پودمان:Lang/data
توضیحات این پودمان می‌تواند در پودمان:Lang/data/توضیحات قرار گیرد.
--[[--------------------------< 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 = (('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, 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', 'var_sup'),
suppressed = key_to_lower ('Module:Language/data/iana suppressed scripts', 'var_sup'), -- script keys are capitalized; set to lower
}
--[[--------------------------< 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 >------------------------------------------------------------
["ca-valencia"] = {"والنسیایی"},
["cu"] = {"اسلاوی کلیسایی"}, --2nd IANA name;
["de-at"] = {"آلمانی اتریشی"}, -- these code-region and code-variant tags to match en.wiki article names
["de-ch"] = {"آلمانی معیار سوئیس"},
["en-au"] = {"انگلیسی استرالیایی"},
["en-ca"] = {"انگلیسی کانادایی"},
["en-emodeng"] = {"انگلیسی نو نخستین"},
["en-gb"] = {"انگلیسی بریتانیایی"},
["en-ie"] = {"انگلیسی ایرلندی"},
["en-in"] = {"انگلیسی هندی"},
["en-nz"] = {"New Zealand English"}, -- no article yet
["en-us"] = {"انگلیسی آمریکایی"},
["en-za"] = {"South African English"}, -- no article yet
["fy"] = {"فریسی غربی"}, -- Western Frisian
["mo"] = {"مولداویایی"}, -- Moldavian (deprecated code); to match en.wiki article title
["oc-provenc"] = {"پرونسی"},
["ps"] = {"پشتو"}, -- Pushto
["tw-asante"] = {"Asante Twi"}, -- no article yet
-- these ISO 639-1 language-name overrides imported from Module:Language/data/wp_languages
--<begin do-not-edit except to comment out>--
["av"] = {"آواری"}, -- Avaric
["bo"] = {"تبتی معیار"}, -- Tibetan
["el"] = {"یونانی"}, -- Modern Greek
-- ["en-SA"] = {"South African English"}, -- English; no; SA is not South Africa it Saudi Arabia; ZA is South Africa
["ff"] = {"فولانی"}, -- Fulah
["ht"] = {"کریول آییسینی"}, -- Haitian
["hz"] = {"هررو"}, -- Herero
["ii"] = {"یی"}, -- Sichuan Yi
["ki"] = {"کیکویو"}, -- Kikuyu
["kl"] = {"گرینلندی"}, -- Kalaallisut
["ky"] = {"قرقیزی"}, -- Kirghiz
["lg"] = {"لوگاندا"}, -- Ganda
["li"] = {"لیمبورخی"}, -- Limburgan
["mi"] = {"مائوری"}, -- Maori
["na"] = {"نائورویی"}, -- Nauru
["nb"] = {"بوکمل"}, -- Norwegian Bokmål
["nd"] = {"اندبله شمالی"}, -- North Ndebele
["nn"] = {"نروژی نو"}, -- Norwegian Nynorsk
["nr"] = {"اندبله جنوبی"}, -- South Ndebele
["ny"] = {"چوایی"}, -- Nyanja
["oj"] = {"اوجیبوی"}, -- Ojibwa
["or"] = {"اوریه"}, -- Oriya
["pa"] = {"پنجابی"}, -- Panjabi
["rn"] = {"روندی"}, -- Rundi
["sl"] = {"اسلوونیایی"}, -- Slovenian
["ss"] = {"سوازی"}, -- Swati
["st"] = {"سوتو"}, -- Southern Sotho
["to"] = {"تونگایی"}, -- Tonga
--<end do-not-edit except to comment out>--
------------------------------< I S O 6 3 9 - 2, - 3, - 5 >----------------------------------------------
["arc"] = {"آرامی"}, -- Official Aramaic (700-300 BCE), Imperial Aramaic (700-300 BCE);
["art"] = {"فراساخته"}, -- 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"] = {"بوریاتی"}, -- Buriat; this is a macro language; these four use wp preferred transliteration;
["bxm"] = {"بوریاتی مغولی"}, -- Mongolia Buriat; these three all redirect to Buryat
["bxr"] = {"بوریاتی روسی"}, -- Russia Buriat;
["bxu"] = {"بوریاتی چینی"}, -- China Buriat;
["byr"] = {"Yipma"}, -- Baruya, Yipma
["egy"] = {"مصری باستان"}, -- Egyptian (Ancient); distinguish from contemporary arz: Egyptian Arabic
["frr"] = {"فریسی شمالی"}, -- Northern Frisian
["frs"] = {"East Frisian Low Saxon"}, -- Eastern Frisian
["ilo"] = {"ایلوکانو"}, -- Iloko; to match en.wiki article title
["jam"] = {"پتوای جامائیکایی"}, -- Jamaican Creole English
["mhr"] = {"ماری مرغزاری"}, -- Eastern Mari
["mid"] = {"مندائی مدرن"}, -- Mandaic
["mla"] = {"Tamambo"}, -- Malo
['mte'] = {"Mono-Alu"}, -- Mono (Solomon Islands)
["nan-tw"] = {"هاکین تایوانی"}, -- make room for IANA / 639-3 nan Min Nan Chinese; match en.wiki article title
["nrf"] = {"نورمان"}, -- not quite a collective - IANA name: Jèrriais; categorizes to Norman-language text
["nzi"] = {"Nzema"}, -- Nzima; to match en.wiki article title
["orv"] = {"اسلاوی شرقی باستان"}, -- Old Russian
["pfl"] = {"آلمانی پالاتن"}, -- Pfaelzisch; to match en.wiki article
["pms"] = {"پیدمونتی"}, -- Piemontese; to match en.wiki article title
["pnb"] = {"پنجابی (غربی)"}, -- Western Panjabi; dab added to override import from ~/wp languages and distinguish pnb from pa in reverse look up tag_from_name()
["stq"] = {"فریسی ساترلند"}, -- Saterfriesisch
["und"] = {"نامشخص"}, -- capitalization to match existing category
["wrg"] = {"Warrongo"}, -- Warungu
["xal-ru"] = {"قالمیق"}, -- to match en.wiki article title
["xgf"] = {"Tongva"}, -- ISO 639-3 is Gabrielino-Fernandeño
-- these ISO 639-2, -3 language-name overrides imported from Module:Language/data/wp_languages
--<begin do-not-edit except to comment out>--
["ace"] = {"آچه‌ای"}, -- Achinese
["aec"] = {"عربی صعیدی"}, -- Saidi Arabic
["akl"] = {"آکلانی"}, -- Aklanon
["alt"] = {"آلتای"}, -- Southern Altai
["apm"] = {"Mescalero-Chiricahua"}, -- Mescalero-Chiricahua Apache
["bal"] = {"بلوچی"}, -- Baluchi
["bcl"] = {"بیکول مرکزی"}, -- Central Bikol
["bin"] = {"ادو"}, -- Bini
["bpy"] = {"بیشنوپریا مانیپوری"}, -- Bishnupriya
["chg"] = {"جغتایی"}, -- Chagatai
["ckb"] = {"کردی سورانی"}, -- Central Kurdish
["cnu"] = {"Shenwa"}, -- Chenoua
["coc"] = {"Cocopah"}, -- Cocopa
["diq"] = {"زازاکی"}, -- Dimli
["fit"] = {"مینکیلی"}, -- Tornedalen Finnish
["fkv"] = {"کون"}, -- Kven Finnish
["frk"] = {"فرانکی باستان"}, -- Frankish
["gez"] = {"گعز"}, -- Geez
["gju"] = {"گوجری"}, -- Gujari
["gsw"] = {"آلمانیش"}, -- Swiss German
["gul"] = {"Gullah"}, -- Sea Island Creole English
["hak"] = {"هاکا"}, -- Hakka Chinese
["hbo"] = {"عبری توراتی"}, -- Ancient Hebrew
["hnd"] = {"هندکو"}, -- Southern Hindko
-- ["ikt"] = {"Inuvialuk"}, -- Inuinnaqtun
["kaa"] = {"قره‌قالپاقی"}, -- Kara-Kalpak
["khb"] = {"تای لو"}, -- Lü
["kmr"] = {"کردی کرمانجی"}, -- Northern Kurdish
["kpo"] = {"Kposo"}, -- Ikposo
["krj"] = {"Kinaray-a"}, -- Kinaray-A
["ktz"] = {"Juǀ'hoan"}, -- Juǀʼhoan
["lez"] = {"لزگی"}, -- Lezghian
["liv"] = {"لیوونیایی"}, -- Liv
["lng"] = {"Lombardic"}, -- Langobardic
["mia"] = {"میامی-ایلینوی"}, -- Miami
["miq"] = {"Miskito"}, -- Mískito
["mix"] = {"Mixtec"}, -- Mixtepec Mixtec
["mni"] = {"مانیپوری"}, -- Manipuri
["mrj"] = {"ماری تپه‌ای"}, -- Western Mari
["mww"] = {"همونگ سفید"}, -- Hmong Daw
["nds-nl"] = {"ساکسونی سفلای هلند"}, -- Low German
["new"] = {"نپال بهاسایی"}, -- Newari
["nso"] = {"سوتوی شمالی"}, -- Pedi
["nwc"] = {"Classical Nepal Bhasa"}, -- Classical Newari
["ood"] = {"اوئدام"}, -- Tohono O'odham
["otk"] = {"ترکی باستان"}, -- Old Turkish
["pal"] = {"پارسی میانه"}, -- Pahlavi
["pam"] = {"کاپامپانگان"}, -- Pampanga
["phr"] = {"پوتواری"}, -- Pahari-Potwari
["pka"] = {"پراکریت"}, -- Ardhamāgadhī Prākrit
-- ["pnb"] = {"پنجابی"}, -- Western Panjabi
["psu"] = {"Shauraseni"}, -- Sauraseni Prākrit
["rap"] = {"رپا نویی"}, -- Rapanui
["rar"] = {"مائوری جزایر کوک"}, -- Rarotongan
["rmu"] = {"Scandoromani"}, -- Tavringer Romani
["rom"] = {"رومانی"}, -- Romany
["rup"] = {"آرومانی"}, -- Macedo-Romanian
["ryu"] = {"اوکیناوایی"}, -- Central Okinawan
["sdc"] = {"ساساری"}, -- Sassarese Sardinian
["sdn"] = {"گالوری"}, -- Gallurese Sardinian
["shp"] = {"Shipibo"}, -- Shipibo-Conibo
["src"] = {"لوگودوری"}, -- Logudorese Sardinian
["sro"] = {"کامپیدانی"}, -- Campidanese Sardinian
["tkl"] = {"توکلائویی"}, -- Tokelau
["tvl"] = {"تووالویی"}, -- Tuvalu
["tyv"] = {"تووایی"}, -- Tuvinian
["vls"] = {"فلاندری غربی"}, -- Vlaams
["wep"] = {"وستفالی"}, -- Westphalien
["xal"] = {"اویرات"}, -- Kalmyk
["xcl"] = {"ارمنی باستان"}, -- Classical Armenian
["yua"] = {"مایایی یوکاتانی"}, -- 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
["gem-x-proto"] = {"Proto-Germanic"}, -- gem in IANA is Germanic languages
["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
["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
["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-hav"] = {"Havasupai"}, -- IANA name for these three is Havasupai-Walapai-Yavapai
["yuf-x-wal"] = {"Walapai"},
["yuf-x-yav"] = {"Yavapai"},
}
--[[--------------------------< 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 = {
["lij"] = {"زبان لیگوری (رومی)"}, -- Ligurian; see Template_talk:Lang#Ligurian_dab
['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)
["xlg"] = {"Ligurian (ancient language)"}, -- see Template_talk:Lang#Ligurian_dab
}
--[=[-------------------------< 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'] = 'آکادمی نویسه‌گردانی زبان عبری',
},
['ala'] = {
['default'] = 'انجمن کتابخانه آمریکا – نویسه‌گردانی کتابخانه کنگره',
},
['ala-lc'] = {
['default'] = 'انجمن کتابخانه آمریکا – نویسه‌گردانی کتابخانه کنگره',
},
['batr'] = {
['default'] = 'قوانین نویسه‌گردانی عربی بیکداش',
},
['bgn/pcgn'] = {
['default'] = 'هیئت نام‌های جغرافیایی / کمیته دائمی نویسه‌گردانی نام‌های جغرافیایی',
},
['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'] = 'نویسه‌گردانی دانشنامه اتیوپیکا',
},
['hepburn'] = {
['default'] = 'نویسه‌گردانی هپبورن',
},
['hunterian'] = {
['default'] = 'نویسه‌گردانی هانتری',
},
['iast'] = {
['default'] = 'الفبای بین‌المللی نویسه‌گردانی سانسکریت',
},
['iso'] = { -- when a transliteration standard is supplied
['ab'] = 'ISO 9 Cyrillic',
['ba'] = 'ISO 9 Cyrillic',
['be'] = 'ISO 9 Cyrillic',
['bg'] = 'ISO 9 Cyrillic',
['kk'] = 'ISO 9 Cyrillic',
['ky'] = 'ISO 9 Cyrillic',
['mn'] = 'ISO 9 Cyrillic',
['ru'] = 'ISO 9 Cyrillic',
['tg'] = 'ISO 9 Cyrillic',
['uk'] = 'ISO 9 Cyrillic',
['bua'] = 'ISO 9 Cyrillic',
['sah'] = 'ISO 9 Cyrillic',
['tut'] = 'ISO 9 Cyrillic',
['xal'] = 'ISO 9 Cyrillic',
['cyrl'] = 'ISO 9 Cyrillic',
['ar'] = 'ISO 233 Arabic',
['ku'] = 'ISO 233 Arabic',
['ps'] = 'ISO 233 Arabic',
['ug'] = 'ISO 233 Arabic',
['ur'] = 'ISO 233 Arabic',
['arab'] = 'ISO 233 Arabic',
['he'] = 'ISO 259 Hebrew',
['yi'] = 'ISO 259 Hebrew',
['hebr'] = 'ISO 259 Hebrew',
['el'] = 'ISO 843 Greek',
['grc'] = 'ISO 843 Greek',
['ja'] = 'ISO 3602 Japanese',
['hira'] = 'ISO 3602 Japanese',
['hrkt'] = 'ISO 3602 Japanese',
['jpan'] = 'ISO 3602 Japanese',
['kana'] = 'ISO 3602 Japanese',
['zh'] = 'ISO 7098 Chinese',
['chi'] = 'ISO 7098 Chinese',
['pny'] = 'ISO 7098 Chinese',
['zho'] = 'ISO 7098 Chinese',
-- ['han'] = 'ISO 7098 Chinese', -- unicode alias of Hani? doesn't belong here? should be Hani?
['hans'] = 'ISO 7098 Chinese',
['hant'] = 'ISO 7098 Chinese',
['ka'] = 'ISO 9984 Georgian',
['kat'] = 'ISO 9984 Georgian',
['arm'] = 'ISO 9985 Armenian',
['hy'] = 'ISO 9985 Armenian',
['th'] = 'ISO 11940 Thai',
['tha'] = 'ISO 11940 Thai',
['ko'] = 'ISO 11941 Korean',
['kor'] = 'ISO 11941 Korean',
['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',
['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',
['raj'] = 'ISO 15919 Indic',
['sa'] = 'ISO 15919 Indic',
['sat'] = 'ISO 15919 Indic',
['sd'] = 'ISO 15919 Indic',
['si'] = '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'] = 'نویسه‌گردانی ایزو',
},
['jyutping'] = {
['default'] = 'نویسه‌گردانی جیوت‌پینگ',
},
['mr'] = {
['default'] = 'نویسه‌گردانی مک‌کیون–ریشاور',
},
['nihon-shiki'] = {
['default'] = 'نویسه‌گردانی نیهان-شیکی',
},
['no_std'] = { -- when no transliteration standard is supplied
['akk'] = 'Semitic transliteration',
['sem'] = 'Semitic transliteration',
['phnx'] = 'Semitic transliteration',
['xsux'] = 'نویسه‌گردانی میخی',
},
['pinyin'] = {
['default'] = 'نویسه‌گردانی پین‌یین',
},
['rr'] = {
['default'] = 'نویسه‌گردانی لاتین‌نویسی کره‌ای اصلاح‌شده',
},
['rtgs'] = {
['default'] = 'Royal Thai General System of Transcription',
},
['satts'] = {
['default'] = 'Standard Arabic Technical Transliteration System transliteration',
},
['ungegn'] = {
['default'] = 'نویسه‌گردانی گروه نام‌های جغرافیایی در سازمان ملل متحد',
},
['wadegile'] = {
['default'] = 'نویسه‌گردانی وید جایلز',
},
['wehr'] = {
['default'] = 'Hans Wehr transliteration',
},
};
return
{
article_name = article_name,
lang_name_table = lang_name_table,
override = override,
rtl_scripts = rtl_scripts,
translit_title_table = translit_title_table,
};