Safer nicotine wiki

Module:Lang/data: Difference between revisions

added private use tags used by Module:Language
 
m 1 revision imported: template update
 
(11 intermediate revisions by 6 users not shown)
Line 1: Line 1:
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 >------------------------------------------------
--[[--------------------------< L A N G _ N A M E _ T A B L E >------------------------------------------------


Line 13: Line 17:
have multiple associated names; Module:lang is only concerned with the first name so key_to_lower() only fetches
have multiple associated names; Module:lang is only concerned with the first name so key_to_lower() only fetches
the first name.
the first name.
TODO: instead of returning:
["key"] = {"name"}
where each table has only one name, return
["key"] = "name"
requires changes in Module:Lang.


]]
]]
Line 24: Line 22:
local function key_to_lower (module, src_type)
local function key_to_lower (module, src_type)
local out = {};
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
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
if 'var_sup' == src_type then
for k, v in pairs (source) do
for k, v in pairs (source_t) do
out[k:lower()] = v; -- for variant, everything is needed
out[k:lower()] = v; -- for variant and suppressed everything is needed
end
end


elseif 'lang' == src_type and source.active then -- for ~/iana_languages (active)
elseif 'lang' == src_type and source_t.active then -- for ~/iana_languages (active)
for k, v in pairs (source.active) do
for k, v in pairs (source_t.active) do
out[k:lower()] = {v[1]}; -- ignore multiple names; take first name only
out[k:lower()] = v[1]; -- ignore multiple names; take first name only
end
end


elseif 'lang_dep' == src_type and source.deprecated then -- for ~/iana_languages (deprecated)
elseif 'lang_dep' == src_type and source_t.deprecated then -- for ~/iana_languages (deprecated)
for k, v in pairs (source.deprecated) do
for k, v in pairs (source_t.deprecated) do
out[k:lower()] = {v[1]}; -- ignore multiple names; take first name only
out[k:lower()] = v[1]; -- ignore multiple names; take first name only
end
end


else -- here for all other sources
else -- here for all other sources
for k, v in pairs (source) do
for k, v in pairs (source_t) do
out[k:lower()] = {v[1]}; -- ignore multiple names; take first name only
out[k:lower()] = v[1]; -- ignore multiple names; take first name only
end
end
end
end
Line 48: Line 47:
end
end


local lang_name_table = {
local lang_name_table_t = {
lang = key_to_lower ('Module:Language/data/iana languages', 'lang'),
lang = key_to_lower ('Module:Lang/data/iana languages', 'lang'),
lang_dep = key_to_lower ('Module:Language/data/iana languages', 'lang_dep'),
lang_dep = key_to_lower ('Module:Lang/data/iana languages', 'lang_dep'),
script = key_to_lower ('Module:Language/data/iana scripts'), -- script keys are capitalized; set to lower
script = key_to_lower ('Module:Lang/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
region = key_to_lower ('Module:Lang/data/iana regions'), -- region keys are uppercase; set to lower
variant = key_to_lower ('Module:Language/data/iana variants', 'var_sup'),
variant = key_to_lower ('Module:Lang/data/iana variants', 'var_sup'),
suppressed = key_to_lower ('Module:Language/data/iana suppressed scripts', 'var_sup'), -- script keys are capitalized; set to lower
suppressed = key_to_lower ('Module: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, 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




Line 69: Line 119:
------------------------------< I S O _ 6 3 9 - 1 >------------------------------------------------------------
------------------------------< I S O _ 6 3 9 - 1 >------------------------------------------------------------


["ca-valencia"] = {"Valencian"},
["ab"] = "Abkhaz",                                                          -- to match en.wiki article name
["cu"] = {"Church Slavonic"}, -- 2nd IANA name;
["ca-valencia"] = "Valencian",
["de-at"] = {"Austrian German"}, -- these code-region and code-variant tags to match en.wiki article names
["cu"] = "Church Slavonic", -- 2nd IANA name;
["de-ch"] = {"Swiss Standard German"},
["de-at"] = "Austrian German", -- these code-region and code-variant tags to match en.wiki article names
["en-au"] = {"Australian English"},
["de-ch"] = "Swiss Standard German",
["en-ca"] = {"Canadian English"},
["en-au"] = "Australian English",
["en-emodeng"] = {"Early Modern English"},
["en-ca"] = "Canadian English",
["en-gb"] = {"British English"},
["en-emodeng"] = "Early Modern English",
["en-ie"] = {"Irish English"},
["en-gb"] = "British English",
["en-in"] = {"Indian English"},
["en-ie"] = "Irish English",
["en-nz"] = {"New Zealand English"},
["en-in"] = "Indian English",
["en-us"] = {"American English"},
["en-nz"] = "New Zealand English",
["en-za"] = {"South African English"},
["en-us"] = "American English",
["fy"] = {"West Frisian"}, -- Western Frisian
["en-za"] = "South African English",
["mo"] = {"Moldovan"}, -- Moldavian (deprecated code); to match en.wiki article title
["fr-ca"] = "Quebec French",
["oc-provenc"] = {"Provençal"},
["fr-gallo"] = "Gallo",
["ps"] = {"Pashto"}, -- Pushto
["fy"] = "West Frisian", -- Western Frisian
["tw-asante"] = {"Asante Twi"},
["mo"] = "Moldovan", -- Moldavian (deprecated code); to match en.wiki article title
["nl-be"] = "Flemish", -- match MediaWiki
["oc-gascon"] = "Gascon",
["oc-provenc"] = "Provençal",
["ps"] = "Pashto", -- Pushto
["pt-br"] = "Brazilian Portuguese", -- match MediaWiki
["ro-md"] = "Moldovan", -- 'not deprecated' form
["ro-cyrl-md"] = "Moldovan", -- 'not deprecated' form
["tw-asante"] = "Asante Twi",
["ug"] = "Uyghur", -- 2nd IANA name; to match en.wiki article name


-- these ISO 639-1 language-name overrides imported from Module:Language/data/wp_languages
-- these ISO 639-1 language-name overrides imported from Module:Language/data/wp_languages (since deleted)
--<begin do-not-edit except to comment out>--
--<begin do-not-edit except to comment out>--
["av"] = {"Avar"}, -- Avaric
["av"] = "Avar", -- Avaric
["bo"] = {"Standard Tibetan"}, -- Tibetan
["bo"] = "Standard Tibetan", -- Tibetan
["el"] = {"Greek"}, -- Modern Greek
["el"] = "Greek", -- Modern Greek
-- ["en-SA"] = {"South African English"}, -- English; no; SA is not South Africa it Saudi Arabia; ZA is South Africa
-- ["en-SA"] = "South African English", -- English; no; SA is not South Africa it Saudi Arabia; ZA is South Africa
["ff"] = {"Fula"}, -- Fulah
["ff"] = "Fula", -- Fulah
["ht"] = {"Haitian Creole"}, -- Haitian
["ht"] = "Haitian Creole", -- Haitian
["hz"] = {"Otjiherero"}, -- Herero
["hz"] = "Otjiherero", -- Herero
["ii"] = {"Yi"}, -- Sichuan Yi
["ii"] = "Yi", -- Sichuan Yi
["ki"] = {"Gikuyu"}, -- Kikuyu
["ki"] = "Gikuyu", -- Kikuyu
["kl"] = {"Greenlandic"}, -- Kalaallisut
["kl"] = "Greenlandic", -- Kalaallisut
["ky"] = {"Kyrgyz"}, -- Kirghiz
["ky"] = "Kyrgyz", -- Kirghiz
["lg"] = {"Luganda"}, -- Ganda
["lg"] = "Luganda", -- Ganda
["li"] = {"Limburgish"}, -- Limburgan
["li"] = "Limburgish", -- Limburgan
["mi"] = {"Māori"}, -- Maori
["mi"] = "Māori", -- Maori
["na"] = {"Nauruan"}, -- Nauru
["na"] = "Nauruan", -- Nauru
["nb"] = {"Bokmål"}, -- Norwegian Bokmål
["nb"] = "Bokmål", -- Norwegian Bokmål
["nd"] = {"Northern Ndebele"}, -- North Ndebele
["nd"] = "Northern Ndebele", -- North Ndebele
["nn"] = {"Nynorsk"}, -- Norwegian Nynorsk
["nn"] = "Nynorsk", -- Norwegian Nynorsk
["nr"] = {"Southern Ndebele"}, -- South Ndebele
["nr"] = "Southern Ndebele", -- South Ndebele
["ny"] = {"Chichewa"}, -- Nyanja
["ny"] = "Chichewa", -- Nyanja
["oj"] = {"Ojibwe"}, -- Ojibwa
["oj"] = "Ojibwe", -- Ojibwa
["or"] = {"Odia"}, -- Oriya
["or"] = "Odia", -- Oriya
["pa"] = {"Punjabi"}, -- Panjabi
["pa"] = "Punjabi", -- Panjabi
["rn"] = {"Kirundi"}, -- Rundi
["rn"] = "Kirundi", -- Rundi
["sl"] = {"Slovene"}, -- Slovenian
["sl"] = "Slovene", -- Slovenian
["ss"] = {"Swazi"}, -- Swati
["ss"] = "Swazi", -- Swati
["st"] = {"Sotho"}, -- Southern Sotho
["st"] = "Sotho", -- Southern Sotho
["to"] = {"Tongan"}, -- Tonga
["to"] = "Tongan", -- Tonga
--<end do-not-edit except to comment out>--
--<end do-not-edit except to comment out>--


Line 123: Line 182:
------------------------------< I S O _ 6 3 9 - 2,  - 3,  - 5 >----------------------------------------------
------------------------------< I S O _ 6 3 9 - 2,  - 3,  - 5 >----------------------------------------------


["arc"] = {"Aramaic"}, -- Official Aramaic (700-300 BCE), Imperial Aramaic (700-300 BCE);
["alv"] = "Atlantic–Congo languages", -- to match en.wiki article title (endash)
["art"] = {"constructed"}, -- to match en.wiki article; lowercase for category name
["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
["bhd"] = {"Bhadarwahi"}, -- Bhadrawahi; to match en.wiki article title
["art"] = "constructed", -- to match en.wiki article; lowercase for category name
["bla"] = {"Blackfoot"}, -- Siksika; to match en.wiki article title
["ast-es"] = "Leonese", -- ast in IANA is Asturian; Leonese is a dialect
["bua"] = {"Buryat"}, -- Buriat; this is a macro language; these four use wp preferred transliteration;
["bea"] = "Dane-zaa", -- Beaver; to match en.wiki article title
["bxm"] = {"Mongolian Buryat"}, -- Mongolia Buriat; these three all redirect to Buryat
["bha"] = "Bhariati", -- Bharia; to match en.wiki article title
["bxr"] = {"Russian Buryat"}, -- Russia Buriat;
["bhd"] = "Bhadarwahi", -- Bhadrawahi; to match en.wiki article title
["bxu"] = {"Chinese Buryat"}, -- China Buriat;
["bla"] = "Blackfoot", -- Siksika; to match en.wiki article title
["byr"] = {"Yipma"}, -- Baruya, Yipma
["blc"] = "Nuxalk", -- Bella Coola; to match en.wiki article title
["egy"] = {"Ancient Egyptian"}, -- Egyptian (Ancient); distinguish from contemporary arz: Egyptian Arabic  
["bua"] = "Buryat", -- Buriat; this is a macro language; these four use wp preferred transliteration;
["frr"] = {"North Frisian"}, -- Northern Frisian
["bxm"] = "Mongolian Buryat", -- Mongolia Buriat; these three all redirect to Buryat
["frs"] = {"East Frisian Low Saxon"}, -- Eastern Frisian
["bxr"] = "Russian Buryat", -- Russia Buriat;
["ilo"] = {"Ilocano"}, -- Iloko; to match en.wiki article title
["bxu"] = "Chinese Buryat", -- China Buriat;
["jam"] = {"Jamaican Patois"}, -- Jamaican Creole English
["byr"] = "Yipma", -- Baruya, Yipma
["mhr"] = {"Meadow Mari"}, -- Eastern Mari
["clm"] = "Klallam", -- Clallam; to match en.wiki article title
["mid"] = {"Modern Mandaic"}, -- Mandaic
["egy"] = "Ancient Egyptian", -- Egyptian (Ancient); distinguish from contemporary arz: Egyptian Arabic  
["mla"] = {"Tamambo"}, -- Malo
["ems"] = "Alutiiq", -- Pacific Gulf Yupik; to match en.wiki article title
['mte'] = {"Mono-Alu"}, -- Mono (Solomon Islands)
["esx"] = "Eskimo–Aleut languages", -- to match en.wiki article title (endash)
["nan-tw"] = {"Taiwanese Hokkien"}, -- make room for IANA / 639-3 nan Min Nan Chinese; match en.wiki article title
["frr"] = "North Frisian", -- Northern Frisian
["nrf"] = {"Norman"}, -- not quite a collective - IANA name: Jèrriais; categorizes to Norman-language text
["frs"] = "East Frisian Low Saxon", -- Eastern Frisian
["nzi"] = {"Nzema"}, -- Nzima; to match en.wiki article title
["gsw-fr"] = "Alsatian", -- match MediaWiki
["orv"] = {"Old East Slavic"}, -- Old Russian
["haa"] = "Hän", -- Han; to match en.wiki article title
["pfl"] = {"Palatine German"}, -- Pfaelzisch; to match en.wiki article
["hei"] = "Heiltsuk–Oowekyala", -- Heiltsuk; to match en.wiki article title
["pms"] = {"Piedmontese"}, -- Piemontese; to match en.wiki article title
["hmx"] = "Hmong–Mien languages", -- to match en.wiki article title (endash)
["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()
["ilo"] = "Ilocano", -- Iloko; to match en.wiki article title
["stq"] = {"Saterland Frisian"}, -- Saterfriesisch
["jam"] = "Jamaican Patois", -- Jamaican Creole English
["und"] = {"undetermined"}, -- capitalization to match existing category
["lij-mc"] = "Monégasque", -- Ligurian as spoken in Monaco; this one for proper tool tip; also in <article_name> table
["wrg"] = {"Warrongo"}, -- Warungu
["luo"] = "Dholuo", -- IANA (primary) /ISO 639-3: Luo (Kenya and Tanzania); IANA (secondary): Dholuo
["xal-ru"] = {"Kalmyk"}, -- to match en.wiki article title
["mhr"] = "Meadow Mari", -- Eastern Mari
["xgf"] = {"Tongva"}, -- ISO 639-3 is Gabrielino-Fernandeño
["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()
['qwm'] = "Cuman", -- Kuman (Russia); to match en.wiki article name
["rop"] = "Australian Kriol", -- Kriol; en.wiki article is a dab; point to correct en.wiki article
["sco-ulster"] = "Ulster Scots",
["sdo"] = "Bukar–Sadong", -- Bukar-Sadung Bidayuh; to match en.wiki article title
["smp"] = "Samaritan Hebrew", -- 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
-- these ISO 639-2, -3 language-name overrides imported from Module:Language/data/wp_languages (since deleted)
--<begin do-not-edit except to comment out>--
--<begin do-not-edit except to comment out>--
["ace"] = {"Acehnese"}, -- Achinese
["ace"] = "Acehnese", -- Achinese
["aec"] = {"Sa'idi Arabic"}, -- Saidi Arabic
["aec"] = "Sa'idi Arabic", -- Saidi Arabic
["akl"] = {"Aklan"}, -- Aklanon
["akl"] = "Aklan", -- Aklanon
["alt"] = {"Altay"}, -- Southern Altai
["alt"] = "Altay", -- Southern Altai
["apm"] = {"Mescalero-Chiricahua"}, -- Mescalero-Chiricahua Apache
["apm"] = "Mescalero-Chiricahua", -- Mescalero-Chiricahua Apache
["bal"] = {"Balochi"}, -- Baluchi
["bal"] = "Balochi", -- Baluchi
["bcl"] = {"Central Bicolano"}, -- Central Bikol
-- ["bcl"] = "Central Bicolano", -- Central Bikol
["bin"] = {"Edo"}, -- Bini
["bin"] = "Edo", -- Bini
["bpy"] = {"Bishnupriya Manipuri"}, -- Bishnupriya
["bpy"] = "Bishnupriya Manipuri", -- Bishnupriya
["chg"] = {"Chagatay"}, -- Chagatai
["chg"] = "Chagatay", -- Chagatai
["ckb"] = {"Sorani Kurdish"}, -- Central Kurdish
["ckb"] = "Sorani Kurdish", -- Central Kurdish
["cnu"] = {"Shenwa"}, -- Chenoua
["cnu"] = "Shenwa", -- Chenoua
["coc"] = {"Cocopah"}, -- Cocopa
["coc"] = "Cocopah", -- Cocopa
["diq"] = {"Zazaki"}, -- Dimli
["diq"] = "Zazaki", -- Dimli
["fit"] = {"Meänkieli"}, -- Tornedalen Finnish
["fit"] = "Meänkieli", -- Tornedalen Finnish
["fkv"] = {"Kven"}, -- Kven Finnish
["fkv"] = "Kven", -- Kven Finnish
["frk"] = {"Old Frankish"}, -- Frankish
["frk"] = "Old Frankish", -- Frankish
["gez"] = {"Ge'ez"}, -- Geez
["gez"] = "Ge'ez", -- Geez
["gju"] = {"Gujari"}, -- Gujari
["gju"] = "Gujari", -- Gujari
["gsw"] = {"Alemannic German"}, -- Swiss German
["gsw"] = "Alemannic German", -- Swiss German
["gul"] = {"Gullah"}, -- Sea Island Creole English
["gul"] = "Gullah", -- Sea Island Creole English
["hak"] = {"Hakka"}, -- Hakka Chinese
["hak"] = "Hakka", -- Hakka Chinese
["hbo"] = {"Biblical Hebrew"}, -- Ancient Hebrew
["hbo"] = "Biblical Hebrew", -- Ancient Hebrew
["hnd"] = {"Hindko"}, -- Southern Hindko
["hnd"] = "Hindko", -- Southern Hindko
-- ["ikt"] = {"Inuvialuk"}, -- Inuinnaqtun
-- ["ikt"] = "Inuvialuk", -- Inuinnaqtun
["kaa"] = {"Karakalpak"}, -- Kara-Kalpak
["kaa"] = "Karakalpak", -- Kara-Kalpak
["khb"] = {"Tai Lü"}, -- Lü
["khb"] = "Tai Lü", -- Lü
["kmr"] = {"Kurmanji Kurdish"}, -- Northern Kurdish
["kmr"] = "Kurmanji Kurdish", -- Northern Kurdish
["kpo"] = {"Kposo"}, -- Ikposo
["kpo"] = "Kposo", -- Ikposo
["krj"] = {"Kinaray-a"}, -- Kinaray-A
["krj"] = "Kinaray-a", -- Kinaray-A
["ktz"] = {"Juǀ'hoan"}, -- Juǀʼhoan
-- ["ktz"] = "Juǀ'hoan", -- Juǀʼhoan
["lez"] = {"Lezgian"}, -- Lezghian
["lez"] = "Lezgian", -- Lezghian
["liv"] = {"Livonian"}, -- Liv
["liv"] = "Livonian", -- Liv
["lng"] = {"Lombardic"}, -- Langobardic
["lng"] = "Lombardic", -- Langobardic
["mia"] = {"Miami-Illinois"}, -- Miami
["mia"] = "Miami-Illinois", -- Miami
["miq"] = {"Miskito"}, -- Mískito
["miq"] = "Miskito", -- Mískito
["mix"] = {"Mixtec"}, -- Mixtepec Mixtec
["mix"] = "Mixtec", -- Mixtepec Mixtec
["mni"] = {"Meitei"}, -- Manipuri
["mni"] = "Meitei", -- Manipuri
["mrj"] = {"Hill Mari"}, -- Western Mari
["mrj"] = "Hill Mari", -- Western Mari
["mww"] = {"White Hmong"}, -- Hmong Daw
["mww"] = "White Hmong", -- Hmong Daw
["nds-nl"] = {"Dutch Low Saxon"}, -- Low German
["nds-nl"] = "Dutch Low Saxon", -- Low German
["new"] = {"Nepal Bhasa"}, -- Newari
-- ["new"] = "Nepal Bhasa", -- Newari
["nso"] = {"Northern Sotho"}, -- Pedi
["nso"] = "Northern Sotho", -- Pedi
["nwc"] = {"Classical Nepal Bhasa"}, -- Classical Newari
-- ["nwc"] = "Classical Nepal Bhasa", -- Classical Newari, Classical Nepal Bhasa, Old Newari
["ood"] = {"O'odham"}, -- Tohono O'odham
["ood"] = "O'odham", -- Tohono O'odham
["otk"] = {"Old Turkic"}, -- Old Turkish
["otk"] = "Old Turkic", -- Old Turkish
["pal"] = {"Middle Persian"}, -- Pahlavi
["pal"] = "Middle Persian", -- Pahlavi
["pam"] = {"Kapampangan"}, -- Pampanga
["pam"] = "Kapampangan", -- Pampanga
["phr"] = {"Potwari"}, -- Pahari-Potwari
["phr"] = "Potwari", -- Pahari-Potwari
["pka"] = {"Jain Prakrit"}, -- Ardhamāgadhī Prākrit
["pka"] = "Jain Prakrit", -- Ardhamāgadhī Prākrit
-- ["pnb"] = {"Punjabi"}, -- Western Panjabi
-- ["pnb"] = "Punjabi", -- Western Panjabi
["psu"] = {"Shauraseni"}, -- Sauraseni Prākrit
["psu"] = "Shauraseni", -- Sauraseni Prākrit
["rap"] = {"Rapa Nui"}, -- Rapanui
["rap"] = "Rapa Nui", -- Rapanui
["rar"] = {"Cook Islands Māori"}, -- Rarotongan
["rar"] = "Cook Islands Māori", -- Rarotongan
["rmu"] = {"Scandoromani"}, -- Tavringer Romani
["rmu"] = "Scandoromani", -- Tavringer Romani
["rom"] = {"Romani"}, -- Romany
["rom"] = "Romani", -- Romany
["rup"] = {"Aromanian"}, -- Macedo-Romanian
["rup"] = "Aromanian", -- Macedo-Romanian
["ryu"] = {"Okinawan"}, -- Central Okinawan
["ryu"] = "Okinawan", -- Central Okinawan
["sdc"] = {"Sassarese"}, -- Sassarese Sardinian
["sdc"] = "Sassarese", -- Sassarese Sardinian
["sdn"] = {"Gallurese"}, -- Gallurese Sardinian
["sdn"] = "Gallurese", -- Gallurese Sardinian
["shp"] = {"Shipibo"}, -- Shipibo-Conibo
["shp"] = "Shipibo", -- Shipibo-Conibo
["src"] = {"Logudorese"}, -- Logudorese Sardinian
["src"] = "Logudorese", -- Logudorese Sardinian
["sro"] = {"Campidanese"}, -- Campidanese Sardinian
["sro"] = "Campidanese", -- Campidanese Sardinian
["tkl"] = {"Tokelauan"}, -- Tokelau
["tkl"] = "Tokelauan", -- Tokelau
["tvl"] = {"Tuvaluan"}, -- Tuvalu
["tvl"] = "Tuvaluan", -- Tuvalu
["tyv"] = {"Tuvan"}, -- Tuvinian
["tyv"] = "Tuvan", -- Tuvinian
["vls"] = {"West Flemish"}, -- Vlaams
["vls"] = "West Flemish", -- Vlaams
["wep"] = {"Westphalian"}, -- Westphalien
["wep"] = "Westphalian", -- Westphalien
["xal"] = {"Oirat"}, -- Kalmyk
["xal"] = "Oirat", -- Kalmyk
["xcl"] = {"Old Armenian"}, -- Classical Armenian
["xcl"] = "Old Armenian", -- Classical Armenian
["yua"] = {"Yucatec Maya"}, -- Yucateco
["yua"] = "Yucatec Maya", -- Yucateco
--<end do-not-edit except to comment out>--
--<end do-not-edit except to comment out>--


Line 232: Line 322:
------------------------------< P R I V A T E _ U S E _ T A G S >----------------------------------------------
------------------------------< P R I V A T E _ U S E _ T A G S >----------------------------------------------


["cel-x-proto"] = {"Proto-Celtic"}, -- cel in IANA is Celtic languages
["akk-x-latbabyl"] = "Late Babylonian Akkadian",
["gem-x-proto"] = {"Proto-Germanic"}, -- gem in IANA is Germanic languages
["akk-x-midassyr"] = "Middle Assyrian Akkadian",
["gmw-x-ecg"] = {"East Central German"},
["akk-x-midbabyl"] = "Middle Babylonian Akkadian",
["grc-x-aeolic"] = {"Aeolic Greek"}, -- these grc-x-... codes are preferred alternates to the non-standard catchall code grc-gre
["akk-x-neoassyr"] = "Neo-Assyrian Akkadian",
["grc-x-attic"] = {"Attic Greek"},
["akk-x-neobabyl"] = "Neo-Babylonian Akkadian",
["grc-x-biblical"] = {"Biblical Greek"},
["akk-x-old"] = "Old Akkadian",
["grc-x-byzant"] = {"Byzantine Greek"},
["akk-x-oldassyr"] = "Old Assyrian Akkadian",
["grc-x-classic"] = {"Classical Greek"},
["akk-x-oldbabyl"] = "Old Babylonian Akkadian",
["grc-x-doric"] = {"Doric Greek"},
["alg-x-proto"] = "Proto-Algonquian", -- alg in IANA is Algonquian languages
["grc-x-hellen"] = {"Hellenistic Greek"},
["ca-x-old"] = "Old Catalan",
["grc-x-ionic"] = {"Ionic Greek"},
["cel-x-combrit"] = "Common Brittonic", -- cel in IANA is Celtic languages
["grc-x-koine"] = {"Koinē Greek"},
["cel-x-proto"] = "Proto-Celtic",
["grc-x-medieval"] = {"Medieval Greek"},
["egy-x-demotic"] = "Demotic Egyptian",
["grc-x-patris"] = {"Patristic Greek"},
["egy-x-late"] = "Late Egyptian",
["grk-x-proto"] = {"Proto-Greek"}, -- grk in IANA is Greek languages
["egy-x-middle"] = "Middle Egyptian",
["iir-x-proto"] = {"Proto-Indo-Iranian"}, -- iir in IANA is Indo-Iranian Languages
["egy-x-old"] = "Old Egyptian",
["ine-x-proto"] = {"Proto-Indo-European"},
["gem-x-proto"] = "Proto-Germanic", -- gem in IANA is Germanic languages
["ira-x-proto"] = {"Proto-Iranian"}, -- ira in IANA is Iranian languages
["gmw-x-ecg"] = "East Central German",
["itc-x-proto"] = {"Proto-Italic"}, -- itc in IANA is Italic languages
["grc-x-aeolic"] = "Aeolic Greek", -- these grc-x-... codes are preferred alternates to the non-standard catchall code grc-gre
["ksh-x-colog"] = {"Colognian"}, -- en.wiki article is Colognian; ksh (Kölsch) redirects there
["grc-x-attic"] = "Attic Greek",
["mis-x-ripuar"] = {"Ripuarian"}, -- replaces improper use of ksh in wp_languages
["grc-x-biblical"] = "Biblical Greek",
["sem-x-proto"] = {"Proto-Semitic"},
["grc-x-byzant"] = "Byzantine Greek",
["sla-x-proto"] = {"Proto-Slavic"}, -- sla in IANA is Slavic languages
["grc-x-classic"] = "Classical Greek",
["yuf-x-hav"] = {"Havasupai"}, -- IANA name for these three is Havasupai-Walapai-Yavapai
["grc-x-doric"] = "Doric Greek",
["yuf-x-wal"] = {"Walapai"},
["grc-x-hellen"] = "Hellenistic Greek",
["yuf-x-yav"] = {"Yavapai"},
["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
["inc-x-mitanni"] = "Mitanni-Aryan", -- inc in IANA is Indic languages
["inc-x-proto"] = "Proto-Indo-Aryan",
["ine-x-anatolia"] = "Anatolian 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-berg"] = "Bergamasque", -- 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"] = "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",
["xsc-x-pontic"] = "Pontic Scythian", -- xsc in IANA is Scythian
["xsc-x-saka"] = "Saka",
["xsc-x-sarmat"] = "Sarmatian",
}
}


Line 263: Line 389:
--[[--------------------------< A R T I C L E _ L I N K >------------------------------------------------------
--[[--------------------------< 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
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
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
that is the long-standing method of handling article names that don't fit with the normal pattern
Line 270: Line 396:


local article_name = {
local article_name = {
["lij"] = {"Ligurian (Romance language)"}, -- Ligurian; see Template_talk:Lang#Ligurian_dab
['kue'] = "Kuman language (New Guinea)", -- Kuman (Papua New Guinea); to avoid Kuman dab page
['mnh'] = {"Mono language (Congo)"}, -- Mono (Democratic Republic of Congo); see Template_talk:Lang#Mono_languages
["lij-mc"] = "Monégasque dialect", -- Ligurian as spoken in Monaco
['mnr'] = {"Mono language (California)"}, -- Mono (USA)
['mbo'] = "Mbo language (Cameroon)", -- Mbo (Cameroon)
['mru'] = {"Mono language (Cameroon)"}, -- Mono (Cameroon)
['mnh'] = "Mono language (Congo)", -- Mono (Democratic Republic of Congo); see Template_talk:Lang#Mono_languages
["xlg"] = {"Ligurian (ancient language)"}, -- see Template_talk:Lang#Ligurian_dab
['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)
}
}


Line 394: Line 526:
['zh'] = 'ISO 7098 Chinese',
['zh'] = 'ISO 7098 Chinese',
['chi'] = 'ISO 7098 Chinese',
['chi'] = 'ISO 7098 Chinese',
['pny'] = 'ISO 7098 Chinese',
['cmn'] = 'ISO 7098 Chinese',
['zho'] = 'ISO 7098 Chinese',
['zho'] = 'ISO 7098 Chinese',
-- ['han'] = 'ISO 7098 Chinese', -- unicode alias of Hani? doesn't belong here? should be Hani?
-- ['han'] = 'ISO 7098 Chinese', -- unicode alias of Hani? doesn't belong here? should be Hani?
Line 421: Line 553:
['gu'] = 'ISO 15919 Indic',
['gu'] = 'ISO 15919 Indic',
['hi'] = 'ISO 15919 Indic',
['hi'] = 'ISO 15919 Indic',
['hno'] = 'ISO 15919 Indic',
['inc'] = 'ISO 15919 Indic',
['inc'] = 'ISO 15919 Indic',
['kn'] = 'ISO 15919 Indic',
['kn'] = 'ISO 15919 Indic',
Line 433: Line 566:
['or'] = 'ISO 15919 Indic',
['or'] = 'ISO 15919 Indic',
['pa'] = 'ISO 15919 Indic',
['pa'] = 'ISO 15919 Indic',
['pnb'] = 'ISO 15919 Indic',
['raj'] = 'ISO 15919 Indic',
['raj'] = 'ISO 15919 Indic',
['sa'] = 'ISO 15919 Indic',
['sa'] = 'ISO 15919 Indic',
Line 438: Line 572:
['sd'] = 'ISO 15919 Indic',
['sd'] = 'ISO 15919 Indic',
['si'] = 'ISO 15919 Indic',
['si'] = 'ISO 15919 Indic',
['skr'] = 'ISO 15919 Indic',
['ta'] = 'ISO 15919 Indic',
['ta'] = 'ISO 15919 Indic',
['tcy'] = 'ISO 15919 Indic',
['tcy'] = 'ISO 15919 Indic',
Line 458: Line 593:
['jyutping'] = {
['jyutping'] = {
['default'] = 'Jyutping transliteration',
['default'] = 'Jyutping transliteration',
},
['mlcts'] = {
['default'] = 'Myanmar Language Commission Transcription System',
},
},


Line 489: Line 628:
['satts'] = {
['satts'] = {
['default'] = 'Standard Arabic Technical Transliteration System transliteration',
['default'] = 'Standard Arabic Technical Transliteration System transliteration',
},
['scientific'] = {
['default'] = 'scientific transliteration',
},
['ukrainian'] = {
['default'] = 'Ukrainian National system of romanization',
},
},


Line 502: Line 649:
['default'] = 'Hans Wehr transliteration',
['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'] = 'romanisation', -- lower case
['romanisz_uc'] = 'Romanisation', -- upper case
['romanisz_pt'] = 'romanised', -- past tense
},
['us_t'] = { -- default engvar
['romanisz_lc'] = 'romanization', -- lower case
['romanisz_uc'] = 'Romanization', -- upper case
['romanisz_pt'] = 'romanized', -- past tense
}
}
--[[--------------------------< E X P O R T S >----------------------------------------------------------------
]]


return
return
{
{
this_wiki_lang_tag = this_wiki_lang_tag,
this_wiki_lang_dir = lang_obj:getDir(), -- wiki's language direction
article_name = article_name,
article_name = article_name,
lang_name_table = lang_name_table,
engvar_t = engvar_t,
engvar_sel_t = engvar_sel_t,
lang_name_table = lang_name_table_t,
override = override,
override = override,
rtl_scripts = rtl_scripts,
rtl_scripts = rtl_scripts,
special_tags_table = special_tags_table,
translit_title_table = translit_title_table,
translit_title_table = translit_title_table,
};
};
Retrieved from "https://safernicotine.wiki/mediawiki/index.php/Module:Lang/data"