Module:Lang/data: Difference between revisions

m
1 revision imported from wikipedia:Module:Lang/data: nihongo update
m (1 revision imported: module, u data)
m (1 revision imported from wikipedia:Module:Lang/data: nihongo update)
 
(3 intermediate revisions by 3 users not shown)
Line 1:
local lang_obj = mw.language.getContentLanguage();
local lang_data = {};
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 = (('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) do
out[k:lower()] = v; -- for variant and suppressed 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_t = {
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', 'var_sup'),
suppressed = key_to_lower ('Module:Language/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 colsole:
=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 exisiting 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 Module:Language/name/datalang_name_table.
 
indexes in this table shall always be lower case
 
code indexes in this table shall always be lower case
]]
 
local override = {
------------------------------< I S O _ 6 3 9 - 1 >------------------------------------------------------------
-- 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 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
["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=
 
["ab"] = "Abkhaz", -- to match en.wiki article name
-- ISO 639-2, -3 codes
["ca-valencia"] = "Valencian",
["arc"] = {"Aramaic"}, -- IANA names are: Official Aramaic (700-300 BCE), Imperial Aramaic (700-300 BCE);
["bercu"] = {"BerberChurch languagesSlavonic"}, -- ISO2nd 639-2IANA collectivename; defined here to override redefinition in wp_languages
["blade-at"] = {"BlackfootAustrian German"}, -- IANA, ISOthese 639code-2,region and code-3 name isvariant Siksika;tags to match en.wiki article titlenames
["de-ch"] = "Swiss Standard German",
["bua"] = {"Buryat"}, -- IANA name Buriat; this is a macro language; these four use wp preferred transliteration;
["en-au"] = "Australian English",
["bxm"] = {"Mongolian Buryat"}, -- IANA name Mongolia Buriat; these three all redirect to Buryat
["en-ca"] = "Canadian English",
["bxr"] = {"Russian Buryat"}, -- IANA name Russia Buriat;
["en-emodeng"] = "Early Modern English",
["bxu"] = {"Chinese Buryat"}, -- IANA name China Buriat;
["en-gb"] = "British English",
["byr"] = {"Yipma"}, -- IANA names are Baruya and Yipma
["en-ie"] = "Irish English",
["cel"] = {"Celtic languages"}, -- ISO 639-2 collective; defined here to override improper redefinition ('Proto-Celtic') in wp_languages; use cel-x-proto instead
["en-in"] = "Indian English",
["egy"] = {"Ancient Egyptian"}, -- IANA name is Egyptian (Ancient); distinguish from contemporary arz: Egyptian Arabic
["en-nz"] = "New Zealand English",
["frr"] = {"North Frisian"}, -- IANA name is Northern Frisian
["en-us"] = "American English",
["frs"] = {"East Frisian Low Saxon"}, -- IANA name is Eastern Frisian
["en-za"] = "South African English",
["gem"] = {"Germanic languages"}, -- ISO 639-2 collective; defined here to override improper redefinition ('Proto-Germanic') in wp_languages; use gem-x-proto instead
["ilofy"] = {"IlocanoWest Frisian"}, -- IANA, ISO 639-2, -3 name is Iloko; to match en.wiki articleWestern titleFrisian
["jammo"] = {"Jamaican PatoisMoldovan"}, -- IANAMoldavian (deprecated code); nameto ismatch Jamaicanen.wiki Creolearticle Englishtitle
["mhrnl-be"] = {"Meadow MariFlemish"}, -- IANA name is Easternmatch MariMediaWiki
["oc-provenc"] = "Provençal",
["mid"] = {"Modern Mandaic"}, -- IANA name is Mandaic
["mlaps"] = {"TamamboPashto"}, -- wp_languages name is Medieval Latin; IANA and ISO 639-1 name is MaloPushto
["mynpt-br"] = {"MayanBrazilian languagesPortuguese"}, -- ISO 639-2 collective; defined here to override redefinition inmatch wp_languagesMediaWiki
["tw-asante"] = "Asante Twi",
["nah"] = {"Nahuatl languages"}, -- ISO 639-2 collective; defined here to override redefinition in wp_languages
["nan-twug"] = {"Taiwanese HokkienUyghur"}, -- make room for2nd IANA /name; 639-3 nan Min Nan Chinese;to match en.wiki article titlename
 
["nrf"] = {"Norman"}, -- not quite a collective - IANA name: Jèrriais; categorizes to Norman-language text
-- these ISO 639-1 language-name overrides imported from Module:Language/data/wp_languages
["nzi"] = {"Nzema"}, -- IANA, ISO 639-2, -3 name is Nzima; to match en.wiki article title
--<begin do-not-edit except to comment out>--
["orv"] = {"Old East Slavic"}, -- IANA name is Old Russian
["pmsav"] = {"PiedmonteseAvar"}, -- IANA / 639-3 name is Piemontese; to match en.wiki article titleAvaric
["prabo"] = {"PrakritStandard languagesTibetan"}, -- ISO 639-2 collective; defined here to override redefinition in wp_languagesTibetan
["el"] = "Greek", -- Modern Greek
["roa"] = {"Romance languages"}, -- ISO 639-2 collective; defined here to override improper redefinition (Jèrriais) in wp_language; IANA name is "Romance languages"
-- ["en-SA"] = "South African English", -- English; no; SA is not South Africa it Saudi Arabia; ZA is South Africa
["sal"] = {"Salishan languages"}, -- ISO 639-2 collective; defined here to override redefinition in wp_languages
["ff"] = "Fula", -- Fulah
["sla"] = {"Slavic languages"}, -- ISO 639-2 collective; defined here to override redefinition in wp_languages
["sonht"] = {"SonghaiHaitian languagesCreole"}, -- ISO 639-2 collective; defined here to override redefinition in wp_languagesHaitian
["stqhz"] = {"Saterland FrisianOtjiherero"}, -- IANA name is SaterfriesischHerero
["undii"] = {"undeterminedYi"}, -- capitalization to match existingSichuan categoryYi
["ki"] = "Gikuyu", -- Kikuyu
["wen"] = {"Sorbian languages"}, -- ISO 639-2 collective; defined here to override redefinition in wp_languages
["wrgkl"] = {"WarrongoGreenlandic"}, -- IANA name is WarunguKalaallisut
["xal-ruky"] = {"KalmykKyrgyz"}, -- to match en.wiki article titleKirghiz
["lg"] = "Luganda", -- Ganda
["li"] = "Limburgish", -- Limburgan
-- private use codes
["cel-x-protomi"] = {"Proto-CelticMāori"}, -- cel in IANA is Celtic languagesMaori
["gem-x-protona"] = {"Proto-GermanicNauruan"}, -- gem in IANA is Germanic languagesNauru
["nb"] = "Bokmål", -- Norwegian Bokmål
["grc-x-aeolic"] = {"Aeolic Greek"}, -- these grc-x-... codes are preferred alternates to the non-standard catchall code grc-gre
["nd"] = "Northern Ndebele", -- North Ndebele
["grc-x-attic"] = {"Attic Greek"},
["nn"] = "Nynorsk", -- Norwegian Nynorsk
["grc-x-biblical"] = {"Biblical Greek"},
["nr"] = "Southern Ndebele", -- South Ndebele
["grc-x-byzant"] = {"Byzantine Greek"},
["ny"] = "Chichewa", -- Nyanja
["grc-x-classic"] = {"Classical Greek"},
["oj"] = "Ojibwe", -- Ojibwa
["grc-x-doric"] = {"Doric Greek"},
["or"] = "Odia", -- Oriya
["grc-x-hellen"] = {"Hellenistic Greek"},
["pa"] = "Punjabi", -- Panjabi
["grc-x-ionic"] = {"Ionic Greek"},
["rn"] = "Kirundi", -- Rundi
["grc-x-koine"] = {"Koinē Greek"},
["sl"] = "Slovene", -- Slovenian
["grc-x-medieval"] = {"Medieval Greek"},
["ss"] = "Swazi", -- Swati
["grc-x-patris"] = {"Patristic Greek"},
["grk-x-protost"] = {"Proto-GreekSotho"}, -- grk in IANA is GreekSouthern languagesSotho
["iir-x-prototo"] = {"Proto-Indo-IranianTongan"}, -- iir in IANA is Indo-Iranian LanguagesTonga
--<end do-not-edit except to comment out>--
["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
------------------------------< I S O _ 6 3 9 - 2, - 3, - 5 >----------------------------------------------
["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-havalv"] = {"HavasupaiAtlantic–Congo languages"}, -- IANAto namematch foren.wiki thesearticle threetitle is Havasupai-Walapai-Yavapai(endash)
["arc"] = "Imperial Aramaic (700-300 BCE)", -- Official Aramaic (700-300 BCE), Imperial Aramaic (700-300 BCE); to match en.wiki article title uses ISO639-2 'preferred' name
["yuf-x-wal"] = {"Walapai"},
["art"] = "constructed", -- to match en.wiki article; lowercase for category name
["yuf-x-yav"] = {"Yavapai"},
["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
["ems"] = "Alutiiq", -- Pacific Gulf Yupik; to match en.wiki article title
["esx"] = "Eskimo–Aleut languages", -- to match en.wiki article title (endash)
["frr"] = "North Frisian", -- Northern Frisian
["frs"] = "East Frisian Low Saxon", -- Eastern Frisian
["gsw-fr"] = "Alsatian", -- match MediaWiki
["haa"] = "Hän", -- Han; to match en.wiki article title
["hmx"] = "Hmong–Mien languages", -- to match en.wiki article title (endash)
["ilo"] = "Ilocano", -- Iloko; to match en.wiki article title
["jam"] = "Jamaican Patois", -- Jamaican Creole English
["lij-mc"] = "Monégasque", -- Ligurian as spoken in Monaco
["luo"] = "Dholuo", -- IANA (primary) /ISO 639-3: Luo (Kenya and Tanzania); IANA (secondary): Dholuo
["mhr"] = "Meadow Mari", -- Eastern Mari
["mid"] = "Modern Mandaic", -- Mandaic
['mis'] = "uncoded", -- Uncoded languages; capitalization; special scope, not collective scope;
["mkh"] = "Mon–Khmer languages", -- to match en.wiki article title (endash)
["mla"] = "Tamambo", -- Malo
['mte'] = "Mono-Alu", -- Mono (Solomon Islands)
['mul'] = "multiple", -- Multiple languages; capitalization; special scope, not collective scope;
["nan-tw"] = "Taiwanese Hokkien", -- 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"] = "Trans–New Guinea languages", -- to match en.wiki article title (endash)
["nic"] = "Niger–Congo languages", -- 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"] = "Old East Slavic", -- Old Russian
["pfl"] = "Palatine German", -- Pfaelzisch; to match en.wiki article
["pie"] = "Piro Pueblo", -- Piro; 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()
["rop"] = "Australian Kriol", -- Kriol; en.wiki article is a dab; point to correct en.wiki article
["sdo"] = "Bukar–Sadong", -- Bukar-Sadung Bidayuh; to match en.wiki article title
["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
["yuf"] = "Havasupai–Hualapai", -- Havasupai-Walapai-Yavapai; to match en.wiki article title
["zxx"] = "no linguistic content", -- capitalization
 
-- 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, Classical Nepal Bhasa, Old 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 >----------------------------------------------
 
["akk-x-latbabyl"] = "Late Babylonian",
["akk-x-midassyr"] = "Middle Assyrian Akkadian",
["akk-x-midbabyl"] = "Middle Babylonian Akkadian",
["akk-x-neoassyr"] = "Neo-Assyrian Akkadian",
["akk-x-neobabyl"] = "Neo-Babylonian Akkadian",
["akk-x-old"] = "Old Akkadian",
["akk-x-oldassyr"] = "Old Assyrian Akkadian",
["akk-x-oldbabyl"] = "Old Babylonian Akkadian",
["alg-x-proto"] = "Proto-Algonquian", -- alg in IANA is Algonquian languages
["ca-x-old"] = "Old Catalan",
["cel-x-proto"] = "Proto-Celtic", -- cel in IANA is Celtic languages
["egy-x-demotic"] = "Demotic Egyptian",
["egy-x-late"] = "Late Egyptian",
["egy-x-middle"] = "Middle Egyptian",
["egy-x-old"] = "Old Egyptian",
["gem-x-proto"] = "Proto-Germanic", -- gem in IANA is Germanic languages
["gmw-x-ecg"] = "East Central German",
["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
["ine-x-proto"] = "Proto-Indo-European",
["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
["la-x-medieval"] = "Medieval Latin",
["la-x-new"] = "New Latin",
["lmo-x-milanese"] = "Milanese", -- lmo in IANA is Lombard; Milanese is a dialect
["mis-x-ripuar"] = "Ripuarian", -- replaces improper use of ksh in wp_languages
["prg-x-old"] = "Old Prussian",
["sem-x-ammonite"] = "Ammonite",
["sem-x-aramaic"] = "Aramaic",
["sem-x-canaan"] = "Canaanite languages",
["sem-x-dumaitic"] = "Dumaitic",
["sem-x-egurage"] = "Eastern Gurage",
["sem-x-hatran"] = "Hatran Aramaic",
["sem-x-oldsoara"] = "Old South Arabian",
["sem-x-palmyren"] = "Palmyrene Aramaic",
["sem-x-proto"] = "Proto-Semitic",
["sem-x-taymanit"] = "Taymanitic",
["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",
}
 
Line 96 ⟶ 366:
 
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
 
Line 102 ⟶ 372:
 
local article_name = {
['kue'] = "Kuman language (New Guinea)", -- Kuman (Papua New Guinea); to avoid Kuman dab page
["lij"] = {"Ligurian (Romance language)"}, -- see Template_talk:Lang#Ligurian_dab
['mnh'"lij"] = {"Mono languageLigurian (CongoRomance language)"}, -- Ligurian; see Template_talk:Lang#Mono_languagesLigurian_dab
['mnrmbo'] = {"MonoMbo language (CaliforniaCameroon)"}, -- Mbo (Cameroon)
['mrumnh'] = {"Mono language (CameroonCongo)"}, -- Mono (Democratic Republic of Congo); see Template_talk:Lang#Mono_languages
['mtemnr'] = {"Mono-Alu language (California)"}, -- Mono (USA)
["xlg"'mru'] = {"LigurianMono language (ancientCameroon)"}, -- seeMono Template_talk:Lang#Ligurian_dab(Cameroon)
['qwm'] = "Kuman (Russia)", -- Kuman (Russia); to avoid Kuman dab page
["snq"] = "Sangu language (Gabon)", -- Sangu (Gabon)
["xlg"] = "Ligurian (ancient language)", -- see Template_talk:Lang#Ligurian_dab
["zmw"] = "Mbo language (Congo)", -- Mbo (Democratic Republic of Congo)
}
 
Line 113 ⟶ 387:
--[=[-------------------------< 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
Line 127 ⟶ 401:
 
 
--[[--------------------------< 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.
 
Line 178 ⟶ 452:
['hepburn'] = {
['default'] = 'Hepburn transliteration',
},
 
['hunterian'] = {
['default'] = 'Hunterian transliteration',
},
 
Line 241 ⟶ 519:
['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'] = 'ISO transliteration',
},
 
['jyutping'] = {
['default'] = 'Jyutping transliteration',
},
 
['mlcts'] = {
['default'] = 'Myanmar Language Commission Transcription System',
},
 
Line 288 ⟶ 603:
['satts'] = {
['default'] = 'Standard Arabic Technical Transliteration System transliteration',
},
 
['scientific'] = {
['default'] = 'scientific transliteration',
},
 
['ukrainian'] = {
['default'] = 'Ukrainian National system of romanization',
},
 
['ungegn'] = {
['default'] = 'United Nations Group of Experts on Geographical Names transliteration',
},
 
['wadegile'] = {
['default'] = 'Wade–Giles transliteration',
},
 
Line 302 ⟶ 629:
return
{
this_wiki_lang_tag = this_wiki_lang_tag,
override = override,
this_wiki_lang_dir = lang_obj:getDir(), -- wiki's language direction
article_name = article_name,
lang_name_table = lang_name_table_t,
override = override,
rtl_scripts = rtl_scripts,
special_tags_table = special_tags_table,
is_rtl_script = is_rtl_script,
translit_title_table = translit_title_table,
};