Module:Language/data/wp languages

From WikiProjectMed
Jump to navigation Jump to search

The provenance of the data in this table is unknown. Possibly some of it comes from an earlier version of this CLDR file: https://phabricator.wikimedia.org/diffusion/ECLD/browse/master/LocalNames/LocalNamesEn.php

For Wikipedia / MediaWiki language code-to-name needs (because MediaWiki codes / names sometimes differ from ISO 639 / IANA standards) consider using this:

local wiki_lang_names_table = mw.language.fetchLanguageNames(mw.getContentLanguage():getCode(), 'all')	-- table of language codes and names (indexed by code) known to MediaWiki

The above will always be current with MediaWiki whereas this module is not. documentation


return 	{	-- wp preferred names												-- IANA language names and notes
--ISO 639-1 codes
	["ab"] = {"Abkhaz"},														-- Abkhazian
	["an"] = {"Aragonese"},														-- Aragonese; same, delete?
	["av"] = {"Avar"},															-- Avaric
	["bh"] = {"Bihari"},														-- Bihari languages; collective
	["bo"] = {"Standard Tibetan"},												-- Tibetan
	["cu"] = {"Old Church Slavonic"},											-- Church Slavic, Church Slavonic, Old Bulgarian, Old Church Slavonic, Old Slavonic
	["de-AT"] = {"Austrian German"},
	["el"] = {"Greek"},															-- Modern Greek (1453-)
	["en-AU"] = {"Australian English"},
	["en-CA"] = {"Canadian English"},
	["en-GB"] = {"British English"},
	["en-IE"] = {"Irish English"},
	["en-NZ"] = {"New Zealand English"},
	["en-SA"] = {"South African English"},
	["en-US"] = {"American English"},
	["ff"] = {"Fula"},															-- Fulah
	["fy"] = {"Frisian"},														-- Western Frisian
	["ht"] = {"Haitian Creole"},												-- Haitian, Haitian Creole
	["hz"] = {"Otjiherero"},													-- Herero
	["ia"] = {"Interlingua"},													-- Interlingua (International Auxiliary Language Association)
	["ii"] = {"Yi"},															-- Sichuan Yi, Nuosu
	["ki"] = {"Gikuyu"},														-- Kikuyu, Gikuyu
	["kk"] = {"Kazakh"},														-- Kazakh; same, delete?
	["kl"] = {"Greenlandic"},													-- Kalaallisut, Greenlandic
	["km"] = {"Khmer"},															-- Central Khmer
	["ky"] = {"Kyrgyz"},														-- Kirghiz, Kyrgyz
	["lg"] = {"Luganda"},														-- Ganda
	["li"] = {"Limburgish"},													-- Limburgan, Limburger, Limburgish
	["mi"] = {"Māori"},															-- Maori
	["ms"] = {"Malay"},															-- Malay (macrolanguage)
	["na"] = {"Nauruan"},														-- Nauru
	["nb"] = {"Bokmål"},														-- Norwegian Bokmål
	["nd"] = {"Northern Ndebele"},												-- North Ndebele
	["ne"] = {"Nepali"},														-- Nepali (macrolanguage)
	["nn"] = {"Nynorsk"},														-- Norwegian Nynorsk
	["nr"] = {"Southern Ndebele"},												-- South Ndebele
	["ny"] = {"Chichewa"},														-- Nyanja, Chewa, Chichewa
	["oc"] = {"Occitan"},														-- Occitan (post 1500)
	["oj"] = {"Ojibwe"},														-- Ojibwa
	["or"] = {"Odia"},															-- Oriya (macrolanguage), Odia (macrolanguage)
	["pa"] = {"Punjabi"},														-- Panjabi, Punjabi
	["pi"] = {"Pali"},															-- Pali; same, delete?
	["rn"] = {"Kirundi"},														-- Rundi
	["ro"] = {"Romanian"},														-- Romanian, Moldavian, Moldovan; same as first in IANA list, delete?
	["rw"] = {"Kinyarwanda"},													-- Kinyarwanda; same, delete?
	["si"] = {"Sinhalese"},														-- Sinhala, Sinhalese
	["sl"] = {"Slovene"},														-- Slovenian
	["sr-Cyrl"] = {"Serbian Cyrillic"},											-- sr = Serbian; Cyrillic is the alphabet
	["ss"] = {"Swazi"},															-- Swati
	["st"] = {"Sotho"},															-- Southern Sotho
	["sw"] = {"Swahili"},														-- Swahili (macrolanguage)
	["to"] = {"Tongan"},														-- Tonga (Tonga Islands)
	["za"] = {"Zhuang"},														-- Zhuang, Chuang; ; same as first in IANA list, delete?


-- ISO 639-2 codes
	["ber"] = {"Berber"},														-- Berber languages
	["cel"] = {"Proto-Celtic"},													-- Celtic languages
	["gem"] = {"Proto-Germanic"},												-- Germanic languages
	["myn"] = {"Mayan"},														-- Mayan languages
	["nah"] = {"Nahuatl"},														-- Nahuatl languages
	["pra"] = {"Prakrit"},														-- Prakrit languages
--	["roa"] = {"Jèrriais"},														-- Romance languages
	["sal"] = {"Salish"},														-- Salishan languages
	["sla"] = {"Slavic"},														-- Slavic languages
	["son"] = {"Songhay"},														-- Songhai languages
	["wen"] = {"Sorbian"},														-- Sorbian languages


-- ISO 639-3 codes
	["abk"] = {"Abkhaz"},														-- not in IANA; see code ab
	["ace"] = {"Acehnese"},														-- Achinese
	["aec"] = {"Sa'idi Arabic"},												-- Saidi Arabic
	["ain"] = {"Ainu"},															-- Ainu (Japan)
	["akl"] = {"Aklan"},														-- Aklanon
	["alt"] = {"Altay"},														-- Southern Altai
	["ang"] = {"Old English"},													-- Old English (ca. 450-1100)
	["apm"] = {"Mescalero-Chiricahua"},											-- Mescalero-Chiricahua Apache
	["bal"] = {"Balochi"},														-- Baluchi
--	["bar"] = {"Austro-Bavarian"},												-- Bavarian
	["bcl"] = {"Central Bicolano"},												-- Central Bikol
	["bin"] = {"Edo"},															-- Bini, Edo
	["bpy"] = {"Bishnupriya Manipuri"},											-- Bishnupriya
	["brx"] = {"Bodo"},															-- Bodo (India)
	["chg"] = {"Chagatay"},														-- Chagatai
	["chm"] = {"Mari"},															-- Mari (Russia)
	["ckb"] = {"Sorani Kurdish"},												-- Central Kurdish
	["cnu"] = {"Shenwa"},														-- Chenoua
	["coc"] = {"Cocopah"},														-- Cocopa
	["deu"] = {"early German"},													-- not in IANA; see code de
	["diq"] = {"Zazaki"},														-- Dimli (individual language)
	["egy"] = {"Egyptian"},														-- Egyptian (Ancient)
	["ell"] = {"Modern Greek"},													-- not in IANA; see code el
	["enm"] = {"Middle English"},												-- Middle English (1100-1500)
	["fit"] = {"Meänkieli"},													-- Tornedalen Finnish
	["fkv"] = {"Kven"},															-- Kven Finnish
	["frk"] = {"Old Frankish"},													-- Frankish
	["frm"] = {"Middle French"},												-- Middle French (ca. 1400-1600)
	["fro"] = {"Old French"},													-- Old French (842-ca. 1400)
	["fry"] = {"West Frisian"},													-- not in IANA; see code fy
	["gez"] = {"Ge'ez"},														-- Geez
	["gju"] = {"Gujari "},														-- Gujari; same, delete?
	["gmh"] = {"Middle High German"},											-- Middle High German (ca. 1050-1500)
	["goh"] = {"Old High German"},												-- Old High German (ca. 750-1050)
	["grc"] = {"Ancient Greek"},												-- Ancient Greek (to 1453)
	["gsw"] = {"Alemannic German"},												-- Swiss German, Alemannic, Alsatian
	["gul"] = {"Gullah"},														-- Sea Island Creole English
	["hak"] = {"Hakka"},														-- Hakka Chinese
	["hbo"] = {"Biblical Hebrew"},												-- Ancient Hebrew
	["hnd"] = {"Hindko"},														-- Southern Hindko
	["ikt"] = {"Inuvialuk"},													-- Inuinnaqtun, Western Canadian Inuktitut
--	["ilo"] = {"Ilokano"},														-- Iloko; disabled here in favor of Ilocano in Module:Lang/data
	["kaa"] = {"Karakalpak"},													-- Kara-Kalpak
	["khb"] = {"Tai Lü"},														-- Lü
	["kmr"] = {"Kurmanji Kurdish"},												-- Northern Kurdish
	["knn"] = {"Konkani"},														-- Konkani (individual language)
	["kok"] = {"Konkani"},														-- Konkani (macrolanguage)
	["kpo"] = {"Kposo"},														-- Ikposo
	["krj"] = {"Kinaray-a"},													-- Kinaray-A
--	["ksh"] = {"Ripuarian"},													-- Kölsch;  --ksh is the code of Colognian, but ksh.wiki is the Ripuarian Wikipedia; disabled here so that:
																				-- ksh -> IANA/ISO-639-3 Kölsch; ksh-x-colog -> Colognian & mis-x-ripuar -> Ripuarian both defined in Module:Lang/data
	["ktz"] = {"Juǀ'hoan"},														-- Ju/'hoan, Juǀʼhoan, Juǀʼhoansi
	["lez"] = {"Lezgian"},														-- Lezghian
	["liv"] = {"Livonian"},														-- Liv
	["lng"] = {"Lombardic"},													-- Langobardic
--	["maz"] = {"Mazovian"},														-- Central Mazahua; a misuse of code for an unrelated language;
	["mga"] = {"Middle Irish"},													-- Middle Irish (900-1200)
	["mhr"] = {"Mari"},															-- Eastern Mari
	["mia"] = {"Miami-Illinois"},												-- Miami
	["miq"] = {"Miskito"},														-- Mískito
	["mix"] = {"Mixtec"},														-- Mixtepec Mixtec
--	["mla"] = {"Medieval Latin"},												-- Malo; clearly a misuse of code mla;
	["mni"] = {"Meitei"},														-- Manipuri
	["mol"] = {"Moldovan", "ro"},												-- Moldavian, Moldovan (639-3, both retired)
	["mrj"] = {"Hill Mari"},													-- Western Mari
	["mww"] = {"White Hmong"},													-- Hmong Daw
	["mzn"] = {"Mazanderani"},													-- Mazanderani
--	["nan"] = {"Taiwanese Hokkien"},											-- Min Nan Chinese; disabled here so that nan -> Min Nan Chinese; nan-tw -> Taiwanese Hokkien in Module:Lang/data
	["naq"] = {"Khoekhoe"},														-- Khoekhoe, Nama (Namibia); same as first in IANA list, delete?
--	["naz"] = {"North Azeri"},													-- Coatepec Nahuatl; clearly a misuse of code naz
	["nci"] = {"Classical Nahuatl"},											-- Classical Nahuatl; same, delete?
	["nds-nl"] = {"Dutch Low Saxon"},											-- Low German, Low Saxon; as spoken in the Netherlands; see code nsd
	["new"] = {"Nepal Bhasa"},													-- Newari, Nepal Bhasa
--	["nrm"] = {"Norman"},														-- Narom; clearly a misuse of code nrm
--	["nsd"] = {"Dutch Low Saxon"},												-- Southern Nisu; how can this be right? typo related to code nds-nl?
	["nso"] = {"Northern Sotho"},												-- Pedi, Northern Sotho, Sepedi
	["nwc"] = {"Classical Nepal Bhasa"},										-- Classical Newari, Classical Nepal Bhasa, Old Newari
	["oci"] = {"Provençal"},													-- oc
	["ood"] = {"O'odham"},														-- Tohono O'odham
	["ota"] = {"Ottoman Turkish"},												-- Ottoman Turkish (1500-1928)
	["otk"] = {"Old Turkic"},													-- Old Turkish
	["pal"] = {"Middle Persian"},												-- Pahlavi
	["pam"] = {"Kapampangan"},													-- Pampanga, Kapampangan
	["peo"] = {"Old Persian"},													-- Old Persian (ca. 600-400 B.C.)
	["phr"] = {"Potwari"},														-- Pahari-Potwari
	["pka"] = {"Jain Prakrit"},													-- Ardhamāgadhī Prākrit
	["pnb"] = {"Punjabi"},														-- Western Panjabi
	["psu"] = {"Shauraseni"},													-- Sauraseni Prākrit
	["rap"] = {"Rapa Nui"},														-- Rapanui
	["rar"] = {"Cook Islands Māori"},											-- Rarotongan, Cook Islands Maori
	["rmu"] = {"Scandoromani"},													-- Tavringer Romani
	["rom"] = {"Romani"},														-- Romany
	["rup"] = {"Aromanian"},													-- Macedo-Romanian, Aromanian, Arumanian
	["rus"] = {"Russian"},														-- not in IANA; see code ru
	["ryu"] = {"Okinawan"},														-- Central Okinawan
--	["sah"] = {"Sakha"},														-- Yakut; article moved to Yakut with this disucssion: Talk:Yakut_language#Requested_move_21_September_2015
	["sdc"] = {"Sassarese"},													-- Sassarese Sardinian
	["sdn"] = {"Gallurese"},													-- Gallurese Sardinian
	["sga"] = {"Old Irish"},													-- Old Irish (to 900)
	["shp"] = {"Shipibo"},														-- Shipibo-Conibo
	["skr"] = {"Saraiki"},														-- Saraiki, Seraiki; same as first in IANA list, delete?
	["src"] = {"Logudorese"},													-- Logudorese Sardinian
	["sro"] = {"Campidanese"},													-- Campidanese Sardinian
	["tkl"] = {"Tokelauan"},													-- Tokelau
	["tvl"] = {"Tuvaluan"},														-- Tuvalu
	["tyv"] = {"Tuvan"},														-- Tuvinian
	["vls"] = {"West Flemish"},													-- Vlaams
	["war"] = {"Waray"},														-- Waray (Philippines)
	["wep"] = {"Westphalian"},													-- Westphalien
	["xal"] = {"Oirat"},														-- Kalmyk, Oirat
	["xal-RU"] = {"Kalmyk Oirat"},
	["xcl"] = {"Old Armenian"},													-- Classical Armenian
	["yua"] = {"Yucatec Maya"},													-- Yucateco, Yucatec Maya


--[[
non-standard codes

these tags are mostly (all?) supported by the MediaWiki {{#language:}} magic word; none are valid IETF language
tags.  Templates needing these tags might be better served by using the magic word or the functions available in
Module:mw lang via its template {{mw lang}}
]]
--[[
	["bat-smg"] = {"Samogitian"},												-- bat = Baltic languages (639-2); dialect of Lithuanian has it's own IANA code sgs; bat-smg
	["be-x-old "] = {"Belarusian (Taraškievica)"},								-- be = Belarusian; x-old = private use tag; be-x-old.wikipedia.org; space char in index may indicate that this code not used
	["cbk-zam"] = {"Chavacano"},												-- cbk = Chavacano; zam = Zamboangueño? zam is not an IANA-registered extlang; cbk-zam.wikipedia.org
--	["cg"] = {"Montenegrin", "sr-ME"},											-- IANA / ISO 639-3 code is cnr
	["en-emodeng"] = {"Early Modern English"},									-- emodeng is not an IANA-registered variant
	["fiu-vro"] = {"Võro"},														-- fiu = Finno-Ugrian languages (639-2); vro = Võro (639-3); fiu-vro.wikipedia.org
	["gkm"] = {"Medieval Greek", "grc"},
	["grc-gre"] = {"Greek", "grc"},												-- grc = Ancient Greek (to 1453); gre not an IANA-registered code; used by Template:lang-grc-gre
	["map-bms"] = {"Banyumasan"},												-- dialect of Javanese; map = Austronesian languages (639-2); bms is an IANA registered code not related to Javanese; map-bms.wikipedia.org
	["roa-rup"] = {"Aromanian"},												-- roa = Romance languages (639-2); rup = Macedo-Romanian, Aromanian, Arumanian (639-3); roa-rup.wikipedia.org
	["roa-tara"] = {"Tarantino"},												-- roa = Romance languages (639-2); tara is not an IANA registered script; roa-tara.wikipedia.org
	["simple"] = {"Simple English"},											-- simple is not an IANA registered variant; simple.wikipedia.org
	["zh-classical"] = {"Classical Chinese"},									-- zh = Chinese; classical is not an IANA-registered variant; zh-classical.wikipedia.org
	["zh-min-nan"] = {"Min Nan"},												-- zh-min-nan = Minnan, Hokkien, Amoy, Taiwanese, Southern Min, Southern Fujian, Hoklo, Southern Fukien, Ho-lo; granfathered in IANA, nan preferred; zh-min-nan.wikipedia.org
	["zh-yue"] = {"Cantonese"}													-- zh-yue = Cantonese; redundant in IANA, yue preferred; zh-yue.wikipedia.org
]]	}