Module:Lang/data: Difference between revisions

script -> ISO 15924 script tags

region -> ISO 3166 region tags

suppressed -> map of scripts tags and their associated language tags

local function key_to_lower (module, src_type)

local out = {};

if 'var_sup' == src_type then

out[k:lower()] = v; -- for variant and suppressed everything is needed

end

out[k:lower()] = v[1]; -- ignore multiple names; take first name only

end

out[k:lower()] = v[1]; -- ignore multiple names; take first name only

end

else -- here for all other sources

out[k:lower()] = v[1]; -- ignore multiple names; take first name only

end

local lang_name_table_t = {

}

use the override table to override language names that are incorrect for your project

=mw.dumpObject (mw.language.fetchLanguageNames ('<tag>', 'all'))

(replacing <tag> with the language tag for your language)

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

end

end

["en-us"] = "American English",

["en-za"] = "South African English",

["fy"] = "West Frisian", -- Western Frisian

["mo"] = "Moldovan", -- Moldavian (deprecated code); to match en.wiki article title

["nl-be"] = "Flemish", -- match MediaWiki

["oc-provenc"] = "Provençal",

["ps"] = "Pashto", -- Pushto

["pt-br"] = "Brazilian Portuguese", -- match MediaWiki

["tw-asante"] = "Asante Twi",

["ug"] = "Uyghur", -- 2nd IANA name; to match en.wiki article 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

["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

["bxu"] = "Chinese Buryat", -- China Buriat;

["byr"] = "Yipma", -- Baruya, Yipma

["egy"] = "Ancient Egyptian", -- Egyptian (Ancient); distinguish from contemporary arz: Egyptian Arabic  

["ems"] = "Alutiiq", -- Pacific Gulf Yupik; to match en.wiki article title

["gsw-fr"] = "Alsatian", -- match MediaWiki

["haa"] = "Hän", -- Han; to match en.wiki article title

["hmx"] = "Hmong–Mien languages", -- to match en.wiki article title (endash)

["ilo"] = "Ilocano", -- Iloko; to match en.wiki article title

["jam"] = "Jamaican Patois", -- Jamaican Creole English

["luo"] = "Dholuo", -- IANA (primary) /ISO 639-3: Luo (Kenya and Tanzania); IANA (secondary): Dholuo

["mhr"] = "Meadow Mari", -- Eastern Mari

["pms"] = "Piedmontese", -- Piemontese; to match en.wiki article title

["pnb"] = "Punjabi (Western)", -- Western Panjabi; dab added to override import from ~/wp languages and distinguish pnb from pa in reverse look up tag_from_name()

["rop"] = "Australian Kriol", -- Kriol; en.wiki article is a dab; point to correct en.wiki article

["sdo"] = "Bukar–Sadong", -- Bukar-Sadung Bidayuh; to match en.wiki article title

["smp"] = "Samaritan Hebrew", -- 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

------------------------------< P R I V A T E _ U S E _ T A G S >----------------------------------------------

["akk-x-midassyr"] = "Middle Assyrian Akkadian",

["akk-x-midbabyl"] = "Middle Babylonian Akkadian",

["akk-x-oldbabyl"] = "Old Babylonian Akkadian",

["alg-x-proto"] = "Proto-Algonquian", -- alg in IANA is Algonquian languages

["ca-x-old"] = "Old Catalan",

["cel-x-combrit"] = "Common Brittonic", -- cel in IANA is Celtic languages

["cel-x-proto"] = "Proto-Celtic",

["egy-x-demotic"] = "Demotic Egyptian",

["egy-x-late"] = "Late Egyptian",

["egy-x-middle"] = "Middle Egyptian",

["egy-x-old"] = "Old Egyptian",

["gem-x-proto"] = "Proto-Germanic", -- gem in IANA is Germanic languages

["gmw-x-ecg"] = "East Central German",

["grc-x-aeolic"] = "Aeolic Greek", -- these grc-x-... codes are preferred alternates to the non-standard catchall code grc-gre

["grc-x-attic"] = "Attic Greek",

["grc-x-biblical"] = "Biblical Greek",

["grc-x-hellen"] = "Hellenistic Greek",

["grc-x-ionic"] = "Ionic Greek",

["grc-x-medieval"] = "Medieval Greek",

["grc-x-patris"] = "Patristic Greek",

["grk-x-proto"] = "Proto-Greek", -- grk in IANA is Greek languages

["itc-x-proto"] = "Proto-Italic", -- itc in IANA is Italic languages

["ksh-x-colog"] = "Colognian", -- en.wiki article is Colognian; ksh (Kölsch) redirects there

["la-x-medieval"] = "Medieval Latin",

["la-x-new"] = "New Latin",

["lmo-x-milanese"] = "Milanese", -- lmo in IANA is Lombard; Milanese is a dialect

["mis-x-ripuar"] = "Ripuarian", -- replaces improper use of ksh in wp_languages

["prg-x-old"] = "Old Prussian",

["sem-x-ammonite"] = "Ammonite",

["sem-x-aramaic"] = "Aramaic",

["sem-x-canaan"] = "Canaanite languages",

["sem-x-dumaitic"] = "Dumaitic",

["sem-x-egurage"] = "Eastern Gurage",

["sem-x-hatran"] = "Hatran Aramaic",

["sem-x-oldsoara"] = "Old South Arabian",

["sem-x-palmyren"] = "Palmyrene Aramaic",

["sem-x-proto"] = "Proto-Semitic",

["sem-x-taymanit"] = "Taymanitic",

["sla-x-proto"] = "Proto-Slavic", -- sla in IANA is Slavic languages

["yuf-x-hav"] = "Havasupai", -- IANA name for these three is Havasupai-Walapai-Yavapai

["yuf-x-wal"] = "Walapai",

["yuf-x-yav"] = "Yavapai",

["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 >------------------------------------------------------

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

['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

["zmw"] = "Mbo language (Congo)", -- Mbo (Democratic Republic of Congo)

}

by some of the {{lang-??}} templates.

the cases when no |std= parameter value is provided.

local translit_title_table = {

['ahl'] = {

['default'] = 'Academy of the Hebrew Language transliteration',

['hepburn'] = {

['default'] = 'Hepburn transliteration',

},

['xal'] = 'ISO 9 Cyrillic',

['cyrl'] = 'ISO 9 Cyrillic',

['ar'] = 'ISO 233 Arabic',

},

['mlcts'] = {

['default'] = 'Myanmar Language Commission Transcription System',

['default'] = 'Hans Wehr transliteration',

},

};

return

article_name = article_name,

lang_name_table = lang_name_table_t,

override = override,