Module:Lang/data

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.

This table may also be used to add 'codes' that aren't BCP47

Linguist list identifier codes may be found at http://multitree.org/codes/ Additional Linguist list idenifier codes may require tweaks to get_ietf_parts() in Module:Lang

]]

local override = { -- linguist list codes & names ['1bd'] = {'Common Brittonic', 'Late British'}, -- Linguist list identifier; Late British is their name for this language ['1ca'] = {'Old Anatolian Turkish'}, -- Linguist list identifier

-- ISO 639-1 codes ["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

-- ISO 639-2, -3 codes ['arc'] = {'Aramaic'}, -- to match en.wiki article title ["chu"] = {"Church Slavonic"}, -- to match en.wiki article title ["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 -- ['hin'] = {'Hindustani'}, -- IANA name is Hindi; module promotes to hi ['jam'] = {'Jamaican Patois'}, -- IANA name is Jamaican Creole English ['mhr'] = {'Meadow Mari'}, -- IANA name is Eastern Mari ['mid'] = {'Modern Mandaic'}, -- IANA name is Mandaic -- ['nav'] = {'Navajo'}, -- preferred spelling to Navaho; promotes to nv ['nrf'] = {'Norman'}, -- not quite a collective - IANA name: Jèrriais; categorizes to Norman-language text ['ps'] = {'Pashto'}, -- IANA name is Pushto ['roa'] = {'Romance'}, -- collective; overrides roa (Jèrriais) in the wp language table; IANA name is "Romance languages" ['sem'] = {'other Semitic'}, -- ISO 639-2 collective; this text used to fit pre-existing: Category:Articles containing other Semitic-language text ['stq'] = {'Saterland Frisian'}, -- IANA name is Saterfriesisch ["tmr"] = {"Jewish Babylonian Aramaic"}, -- ISO 639-3 name is Jewish Babylonian Aramaic (ca. 200-1200 CE) ['und'] = {'undetermined'}, -- capitalization to match existing category ['wrg'] = {'Warrongo'}, -- IANA name is Warungu ["xal-RU"] = {"Kalmyk"}, -- to match en.wiki article title }

--[=[-------------------------< 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

]=]

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', 'samr', 'sarb', '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 Template:Lang-?? templates.

These tables are more-or-less copied directly from [undefined] . 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, };