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; มอดูล: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 ('มอดูล:Lang/data/iana languages', 'lang'),
lang_dep = key_to_lower ('มอดูล:Lang/data/iana languages', 'lang_dep'),
script = key_to_lower ('มอดูล:Lang/data/iana scripts'), -- script keys are capitalized; set to lower
region = key_to_lower ('มอดูล:Lang/data/iana regions'), -- region keys are uppercase; set to lower
variant = key_to_lower ('มอดูล:Lang/data/iana variants', 'var_sup'),
suppressed = key_to_lower ('มอดูล: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, มอดูล: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 lang_name_table.
indexes in this table shall always be lower case
]]
local override = {
------------------------------< I S O _ 6 3 9 - 1 >------------------------------------------------------------
["ab"] = "อับคาเซีย", -- to match en.wiki article name
["ca-valencia"] = "บาเลนเซีย",
["cu"] = "สลาวอนิกคริสตจักรเก่า", -- 2nd IANA name;
["de-at"] = "เยอรมันแบบออสเตรีย", -- these code-region and code-variant tags to match en.wiki article names
["de-ch"] = "เยอรมันมาตรฐานสวิส",
["en-au"] = "อังกฤษแบบออสเตรเลีย",
["en-ca"] = "อังกฤษแบบแคนาดา",
["en-emodeng"] = "อังกฤษสมัยใหม่ตอนต้น",
["en-gb"] = "อังกฤษแบบบริติช",
["en-ie"] = "อังกฤษแบบไอริช",
["en-in"] = "อังกฤษแบบอินเดีย",
["en-nz"] = "อังกฤษแบบนิวซีแลนด์",
["en-us"] = "อังกฤษแบบอเมริกัน",
["en-za"] = "อังกฤษแบบแอฟริกาใต้",
["fr-ca"] = "ฝรั่งเศสแบบเกแบ็ก",
["fr-gallo"] = "กาโล",
["fy"] = "ฟรีเชียตะวันตก", -- Western Frisian
["mo"] = "มอลโดวา", -- Moldavian (deprecated code); to match en.wiki article title
["nl-be"] = "เฟลมิช", -- match MediaWiki
["oc-gascon"] = "กัสกอญ",
["oc-provenc"] = "พรอว็องส์",
["ps"] = "ปาทาน", -- Pushto
["pt-br"] = "โปรตุเกสแบบบราซิล", -- match MediaWiki
["ro-md"] = "มอลโดวา", -- 'not deprecated' form
["ro-cyrl-md"] = "มอลโดวา", -- 'not deprecated' form
["tw-asante"] = "ชวีถิ่นอะแชนตี",
["ug"] = "อุยกูร์", -- 2nd IANA name; to match en.wiki article name
-- these ISO 639-1 language-name overrides imported from มอดูล:Language/data/wp_languages (since deleted)
--<begin do-not-edit except to comment out>--
["av"] = "อาวาร์", -- Avaric
["bo"] = "ทิเบต", -- Tibetan
["el"] = "กรีก", -- Modern Greek
-- ["en-SA"] = "อังกฤษแบบแอฟริกาใต้", -- English; no; SA is not South Africa it Saudi Arabia; ZA is South Africa
["ff"] = "ฟูลา", -- Fulah
["ht"] = "ครีโอลเฮติ", -- Haitian
["hz"] = "เฮเรโร", -- Herero
["ii"] = "อี๋", -- Sichuan Yi
["ki"] = "เกโกโย", -- Kikuyu
["kl"] = "กรีนแลนด์", -- Kalaallisut
["ky"] = "คีร์กีซ", -- Kirghiz
["lg"] = "ลูแกนดา", -- Ganda
["li"] = "ลิมบืร์ค", -- Limburgan
["mi"] = "มาวรี", -- Maori
["na"] = "นาอูรู", -- Nauru
["nb"] = "บูกโมลนอร์เวย์", -- Norwegian Bokmål
["nd"] = "อึนเดเบเลเหนือ", -- North Ndebele
["nn"] = "นีน็อชก์นอร์เวย์", -- Norwegian Nynorsk
["nr"] = "อึนเดเบเลใต้", -- South Ndebele
["ny"] = "เจวา", -- Nyanja
["oj"] = "โอจิบเว", -- Ojibwa
["or"] = "โอเดีย", -- Oriya
["pa"] = "ปัญจาบ", -- Panjabi
["rn"] = "คิรุนดี", -- Rundi
["sl"] = "สโลวีเนีย", -- Slovenian
["ss"] = "สวาซี", -- Swati
["st"] = "ซูทู", -- Southern Sotho
["to"] = "ตองงา", -- Tonga
--<end do-not-edit except to comment out>--
------------------------------< I S O _ 6 3 9 - 2, - 3, - 5 >----------------------------------------------
["alv"] = "แอตแลนติก–คองโก", -- to match en.wiki article title (endash)
["arc"] = "แอราเมอิกจักรวรรดิ (700–300 ปีก่อน ค.ศ.)", -- Official Aramaic (700-300 BCE), Imperial Aramaic (700-300 BCE); to match en.wiki article title uses ISO639-2 'preferred' name
["art"] = "ประดิษฐ์", -- to match en.wiki article; lowercase for category name
["ast-es"] = "ถิ่นเลออน", -- ast in IANA is Asturian; Leonese is a dialect
["bea"] = "ดาเน-ซา", -- Beaver; to match en.wiki article title
["bha"] = "ภรียาฏี", -- Bharia; to match en.wiki article title
["bhd"] = "ภัทรวาห์", -- Bhadrawahi; to match en.wiki article title
["bla"] = "แบล็กฟุต", -- Siksika; to match en.wiki article title
["blc"] = "นูฮอล์ก", -- Bella Coola; to match en.wiki article title
["bua"] = "บูร์ยัต", -- Buriat; this is a macro language; these four use wp preferred transliteration;
["bxm"] = "บูร์ยัตแบบมองโกเลีย", -- Mongolia Buriat; these three all redirect to Buryat
["bxr"] = "บูร์ยัตแบบรัสเซีย", -- Russia Buriat;
["bxu"] = "บูร์ยัตแบบจีน", -- China Buriat;
["byr"] = "ยิปมา", -- Baruya, Yipma
["clm"] = "แคล็ลลัม", -- Clallam; to match en.wiki article title
["egy"] = "อียิปต์โบราณ", -- Egyptian (Ancient); distinguish from contemporary arz: Egyptian Arabic
["ems"] = "อะลูติก", -- Pacific Gulf Yupik; to match en.wiki article title
["esx"] = "เอสกิโม–อะลิวต์", -- to match en.wiki article title (endash)
["frr"] = "ฟรีเชียเหนือ", -- Northern Frisian
["frs"] = "แซกซันต่ำถิ่นฟรีเชียตะวันออก", -- Eastern Frisian
["gsw-fr"] = "ถิ่นอาลซัส", -- match MediaWiki
["haa"] = "ฮัน (ทวีปอเมริกาเหนือ)", -- Han; to match en.wiki article title
["hei"] = "เฮลต์ซัก–อูวีเคียลา", -- Heiltsuk; to match en.wiki article title
["hmx"] = "ม้ง–เมี่ยน", -- to match en.wiki article title (endash)
["ilo"] = "อีโลกาโน", -- Iloko; to match en.wiki article title
["jam"] = "ครีโอลจาเมกา", -- Jamaican Creole English
["lij-mc"] = "ถิ่นโมนาโก", -- Ligurian as spoken in Monaco; this one for proper tool tip; also in <article_name> table
["luo"] = "โดลูโอ", -- IANA (primary) /ISO 639-3: Luo (Kenya and Tanzania); IANA (secondary): Dholuo
["mhr"] = "มารีทุ่งหญ้า", -- Eastern Mari
["mid"] = "มันดาอิกสมัยใหม่", -- Mandaic
['mis'] = "ไร้รหัส", -- Uncoded languages; capitalization; special scope, not collective scope;
["mkh"] = "มอญ–เขมร", -- to match en.wiki article title (endash)
["mla"] = "ตามัมโบ", -- Malo
['mte'] = "โมโน-อาลู", -- Mono (Solomon Islands)
['mul'] = "multiple", -- Multiple languages; capitalization; special scope, not collective scope;
["nan-tw"] = "จีนฮกเกี้ยนสำเนียงไต้หวัน", -- make room for IANA / 639-3 nan Min Nan Chinese; match en.wiki article title
["new"] = "เนวาร์", -- Newari, Nepal Bhasa; to match en,wiki article title
["ngf"] = "ทรานส์–นิวกินี", -- to match en.wiki article title (endash)
["nic"] = "ไนเจอร์–คองโก", -- Niger-Kordofanian languages; to match en,wiki article title
["nrf"] = "นอร์มัน", -- not quite a collective - IANA name: Jèrriais + Guernésiais; categorizes to Norman-language text
["nrf-gg"] = "เกิร์นซีย์", -- match MediaWiki
["nrf-je"] = "เจอร์ซีย์", -- match MediaWiki
["nzi"] = "อึนเซมา", -- Nzima; to match en.wiki article title
["oma"] = "โอมาฮา–พองกา", -- to match en.wiki article title (endash)
["orv"] = "สลาฟตะวันออกเก่า", -- Old Russian
["pfl"] = "ถิ่นฟัลทซ์", -- Pfaelzisch; to match en.wiki article
["pie"] = "พีโร", -- Piro; to match en.wiki article
["pms"] = "ปีเยมอนเต", -- Piemontese; to match en.wiki article title
["pnb"] = "ปัญจาบตะวันตก", -- Western Panjabi; dab added to override import from ~/wp languages and distinguish pnb from pa in reverse look up tag_from_name()
['qwm'] = "คิวมัน", -- Kuman (Russia); to match en.wiki article name
["rop"] = "ครีโอลออสเตรเลีย", -- Kriol; en.wiki article is a dab; point to correct en.wiki article
["sco-ulster"] = "สกอตถิ่นอัลสเตอร์",
["sdo"] = "บูการ์–ซาดง", -- Bukar-Sadung Bidayuh; to match en.wiki article title
["smp"] = "ฮีบรูสะมาริตัน", -- to match en.wiki article title
["stq"] = "ฟรีเชียถิ่นซาเทอร์ลันท์", -- Saterfriesisch
["und"] = "ไม่แน่ชัด", -- capitalization to match existing category
["wrg"] = "วารูงู", -- Warungu
["xal-ru"] = "คัลมึค", -- to match en.wiki article title
["xgf"] = "ทองวา", -- ISO 639-3 is Gabrielino-Fernandeño
["yuf"] = "ฮาวาซูพาย–วาลาพาย", -- Havasupai-Walapai-Yavapai; to match en.wiki article title
["zxx"] = "ไม่มีเนื้อหา", -- capitalization
-- these ISO 639-2, -3 language-name overrides imported from มอดูล:Language/data/wp_languages (since deleted)
--<begin do-not-edit except to comment out>--
["ace"] = "อาเจะฮ์", -- Achinese
["aec"] = "อาหรับเศาะอีด", -- Saidi Arabic
["akl"] = "อักลัน", -- Aklanon
["alt"] = "อัลไต", -- Southern Altai
["apm"] = "เมสกาเลโร-ชิริคาวา", -- Mescalero-Chiricahua Apache
["bal"] = "บาโลจ", -- Baluchi
-- ["bcl"] = "บีโคลกลาง", -- Central Bikol
["bin"] = "เอโด", -- Bini
["bpy"] = "มณีปุระพิษณุปุระ", -- Bishnupriya
["chg"] = "ชากาทาย", -- 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"] = "กืออึซ", -- Geez
["gju"] = "Gujari", -- Gujari
["gsw"] = "Alemannic German", -- Swiss German
["gul"] = "Gullah", -- Sea Island Creole English
["hak"] = "แคะ", -- Hakka Chinese
["hbo"] = "ฮีบรูไบเบิล", -- Ancient Hebrew
["hnd"] = "Hindko", -- Southern Hindko
-- ["ikt"] = "Inuvialuk", -- Inuinnaqtun
["kaa"] = "การากัลปัก", -- Kara-Kalpak
["khb"] = "ไทลื้อ", -- Lü
["kmr"] = "Kurmanji Kurdish", -- Northern Kurdish
["kpo"] = "Kposo", -- Ikposo
["krj"] = "กินาไรอา", -- Kinaray-A
-- ["ktz"] = "Juǀ'hoan", -- Juǀʼhoan
["lez"] = "Lezgian", -- Lezghian
["liv"] = "ลิโวเนีย", -- Liv
["lng"] = "Lombardic", -- Langobardic
["mia"] = "ไมแอมี-อิลลินอย", -- Miami
["miq"] = "Miskito", -- Mískito
["mix"] = "Mixtec", -- Mixtepec Mixtec
["mni"] = "มณีปุระ", -- Manipuri
["mrj"] = "มารีเนินเขา", -- Western Mari
["mww"] = "White Hmong", -- Hmong Daw
["nds-nl"] = "Dutch Low Saxon", -- Low German
-- ["new"] = "Nepal Bhasa", -- Newari
["nso"] = "ซูทูเหนือ", -- Pedi
-- ["nwc"] = "Classical Nepal Bhasa", -- Classical Newari, Classical Nepal Bhasa, Old Newari
["ood"] = "ออ-ออดัม", -- Tohono O'odham
["otk"] = "เตอร์กิกเก่า", -- Old Turkish
["pal"] = "Middle Persian", -- Pahlavi
["pam"] = "กาปัมปางัน", -- Pampanga
["phr"] = "Potwari", -- Pahari-Potwari
["pka"] = "Jain Prakrit", -- Ardhamāgadhī Prākrit
-- ["pnb"] = "ปัญจาบตะวันตก", -- Western Panjabi
["psu"] = "เศารเสนี", -- Sauraseni Prākrit
["rap"] = "ราปานูอี", -- Rapanui
["rar"] = "มาวรีหมู่เกาะคุก", -- Rarotongan
["rmu"] = "สแกนโดโรมานี", -- Tavringer Romani
["rom"] = "โรมานี", -- Romany
["rup"] = "อาโรมาเนียน", -- Macedo-Romanian
["ryu"] = "โอกินาวะ", -- Central Okinawan
["sdc"] = "ซัสซารี", -- Sassarese Sardinian
["sdn"] = "ถิ่นกัลลูรา", -- Gallurese Sardinian
["shp"] = "ชีปีโบ", -- Shipibo-Conibo
["src"] = "ซาร์ดิเนียถิ่นโลกูโดโร", -- Logudorese Sardinian
["sro"] = "ซาร์ดิเนียถิ่นคัมปีดาโน", -- Campidanese Sardinian
["tkl"] = "โตเกเลา", -- Tokelau
["tvl"] = "ตูวาลู", -- Tuvalu
["tyv"] = "ตูวา", -- Tuvinian
["vls"] = "เฟลมิชตะวันตก", -- Vlaams
["wep"] = "เว็สท์ฟาเลิน", -- Westphalien
["xal"] = "เออรัต", -- Kalmyk
["xcl"] = "อาร์มีเนียเก่า", -- Classical Armenian
["yua"] = "มายายูกาตัน", -- 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 Akkadian",
["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"] = "แอลกองเควียนดั้งเดิม", -- alg in IANA is Algonquian languages
["ca-x-old"] = "กาตาลาเก่า",
["cel-x-combrit"] = "Common Brittonic", -- cel in IANA is Celtic languages
["cel-x-proto"] = "เคลต์ดั้งเดิม",
["egy-x-demotic"] = "Demotic Egyptian",
["egy-x-late"] = "Late Egyptian",
["egy-x-middle"] = "Middle Egyptian",
["egy-x-old"] = "Old Egyptian",
["gem-x-proto"] = "เจอร์แมนิกดั้งเดิม", -- 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"] = "กรีกแอตติก",
["grc-x-biblical"] = "Biblical Greek",
["grc-x-byzant"] = "Byzantine Greek",
["grc-x-classic"] = "Classical Greek",
["grc-x-doric"] = "กรีกดอริก",
["grc-x-hellen"] = "Hellenistic Greek",
["grc-x-ionic"] = "Ionic Greek",
["grc-x-koine"] = "กรีกคอยนี",
["grc-x-medieval"] = "กรีกสมัยกลาง",
["grc-x-patris"] = "Patristic Greek",
["grk-x-proto"] = "กรีกดั้งเดิม", -- grk in IANA is Greek languages
["iir-x-proto"] = "อินโด-อิเรเนียนดั้งเดิม", -- iir in IANA is Indo-Iranian Languages
["inc-x-mitanni"] = "Mitanni-Aryan", -- inc in IANA is Indic languages
["inc-x-proto"] = "อินโด-อารยันดั้งเดิม",
["ine-x-anatolia"] = "อานาโตเลีย",
["ine-x-proto"] = "อินโด-ยูโรเปียนดั้งเดิม",
["ira-x-proto"] = "อิหร่านดั้งเดิม", -- ira in IANA is Iranian languages
["itc-x-proto"] = "อิตาลิกดั้งเดิม", -- itc in IANA is Italic languages
["ksh-x-colog"] = "ถิ่นโคโลญ", -- en.wiki article is Colognian; ksh (Kölsch) redirects there
["la-x-medieval"] = "ละตินสมัยกลาง",
["la-x-new"] = "New Latin",
["lmo-x-berg"] = "ถิ่นแบร์กาโม", -- lmo in IANA is Lombard; Bergamasque is a dialect
["lmo-x-cremish"] = "Cremish", -- lmo in IANA is Lombard; Cremish is a dialect
["lmo-x-milanese"] = "ถิ่นมิลาน", -- lmo in IANA is Lombard; Milanese is a dialect
["mis-x-ripuar"] = "ริพิวแอเรียน", -- replaces improper use of ksh in wp_languages
["prg-x-old"] = "ปรัสเซียเก่า",
["sem-x-ammonite"] = "Ammonite",
["sem-x-aramaic"] = "แอราเมอิก",
["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"] = "เซมิติกดั้งเดิม",
["sem-x-taymanit"] = "Taymanitic",
["sla-x-proto"] = "สลาฟดั้งเดิม", -- 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",
["xsc-x-pontic"] = "Pontic Scythian", -- xsc in IANA is Scythian
["xsc-x-saka"] = "Saka",
["xsc-x-sarmat"] = "Sarmatian",
}
--[[--------------------------< 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"] = "ถิ่นโมนาโก", -- 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 {{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',
['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'] = 'ISO transliteration',
},
['jyutping'] = {
['default'] = 'Jyutping transliteration',
},
['mlcts'] = {
['default'] = 'Myanmar Language Commission Transcription System',
},
['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',
},
['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',
},
['wehr'] = {
['default'] = 'Hans Wehr transliteration',
},
['yaleko'] = {
['default'] = 'Yale romanization of Korean',
}
};
--[[--------------------------< 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'] = 'อักษรโรมัน', -- lower case
['romanisz_uc'] = 'อักษรโรมัน', -- upper case
['romanisz_pt'] = 'อักษรโรมัน', -- past tense
},
['us_t'] = { -- default engvar
['romanisz_lc'] = 'อักษรโรมัน', -- lower case
['romanisz_uc'] = 'อักษรโรมัน', -- upper case
['romanisz_pt'] = 'อักษรโรมัน', -- 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,
};
