Module:Lang/data

This module holds various support tables used by Module:Lang

• override – this table provides language name data used in the creation of categories and, for the {{lang-??}} templates, the language name annotation.
• rtl_scripts – a list of ISO 15924 scripts that are written right-to-left; data taken from the table at ISO 15924#List of codes
• translit_title_table – a table of tables that is used in the creation of the title= attribute of the <i>...</i> tags that wrap transliterated text; data adapted from {{transl}}

---

local lang_data = {};


--[[--------------------------< O V E R R I D E >--------------------------------------------------------------

Language codes and names in this table override the BCP47 names in Module:Language/name/data.

code indexes in this table shall always be lower case
]]

local override = {
-- ISO 639-1 codes
	["ab"] = {"Abkhazian"},														-- IANA name is Abkhazian; override wp_languages {"Abkhaz"}; to achieve this, use |label=
	["bh"] = {"Bihari languages"},												-- only ISO 639-1 collective; defined here to override improper redefinition (Bihari) in wp_languages
	["cu"] = {"Church Slavonic"},												-- 2nd IANA name;
	["de-at"] = {"Austrian German"},											-- these code-region and code-variant 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"},													-- IANA name is Western Frisian
	["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"] = {"Serbian"},													-- override wp_languages Serbian Cyrillic; to achieve this, use |label=

-- ISO 639-2, -3 codes
	["arc"] = {"Aramaic"},														-- IANA names are: Official Aramaic (700-300 BCE), Imperial Aramaic (700-300 BCE);
	["ber"] = {"Berber languages"},												-- ISO 639-2 collective; defined here to override redefinition in wp_languages
	["bhd"] = {"Bhadarwahi"},													-- IANA, ISO 639-3 name is Bhadrawahi; to match en.wiki article title
	["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"] = {"Mongolian Buryat"},												-- IANA name Mongolia Buriat; these three all redirect to Buryat
	["bxr"] = {"Russian Buryat"},												-- IANA name Russia Buriat;
	["bxu"] = {"Chinese Buryat"},												-- IANA name China Buriat;
	["byr"] = {"Yipma"},														-- IANA names are Baruya and Yipma
	["cel"] = {"Celtic languages"},												-- ISO 639-2 collective; defined here to override improper redefinition ('Proto-Celtic') in wp_languages; use cel-x-proto instead
	["egy"] = {"Ancient Egyptian"},												-- IANA name is Egyptian (Ancient); distinguish from contemporary arz: Egyptian Arabic 
	["frr"] = {"North Frisian"},												-- IANA name is Northern Frisian
	["frs"] = {"East Frisian Low Saxon"},										-- IANA name is Eastern Frisian
	["gem"] = {"Germanic languages"},											-- 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"] = {"Modern Mandaic"},												-- IANA name is Mandaic
	["mla"] = {"Tamambo"},														-- wp_languages name is Medieval Latin; IANA and ISO 639-1 name is Malo
	["myn"] = {"Mayan languages"},												-- ISO 639-2 collective; defined here to override redefinition in wp_languages
	["nah"] = {"Nahuatl languages"},											-- 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"] = {"Old East Slavic"},												-- IANA name is Old Russian
	["pfl"] = {"Palatine German"},												-- IANA name is Pfaelzisch; to match en.wiki article
	["pms"] = {"Piedmontese"},													-- IANA / 639-3 name is Piemontese; to match en.wiki article title
	["pra"] = {"Prakrit languages"},											-- ISO 639-2 collective; defined here to override redefinition in wp_languages
	["roa"] = {"Romance languages"},											-- ISO 639-2 collective; defined here to override improper redefinition (Jèrriais) in wp_language; IANA name is "Romance languages"
	["sal"] = {"Salishan languages"},											-- ISO 639-2 collective; defined here to override redefinition in wp_languages
	["sla"] = {"Slavic languages"},												-- ISO 639-2 collective; defined here to override redefinition in wp_languages
	["son"] = {"Songhai languages"},											-- ISO 639-2 collective; defined here to override redefinition in wp_languages
	["stq"] = {"Saterland Frisian"},											-- IANA name is Saterfriesisch
	["und"] = {"undetermined"},													-- capitalization to match existing category
	["wen"] = {"Sorbian languages"},											-- 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
	
-- private use codes
	["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)"},									-- see Template_talk:Lang#Ligurian_dab
	['mnh'] = {"Mono language (Congo)"},										-- see Template_talk:Lang#Mono_languages
	['mnr'] = {"Mono language (California)"},
	['mru'] = {"Mono language (Cameroon)"},
	['mte'] = {"Mono-Alu language"},
	["xlg"] = {"Ligurian language (ancient)"},									-- 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',

		['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 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',
		},

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


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