Seeds of the Word

Module:Lang/data: Difference between revisions

Module Discussion

Module:Lang/data (view source)

Revision as of 10:57, October 4, 2020

6,461 bytes added ,  3 years ago
+art;
m (1 revision imported)
(+art;)
Line 1: Line 1:
local lang_data = {};
--[[--------------------------< 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.
 
TODO: instead of returning:
["key"] = {"name"}
where each table has only one name, return
["key"] = "name"
requires changes in Module:Lang.
 
]]
 
local function key_to_lower (module, src_type)
local out = {};
local source = (('variants' == src_type) and require (module)) or mw.loadData (module); -- fetch data from this module; require() avoids metatable trap for variant data
if 'variants' == src_type then
for k, v in pairs (source) do
out[k:lower()] = v; -- for variant, 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 = {
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', 'variants'),
suppressed = key_to_lower ('Module:Language/data/iana suppressed scripts'), -- script keys are capitalized; set to lower
}




--[[--------------------------< O V E R R I D E >--------------------------------------------------------------
--[[--------------------------< O V E R R I D E >--------------------------------------------------------------


Language codes and names in this table override the BCP47 names in Module:Language/name/data.
Language codes and names in this table override the BCP47 names in lang_name_table.
 
indexes in this table shall always be lower case


code indexes in this table shall always be lower case
]]
]]


local override = {
local override = {
-- ISO 639-1 codes
------------------------------< I S O  6 3 9 - 1 >------------------------------------------------------------
["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
["ca-valencia"] = {"Valencian"},
["ca-valencia"] = {"Valencian"},
["cu"] = {"Church Slavonic"}, -- 2nd IANA name;
["cu"] = {"Church Slavonic"}, -- 2nd IANA name;
["de-at"] = {"Austrian German"}, -- these code-region and code-variant to match en.wiki article names
["de-at"] = {"Austrian German"}, -- these code-region and code-variant tags to match en.wiki article names
["de-ch"] = {"Swiss Standard German"},
["de-ch"] = {"Swiss Standard German"},
["en-au"] = {"Australian English"},
["en-au"] = {"Australian English"},
Line 26: Line 82:
["en-us"] = {"American English"},
["en-us"] = {"American English"},
["en-za"] = {"South African English"},
["en-za"] = {"South African English"},
["fy"] = {"West Frisian"}, -- IANA name is Western Frisian
["fy"] = {"West Frisian"}, -- Western Frisian
["ps"] = {"Pashto"}, -- IANA name is Pushto
["mo"] = {"Moldovan"}, -- Moldavian (deprecated code); to match en.wiki article title
["si"] = {"Sinhala"}, -- IANA name is Sinhala, Sinhalese; override wp_languages {"Sinhalese"}; see Module talk:Language/data/wp languages#Request to undo an edit
["oc-provenc"] = {"Provençal"},
["ps"] = {"Pashto"}, -- Pushto
["tw-asante"] = {"Asante Twi"},
["tw-asante"] = {"Asante Twi"},
["sr-cyrl"] = {"Serbian"}, -- override wp_languages Serbian Cyrillic; to achieve this, use |label=


-- ISO 639-2, -3 codes
-- these ISO 639-1 language-name overrides imported from Module:Language/data/wp_languages
["arc"] = {"Aramaic"}, -- IANA names are: Official Aramaic (700-300 BCE), Imperial Aramaic (700-300 BCE);
--<begin do-not-edit except to comment out>--
["ber"] = {"Berber languages"}, -- ISO 639-2 collective; defined here to override redefinition in wp_languages
["av"] = {"Avar"}, -- Avaric
["bhd"] = {"Bhadarwahi"}, -- IANA, ISO 639-3 name is Bhadrawahi; to match en.wiki article title
["bo"] = {"Standard Tibetan"}, -- Tibetan
["bla"] = {"Blackfoot"}, -- IANA, ISO 639-2, -3 name is Siksika; to match en.wiki article title
["el"] = {"Greek"}, -- Modern Greek
["bua"] = {"Buryat"}, -- IANA name Buriat; this is a macro language; these four use wp preferred transliteration;
-- ["en-SA"] = {"South African English"}, -- English; no; SA is not South Africa it Saudi Arabia;  ZA is South Africa
["bxm"] = {"Mongolian Buryat"}, -- IANA name Mongolia Buriat; these three all redirect to Buryat
["ff"] = {"Fula"}, -- Fulah
["bxr"] = {"Russian Buryat"}, -- IANA name Russia Buriat;
["ht"] = {"Haitian Creole"}, -- Haitian
["bxu"] = {"Chinese Buryat"}, -- IANA name China Buriat;
["hz"] = {"Otjiherero"}, -- Herero
["byr"] = {"Yipma"}, -- IANA names are Baruya and Yipma
["ii"] = {"Yi"}, -- Sichuan Yi
["cel"] = {"Celtic languages"}, -- ISO 639-2 collective; defined here to override improper redefinition ('Proto-Celtic') in wp_languages; use cel-x-proto instead
["ki"] = {"Gikuyu"}, -- Kikuyu
["egy"] = {"Ancient Egyptian"}, -- IANA name is Egyptian (Ancient); distinguish from contemporary arz: Egyptian Arabic  
["kl"] = {"Greenlandic"}, -- Kalaallisut
["frr"] = {"North Frisian"}, -- IANA name is Northern Frisian
["ky"] = {"Kyrgyz"}, -- Kirghiz
["frs"] = {"East Frisian Low Saxon"}, -- IANA name is Eastern Frisian
["lg"] = {"Luganda"}, -- Ganda
["gem"] = {"Germanic languages"}, -- ISO 639-2 collective; defined here to override improper redefinition ('Proto-Germanic') in wp_languages; use gem-x-proto instead
["li"] = {"Limburgish"}, -- Limburgan
["ilo"] = {"Ilocano"}, -- IANA, ISO 639-2, -3 name is Iloko; to match en.wiki article title
["mi"] = {"Māori"}, -- Maori
["jam"] = {"Jamaican Patois"}, -- IANA name is Jamaican Creole English
["na"] = {"Nauruan"}, -- Nauru
["mhr"] = {"Meadow Mari"}, -- IANA name is Eastern Mari
["nb"] = {"Bokmål"}, -- Norwegian Bokmål
["mid"] = {"Modern Mandaic"}, -- IANA name is Mandaic
["nd"] = {"Northern Ndebele"}, -- North Ndebele
["mla"] = {"Tamambo"}, -- wp_languages name is Medieval Latin; IANA and ISO 639-1 name is Malo
["nn"] = {"Nynorsk"}, -- Norwegian Nynorsk
["myn"] = {"Mayan languages"}, -- ISO 639-2 collective; defined here to override redefinition in wp_languages
["nr"] = {"Southern Ndebele"}, -- South Ndebele
["nah"] = {"Nahuatl languages"}, -- ISO 639-2 collective; defined here to override redefinition in wp_languages
["ny"] = {"Chichewa"}, -- Nyanja
["oj"] = {"Ojibwe"}, -- Ojibwa
["or"] = {"Odia"}, -- Oriya
["pa"] = {"Punjabi"}, -- Panjabi
["rn"] = {"Kirundi"}, -- Rundi
["sl"] = {"Slovene"}, -- Slovenian
["ss"] = {"Swazi"}, -- Swati
["st"] = {"Sotho"}, -- Southern Sotho
["to"] = {"Tongan"}, -- Tonga
--<end do-not-edit except to comment out>--
 
 
------------------------------< I S O  6 3 9 - 2,   - 3,  - 5 >----------------------------------------------
 
["arc"] = {"Aramaic"}, -- Official Aramaic (700-300 BCE), Imperial Aramaic (700-300 BCE);
["art"] = {"constructed"}, -- to match en.wiki article; lowercase for category name
["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  
["frr"] = {"North Frisian"}, -- Northern Frisian
["frs"] = {"East Frisian Low Saxon"}, -- Eastern Frisian
["ilo"] = {"Ilocano"}, -- Iloko; to match en.wiki article title
["jam"] = {"Jamaican Patois"}, -- Jamaican Creole English
["mhr"] = {"Meadow Mari"}, -- Eastern Mari
["mid"] = {"Modern Mandaic"}, -- Mandaic
["mla"] = {"Tamambo"}, -- Malo
['mte'] = {"Mono-Alu"}, -- Mono (Solomon Islands)
["nan-tw"] = {"Taiwanese Hokkien"}, -- make room for IANA / 639-3 nan Min Nan Chinese; match en.wiki article title
["nan-tw"] = {"Taiwanese Hokkien"}, -- make room for IANA / 639-3 nan Min Nan Chinese; match en.wiki article title
["nrf"] = {"Norman"}, -- not quite a collective - IANA name: Jèrriais; categorizes to Norman-language text
["nrf"] = {"Norman"}, -- not quite a collective - IANA name: Jèrriais; categorizes to Norman-language text
["nzi"] = {"Nzema"}, -- IANA, ISO 639-2, -3 name is Nzima; to match en.wiki article title
["nzi"] = {"Nzema"}, -- Nzima; to match en.wiki article title
["orv"] = {"Old East Slavic"}, -- IANA name is Old Russian
["orv"] = {"Old East Slavic"}, -- Old Russian
["pfl"] = {"Palatine German"}, -- IANA name is Pfaelzisch; to match en.wiki article
["pfl"] = {"Palatine German"}, -- Pfaelzisch; to match en.wiki article
["pms"] = {"Piedmontese"}, -- IANA / 639-3 name is Piemontese; to match en.wiki article title
["pms"] = {"Piedmontese"}, -- Piemontese; to match en.wiki article title
["pra"] = {"Prakrit languages"}, -- ISO 639-2 collective; defined here to override redefinition in wp_languages
["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()
["roa"] = {"Romance languages"}, -- ISO 639-2 collective; defined here to override improper redefinition (Jèrriais) in wp_language; IANA name is "Romance languages"
["stq"] = {"Saterland Frisian"}, -- Saterfriesisch
["sal"] = {"Salishan languages"}, -- ISO 639-2 collective; defined here to override redefinition in wp_languages
["sla"] = {"Slavic languages"}, -- ISO 639-2 collective; defined here to override redefinition in wp_languages
["son"] = {"Songhai languages"}, -- ISO 639-2 collective; defined here to override redefinition in wp_languages
["stq"] = {"Saterland Frisian"}, -- IANA name is Saterfriesisch
["und"] = {"undetermined"}, -- capitalization to match existing category
["und"] = {"undetermined"}, -- capitalization to match existing category
["wen"] = {"Sorbian languages"}, -- ISO 639-2 collective; defined here to override redefinition in wp_languages
["wrg"] = {"Warrongo"}, -- Warungu
["wrg"] = {"Warrongo"}, -- IANA name is Warungu
["xal-ru"] = {"Kalmyk"}, -- to match en.wiki article title
["xal-ru"] = {"Kalmyk"}, -- to match en.wiki article title
["xgf"] = {"Tongva"}, -- ISO 639-3 is Gabrielino-Fernandeño
["xgf"] = {"Tongva"}, -- ISO 639-3 is Gabrielino-Fernandeño
 
-- private use codes
-- 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
["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 >----------------------------------------------
 
["cel-x-proto"] = {"Proto-Celtic"}, -- cel in IANA is Celtic languages
["cel-x-proto"] = {"Proto-Celtic"}, -- cel in IANA is Celtic languages
["gem-x-proto"] = {"Proto-Germanic"}, -- gem in IANA is Germanic languages
["gem-x-proto"] = {"Proto-Germanic"}, -- gem in IANA is Germanic languages
Line 108: Line 267:


local article_name = {
local article_name = {
["lij"] = {"Ligurian (Romance language)"}, -- see Template_talk:Lang#Ligurian_dab
["lij"] = {"Ligurian (Romance language)"}, -- Ligurian; see Template_talk:Lang#Ligurian_dab
['mnh'] = {"Mono language (Congo)"}, -- see Template_talk:Lang#Mono_languages
['mnh'] = {"Mono language (Congo)"}, -- Mono (Democratic Republic of Congo); see Template_talk:Lang#Mono_languages
['mnr'] = {"Mono language (California)"},
['mnr'] = {"Mono language (California)"}, -- Mono (USA)
['mru'] = {"Mono language (Cameroon)"},
['mru'] = {"Mono language (Cameroon)"}, -- Mono (Cameroon)
['mte'] = {"Mono-Alu language"},
["xlg"] = {"Ligurian (ancient language)"}, -- see Template_talk:Lang#Ligurian_dab
["xlg"] = {"Ligurian (ancient language)"}, -- see Template_talk:Lang#Ligurian_dab
}
}
Line 346: Line 504:
return
return
{
{
article_name = article_name,
lang_name_table = lang_name_table,
override = override,
override = override,
article_name = article_name,
rtl_scripts = rtl_scripts,
rtl_scripts = rtl_scripts,
translit_title_table = translit_title_table,
translit_title_table = translit_title_table,
};
};
Anonymous user
Retrieved from "https://en.seminaverbi.bibleget.io/wiki/Special:MobileDiff/24603"