Module:Lang/data

Documentation for this module may be created at Module:Lang/data/doc

--[[--------------------------< 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 >------------------------------------------------------------

	["ca-valencia"] = {"Valencian"},
	["cu"] = {"Church Slavonic"},												-- 2nd IANA name;
	["de-at"] = {"Austrian German"},											-- these code-region and code-variant tags to match en.wiki article names
	["de-ch"] = {"Swiss Standard German"},
	["en-au"] = {"Australian English"},
	["en-ca"] = {"Canadian English"},
	["en-emodeng"] = {"Early Modern English"},
	["en-gb"] = {"British English"},
	["en-ie"] = {"Irish English"},
	["en-in"] = {"Indian English"},
	["en-nz"] = {"New Zealand English"},
	["en-us"] = {"American English"},
	["en-za"] = {"South African English"},
	["fy"] = {"West Frisian"},													-- Western Frisian
	["mo"] = {"Moldovan"},														-- Moldavian (deprecated code); to match en.wiki article title
	["oc-provenc"] = {"Provençal"},
	["ps"] = {"Pashto"},														-- Pushto
	["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"},														-- Official Aramaic (700-300 BCE), Imperial Aramaic (700-300 BCE);
	["art"] = {"constructed"},													-- to match en.wiki article; lowercase for category name
	["bhd"] = {"Bhadarwahi"},													-- Bhadrawahi; to match en.wiki article title
	["bla"] = {"Blackfoot"},													-- Siksika; to match en.wiki article title
	["bua"] = {"Buryat"},														-- Buriat; this is a macro language; these four use wp preferred transliteration;
	["bxm"] = {"Mongolian Buryat"},												-- Mongolia Buriat; these three all redirect to Buryat
	["bxr"] = {"Russian Buryat"},												-- Russia Buriat;
	["bxu"] = {"Chinese Buryat"},												-- China Buriat;
	["byr"] = {"Yipma"},														-- Baruya, Yipma
	["egy"] = {"Ancient Egyptian"},												-- Egyptian (Ancient); distinguish from contemporary arz: Egyptian Arabic 
	["frr"] = {"North Frisian"},												-- Northern Frisian
	["frs"] = {"East Frisian Low Saxon"},										-- Eastern Frisian
	["ilo"] = {"Ilocano"},														-- Iloko; to match en.wiki article title
	["jam"] = {"Jamaican Patois"},												-- Jamaican Creole English
	["mhr"] = {"Meadow Mari"},													-- Eastern Mari
	["mid"] = {"Modern Mandaic"},												-- Mandaic
	["mla"] = {"Tamambo"},														-- Malo
	['mte'] = {"Mono-Alu"},														-- Mono (Solomon Islands)
	["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"},														-- Nzima; to match en.wiki article title
	["orv"] = {"Old East Slavic"},												-- Old Russian
	["pfl"] = {"Palatine German"},												-- Pfaelzisch; to match en.wiki article
	["pms"] = {"Piedmontese"},													-- Piemontese; to match en.wiki article title
	["pnb"] = {"Punjabi (Western)"},											-- Western Panjabi; dab added to override import from ~/wp languages and distinguish pnb from pa in reverse look up tag_from_name()
	["stq"] = {"Saterland Frisian"},											-- Saterfriesisch
	["und"] = {"undetermined"},													-- capitalization to match existing category
	["wrg"] = {"Warrongo"},														-- 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"] = {"Old 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 Hebrew"},											-- 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 Low Saxon"},										-- Low German
		["new"] = {"Nepal Bhasa"},												-- Newari
		["nso"] = {"Northern Sotho"},											-- Pedi
		["nwc"] = {"Classical Nepal Bhasa"},									-- Classical Newari
		["ood"] = {"O'odham"},													-- Tohono O'odham
		["otk"] = {"Old 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"] = {"West Flemish"},												-- Vlaams
		["wep"] = {"Westphalian"},												-- Westphalien
		["xal"] = {"Oirat"},													-- Kalmyk
		["xcl"] = {"Old 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"] = {"Classical 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 language)"},									-- Ligurian; see Template_talk:Lang#Ligurian_dab
	['mnh'] = {"Mono language (Congo)"},										-- Mono (Democratic Republic of Congo); see Template_talk:Lang#Mono_languages
	['mnr'] = {"Mono language (California)"},									-- Mono (USA)
	['mru'] = {"Mono language (Cameroon)"},										-- Mono (Cameroon)
	["xlg"] = {"Ligurian (ancient language)"},									-- 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 of the Hebrew Language transliteration',
		},

	['ala'] = {
		['default'] = 'American Library Association – Library of Congress transliteration',
		},

	['ala-lc'] = {
		['default'] = 'American Library Association – Library of Congress transliteration',
		},

	['batr'] = {
		['default'] = 'Bikdash Arabic Transliteration Rules',
		},

	['bgn/pcgn'] = {
		['default'] = 'Board on Geographic Names / Permanent Committee on Geographical Names transliteration',
		},

	['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 transliteration',
		},

	['eae'] = {
		['default'] = 'Encyclopaedia Aethiopica transliteration',
		},

	['hepburn'] = {
		['default'] = 'Hepburn transliteration',
		},

	['hunterian'] = {
		['default'] = 'Hunterian transliteration',
		},

	['iast'] = {
		['default'] = 'International Alphabet of Sanskrit transliteration',
		},

	['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',

		['awa'] = 'ISO 15919 Indic',
		['bho'] = 'ISO 15919 Indic',
		['bn'] = 'ISO 15919 Indic',
		['bra'] = 'ISO 15919 Indic',
		['doi'] = 'ISO 15919 Indic',
		['dra'] = 'ISO 15919 Indic',
		['gon'] = 'ISO 15919 Indic',
		['gu'] = 'ISO 15919 Indic',
		['hi'] = 'ISO 15919 Indic',
		['inc'] = 'ISO 15919 Indic',
		['kn'] = 'ISO 15919 Indic',
		['kok'] = 'ISO 15919 Indic',
		['ks'] = 'ISO 15919 Indic',
		['mag'] = 'ISO 15919 Indic',
		['mai'] = 'ISO 15919 Indic',
		['ml'] = 'ISO 15919 Indic',
		['mr'] = 'ISO 15919 Indic',
		['ne'] = 'ISO 15919 Indic',
		['new'] = 'ISO 15919 Indic',
		['or'] = 'ISO 15919 Indic',
		['pa'] = 'ISO 15919 Indic',
		['raj'] = 'ISO 15919 Indic',
		['sa'] = 'ISO 15919 Indic',
		['sat'] = 'ISO 15919 Indic',
		['sd'] = 'ISO 15919 Indic',
		['si'] = 'ISO 15919 Indic',
		['ta'] = 'ISO 15919 Indic',
		['tcy'] = 'ISO 15919 Indic',
		['te'] = 'ISO 15919 Indic',
		['beng'] = 'ISO 15919 Indic',
		['brah'] = 'ISO 15919 Indic',
		['deva'] = 'ISO 15919 Indic',
		['gujr'] = 'ISO 15919 Indic',
		['guru'] = 'ISO 15919 Indic',
		['knda'] = 'ISO 15919 Indic',
		['mlym'] = 'ISO 15919 Indic',
		['orya'] = 'ISO 15919 Indic',
		['sinh'] = 'ISO 15919 Indic',
		['taml'] = 'ISO 15919 Indic',
		['telu'] = 'ISO 15919 Indic',

		['default'] = 'ISO transliteration',
		},

	['jyutping'] = {
		['default'] = 'Jyutping transliteration',
		},

	['mr'] = {
		['default'] = 'McCune–Reischauer transliteration',
		},

	['nihon-shiki'] = {
		['default'] = 'Nihon-shiki transliteration',
		},

	['no_std'] = {																-- when no transliteration standard is supplied
		['akk'] = 'Semitic transliteration',
		['sem'] = 'Semitic transliteration',
		['phnx'] = 'Semitic transliteration',
		['xsux'] = 'Cuneiform transliteration',
		},

	['pinyin'] = {
		['default'] = 'Pinyin transliteration',
		},

	['rr'] = {
		['default'] = 'Revised Romanization of Korean transliteration',
		},

	['rtgs'] = {
		['default'] = 'Royal Thai General System of Transcription',
		},
	
	['satts'] = {
		['default'] = 'Standard Arabic Technical Transliteration System transliteration',
		},

	['ungegn'] = {
		['default'] = 'United Nations Group of Experts on Geographical Names transliteration',
		},

	['wadegile'] = {
		['default'] = 'Wade–Giles transliteration',
		},

	['wehr'] = {
		['default'] = 'Hans Wehr transliteration',
		},
	};


return
	{
	article_name = article_name,
	lang_name_table = lang_name_table,
	override = override,
	rtl_scripts = rtl_scripts,
	translit_title_table = translit_title_table,
	};