Модуль:Language/data Документація модуля[перегляд] [редагувати] [історія] [очистити кеш]
Таблиця
local U = mw.ustring.char
-- Diacritics, from the [[Combining Diacritical Marks]] block.
local grave = U(0x300)
local acute = U(0x301)
local circumflex = U(0x302)
local tilde = U(0x303)
local macron = U(0x304)
local breve = U(0x306)
local dot = U(0x307)
local diaeresis = U(0x308)
local double_acute = U(0x30B)
local caron = U(0x30C)
local double_grave = U(0x30F)
local invbreve = U(0x311)
local dot_below = U(0x323)
local undertie = U(0x35C)
--[[
This is a table of Wiktionary language codes with data belonging to them.
Name is the "canonical name" used on Wiktionary.
Article is the Wikipedia article.
Script is the ISO 15924 code.
]]
local data = {
["languages"] = {
["ab"] = {
["name"] = "Абхазька",
},
["ang"] = {
["name"] = "Давньоанглійська",
["article"] = {"Давньоанглійська мова"},
-- Remove macrons, acutes, and overdots
["replacements"] = {
decompose = true,
from = { "[" .. macron .. acute .. dot .. "]" },
},
},
["ar"] = {
["name"] = "Арабська",
["article"] = "Арабська мова",
["direction"] = "rtl", -- Should be in the script data module.
["replacements"] = {
-- ālif with wasla is replaced by ālif;
[U(0x0671)] = U(0x0627),
-- taṭwīl, fatḥatan, ḍammatan, kasratan,
-- fatḥa, ḍamma, kasra,
-- shadda, sukūn, and superscript (dagger) ālif are removed.
["["..U(0x0640)..U(0x064B)..U(0x064C)..U(0x064D)
..U(0x064E)..U(0x064F)..U(0x0650)
..U(0x0651)..U(0x0652)..U(0x0670).."]"] = "",
},
},
["ara"] = {
["name"] = "Арабська",
["article"] = "Арабська мова",
["direction"] = "rtl", -- Should be in the script data module.
["replacements"] = {
-- ālif with wasla is replaced by ālif;
[U(0x0671)] = U(0x0627),
-- taṭwīl, fatḥatan, ḍammatan, kasratan,
-- fatḥa, ḍamma, kasra,
-- shadda, sukūn, and superscript (dagger) ālif are removed.
["["..U(0x0640)..U(0x064B)..U(0x064C)..U(0x064D)
..U(0x064E)..U(0x064F)..U(0x0650)
..U(0x0651)..U(0x0652)..U(0x0670).."]"] = "",
},
},
["arb"] = {
["name"] = "Арабська літературна",
["article"] = "Арабська літературна мова",
["direction"] = "rtl", -- Should be in the script data module.
["replacements"] = {
-- ālif with wasla is replaced by ālif;
[U(0x0671)] = U(0x0627),
-- taṭwīl, fatḥatan, ḍammatan, kasratan,
-- fatḥa, ḍamma, kasra,
-- shadda, sukūn, and superscript (dagger) ālif are removed.
["["..U(0x0640)..U(0x064B)..U(0x064C)..U(0x064D)
..U(0x064E)..U(0x064F)..U(0x0650)
..U(0x0651)..U(0x0652)..U(0x0670).."]"] = "",
},
},
["apc"] = {
["name"] = "Північно-левантійська арабська",
["article"] = "Північно-левантійська арабська мова",
["direction"] = "rtl", -- Should be in the script data module.
["replacements"] = {
-- ālif with wasla is replaced by ālif;
[U(0x0671)] = U(0x0627),
-- taṭwīl, fatḥatan, ḍammatan, kasratan,
-- fatḥa, ḍamma, kasra,
-- shadda, sukūn, and superscript (dagger) ālif are removed.
["["..U(0x0640)..U(0x064B)..U(0x064C)..U(0x064D)
..U(0x064E)..U(0x064F)..U(0x0650)
..U(0x0651)..U(0x0652)..U(0x0670).."]"] = "",
},
},
["ajp"] = {
["name"] = "Південно-левантійська арабська",
["article"] = "Південно-левантійська арабська мова",
["direction"] = "rtl", -- Should be in the script data module.
["replacements"] = {
-- ālif with wasla is replaced by ālif;
[U(0x0671)] = U(0x0627),
-- taṭwīl, fatḥatan, ḍammatan, kasratan,
-- fatḥa, ḍamma, kasra,
-- shadda, sukūn, and superscript (dagger) ālif are removed.
["["..U(0x0640)..U(0x064B)..U(0x064C)..U(0x064D)
..U(0x064E)..U(0x064F)..U(0x0650)
..U(0x0651)..U(0x0652)..U(0x0670).."]"] = "",
},
},
["arz"] = {
["name"] = "Єгипетська арабська мова",
["article"] = "Єгипетська арабська мова",
["direction"] = "rtl", -- Should be in the script data module.
["replacements"] = {
-- ālif with wasla is replaced by ālif;
[U(0x0671)] = U(0x0627),
-- taṭwīl, fatḥatan, ḍammatan, kasratan,
-- fatḥa, ḍamma, kasra,
-- shadda, sukūn, and superscript (dagger) ālif are removed.
["["..U(0x0640)..U(0x064B)..U(0x064C)..U(0x064D)
..U(0x064E)..U(0x064F)..U(0x0650)
..U(0x0651)..U(0x0652)..U(0x0670).."]"] = "",
},
},
["av"] = {
["article"] = "Аварська мова",
},
["be"] = {
["name"] = "Білоруська",
["article"] = "Білоруська мова",
["replacements"] = { [acute] = "", },
},
["bn"] = {
["name"] = "Бенгальська",
["article"] = "Бенгальська мова",
},
["bsk"] = {
["name"] = "Бурушаскі",
["article"] = "Бурушаскі (мова)",
["direction"] = "rtl",
},
["bua"] = {
["name"] = "Бурятська",
["article"] = "Білоруська мова",
},
["cel-pro"] = { -- Incorrect tag
["name"] = "Пракельтська",
["article"] = "Пракельтська мова",
["Wikipedia_code"] = "cel-x-proto",
},
["cel-x-proto"] = {
["name"] = "Пракельтська",
},
["cu"] = {
["name"] = "Староцерковнослов'янська",
["article"] = "Староцерковнослов'янська мова",
},
["de"] = {
["name"] = "Німецька",
["article"] = "Німецька мова",
},
["en"] = {
["name"] = "Англійська",
["article"] = "Англійська мова",
},
["es"] = {
["name"] = "Іспанська",
["article"] = "Іспанська мова",
},
["egy"] = {
["name"] = "Єгипетська",
["article"] = "Єгипетська мова",
},
["fr"] = {
["name"] = "Французька",
["article"] = "Французька мова",
},
["frm"] = {
["name"] = "Середньофранцузька",
["article"] = "Середньофранцузька мова",
},
["frp"] = {
["name"] = "Франко-провансальська",
["article"] = "Франко-провансальська мова",
},
["ff"] = {
["name"] = "Фульфульде",
},
["gem-pro"] = { -- Incorrect tag
["name"] = "Прагерманська",
["article"] = "Прагерманська мова",
["type"] = "reconstructed",
["replacements"] = {},
["Wikipedia_code"] = "gem-x-proto",
},
["gem-x-proto"] = {
["name"] = "Прагерманська",
["article"] = "Прагерманська мова",
["type"] = "reconstructed",
["replacements"] = {},
},
["gml"] = {
["name"] = "Середньонижньонімецька",
["article"] = "Середньонижньонімецька мова",
},
["gmw-ecg"] = {
["name"] = "Східноцентральнонімецька",
["article"] = "Східноцентральнонімецька мова",
},
["gmw-x-proto"] = {
["name"] = "Празахідногерманська",
["article"] = "Празахідногерманська мова",
["type"] = "reconstructed",
["replacements"] = {},
},
["gmq-x-gut"] = {
["name"] = "Гутнічна",
["article"] = "Гутнічна мова",
},
["goh"] = {
["replacements"] = {
decompose = true,
from = {
"[" .. macron .. circumflex .. diaeresis .. "]",
},
},
},
["got"] = {
["name"] = "Готська",
["article"] = "Готська мова",
["replacements"] = {
-- Latin to Gothic since people will not want to have to copy
-- and paste Gothic letters in
["[AÁaáĀā]"] = "𐌰",
["[Bb]"] = "𐌱",
["[Gg]"] = "𐌲",
["[Dd]"] = "𐌳",
["[EeĒē]"] = "𐌴",
["[Qq]"] = "𐌵",
["[Zz]"] = "𐌶",
["[Hh]"] = "𐌷",
["[Þþ]"] = "𐌸",
["[IiÍí]"] = "𐌹",
["[Kk]"] = "𐌺",
["[Ll]"] = "𐌻",
["[Mm]"] = "𐌼",
["[Nn]"] = "𐌽",
["[Jj]"] = "𐌾",
["[UuÚúŪū]"] = "𐌿",
["[Pp]"] = "𐍀",
["[Rr]"] = "𐍂",
["[Ss]"] = "𐍃",
["[Tt]"] = "𐍄",
["[WwYy]"] = "𐍅",
["[Ff]"] = "𐍆",
["[Xx]"] = "𐍇",
["[Ƕƕ]"] = "𐍈", -- Not sure if "hw" and "hv" can safely be converted
["[OoŌō]"] = "𐍉",
},
},
["gsw"] = {
["name"] = "Алеманська",
["article"] = "Алеманський діалект",
},
["grc"] = {
["name"] = "Давньогрецька",
["article"] = "Давньогрецька мова",
["replacements"] = {
decompose = true,
from = {
-- Replace variant letterforms with standard ones.
"ϐ", "ϵ", "ϑ", "ϰ", "ϱ", "ϲ", "ϕ",
-- Remove macrons and breves.
"[" .. macron .. breve .. undertie .. "]"
},
to = {
"β", "ε", "θ", "κ", "ρ", "σ", "φ",
}
},
},
["grk-pro"] = { -- Incorrect tag
["name"] = "Праоеллінська",
["Wikipedia_name"] = "Прагрецька",
["article"] = "Прагрецька мова",
["type"] = "reconstructed",
["replacements"] = {},
["Wikipedia_code"] = "gem-x-proto",
},
["grk-x-proto"] = {
["name"] = "Праоеллінська",
["Wikipedia_name"] = "Прагрецька",
["article"] = "Прагрецька мова",
["type"] = "reconstructed",
["replacements"] = {},
},
["grt"] = {
["name"] = "Гаро",
["article"] = "Гаро (мова)",
},
["ha"] = {
["name"] = "Хауса",
["article"] = "Хауса (мова)",
-- remove tilde, grave, acute, macron, circumflex
["replacements"] = {
decompose = true,
from = { "[" .. grave .. circumflex .. macron .. acute .. tilde .. "]" },
},
},
["hi"] = {
["name"] = "Гінді",
["article"] = "Гінді",
},
["ine-bsl-pro"] = {
["name"] = "Прабалто-слов'янська",
["article"] = "Прабалто-слов'янська мова",
["type"] = "reconstructed",
},
["ine-pro"] = { -- Incorrect tag
["name"] = "Праіндоєвропейська",
["article"] = "Праіндоєвропейська мова",
["type"] = "reconstructed",
["replacements"] = {},
["Wikipedia_code"] = "ine-x-proto",
},
["ine-x-proto"] = {
["name"] = "Праіндоєвропейська",
["article"] = "Праіндоєвропейська мова",
["type"] = "reconstructed",
["replacements"] = {},
},
["ja"] = {
["name"] = "Японська",
["article"] = "Японська мова",
},
["jbo"] = { -- Lojban
["type"] = "appendix",
},
["la"] = {
["name"] = "Латинська",
["article"] = "Латинська мова",
["replacements"] = {
decompose = true,
from = { "[" .. macron .. breve .. diaeresis .. "]" },
},
},
["lt"] = {
["name"] = "Литовська",
["article"] = "Литовська мова",
-- remove acute, tilde, grave
["replacements"] = {
decompose = true,
from = { "[" .. acute .. tilde .. grave .. "]" },
},
},
["khw"] = {
["name"] = "Кховар",
["article"] = "Кховар",
["direction"] = "rtl",
},
["moe"] = {
["name"] = "Крі",
["article"] = "Крі (мова)",
},
["mul"] = {
["name"] = "Транслінгвальна",
["article"] = "",
},
["nci"] = {
["name"] = "Класичний науатль",
["article"] = "Класичний науатль",
-- Remove macrons, acutes, circumflexes and graves
["replacements"] = {
decompose = true,
-- Remove macrons, acutes, circumflexes, graves, and saltillo;
-- see [[Saltillo (linguistics)]].
from = { "[" .. grave .. acute .. macron .. circumflex .. "Ꞌꞌʻʼ'ʔ]" },
},
},
["nds-de"] = {
["name"] = "Німецька нижньонімецька",
},
["odt"] = {
["name"] = "Старонідерландська",
["article"] = "Старонідерландська мова",
},
["oge"] = {
["name"] = "Давньогрузинська",
["article"] = "Давньогрузинська мова",
},
["oj"] = {
["name"] = "Оджибве",
},
["orv"] = {
["name"] = "Давньоруська",
["article"] = "Давньоруська мова",
["replacements"] = {
[U(0x484)] = "",
},
},
["osx"] = {
["name"] = "Старосаксонська",
["article"] = "Старосаксонська мова",
},
["pt"] = {
["name"] = "Португальська",
["article"] = "Португальська мова",
-- ["scripts"] = { "Latn" },
},
["pa"] = {
["name"] = "Пенджабська",
["article"] = "Пенджабська мова",
},
["pis"] = {
["name"] = "Піджин Соломонових Островів",
["article"] = "Піджин Соломонових Островів",
},
["poz-x-poly-proto"] = {
["name"] = "Праполінезійська",
["article"] = "Праполінезійська мова",
["type"] = "reconstructed",
},
["rap"] = {
["name"] = "Рапануйська",
["article"] = "Рапануйська мова",
},
["ru"] = {
["name"] = "Російська",
["article"] = "Російська мова",
["replacements"] = { [acute] = "", },
},
["rw"] = {
["name"] = "Руанда-рунді",
},
["se"] = {
["replacements"] = {
["([đflmnŋrsšŧv])'%1"] = "%1%1",
},
},
["sem-pro"] = {
["name"] = "Прасемітська",
["article"] = "Прасемітська мова",
["type"] = "reconstructed",
},
["sh"] = {
["name"] = "Сербохорватська",
["article"] = "Сербохорватська мова",
["replacements"] = {
decompose = true,
from = { "([AaEeIiOoUuRrАаЕеИиОоУуРр])[" .. double_grave
.. grave .. invbreve .. acute .. macron .. tilde .. "]" },
to = { "%1" },
},
},
["sl"] = {
["name"] = "Словенська",
["article"] = "Словенська мова",
["replacements"] = {
decompose = true,
-- remove tonal orthography
from = {"ł", "[" .. grave .. acute .. macron .. double_grave .. invbreve .. circumflex .. dot_below .. "]"},
to = {"l"},
},
},
["sla-pro"] = {
["name"] = "Праслов'янська", -- also Common Slavic
["article"] = "Праслов'янська мова",
["type"] = "reconstructed",
["replacements"] = {
["[ÀÁÃĀȀȂ]"] = "A",
["[àáãāȁȃ]"] = "a",
["[ÈÉẼĒȄȆ]"] = "E",
["[èéẽēȅȇ]"] = "e",
["[ÌÍĨĪȈȊ]"] = "I",
["[ìíĩīȉȋ]"] = "i",
["[ÒÓÕŌȌȎŐ]"] = "O",
["[òóõōȍȏő]"] = "o",
["[ÙÚŨŪȔȖŰ]"] = "U",
["[ùúũūȕȗű]"] = "u",
["[ỲÝỸȲ]"] = "Y",
["[ỳýỹȳ]"] = "y",
["Ǭ"] = "Ǫ",
["ǭ"] = "ǫ",
["[" .. grave .. acute .. double_acute .. tilde .. macron .. double_grave .. invbreve .. "]"] = "",
["ĭ"] = "ь",
["ŭ"] = "ъ",
},
},
["uk"] = {
["name"] = "Українська",
["article"] = "Українська мова",
["replacements"] = { [acute] = "", }
},
["ur"] = {
["name"] = "Урду",
["article"] = "Урду",
},
["xcl"] = {
["name"] = "Старовірменська",
["article"] = "Грабар (мова)",
["replacements"] = {
["[՞՜՛՟]"] = "",
["և"] = "եւ",
},
},
["xgf"] = {
["name"] = "Тонгва", -- not ISO name "Gabrielino-Fernandeño"
["article"] = "Tongva language",
["replacements"] = {
["['`ʔ]"] = "ʼ",
},
},
["xlu"] = {
["name"] = "Лувійська", -- not ISO name "Cuneiform Luwian"
},
["xxt"] = {
["name"] = "Тамборська",
["article"] = "Тамборська мова",
},
["xvn"] = {
["name"] = "Вандальська",
["article"] = "Вандальська мова",
},
["yua"] = {
["name"] = "Юкатекська",
["article"] = "Юкатекська мова",
},
["zh"] = {
["name"] = "Китайська",
["article"] = "Китайська мова",
-- ["scripts"] = { "Hani" },
},
},
-- Here, keys (for example, "gem") are Wikipedia language codes used in
-- {{lang}}, and values (for example, "gem-pro") are the equivalent Wiktionary
-- code.
-- Subtags are not currently supported.
["redirects"] = {
["aae"] = "sq",
["aiq"] = "fa",
["aln"] = "sq",
["als"] = "sq",
["azb"] = "az",
["azj"] = "az",
["bgn"] = "bal",
["bs"] = "sh",
["bxr"] = "bua",
["ciw"] = "oj",
["cnr"] = "sh",
["fil"] = "tl",
["fuf"] = "ff",
["gem"] = "gem-pro", -- Not correct, but is commonly used.
["hak"] = "zh",
["hbo"] = "he",
["hr"] = "sh",
["ine"] = "ine-pro", -- Not correct, but might be commonly used.
["kjv"] = "sh",
["nan"] = "zh",
["prs"] = "fa",
["rn"] = "rw",
["sli"] = "gmw-ecg",
["sr"] = "sh",
["src"] = "sc",
["sro"] = "sc",
["tw"] = "ak",
["wae"] = "gsw",
["wep"] = "nds-de",
["yue"] = "zh",
["xno"] = "fro",
},
}
return data
|
Index:
pl ar de en es fr it arz nl ja pt ceb sv uk vi war zh ru af ast az bg zh-min-nan bn be ca cs cy da et el eo eu fa gl ko hi hr id he ka la lv lt hu mk ms min no nn ce uz kk ro simple sk sl sr sh fi ta tt th tg azb tr ur zh-yue hy my ace als am an hyw ban bjn map-bms ba be-tarask bcl bpy bar bs br cv nv eml hif fo fy ga gd gu hak ha hsb io ig ilo ia ie os is jv kn ht ku ckb ky mrj lb lij li lmo mai mg ml zh-classical mr xmf mzn cdo mn nap new ne frr oc mhr or as pa pnb ps pms nds crh qu sa sah sco sq scn si sd szl su sw tl shn te bug vec vo wa wuu yi yo diq bat-smg zu lad kbd ang smn ab roa-rup frp arc gn av ay bh bi bo bxr cbk-zam co za dag ary se pdc dv dsb myv ext fur gv gag inh ki glk gan guw xal haw rw kbp pam csb kw km kv koi kg gom ks gcr lo lbe ltg lez nia ln jbo lg mt mi tw mwl mdf mnw nqo fj nah na nds-nl nrm nov om pi pag pap pfl pcd krc kaa ksh rm rue sm sat sc trv stq nso sn cu so srn kab roa-tara tet tpi to chr tum tk tyv udm ug vep fiu-vro vls wo xh zea ty ak bm ch ny ee ff got iu ik kl mad cr pih ami pwn pnt dz rmy rn sg st tn ss ti din chy ts kcg ve
Portal di Ensiklopedia Dunia
