Binabago: Module:Lang/data/sandbox

local lang_obj = mw.language.getContentLanguage();
local this_wiki_lang_tag = lang_obj.code;										-- get this wiki's language tag


--[[--------------------------< 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.

]]

local function key_to_lower (module, src_type)
	local out = {};
	local source_t = (('var_sup' == src_type) and require (module)) or mw.loadData (module);		-- fetch data from this module; require() avoids metatable trap for variant data

	if 'var_sup' == src_type then
		for k, v in pairs (source_t) do
			out[k:lower()] = v;													-- for variant and suppressed everything is needed
		end

	elseif 'lang' == src_type and source_t.active then							-- for ~/iana_languages (active)
		for k, v in pairs (source_t.active) do
			out[k:lower()] = v[1];												-- ignore multiple names; take first name only
		end

	elseif 'lang_dep' == src_type and source_t.deprecated then					-- for ~/iana_languages (deprecated)
		for k, v in pairs (source_t.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_t) do
			out[k:lower()] = v[1];												-- ignore multiple names; take first name only
		end
	end
	return out;
end

local lang_name_table_t = {
	lang = key_to_lower ('Module:Lang/data/iana languages', 'lang'),
	lang_dep = key_to_lower ('Module:Lang/data/iana languages', 'lang_dep'),
	script = key_to_lower ('Module:Lang/data/iana scripts'),					-- script keys are capitalized; set to lower
	region = key_to_lower ('Module:Lang/data/iana regions'),					-- region keys are uppercase; set to lower
	variant = key_to_lower ('Module:Lang/data/iana variants', 'var_sup'),
	suppressed = key_to_lower ('Module:Lang/data/iana suppressed scripts', 'var_sup'),	-- script keys are capitalized; set to lower
	}


--[[--------------------------< I 1 8 N   M E D I A W I K I   O V E R R I D E >--------------------------------

For internationalization; not used at en.wiki

The language names taken from the IANA language-subtag-registry file are given in English. That may not be ideal.
Translating ~8,000 language names is also not ideal.  MediaWiki maintains (much) shorter lists of language names
in most languages for which there is a Wikipedia edition.  When desired, Module:Lang can use the MediaWiki 
language list for the local language.

Caveat lector: the list of MediaWiki language names for your language may not be complete or may not exist at all.
When incomplete, MediaWiki's list will 'fall back' to another language (typically English).  When that happens
add an appropriate entry to the override table below.

Caveat lector: the list of MediaWiki language names for your language may not be correct.  At en.wiki, the
MediaWiki language names do not agree with the IANA language names for these ISO 639-1 tags.  Often it is simply
spelling differences:
	bh: IANA: Bihari languages MW: Bhojpuri – the ISO 639-3 tag for Bhojpuri is bho
	bn: IANA: Bengali MW: Bangla – Bengali is the exonym, Bangla is the endonym
	dv: IANA: Dhivehi MW: Divehi
	el: IANA: Modern Greek MW: Greek
	ht: IANA: Haitian MW: Haitian Creole
	ky: IANA: Kirghiz MW: Kyrgyz
	li: IANA: Limburgan MW: Limburgish
	or: IANA: Oriya MW: Odia
	os: IANA: Ossetian MW: Ossetic
	"pa: IANA: Panjabi MW: Punjabi
	"ps: IANA: Pushto MW: Pashto
	"to: IANA: Tonga MW: Tongan
	"ug: IANA: Uighur MW: Uyghur
use the override table to override language names that are incorrect for your project

To see the list of names that MediaWiki has for your language, enter this in the Debug console:
	=mw.dumpObject (mw.language.fetchLanguageNames ('<tag>', 'all'))
(replacing <tag> with the language tag for your language)

Use of the MediaWiki language names lists is enabled when media_wiki_override_enable is set to boolean true.
	
]]

local media_wiki_override_enable = false;										-- set to true to override IANA names with MediaWiki names; always false at en.wiki
																				-- caveat lector: the list of MediaWiki language names for your language may not be complete or may not exist at all
	if true == media_wiki_override_enable then
		local mw_languages_by_tag_t = mw.language.fetchLanguageNames (this_wiki_lang_tag, 'all');	-- get a table of language tag/name pairs known to MediaWiki
		for tag, name in pairs (mw_languages_by_tag_t) do						-- loop through each tag/name pair in the MediaWiki list
			if lang_name_table_t.lang[tag] then									-- if the tag is in the main list
				lang_name_table_t.lang[tag] = name;								-- overwrite existing name with the name from MediaWiki
			end
		end
	end


--[[--------------------------< 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"] = "Abkhaz",                                                          -- to match en.wiki article name
	["ca-valencia"] = "Valencia",
	["cu"] = "Church Slavonic",													-- 2nd IANA name;
	["de-at"] = "Aleman ng Austria",												-- these code-region and code-variant tags to match en.wiki article names
	["de-ch"] = "Pamantayang Aleman ng Suwisa",
	["en-au"] = "Ingles ng Australia",
	["en-ca"] = "Ingles ng Canada",
	["en-emodeng"] = "Maagang Modernong Ingles",
	["en-gb"] = "Ingles ng Britanya",
	["en-ie"] = "Ingles ng Irlanda",
	["en-in"] = "Ingles ng India",
	["en-nz"] = "Ingles ng Nueva Selanda",
	["en-us"] = "Ingles ng Amerika",
	["en-za"] = "Ingles ng Timog Aprika",
	["fr-ca"] = "Pranses ng Quebec",
	["fr-gallo"] = "Gallo",
	["fy"] = "Kanlurang Frison",													-- Western Frisian
	["mo"] = "Moldova",														-- Moldavian (deprecated code); to match en.wiki article title
	["nl-be"] = "Flamenco",														-- match MediaWiki
	["oc-gascon"] = "Gascon",
	["oc-provenc"] = "Provencal",
	["ps"] = "Pashto",															-- Pushto
	["pt-br"] = "Portuges ng Brasil",											-- match MediaWiki
	["ro-md"] = "Moldova",														-- 'not deprecated' form
	["ro-cyrl-md"] = "Moldova",												-- 'not deprecated' form
	["tw-asante"] = "Asante Twi",
	["ug"] = "Uyghur",															-- 2nd IANA name; to match en.wiki article name

-- these ISO 639-1 language-name overrides imported from Module:Language/data/wp_languages (since deleted)
--<begin do-not-edit except to comment out>--
		["av"] = "Avar",														-- Avaric
		["bo"] = "Pamantayang Tibetano",											-- Tibetan
		["el"] = "Griyego",														-- Modern Greek
--		["en-SA"] = "Ingles ng Timog Aprika",									-- English; no; SA is not South Africa it Saudi Arabia; ZA is South Africa
		["ff"] = "Fula",														-- Fulah
		["ht"] = "Creole ng Haiti",												-- Haitian
		["hz"] = "Otjiherero",													-- Herero
		["ii"] = "Yi",															-- Sichuan Yi
		["ki"] = "Gikuyu",														-- Kikuyu
		["kl"] = "Greenland",													-- Kalaallisut
		["ky"] = "Kirgis",														-- Kirghiz
		["lg"] = "Luganda",														-- Ganda
		["li"] = "Limburgo",													-- Limburgan
		["mi"] = "Maori",														-- Maori
		["na"] = "Nauru",														-- Nauru
		["nb"] = "Bokmål",														-- Norwegian Bokmål
		["nd"] = "Hilagang Ndebele",											-- North Ndebele
		["nn"] = "Nynorsk",														-- Norwegian Nynorsk
		["nr"] = "Timog Ndebele",											-- South Ndebele
		["ny"] = "Chichewa",													-- Nyanja
		["oj"] = "Ojibwe",														-- Ojibwa
		["or"] = "Odia",														-- Oriya
		["pa"] = "Punjabi",														-- Panjabi
		["rn"] = "Kirundi",														-- Rundi
		["sl"] = "Sloben",														-- Slovenian
		["ss"] = "Swazi",														-- Swati
		["st"] = "Sotho",														-- Southern Sotho
		["to"] = "Tonga",														-- Tonga
--<end do-not-edit except to comment out>--


------------------------------< I S O _ 6 3 9 - 2,   - 3,   - 5 >----------------------------------------------

	["alv"] = "Mga wikang Atlantiko–Congo",										-- to match en.wiki article title (endash)
	["arc"] = "Aramaikong Imperyal (700-300 BKP)",									-- Official Aramaic (700-300 BCE), Imperial Aramaic (700-300 BCE); to match en.wiki article title uses ISO639-2 'preferred' name
	["art"] = "gawa-gawa",													-- to match en.wiki article; lowercase for category name
	["ast-es"] = "Leon",														-- ast in IANA is Asturian; Leonese is a dialect
	["bea"] = "Dane-zaa",														-- Beaver; to match en.wiki article title
	["bha"] = "Bhariati",														-- Bharia; to match en.wiki article title
	["bhd"] = "Bhadarwahi",														-- Bhadrawahi; to match en.wiki article title
	["bla"] = "Blackfoot",														-- Siksika; to match en.wiki article title
	["blc"] = "Nuxalk",															-- Bella Coola; to match en.wiki article title
	["bua"] = "Buryat",															-- Buriat; this is a macro language; these four use wp preferred transliteration;
	["bxm"] = "Buryat ng Mongolia",												-- Mongolia Buriat; these three all redirect to Buryat
	["bxr"] = "Buryat ng Rusya",													-- Russia Buriat;
	["bxu"] = "Buryat ng Tsina",													-- China Buriat;
	["byr"] = "Yipma",															-- Baruya, Yipma
	["clm"] = "Klallam",														-- Clallam; to match en.wiki article title
	["egy"] = "Sinaunang Ehipto",												-- Egyptian (Ancient); distinguish from contemporary arz: Egyptian Arabic 
	["ems"] = "Alutiiq",														-- Pacific Gulf Yupik; to match en.wiki article title
	["esx"] = "Mga wikang Eskimo–Aleut",											-- to match en.wiki article title (endash)
	["frr"] = "Hilagang Frison",													-- Northern Frisian
	["frs"] = "East Frisian Low Saxon",											-- Eastern Frisian
	["gsw-fr"] = "Alsacia",													-- match MediaWiki
	["haa"] = "Hän",															-- Han; to match en.wiki article title
	["hei"] = "Heiltsuk–Oowekyala",												-- Heiltsuk; to match en.wiki article title
	["hmx"] = "Mga wikang Hmong–Mien",											-- to match en.wiki article title (endash)
	["ilo"] = "Ilokano",														-- Iloko; to match en.wiki article title
	["jam"] = "Patois ng Jamaica",												-- Jamaican Creole English
	["lij-mc"] = "Monaco",													-- Ligurian as spoken in Monaco; this one for proper tool tip; also in <article_name> table
	["luo"] = "Dholuo",															-- IANA (primary) /ISO 639-3: Luo (Kenya and Tanzania); IANA (secondary): Dholuo
	["mhr"] = "Meadow Mari",													-- Eastern Mari
	["mid"] = "Modernong Mandaic",													-- Mandaic
	['mis'] = "walang kodigo",														-- Uncoded languages; capitalization; special scope, not collective scope;
	["mkh"] = "Mga wikang Mon–Khmer",											-- to match en.wiki article title (endash)
	["mla"] = "Tamambo",														-- Malo
	['mte'] = "Mono-Alu",														-- Mono (Solomon Islands)
	['mul'] = "marami",														-- Multiple languages; capitalization; special scope, not collective scope;
	["nan-tw"] = "Hokkien ng Taiwan",											-- make room for IANA / 639-3 nan Min Nan Chinese; match en.wiki article title
	["new"] = "Newar",															-- Newari, Nepal Bhasa; to match en,wiki article title
	["ngf"] = "Mga wikang Trans–New Guinea",										-- to match en.wiki article title (endash)
	["nic"] = "Mga wikang Niger–Congo",											-- Niger-Kordofanian languages; to match en,wiki article title
	["nrf"] = "Norman",															-- not quite a collective - IANA name: Jèrriais + Guernésiais; categorizes to Norman-language text
	["nrf-gg"] = "Guernésiais",													-- match MediaWiki
	["nrf-je"] = "Jèrriais",													-- match MediaWiki
	["nzi"] = "Nzema",															-- Nzima; to match en.wiki article title
	["oma"] = "Omaha–Ponca",													-- to match en.wiki article title (endash)
	["orv"] = "Lumang SIlangang Slabo",												-- Old Russian
	["pfl"] = "Palatinong Aleman",												-- Pfaelzisch; to match en.wiki article
	["pie"] = "Piro Pueblo",													-- Piro; to match en.wiki article
	["pms"] = "Piedmont",													-- Piemontese; to match en.wiki article title
	["pnb"] = "Punjabi (Kanluran)",												-- Western Panjabi; dab added to override import from ~/wp languages and distinguish pnb from pa in reverse look up tag_from_name()
	['qwm'] = "Cuman",															-- Kuman (Russia); to match en.wiki article name
	["rop"] = "Kriol ng Australia",												-- Kriol; en.wiki article is a dab; point to correct en.wiki article
	["rsk"] = "Pannonian Rusyn",												-- Ruthenian; en.wiki preferred name
	["sco-ulster"] = "Ulster Scots",
	["sdo"] = "Bukar–Sadong",													-- Bukar-Sadung Bidayuh; to match en.wiki article title
	["smp"] = "Samaritanong Ebreo",												-- to match en.wiki article title
	["stq"] = "Freson ng Saterland",												-- Saterfriesisch
	["und"] = "di tukoy",													-- 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
	["yuf"] = "Havasupai–Hualapai",												-- Havasupai-Walapai-Yavapai; to match en.wiki article title
	["zkt"] = "Khitan",															-- Kitan; to match en.wiki article title
	["zxx"] = "walang laman",											-- capitalization

-- these ISO 639-2, -3 language-name overrides imported from Module:Language/data/wp_languages (since deleted)
--<begin do-not-edit except to comment out>--
		["ace"] = "Aceh",													-- Achinese
		["aec"] = "Arabong Sa'idi",												-- Saidi Arabic
		["akl"] = "Aklanon",														-- Aklanon
		["alt"] = "Altay",														-- Southern Altai
		["apm"] = "Mescalero-Chiricahua",										-- Mescalero-Chiricahua Apache
		["bal"] = "Balochi",													-- Baluchi
--		["bcl"] = "Gitnang Bikolano",											-- Central Bikol
		["bin"] = "Edo",														-- Bini
		["bpy"] = "Bishnupriya Manipuri",										-- Bishnupriya
		["chg"] = "Chagatay",													-- Chagatai
		["ckb"] = "Kurdong Sorani",												-- Central Kurdish
		["cnu"] = "Shenwa",														-- Chenoua
		["coc"] = "Cocopah",													-- Cocopa
		["diq"] = "Zazaki",														-- Dimli
		["fit"] = "Meänkieli",													-- Tornedalen Finnish
		["fkv"] = "Kven",														-- Kven Finnish
		["frk"] = "Lumang Franko",												-- Frankish
		["gez"] = "Ge'ez",														-- Geez
		["gju"] = "Gujari",														-- Gujari
		["gsw"] = "Alemanikong Aleman",											-- Swiss German
		["gul"] = "Gullah",														-- Sea Island Creole English
		["hak"] = "Hakka",														-- Hakka Chinese
		["hbo"] = "Biblikal na Ebreo",											-- Ancient Hebrew
		["hnd"] = "Hindko",														-- Southern Hindko
--		["ikt"] = "Inuvialuk",													-- Inuinnaqtun
		["kaa"] = "Karakalpak",													-- Kara-Kalpak
		["khb"] = "Tai Lü",														-- Lü
		["kmr"] = "Kurdong Kurmanji",											-- Northern Kurdish
		["kpo"] = "Kposo",														-- Ikposo
		["krj"] = "Kinaray-a",													-- Kinaray-A
--		["ktz"] = "Juǀ'hoan",													-- Juǀʼhoan
		["lez"] = "Lezguino",													-- Lezghian
		["liv"] = "Livonia",													-- Liv
		["lng"] = "Lombardo",													-- 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"] = "Bhasa ng Nepal",												-- Newari
		["nso"] = "Hilagang Sotho",												-- Pedi
--		["nwc"] = "Klasikal na Bhasa ng Nepal",										-- Classical Newari, Classical Nepal Bhasa, Old Newari
		["ood"] = "O'odham",													-- Tohono O'odham
		["otk"] = "Lumang Turkiko",													-- Old Turkish
		["pal"] = "Gitnang Persa",												-- 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"] = "Maori ng Kapuluang Cook",											-- Rarotongan
		["rmu"] = "Scandoromani",												-- Tavringer Romani
		["rom"] = "Romani",														-- Romany
		["rup"] = "Aromania",													-- Macedo-Romanian
		["ryu"] = "Okinawa",													-- Central Okinawan
		["sdc"] = "Sasares",													-- Sassarese Sardinian
		["sdn"] = "Galures",													-- Gallurese Sardinian
		["shp"] = "Shipibo",													-- Shipibo-Conibo
		["src"] = "Logudores",													-- Logudorese Sardinian
		["sro"] = "Campidanes",												-- Campidanese Sardinian
		["tkl"] = "Tokelau",													-- Tokelau
		["tvl"] = "Tuvalu",													-- Tuvalu
		["tyv"] = "Tuva",														-- Tuvinian
		["vls"] = "Kanlurang Flamenco",												-- Vlaams
		["wep"] = "Westphalia",												-- Westphalien
		["xal"] = "Oirat",														-- Kalmyk
		["xcl"] = "Lumang Armenia",												-- 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 >----------------------------------------------

	["akk-x-latbabyl"] = "Huling Akadiyo ng Babylonia",
	["akk-x-midassyr"] = "Gitnang Akadiyo ng Asirya",
	["akk-x-midbabyl"] = "Gitnang Akadiyo ng Babylonia",
	["akk-x-neoassyr"] = "Akadiyo ng Neoasirya",
	["akk-x-neobabyl"] = "Akadiyo ng Neobabylonia",
	["akk-x-old"] = "Lumang Akadiyo",
	["akk-x-oldassyr"] = "Lumang Akadiyo ng Asirya",
	["akk-x-oldbabyl"] = "Lumang Akadiyo ng Babylonia",
	["alg-x-proto"] = "Proto-Algonquian",										-- alg in IANA is Algonquian languages
	["ca-x-old"] = "Lumang Catalan",
	["cel-x-combrit"] = "Karaniwang Britoniko",										-- cel in IANA is Celtic languages
	["cel-x-proto"] = "Proto-Keltiko",
	["ccs-x-proto"] = "Proto-Kartvel",										-- ccs in IANA is Kartvelian languages
	["egy-x-demotic"] = "Demotikong Ehipto",
	["egy-x-late"] = "Huling Ehipto",
	["egy-x-middle"] = "Gitnang Ehipto",
	["egy-x-old"] = "Lumang Ehipto",
	["fiu-x-proto"] = "Proto-Finno-Ugriko",										-- fiu in IANA is Finno-Ugric languages
	["gem-x-proto"] = "Proto-Alemaniko",											-- gem in IANA is Germanic languages
	["gmw-x-ecg"] = "Silangang Gitnang Aleman",
	["grc-x-aeolic"] = "Aeolikong Griyego",											-- these grc-x-... codes are preferred alternates to the non-standard catchall code grc-gre
	["grc-x-arcadcyp"] = "Arkadotsipriotang Griyego",
	["grc-x-attic"] = "Atikong Griyego",
	["grc-x-biblical"] = "Biblikal na Griyego",
	["grc-x-byzant"] = "Bisantinong Griyego",
	["grc-x-classic"] = "Klasikal na Griyego",
	["grc-x-doric"] = "Griyego ng Doria",
	["grc-x-hellen"] = "Hellenistikong Griyego",
	["grc-x-ionic"] = "Griyego ng Ionia",
	["grc-x-koine"] = "Griyegong Koinē",
	["grc-x-medieval"] = "Medyebal na Griyego",
	["grc-x-patris"] = "Patristikong Griyego",
	["grk-x-proto"] = "Proto-Griyego",											-- grk in IANA is Greek languages
	["iir-x-proto"] = "Proto-Indo-Iranyano",										-- iir in IANA is Indo-Iranian Languages
	["inc-x-mitanni"] = "Mitanni-Aryan",										-- inc in IANA is Indic languages
	["inc-x-proto"] = "Proto-Indo-Aryan",
	["ine-x-anatolia"] = "Mga wikang Anatolia",
	["ine-x-proto"] = "Proto-Indo-Europeo",
	["ira-x-proto"] = "Proto-Iranyano",											-- ira in IANA is Iranian languages
	["itc-x-proto"] = "Proto-Italiko",											-- itc in IANA is Italic languages
	["ksh-x-colog"] = "Cologne",												-- en.wiki article is Colognian; ksh (Kölsch) redirects there
	["la-x-medieval"] = "Medyebal na Latin",
	["la-x-new"] = "Bagong Latin",
	["lmo-x-berg"] = "Bergamasque",												-- lmo in IANA is Lombard; Bergamasque is a dialect
	["lmo-x-cremish"] = "Cremasko",												-- lmo in IANA is Lombard; Cremish is a dialect
	["lmo-x-milanese"] = "Milane",											-- lmo in IANA is Lombard; Milanese is a dialect
	["mis-x-ripuar"] = "Ripuaria",												-- replaces improper use of ksh in wp_languages
	["prg-x-old"] = "Lumang Pruso",
	["sem-x-ammonite"] = "Amonita",
	["sem-x-aramaic"] = "Aramaiko",
	["sem-x-canaan"] = "Mga wikang Kanaan",
	["sem-x-dumaitic"] = "Dumaitiko",
	["sem-x-egurage"] = "Silangang Gurage",
	["sem-x-hatran"] = "Aramaiko ng Hatran",
	["sem-x-oldsoara"] = "Lumang Timog Arabo",
	["sem-x-palmyren"] = "Aramaiko ng Palmyra",
	["sem-x-proto"] = "Proto-Semitiko",
	["sem-x-taymanit"] = "Taymanit",
	["smi-x-proto"] = "Proto-Samiko",											-- smi in IANA is Samic languages
	["sla-x-proto"] = "Proto-Slabiko",											-- sla in IANA is Slavic languages
	["urj-x-proto"] = "Proto-Uraliko",											-- urj in IANA is Uralic languages
	["yuf-x-hav"] = "Havasupai",												-- IANA name for these three is Havasupai-Walapai-Yavapai
	["yuf-x-wal"] = "Walapai",
	["yuf-x-yav"] = "Yavapai",
	["xsc-x-pontic"] = "Pontikong Eskito",										-- xsc in IANA is Scythian
	["xsc-x-saka"] = "Saka",
	["xsc-x-sarmat"] = "Sarmat",
	["zle-x-ruthenia"] = "Ruthenia",											-- zle in IANA is East Slavic languages collective; moved to allow rsk for Pannonian Rusyn
	}


--[[--------------------------< 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 = {
	['kue'] = "Kuman language (New Guinea)",									-- Kuman (Papua New Guinea); to avoid Kuman dab page
	["lij-mc"] = "Monégasque dialect",											-- Ligurian as spoken in Monaco
	['mbo'] = "Mbo language (Cameroon)",										-- Mbo (Cameroon)
	['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)
	["snq"] = "Sangu language (Gabon)",											-- Sangu (Gabon)
	["toi"] = "Tonga language (Zambia and Zimbabwe)",                           -- Tonga (Zambia and Zimbabwe); to avoid Tonga language dab page
	["vwa"] = "Awa language (China)",											-- Awa (China); to avoid Awa dab page
	["xlg"] = "Ligurian language (ancient)",									-- see Template_talk:Lang#Ligurian_dab
	["zmw"] = "Mbo language (Congo)",											-- Mbo (Democratic Republic of Congo)
	}


--[=[-------------------------< 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 {{special|PermaLink/680078354}}. 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'] = 'Transliterasyon ng Academy of the Hebrew Language',
		},

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

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

	['batr'] = {
		['default'] = 'Tuntunin sa Transliterasyon ng Arabong Bikdash',
		},

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

	['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'] = 'Transliterasyong DIN',
		},

	['eae'] = {
		['default'] = 'Transliterasyon ng Encyclopaedia Aethiopica',
		},

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

	['hunterian'] = {
		['default'] = 'Transliterasyong Hunteriano',
		},

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

	['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',
		['cyrs'] = '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',
		['cmn'] = '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',
		['hno'] = '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',
		['pnb'] = 'ISO 15919 Indic',
		['raj'] = 'ISO 15919 Indic',
		['sa'] = 'ISO 15919 Indic',
		['sat'] = 'ISO 15919 Indic',
		['sd'] = 'ISO 15919 Indic',
		['si'] = 'ISO 15919 Indic',
		['skr'] = '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'] = 'Transliterasyong ISO',
		},

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

	['mlcts'] = {
		['default'] = 'Myanmar Language Commission Transcription System',
		},

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

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

	['no_std'] = {																-- when no transliteration standard is supplied
		['akk'] = 'Transliterasyong Semitiko',
		['sem'] = 'Transliterasyong Semitiko',
		['phnx'] = 'Transliterasyong Semitiko',
		['xsux'] = 'Transliterasyon ng Kuniporme',
		},

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

	['rr'] = {
		['default'] = 'Binagong Romanisasyon ng Transliterasyong Koreano',
		},

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

	['scientific'] = {
		['default'] = 'transliterasyong maagham',
		},

	['ukrainian'] = {
		['default'] = 'Pambansang sistema ng romanisasyon ng Ukranya',
		},

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

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

	['wehr'] = {
		['default'] = 'Transliterasyong Hans Wehr',
		},
	['yaleko'] = {
		['default'] = 'Romanisasyong Yale sa Koreano',
	}
};


--[[--------------------------< E N G _ V A R >----------------------------------------------------------------

Used at en.wiki so that spelling of 'romanized' (US, default) can be changed to 'romanised' to match the envar
specified by a {{Use xxx English}}.

This is accomplished by setting |engvar=gb; can, should be omitted in articles that use American English; no
need for the clutter.

]]

local engvar_sel_t = {															-- select either UK English or US English
	['au'] = 'gb_t',															-- these match IANA region codes (except in lower case)
	['ca'] = 'us_t',
	['gb'] = 'gb_t',
	['ie'] = 'gb_t',
	['in'] = 'gb_t',
	['nz'] = 'gb_t',
	['us'] = 'us_t',															-- default engvar
	['za'] = 'gb_t'
	};

local engvar_t = {
	['gb_t'] = {
		['romanisz_lc'] = 'romanisasyon',										-- lower case
		['romanisz_uc'] = 'Romanisasyon',										-- upper case
		['romanisz_pt'] = 'romanisado',											-- past tense
		},
	['us_t'] = {																-- default engvar
		['romanisz_lc'] = 'romanisasyon',										-- lower case
		['romanisz_uc'] = 'Romanisasyon',										-- upper case
		['romanisz_pt'] = 'romanisado',											-- past tense
		}
	}


--[[--------------------------< E X P O R T S >----------------------------------------------------------------
]]

return
	{
	this_wiki_lang_tag = this_wiki_lang_tag,
	this_wiki_lang_dir = lang_obj:getDir(),										-- wiki's language direction
	
	article_name = article_name,
	engvar_t = engvar_t,
	engvar_sel_t = engvar_sel_t,
	lang_name_table = lang_name_table_t,
	override = override,
	rtl_scripts = rtl_scripts,
	special_tags_table = special_tags_table,
	translit_title_table = translit_title_table,
	};