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
	['bh'] = {'Bihari languages'},												-- only ISO 639-1 collective; defined here to override improper redefinition (Bihari) in wp_languages
	['de-at'] = {'Austrian German'},											-- these code-region and code-variant to match en.wiki article names
	['de-ch'] = {'Swiss German'},
	['en-au'] = {'Australian English'},
	['en-ca'] = {'Canadian English'},
	['en-emodeng'] = {'Early Modern English'},
	['en-gb'] = {'British English'},
	['en-ie'] = {'Irish 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
	['sr-Cyrl'] = {'Serbian'},													-- override wp_languages {'Serbian Cyrillic'}; to achieve this, use |label=

-- ISO 639-2, -3 codes
	['arc'] = {'Aramaic'},														-- to match en.wiki article title
	['ber'] = {'Berber languages'},												-- ISO 639-2 collective; defined here to override redefinition in wp_languages
	['cel'] = {'Celtic languages'},												-- ISO 639-2 collective; defined here to override improper redefinition ('Proto-Celtic') in wp_languages; use cel-x-proto instead
	['chu'] = {'Church Slavonic'},												-- to match en.wiki article title
	['egy'] = {'Ancient Egyptian'},												-- IANA name is Egyptian (Ancient); distinguish from contemporary arz: Egyptian Arabic 
	['fan'] = {'Fang'},															-- IANA name is Fang (Equatorial Guinea); disambiguation from fak: Fang (Camaroon)
	['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
	['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
	['nrf'] = {'Norman'},														-- not quite a collective - IANA name: Jèrriais; categorizes to Norman-language text
	['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
	
-- 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'},
	['yuf-x-hav'] = {'Havasupai'},												-- IANA name for these three is Havasupai-Walapai-Yavapai
	['yuf-x-wal'] = {'Walapai'},
	['yuf-x-yav'] = {'Yavapai'},
	}


--[=[-------------------------< 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',
	};

local is_rtl_script = require("Module:Table").listToSet(rtl_scripts)


--[[--------------------------< 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 = {
	['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',
		},

	['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',
		},

	['IAST'] = {
		['default'] = 'International Alphabet of Sanskrit Transliteration',
		},

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

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

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


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