--[[--------------------------< L A N G _ N A M E _ T A B L E >------------------------------------------------
primary table of tables that decode:
lang -> language tags and names
script -> ISO 15924 script tags
region -> ISO 3166 region tags
variant -> iana registered variant tags
suppressed -> map of scripts tags and their associated language tags
all of these data come from separate modules that are derived from the IANA language-subtag-registry file
key_to_lower() avoids the metatable trap and sets all keys in the subtables to lowercase. Many language codes
have multiple associated names; Module:lang is only concerned with the first name so key_to_lower() only fetches
the first name.
TODO: instead of returning:
["key"] = {"name"}
where each table has only one name, return
["key"] = "name"
requires changes in Module:Lang.
]]
local function key_to_lower (module, src_type)
local out = {};
local source = (('variants' == src_type) and require (module)) or mw.loadData (module); -- fetch data from this module; require() avoids metatable trap for variant data
if 'variants' == src_type then
for k, v in pairs (source) do
out[k:lower()] = v; -- for variant, everything is needed
end
elseif 'lang' == src_type and source.active then -- for ~/iana_languages (active)
for k, v in pairs (source.active) do
out[k:lower()] = {v[1]}; -- ignore multiple names; take first name only
end
elseif 'lang_dep' == src_type and source.deprecated then -- for ~/iana_languages (deprecated)
for k, v in pairs (source.deprecated) do
out[k:lower()] = {v[1]}; -- ignore multiple names; take first name only
end
else -- here for all other sources
for k, v in pairs (source) do
out[k:lower()] = {v[1]}; -- ignore multiple names; take first name only
end
end
return out;
end
local lang_name_table = {
lang = key_to_lower ('Module:Language/data/iana languages', 'lang'),
lang_dep = key_to_lower ('Module:Language/data/iana languages', 'lang_dep'),
script = key_to_lower ('Module:Language/data/iana scripts'), -- script keys are capitalized; set to lower
region = key_to_lower ('Module:Language/data/iana regions'), -- region keys are uppercase; set to lower
variant = key_to_lower ('Module:Language/data/iana variants', 'variants'),
suppressed = key_to_lower ('Module:Language/data/iana suppressed scripts'), -- script keys are capitalized; set to lower
}
--[[--------------------------< O V E R R I D E >--------------------------------------------------------------
Language codes and names in this table override the BCP47 names in lang_name_table.
indexes in this table shall always be lower case
]]
local override = {
------------------------------< I S O 6 3 9 - 1 >------------------------------------------------------------
["ab"] = {"Abkhazie"}, -- IANA name is Abkhazian; override wp_languages {"Abkhaz"}; to achieve this, use |label=
["bh"] = {"Bihari leids"}, -- only ISO 639-1 collective; defined here to override improper redefinition (Bihari) in wp_languages
["ca-valencia"] = {"Valencian"},
["cu"] = {"Kirk Slavonic"}, -- 2nd IANA name;
["de-at"] = {"Austrick German"}, -- these code-region and code-variant to match en.wiki article names
["de-ch"] = {"Swiss German"},
["en-au"] = {"Australie Inglis"},
["en-ca"] = {"Canadian Inglis"},
["en-emodeng"] = {"Early Modren Inglis"},
["en-gb"] = {"Breetish Inglis"},
["en-ie"] = {"Erse Inglis"},
["en-in"] = {"Indie Inglis"},
["en-nz"] = {"New Zealand Inglis"},
["en-us"] = {"American Inglis"},
["en-za"] = {"Sooth African Inglis"},
["fy"] = {"Wast Frisie"}, -- IANA name is Western Frisian
["mo"] = {"Moldovan"}, -- Moldavian (deprecated code); to match en.wiki article title
["oc-provenc"] = {"Provençal"},
["ps"] = {"Pashto"}, -- IANA name is Pushto
["si"] = {"Sinhala"}, -- IANA name is Sinhala, Sinhalese; override wp_languages {"Sinhalese"}; see Module talk:Language/data/wp languages#Request to undo an edit
["sr-cyrl"] = {"Serbie"}, -- override wp_languages Serbian Cyrillic; to achieve this, use |label=
["tw-asante"] = {"Asante Twi"},
-- these ISO 639-1 language-name overrides imported from Module:Language/data/wp_languages
--<begin do-not-edit except to comment out>--
["av"] = {"Avar"}, -- Avaric
["bo"] = {"Standard Tibetan"}, -- Tibetan
["el"] = {"Greek"}, -- Modern Greek
-- ["en-SA"] = {"South African English"}, -- English; no; SA is not South Africa it Saudi Arabia; ZA is South Africa
["ff"] = {"Fula"}, -- Fulah
["ht"] = {"Haitian Creole"}, -- Haitian
["hz"] = {"Otjiherero"}, -- Herero
["ii"] = {"Yi"}, -- Sichuan Yi
["ki"] = {"Gikuyu"}, -- Kikuyu
["kl"] = {"Greenlandic"}, -- Kalaallisut
["ky"] = {"Kyrgyz"}, -- Kirghiz
["lg"] = {"Luganda"}, -- Ganda
["li"] = {"Limburgish"}, -- Limburgan
["mi"] = {"Māori"}, -- Maori
["na"] = {"Nauruan"}, -- Nauru
["nb"] = {"Bokmål"}, -- Norwegian Bokmål
["nd"] = {"Northern Ndebele"}, -- North Ndebele
["nn"] = {"Nynorsk"}, -- Norwegian Nynorsk
["nr"] = {"Southern Ndebele"}, -- South Ndebele
["ny"] = {"Chichewa"}, -- Nyanja
["oj"] = {"Ojibwe"}, -- Ojibwa
["or"] = {"Odia"}, -- Oriya
["pa"] = {"Punjabi"}, -- Panjabi
["rn"] = {"Kirundi"}, -- Rundi
["sl"] = {"Slovene"}, -- Slovenian
["ss"] = {"Swazi"}, -- Swati
["st"] = {"Sotho"}, -- Southern Sotho
["to"] = {"Tongan"}, -- Tonga
--<end do-not-edit except to comment out>--
------------------------------< I S O 6 3 9 - 2, - 3, - 5 >----------------------------------------------
["arc"] = {"Aramaic"}, -- IANA names are: Official Aramaic (700-300 BCE), Imperial Aramaic (700-300 BCE);
["art"] = {"constructit"}, -- to match en.wiki article; lowercase for category name
["ber"] = {"Berber leids"}, -- ISO 639-2 collective; defined here to override redefinition in wp_languages
["bla"] = {"Blackfoot"}, -- IANA, ISO 639-2, -3 name is Siksika; to match en.wiki article title
["bua"] = {"Buryat"}, -- IANA name Buriat; this is a macro language; these four use wp preferred transliteration;
["bxm"] = {"Mongolie Buryat"}, -- IANA name Mongolia Buriat; these three all redirect to Buryat
["bxr"] = {"Roushie Buryat"}, -- IANA name Russia Buriat;
["bxu"] = {"Cheenese Buryat"}, -- IANA name China Buriat;
["byr"] = {"Yipma"}, -- IANA names are Baruya and Yipma
["cel"] = {"Celtic leids"}, -- ISO 639-2 collective; defined here to override improper redefinition ('Proto-Celtic') in wp_languages; use cel-x-proto instead
["egy"] = {"Auncient Egyptian"}, -- IANA name is Egyptian (Ancient); distinguish from contemporary arz: Egyptian Arabic
["frr"] = {"North Frisie"}, -- IANA name is Northern Frisian
["frs"] = {"East Frisie Law Saxon"}, -- IANA name is Eastern Frisian
["gem"] = {"Germanic leids"}, -- ISO 639-2 collective; defined here to override improper redefinition ('Proto-Germanic') in wp_languages; use gem-x-proto instead
["ilo"] = {"Ilocano"}, -- IANA, ISO 639-2, -3 name is Iloko; to match en.wiki article title
["jam"] = {"Jamaican Patois"}, -- IANA name is Jamaican Creole English
["mhr"] = {"Meadow Mari"}, -- IANA name is Eastern Mari
["mid"] = {"Modren Mandaic"}, -- IANA name is Mandaic
["mla"] = {"Tamambo"}, -- wp_languages name is Medieval Latin; IANA and ISO 639-1 name is Malo
['mte'] = {"Mono-Alu"}, -- Mono (Solomon Islands)
["myn"] = {"Mayan leids"}, -- ISO 639-2 collective; defined here to override redefinition in wp_languages
["nah"] = {"Nahuatl leids"}, -- ISO 639-2 collective; defined here to override redefinition in wp_languages
["nan-tw"] = {"Taiwanese Hokkien"}, -- make room for IANA / 639-3 nan Min Nan Chinese; match en.wiki article title
["nrf"] = {"Norman"}, -- not quite a collective - IANA name: Jèrriais; categorizes to Norman-language text
["nzi"] = {"Nzema"}, -- IANA, ISO 639-2, -3 name is Nzima; to match en.wiki article title
["orv"] = {"Auld East Slavic"}, -- IANA name is Old Russian
["pfl"] = {"Palatine German"}, -- Pfaelzisch; to match en.wiki article
["pms"] = {"Piedmontese"}, -- IANA / 639-3 name is Piemontese; to match en.wiki article title
["pra"] = {"Prakrit leids"}, -- ISO 639-2 collective; defined here to override redefinition in wp_languages
["roa"] = {"Romance leids"}, -- ISO 639-2 collective; defined here to override improper redefinition (Jèrriais) in wp_language; IANA name is "Romance leids"
["sal"] = {"Salishan leids"}, -- ISO 639-2 collective; defined here to override redefinition in wp_languages
["sla"] = {"Slavic leids"}, -- ISO 639-2 collective; defined here to override redefinition in wp_languages
["son"] = {"Songhai leids"}, -- ISO 639-2 collective; defined here to override redefinition in wp_languages
["stq"] = {"Saterland Frisie"}, -- IANA name is Saterfriesisch
["und"] = {"undetermined"}, -- capitalization to match existing category
["wen"] = {"Sorbian leids"}, -- ISO 639-2 collective; defined here to override redefinition in wp_languages
["wrg"] = {"Warrongo"}, -- IANA name is Warungu
["xal-ru"] = {"Kalmyk"}, -- to match en.wiki article title
["xgf"] = {"Tongva"}, -- ISO 639-3 is Gabrielino-Fernandeño
-- these ISO 639-2, -3 language-name overrides imported from Module:Language/data/wp_languages
--<begin do-not-edit except to comment out>--
["ace"] = {"Acehnese"}, -- Achinese
["aec"] = {"Sa'idi Arabic"}, -- Saidi Arabic
["akl"] = {"Aklan"}, -- Aklanon
["alt"] = {"Altay"}, -- Southern Altai
["apm"] = {"Mescalero-Chiricahua"}, -- Mescalero-Chiricahua Apache
["bal"] = {"Balochi"}, -- Baluchi
["bcl"] = {"Central Bicolano"}, -- Central Bikol
["bin"] = {"Edo"}, -- Bini
["bpy"] = {"Bishnupriya Manipuri"}, -- Bishnupriya
["chg"] = {"Chagatay"}, -- Chagatai
["ckb"] = {"Sorani Kurdish"}, -- Central Kurdish
["cnu"] = {"Shenwa"}, -- Chenoua
["coc"] = {"Cocopah"}, -- Cocopa
["diq"] = {"Zazaki"}, -- Dimli
["fit"] = {"Meänkieli"}, -- Tornedalen Finnish
["fkv"] = {"Kven"}, -- Kven Finnish
["frk"] = {"Auld Frankish"}, -- Frankish
["gez"] = {"Ge'ez"}, -- Geez
["gju"] = {"Gujari"}, -- Gujari
["gsw"] = {"Alemannic German"}, -- Swiss German
["gul"] = {"Gullah"}, -- Sea Island Creole English
["hak"] = {"Hakka"}, -- Hakka Chinese
["hbo"] = {"Biblical Ebreu"}, -- Ancient Hebrew
["hnd"] = {"Hindko"}, -- Southern Hindko
-- ["ikt"] = {"Inuvialuk"}, -- Inuinnaqtun
["kaa"] = {"Karakalpak"}, -- Kara-Kalpak
["khb"] = {"Tai Lü"}, -- Lü
["kmr"] = {"Kurmanji Kurdish"}, -- Northern Kurdish
["kpo"] = {"Kposo"}, -- Ikposo
["krj"] = {"Kinaray-a"}, -- Kinaray-A
["ktz"] = {"Juǀ'hoan"}, -- Juǀʼhoan
["lez"] = {"Lezgian"}, -- Lezghian
["liv"] = {"Livonian"}, -- Liv
["lng"] = {"Lombardic"}, -- Langobardic
["mia"] = {"Miami-Illinois"}, -- Miami
["miq"] = {"Miskito"}, -- Mískito
["mix"] = {"Mixtec"}, -- Mixtepec Mixtec
["mni"] = {"Meitei"}, -- Manipuri
["mrj"] = {"Hill Mari"}, -- Western Mari
["mww"] = {"White Hmong"}, -- Hmong Daw
["nds-nl"] = {"Dutch Law Saxon"}, -- Law German
["new"] = {"Nepal Bhasa"}, -- Newari
["nso"] = {"Northern Sotho"}, -- Pedi
["nwc"] = {"Clessical Nepal Bhasa"}, -- Classical Newari
["ood"] = {"O'odham"}, -- Tohono O'odham
["otk"] = {"Auld Turkic"}, -- Old Turkish
["pal"] = {"Middle Persian"}, -- Pahlavi
["pam"] = {"Kapampangan"}, -- Pampanga
["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
["rmu"] = {"Scandoromani"}, -- Tavringer Romani
["rom"] = {"Romani"}, -- Romany
["rup"] = {"Aromanian"}, -- Macedo-Romanian
["ryu"] = {"Okinawan"}, -- Central Okinawan
["sdc"] = {"Sassarese"}, -- Sassarese Sardinian
["sdn"] = {"Gallurese"}, -- Gallurese Sardinian
["shp"] = {"Shipibo"}, -- Shipibo-Conibo
["src"] = {"Logudorese"}, -- Logudorese Sardinian
["sro"] = {"Campidanese"}, -- Campidanese Sardinian
["tkl"] = {"Tokelauan"}, -- Tokelau
["tvl"] = {"Tuvaluan"}, -- Tuvalu
["tyv"] = {"Tuvan"}, -- Tuvinian
["vls"] = {"Wast Flemish"}, -- Vlaams
["wep"] = {"Westphalian"}, -- Westphalien
["xal"] = {"Oirat"}, -- Kalmyk
["xcl"] = {"Auld Armenian"}, -- Classical Armenian
["yua"] = {"Yucatec Maya"}, -- Yucateco
--<end do-not-edit except to comment out>--
------------------------------< P R I V A T E - U S E T A G S >----------------------------------------------
["cel-x-proto"] = {"Proto-Celtic"}, -- cel in IANA is Celtic languages
["gem-x-proto"] = {"Proto-Germanic"}, -- gem in IANA is Germanic languages
["grc-x-aeolic"] = {"Aeolic Greek"}, -- these grc-x-... codes are preferred alternates to the non-standard catchall code grc-gre
["grc-x-attic"] = {"Attic Greek"},
["grc-x-biblical"] = {"Biblical Greek"},
["grc-x-byzant"] = {"Byzantine Greek"},
["grc-x-classic"] = {"Clessical Greek"},
["grc-x-doric"] = {"Doric Greek"},
["grc-x-hellen"] = {"Hellenistic Greek"},
["grc-x-ionic"] = {"Ionic Greek"},
["grc-x-koine"] = {"Koinē Greek"},
["grc-x-medieval"] = {"Medieval Greek"},
["grc-x-patris"] = {"Patristic Greek"},
["grk-x-proto"] = {"Proto-Greek"}, -- grk in IANA is Greek languages
["iir-x-proto"] = {"Proto-Indo-Iranian"}, -- iir in IANA is Indo-Iranian Languages
["ira-x-proto"] = {"Proto-Iranian"}, -- ira in IANA is Iranian languages
["itc-x-proto"] = {"Proto-Italic"}, -- itc in IANA is Italic languages
["ksh-x-colog"] = {"Colognian"}, -- en.wiki article is Colognian; ksh (Kölsch) redirects there
["mis-x-ripuar"] = {"Ripuarian"}, -- replaces improper use of ksh in wp_languages
["sla-x-proto"] = {"Proto-Slavic"}, -- sla in IANA is Slavic languages
["yuf-x-hav"] = {"Havasupai"}, -- IANA name for these three is Havasupai-Walapai-Yavapai
["yuf-x-wal"] = {"Walapai"},
["yuf-x-yav"] = {"Yavapai"},
}
--[[--------------------------< A R T I C L E _ L I N K >------------------------------------------------------
for those rare occasions when article titles don't fit with the normal '<language name>-language', this table
maps language code to article title. Use of this table should be avoided and the use of redirects preferred as
that is the long-standing method of handling article names that don't fit with the normal pattern
]]
local article_name = {
["lij"] = {"Ligurian (Romance leid)"}, -- see Template_talk:Lang#Ligurian_dab
['mnh'] = {"Mono leid (Congo)"}, -- see Template_talk:Lang#Mono_languages
['mnr'] = {"Mono leid (California)"},
['mru'] = {"Mono leid (Cameroon)"},
['mte'] = {"Mono-Alu leid"},
["xlg"] = {"Ligurian leid (auncient)"}, -- see Template_talk:Lang#Ligurian_dab
}
--[=[-------------------------< R T L _ S C R I P T S >--------------------------------------------------------
ISO 15924 scripts that are written right-to-left. Data in this table taken from [[ISO 15924#List of codes]]
last update to this list: 2017-12-24
]=]
local rtl_scripts = {
'adlm', 'arab', 'aran', 'armi', 'avst', 'cprt', 'egyd', 'egyh', 'hatr', 'hebr',
'hung', 'inds', 'khar', 'lydi', 'mand', 'mani', 'mend', 'merc', 'mero', 'narb',
'nbat', 'nkoo', 'orkh', 'palm', 'phli', 'phlp', 'phlv', 'phnx', 'prti', 'rohg',
'samr', 'sarb', 'sogd', 'sogo', 'syrc', 'syre', 'syrj', 'syrn', 'thaa', 'wole',
};
--[[--------------------------< T R A N S L I T T I T L E S >------------------------------------------------
This is a table of tables of transliteration standards and the language codes or language scripts that apply to
those standards. This table is used to create the tool-tip text associated with the transliterated text displayed
by some of the {{lang-??}} templates.
These tables are more-or-less copied directly from {{transl}}. The standard 'NO_STD' is a construct to allow for
the cases when no |std= parameter value is provided.
]]
local translit_title_table = {
['ahl'] = {
['default'] = 'Academy o the Ebreu Leid transleeteration',
},
['ala'] = {
['default'] = 'American Leebrar Association – Leebrar o Congress transleeteration',
},
['ala-lc'] = {
['default'] = 'American Leebrar Association – Leebrar o Congress transleeteration',
},
['batr'] = {
['default'] = 'Bikdash Arabic Transleeteration Rules',
},
['bgn/pcgn'] = {
['default'] = 'Board on Geografic Names / Permanent Committee on Geografical Names transleeteration',
},
['din'] = {
['ar'] = 'DIN 31635 Arabic',
['fa'] = 'DIN 31635 Arabic',
['ku'] = 'DIN 31635 Arabic',
['ps'] = 'DIN 31635 Arabic',
['tg'] = 'DIN 31635 Arabic',
['ug'] = 'DIN 31635 Arabic',
['ur'] = 'DIN 31635 Arabic',
['arab'] = 'DIN 31635 Arabic',
['default'] = 'DIN transleeteration',
},
['eae'] = {
['default'] = 'Encyclopaedia Aethiopica transleeteration',
},
['hepburn'] = {
['default'] = 'Hepburn transleeteration',
},
['iast'] = {
['default'] = 'Internaitional Alphabet o Sanskrit transleeteration',
},
['iso'] = { -- when a transliteration standard is supplied
['ab'] = 'ISO 9 Cyrillic',
['ba'] = 'ISO 9 Cyrillic',
['be'] = 'ISO 9 Cyrillic',
['bg'] = 'ISO 9 Cyrillic',
['kk'] = 'ISO 9 Cyrillic',
['ky'] = 'ISO 9 Cyrillic',
['mn'] = 'ISO 9 Cyrillic',
['ru'] = 'ISO 9 Cyrillic',
['tg'] = 'ISO 9 Cyrillic',
['uk'] = 'ISO 9 Cyrillic',
['bua'] = 'ISO 9 Cyrillic',
['sah'] = 'ISO 9 Cyrillic',
['tut'] = 'ISO 9 Cyrillic',
['xal'] = 'ISO 9 Cyrillic',
['cyrl'] = 'ISO 9 Cyrillic',
['ar'] = 'ISO 233 Arabic',
['ku'] = 'ISO 233 Arabic',
['ps'] = 'ISO 233 Arabic',
['ug'] = 'ISO 233 Arabic',
['ur'] = 'ISO 233 Arabic',
['arab'] = 'ISO 233 Arabic',
['he'] = 'ISO 259 Hebrew',
['yi'] = 'ISO 259 Hebrew',
['hebr'] = 'ISO 259 Hebrew',
['el'] = 'ISO 843 Greek',
['grc'] = 'ISO 843 Greek',
['ja'] = 'ISO 3602 Japanese',
['hira'] = 'ISO 3602 Japanese',
['hrkt'] = 'ISO 3602 Japanese',
['jpan'] = 'ISO 3602 Japanese',
['kana'] = 'ISO 3602 Japanese',
['zh'] = 'ISO 7098 Chinese',
['chi'] = 'ISO 7098 Chinese',
['pny'] = 'ISO 7098 Chinese',
['zho'] = 'ISO 7098 Chinese',
-- ['han'] = 'ISO 7098 Chinese', -- unicode alias of Hani? doesn't belong here? should be Hani?
['hans'] = 'ISO 7098 Chinese',
['hant'] = 'ISO 7098 Chinese',
['ka'] = 'ISO 9984 Georgian',
['kat'] = 'ISO 9984 Georgian',
['arm'] = 'ISO 9985 Armenian',
['hy'] = 'ISO 9985 Armenian',
['th'] = 'ISO 11940 Thai',
['tha'] = 'ISO 11940 Thai',
['ko'] = 'ISO 11941 Korean',
['kor'] = 'ISO 11941 Korean',
['bn'] = 'ISO 15919 Indic',
['dra'] = 'ISO 15919 Indic',
['gu'] = 'ISO 15919 Indic',
['hi'] = 'ISO 15919 Indic',
['inc'] = 'ISO 15919 Indic',
['kn'] = 'ISO 15919 Indic',
['ml'] = 'ISO 15919 Indic',
['mr'] = 'ISO 15919 Indic',
['sa'] = 'ISO 15919 Indic',
['ta'] = 'ISO 15919 Indic',
['te'] = 'ISO 15919 Indic',
['beng'] = 'ISO 15919 Indic',
['brah'] = 'ISO 15919 Indic',
['deva'] = 'ISO 15919 Indic',
['default'] = 'ISO transleeteration',
},
['mr'] = {
['default'] = 'McCune–Reischauer transleeteration',
},
['nihon-shiki'] = {
['default'] = 'Nihon-shiki transleeteration',
},
['no_std'] = { -- when no transliteration standard is supplied
['akk'] = 'Semitic transleeteration',
['sem'] = 'Semitic transleeteration',
['phnx'] = 'Semitic transleeteration',
['xsux'] = 'Cuneiform transleeteration',
},
['pinyin'] = {
['default'] = 'Pinyin transleeteration',
},
['rr'] = {
['default'] = 'Revised Romanisation o Korean transleeteration',
},
['rtgs'] = {
['default'] = 'Ryal Thai General Seestem o Transcription',
},
['satts'] = {
['default'] = 'Staundart Arabic Technical Transleeteration Seestem transleeteration',
},
['ungegn'] = {
['default'] = 'Unitit Naitions Group o Experts on Geografical Names transleeteration',
},
['wehr'] = {
['default'] = 'Hans Wehr transleeteration',
},
};
return
{
article_name = article_name,
lang_name_table = lang_name_table,
override = override,
rtl_scripts = rtl_scripts,
translit_title_table = translit_title_table,
};
