0qkv7mdzchzvo8t7g great great grandfathers 0 79241 103857 2024-11-01T08:19:54Z 咽頭べさ 33 ခၞံကၠောန်လဝ် မုက်လိက် နကဵု "{{also|great-great-grandfathers}} =={{=en=}}== ===နာမ်=== {{head|en|ဗီုပြင်နာမ်}} # {{plural of|en|great great grandfather|nodot=1}} ({{alternative spelling of|en|great-great-grandfathers|nocap=1|nodot=1}})" 103857 wikitext text/x-wiki {{also|great-great-grandfathers}} =={{=en=}}== ===နာမ်=== {{head|en|ဗီုပြင်နာမ်}} # {{plural of|en|great great grandfather|nodot=1}} ({{alternative spelling of|en|great-great-grandfathers|nocap=1|nodot=1}}) ssnekg74b5jat6rlizkg5ddm1l0binp great great grandfather 0 79242 103858 2024-11-01T08:20:40Z 咽頭べさ 33 ခၞံကၠောန်လဝ် မုက်လိက် နကဵု "{{also|great-great-grandfather}} =={{=en=}}== ===နာမ်=== {{en-noun}} # {{alternative spelling of|en|great-great-grandfather}}" 103858 wikitext text/x-wiki {{also|great-great-grandfather}} =={{=en=}}== ===နာမ်=== {{en-noun}} # {{alternative spelling of|en|great-great-grandfather}} ly1ez4t962xwajzpk8mq329plvxi2mt great-great-granddaughter 0 79243 103859 2024-11-01T08:23:28Z 咽頭べさ 33 ခၞံကၠောန်လဝ် မုက်လိက် နကဵု "{{also|great great granddaughter}} =={{=en=}}== ===ပွံင်နဲတၞဟ်=== * {{alter|en|great great granddaughter}} ===နာမ်=== {{en-noun|head=[[great-]][[great-granddaughter]]}} # ကောန်စဴကောန်စေက်မၞိဟ်ဗြဴဗြဴ။" 103859 wikitext text/x-wiki {{also|great great granddaughter}} =={{=en=}}== ===ပွံင်နဲတၞဟ်=== * {{alter|en|great great granddaughter}} ===နာမ်=== {{en-noun|head=[[great-]][[great-granddaughter]]}} # ကောန်စဴကောန်စေက်မၞိဟ်ဗြဴဗြဴ။ psxc648w9mzkn2lmtzftpprk0cl3rvj great-great-granddaughters 0 79244 103860 2024-11-01T08:27:10Z 咽頭べさ 33 ခၞံကၠောန်လဝ် မုက်လိက် နကဵု "{{also|great great granddaughters}} =={{=en=}}== ===နာမ်=== {{head|en|ဗီုပြင်နာမ်|head=[[great-]][[great-granddaughters]]}} # {{plural of|en|great-great-granddaughter}}" 103860 wikitext text/x-wiki {{also|great great granddaughters}} =={{=en=}}== ===နာမ်=== {{head|en|ဗီုပြင်နာမ်|head=[[great-]][[great-granddaughters]]}} # {{plural of|en|great-great-granddaughter}} mvdyzoybututgehr355yi5r8nh4iv8q great great granddaughters 0 79245 103861 2024-11-01T08:28:10Z 咽頭べさ 33 ခၞံကၠောန်လဝ် မုက်လိက် နကဵု "{{also|great-great-granddaughters}} =={{=en=}}== ===နာမ်=== {{head|en|ဗီုပြင်နာမ်}} # {{plural of|en|great great granddaughter|nodot=1}} ({{alternative spelling of|en|great-great-granddaughters|nocap=1|nodot=1}})" 103861 wikitext text/x-wiki {{also|great-great-granddaughters}} =={{=en=}}== ===နာမ်=== {{head|en|ဗီုပြင်နာမ်}} # {{plural of|en|great great granddaughter|nodot=1}} ({{alternative spelling of|en|great-great-granddaughters|nocap=1|nodot=1}}) pmip05o351cqjvwdnofpc4p17g3db18 great great granddaughter 0 79246 103862 2024-11-01T08:28:45Z 咽頭べさ 33 ခၞံကၠောန်လဝ် မုက်လိက် နကဵု "{{also|great-great-granddaughter}} =={{=en=}}== ===နာမ်=== {{en-noun|head=[[great]] [[granddaughter]]}} # {{alternative spelling of|en|great-great-granddaughter}}" 103862 wikitext text/x-wiki {{also|great-great-granddaughter}} =={{=en=}}== ===နာမ်=== {{en-noun|head=[[great]] [[granddaughter]]}} # {{alternative spelling of|en|great-great-granddaughter}} bqgqjk52f04m7bnh321d49debitkeky ကဏ္ဍ:ဝေါဟာခ္ဍံလိက်အင်္ဂလိက်မရပ်စပ်လဝ်အခဝ်- 14 79247 103867 2024-11-01T08:43:51Z 咽頭べさ 33 ခၞံကၠောန်လဝ် မုက်လိက် နကဵု "[[ကဏ္ဍ:ဘာသာအင်္ဂလိက်]]" 103867 wikitext text/x-wiki [[ကဏ္ဍ:ဘာသာအင်္ဂလိက်]] oytp5j7uvq8q3lm4q5329nty1ylp9hn ကဏ္ဍ:ဝေါဟာခ္ဍံလိက်အင်္ဂလိက်မရပ်စပ်လဝ်အခဝ်' 14 79248 103868 2024-11-01T08:45:57Z 咽頭べさ 33 ခၞံကၠောန်လဝ် မုက်လိက် နကဵု "[[ကဏ္ဍ:ဘာသာအင်္ဂလိက်]]" 103868 wikitext text/x-wiki [[ကဏ္ဍ:ဘာသာအင်္ဂလိက်]] oytp5j7uvq8q3lm4q5329nty1ylp9hn great-great-grandson 0 79249 103869 2024-11-01T08:57:04Z 咽頭べさ 33 ခၞံကၠောန်လဝ် မုက်လိက် နကဵု "{{also|great great grandson}} =={{=en=}}== ===ပွံင်နဲတၞဟ်=== * {{alter|en|great great grandson}} ===နာမ်=== {{en-noun|head=[[great-]][[great-grandson]]}} # ကောန်စဴကောန်စေက်မၞိဟ်တြုံတြုံ။" 103869 wikitext text/x-wiki {{also|great great grandson}} =={{=en=}}== ===ပွံင်နဲတၞဟ်=== * {{alter|en|great great grandson}} ===နာမ်=== {{en-noun|head=[[great-]][[great-grandson]]}} # ကောန်စဴကောန်စေက်မၞိဟ်တြုံတြုံ။ 8to34jhb3g5druxij2wnbt9q2pypquz great-great-grandsons 0 79250 103870 2024-11-01T08:58:18Z 咽頭べさ 33 ခၞံကၠောန်လဝ် မုက်လိက် နကဵု "{{also|great great grandsons}} =={{=en=}}== ===နာမ်=== {{head|en|ဗီုပြင်နာမ်|head=[[great-]][[great-grandsons]]}} # {{plural of|en|great-great-grandson}}" 103870 wikitext text/x-wiki {{also|great great grandsons}} =={{=en=}}== ===နာမ်=== {{head|en|ဗီုပြင်နာမ်|head=[[great-]][[great-grandsons]]}} # {{plural of|en|great-great-grandson}} c1w1ildrkvj7vuxhxtumnxlwznqjt1o great great grandsons 0 79251 103871 2024-11-01T08:59:04Z 咽頭べさ 33 ခၞံကၠောန်လဝ် မုက်လိက် နကဵု "{{also|great-great-grandsons}} =={{=en=}}== ===နာမ်=== {{head|en|ဗီုပြင်နာမ်}} # {{plural of|en|great great grandson|nodot=1}} ({{alternative spelling of|en|great-great-grandsons|nocap=1|nodot=1}})" 103871 wikitext text/x-wiki {{also|great-great-grandsons}} =={{=en=}}== ===နာမ်=== {{head|en|ဗီုပြင်နာမ်}} # {{plural of|en|great great grandson|nodot=1}} ({{alternative spelling of|en|great-great-grandsons|nocap=1|nodot=1}}) b1bf6gnjg8yxnwie2hfg17dfkwokurc great great grandson 0 79252 103873 2024-11-01T09:00:53Z 咽頭べさ 33 ခၞံကၠောန်လဝ် မုက်လိက် နကဵု "{{also|great-great-grandson}} =={{=en=}}== ===နာမ်=== {{en-noun}} # {{alternative spelling of|en|great-great-grandson}}" 103873 wikitext text/x-wiki {{also|great-great-grandson}} =={{=en=}}== ===နာမ်=== {{en-noun}} # {{alternative spelling of|en|great-great-grandson}} sj43wsl3lz1mja49vp78uavt6yth3tt ထာမ်ပလိက်:my-pronoun 10 79253 103878 2024-11-01T09:54:26Z 咽頭べさ 33 ခၞံကၠောန်လဝ် မုက်လိက် နကဵု "{{head|my|သဗ္ဗနာမ်|sort={{{sort|}}}|head={{{sg|{{{head|}}}}}}|tr={{{tr|}}}}}<noinclude>{{hwcat}}</noinclude>" 103878 wikitext text/x-wiki {{head|my|သဗ္ဗနာမ်|sort={{{sort|}}}|head={{{sg|{{{head|}}}}}}|tr={{{tr|}}}}}<noinclude>{{hwcat}}</noinclude> ffeoxrjwzxfrkrphxs2qnfff86p5z1l ထာမ်ပလိက်:list:kinship generations/my 10 79254 103879 2024-11-01T09:59:18Z 咽頭べさ 33 ခၞံကၠောန်လဝ် မုက်လိက် နကဵု "{{list helper 2 |title=ကောန်ဇာတ်မသတၞောဝ်ဒတောဝ်ဝေါၚ်သဂမၠိုၚ် |cat= |hypernym={{l-self|my|မျိုးဆက်}} |hypernym2=parente |list=<!-- -->{{l-self|my|ဘော}}, <!-- -->{{l-self|my|ဘဲ}}, <!-- -->{{l-self|my|ဘင်}}, <!-- -->{{l-self|my|ဘီ}}, <!-- -->{{l-self|my|ဘေး}}, <!-- -->{{l-self|my|ဘိုး}}, <!-- -->{{l..." 103879 wikitext text/x-wiki {{list helper 2 |title=ကောန်ဇာတ်မသတၞောဝ်ဒတောဝ်ဝေါၚ်သဂမၠိုၚ် |cat= |hypernym={{l-self|my|မျိုးဆက်}} |hypernym2=parente |list=<!-- -->{{l-self|my|ဘော}}, <!-- -->{{l-self|my|ဘဲ}}, <!-- -->{{l-self|my|ဘင်}}, <!-- -->{{l-self|my|ဘီ}}, <!-- -->{{l-self|my|ဘေး}}, <!-- -->{{l-self|my|ဘိုး}}, <!-- -->{{l-self|my|ဘ}}, <!-- -->{{l-self|my|သား}}, <!-- -->{{l-self|my|မြေး}}, <!-- -->{{l-self|my|မြစ်}}, <!-- -->{{l-self|my|တီ}}, <!-- -->{{l-self|my|တွတ်}} / {{l-self|my|မျှော့}}, <!-- -->{{l-self|my|ကျွတ်}}, <!-- -->{{l-self|my|ဆက်}}, <!-- -->}}<!-- --><noinclude>{{list doc}}</noinclude> jnygy3ud2vp7xx71ku74n3nae8179fk ကဏ္ဍ:ဝေါဟာဗၟာကၠုင်နူဝေါဟာကြုက်ဂမၠိုင် 14 79255 103881 2024-11-01T10:02:59Z 咽頭べさ 33 ခၞံကၠောန်လဝ် မုက်လိက် နကဵု "[[ကဏ္ဍ:ဘာသာဗၟာ]]" 103881 wikitext text/x-wiki [[ကဏ္ဍ:ဘာသာဗၟာ]] m4ia0kjy8zlqxecqhd1qnx8uhvqvfea ကဏ္ဍ:ဝေါဟာဗၟာလွဳလဝ် နူဝေါဟာ ကြုက်ဂမၠိုင် 14 79256 103882 2024-11-01T10:03:48Z 咽頭べさ 33 ခၞံကၠောန်လဝ် မုက်လိက် နကဵု "[[ကဏ္ဍ:ဘာသာဗၟာ]]" 103882 wikitext text/x-wiki [[ကဏ္ဍ:ဘာသာဗၟာ]] m4ia0kjy8zlqxecqhd1qnx8uhvqvfea လွင်ႈတီ 0 79257 103884 2024-11-01T10:28:25Z 咽頭べさ 33 ခၞံကၠောန်လဝ် မုက်လိက် နကဵု "=={{=shn=}}== ====နာမ်==== {{shn-noun}} # {{abstract noun of|shn|တီ}}" 103884 wikitext text/x-wiki =={{=shn=}}== ====နာမ်==== {{shn-noun}} # {{abstract noun of|shn|တီ}} r4lk3u1iz6760v46o3fa44a32p8dusd တည် 0 79258 103885 2024-11-01T10:30:35Z 咽頭べさ 33 ခၞံကၠောန်လဝ် မုက်လိက် နကဵု "{{also|တည်း|တည့်}} =={{=mnw=}}== ===ဗွဟ်ရမ္သာင်=== * {{IPA|mnw|/tɔn/}} * {{homophones|mnw|တန်}} * {{audio|mnw|LL-Q13349 (mnw)-咽頭べさ-တန်.wav}} ===ကြိယာ=== {{mnw-verb}} # (ဗီုပြၚ်ခ္ဍံက်လိက်ဘာသာ[[မန်ညှ]]) {{alt form|mnw|တန်}}" 103885 wikitext text/x-wiki {{also|တည်း|တည့်}} =={{=mnw=}}== ===ဗွဟ်ရမ္သာင်=== * {{IPA|mnw|/tɔn/}} * {{homophones|mnw|တန်}} * {{audio|mnw|LL-Q13349 (mnw)-咽頭べさ-တန်.wav}} ===ကြိယာ=== {{mnw-verb}} # (ဗီုပြၚ်ခ္ဍံက်လိက်ဘာသာ[[မန်ညှ]]) {{alt form|mnw|တန်}} 6150xd8tlb6e9td2iimcd75ylmczjr3 ဒဒက် 0 79259 103886 2024-11-01T11:06:02Z Ramonnya Jay 40 ခၞံကၠောန်လဝ် မုက်လိက် နကဵု "== {{=mnw=}} == === နိရုတ် === နူကြိယာ [[ဒက်]] === ဗွဟ်ရမ္သာင် === {{IPA|mnw|/dɛ̀dɛ̀k/}} === ဝိဘတ် === {{mnw-noun|tr=dadak}} * ဝတ္ထုမွဲကဵုမွဲ ဒဒှ်မဆက်စပ်မံၚ်ဂှ် ထ္ၜးကဵု။ ==== ဝေါဟာတၟုပ် ==== ==== ဝေါဟာဒစး ==== ယၚ်၊ ဟ..." 103886 wikitext text/x-wiki == {{=mnw=}} == === နိရုတ် === နူကြိယာ [[ဒက်]] === ဗွဟ်ရမ္သာင် === {{IPA|mnw|/dɛ̀dɛ̀k/}} === ဝိဘတ် === {{mnw-noun|tr=dadak}} * ဝတ္ထုမွဲကဵုမွဲ ဒဒှ်မဆက်စပ်မံၚ်ဂှ် ထ္ၜးကဵု။ ==== ဝေါဟာတၟုပ် ==== ==== ဝေါဟာဒစး ==== ယၚ်၊ ဟိုန်၊ ပၞောဝ် ==== ဝေါဟာလွာ ==== ဒဒက်တဴကဵု ==== တြာဲ ==== {{VN|my=[[သမ္ဗန်အနက်ပြပုဒ်]]|en=[[]]}} m56igz59mwl5cclwbx70olklhayobx0