Module:languages/data/2
< Module:languages | data
Ang dokumentasyon ng ng modyul na ito ay maaaring likhain sa Module:languages/data/2/doc
local m_langdata = require("Module:languages/data")
-- Loaded on demand, as it may not be needed (depending on the data).
local function u(...)
u = require("Module:string utilities").char
return u(...)
end
local c = m_langdata.chars
local p = m_langdata.puaChars
local s = m_langdata.shared
-- Ideally, we want to move these into [[Module:languages/data]], but because (a) it's necessary to use require on that module, and (b) they're only used in this data module, it's less memory-efficient to do that at the moment. If it becomes possible to use mw.loadData, then these should be moved there.
s["de-Latn-sortkey"] = {
remove_diacritics = c.grave .. c.acute .. c.circ .. c.diaer .. c.ringabove,
from = {"æ", "œ", "ß"},
to = {"ae", "oe", "ss"}
}
s["de-Latn-standardchars"] = "AaÄäBbCcDdEeFfGgHhIiJjKkLlMmNnOoÖöPpQqRrSsẞßTtUuÜüVvWwXxYyZz"
s["ka-entryname"] = {remove_diacritics = c.circ}
s["no-sortkey"] = {
remove_diacritics = c.grave .. c.acute .. c.circ .. c.tilde .. c.macron .. c.dacute .. c.caron .. c.cedilla,
remove_exceptions = {"å"},
from = {"æ", "ø", "å"},
to = {"z" .. p[1], "z" .. p[2], "z" .. p[3]}
}
s["no-standardchars"] = "AaBbDdEeFfGgHhIiJjKkLlMmNnOoPpRrSsTtUuVvYyÆæØøÅå" .. c.punc
s["tg-entryname"] = {remove_diacritics = c.grave .. c.acute}
s["tk-entryname"] = {remove_diacritics = c.macron}
local m = {}
m["aa"] = {
"Afar",
27811,
"cus-eas",
"Latn, Ethi",
entry_name = {
Latn = {remove_diacritics = c.acute},
},
english_name = "Afar", --TLCHANGE
}
m["ab"] = {
"Abhasiyo", --TLCHANGE From spanish "abjasio"
5111,
"cau-abz",
"Cyrl, Geor, Latn",
translit = {
Cyrl = "ab-translit",
Geor = "Geor-translit",
},
override_translit = true,
display_text = {
Cyrl = s["cau-Cyrl-displaytext"]
},
entry_name = {
Cyrl = {
remove_diacritics = c.acute,
from = {"^а%-"},
to = {"а"},
},
Latn = s["cau-Latn-entryname"],
},
sort_key = {
Cyrl = {
from = {
"х'ә", -- 3 chars
"гь", "гә", "ӷь", "ҕь", "ӷә", "ҕә", "дә", "ё", "жь", "жә", "ҙә", "ӡә", "ӡ'", "кь", "кә", "қь", "қә", "ҟь", "ҟә", "ҫә", "тә", "ҭә", "ф'", "хь", "хә", "х'", "ҳә", "ць", "цә", "ц'", "ҵә", "ҵ'", "шь", "шә", "џь", -- 2 chars
"ӷ", "ҕ", "ҙ", "ӡ", "қ", "ҟ", "ԥ", "ҧ", "ҫ", "ҭ", "ҳ", "ҵ", "ҷ", "ҽ", "ҿ", "ҩ", "џ", "ә", -- 1 char
"^а",
},
to = {
"х" .. p[4],
"г" .. p[1], "г" .. p[2], "г" .. p[5], "г" .. p[6], "г" .. p[7], "г" .. p[8], "д" .. p[1], "е" .. p[1], "ж" .. p[1], "ж" .. p[2], "з" .. p[2], "з" .. p[4], "з" .. p[5], "к" .. p[1], "к" .. p[2], "к" .. p[4], "к" .. p[5], "к" .. p[7], "к" .. p[8], "с" .. p[2], "т" .. p[1], "т" .. p[3], "ф" .. p[1], "х" .. p[1], "х" .. p[2], "х" .. p[3], "х" .. p[6], "ц" .. p[1], "ц" .. p[2], "ц" .. p[3], "ц" .. p[5], "ц" .. p[6], "ш" .. p[1], "ш" .. p[2], "ы" .. p[3],
"г" .. p[3], "г" .. p[4], "з" .. p[1], "з" .. p[3], "к" .. p[3], "к" .. p[6], "п" .. p[1], "п" .. p[2], "с" .. p[1], "т" .. p[2], "х" .. p[5], "ц" .. p[4], "ч" .. p[1], "ч" .. p[2], "ч" .. p[3], "ы" .. p[1], "ы" .. p[2], "ь" .. p[1],
"",
}
},
},
english_name = "Abkahz", --TLCHANGE
spanish_name = "Abjasio", --TLCHANGE
}
m["ae"] = {
"Avestiko", --TLCHANGE from Spanish "avéstico"
29572,
"ira-cen",
"Avst, Gujr",
translit = {
Avst = "Avst-translit"
},
english_name = "Avestan", --TLCHANGE
spanish_name = "Avéstico" --TLCHANGE
}
m["af"] = {
"Afrikaans", --from Spanish "Afrikáans"
14196,
"gmw-frk",
"Latn, Arab",
ancestors = "nl",
sort_key = {
Latn = {
remove_diacritics = c.grave .. c.acute .. c.circ .. c.tilde .. c.diaer .. c.ringabove .. c.cedilla .. "'",
from = {"['ʼ]n"},
to = {"n" .. p[1]}
}
},
spanish_name = "Afrikáans" --TLCHANGE
}
m["ak"] = {
"Akan",
28026,
"alv-ctn",
"Latn",
}
m["am"] = {
"Amhariko", -- from Spanish "amhárico"
28244,
"sem-eth",
"Ethi",
translit = "Ethi-translit",
english_name = "Amharic", --TLCHANGE
spanish_name = "Amhárico" --TLCHANGE
}
m["an"] = {
"Aragones", --from Spanish "aragonés"
8765,
"roa-nar",
"Latn",
english_name = "Aragonese", --TLCHANGE
spanish_name = "Aragonés" --TLCHANGE
}
m["ar"] = {
"Arabe", --TLCHANGE
13955,
"sem-arb",
"Arab, Hebr, Syrc, Brai",
translit = {
Arab = "ar-translit"
},
display_text = {
Hebr = "Hebr-common",
},
entry_name = {
Arab = "ar-entryname",
Hebr = "Hebr-common",
},
sort_key = {
Hebr = "Hebr-common",
},
is_official_kwf_name = "https://kwf.gov.ph/wp-content/uploads/MMP_Full.pdf#page=96", --TLCHANGE
english_name = "Arabic", --TLCHANGE
}
m["as"] = {
"Asames", --from Spanish "asamés"
29401,
"inc-bas",
"as-Beng",
ancestors = "inc-mas",
translit = "as-translit",
english_name = "Assamese", --TLCHANGE
spanish_name = "Asamés" --TLCHANGE
}
m["av"] = {
"Avar",
29561,
"cau-ava",
"Cyrl, Latn, Arab",
ancestors = "oav",
translit = {
Cyrl = "cau-nec-translit",
Arab = "ar-translit",
},
override_translit = true,
display_text = {
Cyrl = s["cau-Cyrl-displaytext"],
},
entry_name = {
Cyrl = s["cau-Cyrl-entryname"],
Latn = s["cau-Latn-entryname"],
},
sort_key = {
Cyrl = {
from = {"гъ", "гь", "гӏ", "ё", "кк", "къ", "кь", "кӏ", "лъ", "лӏ", "тӏ", "хх", "хъ", "хь", "хӏ", "цӏ", "чӏ"},
to = {"г" .. p[1], "г" .. p[2], "г" .. p[3], "е" .. p[1], "к" .. p[1], "к" .. p[2], "к" .. p[3], "к" .. p[4], "л" .. p[1], "л" .. p[2], "т" .. p[1], "х" .. p[1], "х" .. p[2], "х" .. p[3], "х" .. p[4], "ц" .. p[1], "ч" .. p[1]}
},
},
english_name = "Avar", --TLCHANGE
}
m["ay"] = {
"Aymara", --from Spanish "aimara"
4627,
"sai-aym",
"Latn",
english_name = "Aymara", --TLCHANGE
spanish_name = "Aimara" --TLCHANGE
}
m["az"] = {
"Azeri", --TLCHANGE from Spanish "azerí"
9292,
"trk-ogz",
"Latn, Cyrl, fa-Arab",
ancestors = "trk-oat",
dotted_dotless_i = true,
entry_name = {
Latn = {
from = {"ʼ"},
to = {"'"},
},
["fa-Arab"] = {
module = "ar-entryname",
["from"] = {
"ۆ",
"ۇ",
"وْ",
"ڲ",
"ؽ",
},
["to"] = {
"و",
"و",
"و",
"گ",
"ی",
},
},
},
display_text = {
Latn = {
from = {"'"},
to = {"ʼ"}
}
},
sort_key = {
Latn = {
from = {
"i", -- Ensure "i" comes after "ı".
"ç", "ə", "ğ", "x", "ı", "q", "ö", "ş", "ü", "w"
},
to = {
"i" .. p[1],
"c" .. p[1], "e" .. p[1], "g" .. p[1], "h" .. p[1], "i", "k" .. p[1], "o" .. p[1], "s" .. p[1], "u" .. p[1], "z" .. p[1]
}
},
Cyrl = {
from = {"ғ", "ә", "ы", "ј", "ҝ", "ө", "ү", "һ", "ҹ"},
to = {"г" .. p[1], "е" .. p[1], "и" .. p[1], "и" .. p[2], "к" .. p[1], "о" .. p[1], "у" .. p[1], "х" .. p[1], "ч" .. p[1]}
},
},
english_name = "Azerbaijani", --TLCHANGE
spanish_name = "Azerí" --TLCHANGE
}
m["ba"] = {
"Baskir", --TLCHANGE from Spanish "baskir"
13389,
"trk-kbu",
"Cyrl",
translit = "ba-translit",
override_translit = true,
sort_key = {
from = {"ғ", "ҙ", "ё", "ҡ", "ң", "ө", "ҫ", "ү", "һ", "ә"},
to = {"г" .. p[1], "д" .. p[1], "е" .. p[1], "к" .. p[1], "н" .. p[1], "о" .. p[1], "с" .. p[1], "у" .. p[1], "х" .. p[1], "э" .. p[1]}
},
english_name = "Bashkir", --TLCHANGE
spanish_name = "Baskir" --TLCHANGE
}
m["be"] = {
"Biyeloruso", --from Spanish "bielorruso"
9091,
"zle",
"Cyrl, Latn",
ancestors = "zle-obe",
translit = {
Cyrl = "be-translit",
},
entry_name = {
Cyrl = {
remove_diacritics = c.grave .. c.acute,
},
Latn = {
remove_diacritics = c.grave .. c.acute,
remove_exceptions = {"Ć", "ć", "Ń", "ń", "Ś", "ś", "Ź", "ź"},
},
},
sort_key = {
Cyrl = {
remove_diacritics = c.grave .. c.acute,
from = {"ґ", "ё", "і", "ў"},
to = {"г" .. p[1], "е" .. p[1], "и" .. p[1], "у" .. p[1]}
},
Latn = {
remove_diacritics = c.grave .. c.acute,
remove_exceptions = {"Ć", "ć", "Ń", "ń", "Ś", "ś", "Ź", "ź"},
from = {"ć", "č", "dz", "dź", "dž", "ch", "ł", "ń", "ś", "š", "ŭ", "ź", "ž"},
to = {"c" .. p[1], "c" .. p[2], "d" .. p[1], "d" .. p[2], "d" .. p[3], "h" .. p[1], "l" .. p[1], "n" .. p[1], "s" .. p[1], "s" .. p[2], "u" .. p[1], "z" .. p[1], "z" .. p[2]}
},
},
standardChars = {
Cyrl = "АаБбВвГгДдЕеЁёЖжЗзІіЙйКкЛлМмНнОоПпРрСсТтУуЎўФфХхЦцЧчШшЫыЬьЭэЮюЯя",
Latn = "AaBbCcĆćČčDdEeFfGgHhIiJjKkLlŁłMmNnŃńOoPpRrSsŚśŠšTtUuŬŭVvYyZzŹźŽž",
(c.punc:gsub("'", "")) -- Exclude apostrophe.
},
english_name = "Belarusian", --TLCHANGE
spanish_name = "Bielorruso" --TLCHANGE
}
m["bg"] = {
"Bulgaro", --from Spanish "búlgaro"
7918,
"zls",
"Cyrl",
ancestors = "cu-bgm",
translit = "bg-translit",
entry_name = {
remove_diacritics = c.grave .. c.acute,
remove_exceptions = {"%f[^%z%s]ѝ%f[%z%s]"},
},
sort_key = {
remove_diacritics = c.grave .. c.acute,
remove_exceptions = {"%f[^%z%s]ѝ%f[%z%s]"},
},
standardChars = "АаБбВвГгДдЕеЖжЗзИиЙйКкЛлМмНнОоПпРрСсТтУуФфХхЦцЧчШшЩщЪъЬьЮюЯя" .. c.punc,
english_name = "Buglarian", --TLCHANGE
spanish_name = "Búlgaro" --TLCHANGE
}
m["bh"] = {
"Bihari", --from Spanish "bihari"
135305,
"inc-eas",
"Deva",
english_name = "Bihari", --TLCHANGE
spanish_name = "Bihari" --TLCHANGE
}
m["bi"] = {
"Bislama",
35452,
"crp",
"Latn",
ancestors = "en",
english_name = "Bislama", --TLCHANGE
}
m["bm"] = {
"Bambara",
33243,
"dmn-emn",
"Latn, Nkoo",
sort_key = {
Latn = {
from = {"ɛ", "ɲ", "ŋ", "ɔ"},
to = {"e" .. p[1], "n" .. p[1], "n" .. p[2], "o" .. p[1]}
},
},
english_name = "Bambara", --TLCHANGE
}
m["bn"] = {
"Bengali", --from Spanish "bengalí"
9610,
"inc-bas",
"Beng, Newa",
ancestors = "inc-mbn",
translit = {
Beng = "bn-translit"
},
english_name = "Bengali", --TLCHANGE
spanish_name = "Bengalí" --TLCHANGE
}
m["bo"] = {
"Tibetano", --from Spanish "tibetano"
34271,
"sit-tib",
"Tibt", -- sometimes Deva?
ancestors = "xct",
translit = "Tibt-translit",
override_translit = true,
display_text = s["Tibt-displaytext"],
entry_name = s["Tibt-entryname"],
sort_key = "Tibt-sortkey",
english_name = "Tibetan", --TLCHANGE
spanish_name = "Tibetano" --TLCHANGE
}
m["br"] = {
"Breton",
12107,
"cel-brs",
"Latn",
ancestors = "xbm",
sort_key = {
from = {"ch", "c['ʼ’]h"},
to = {"c" .. p[1], "c" .. p[2]}
},
english_name = "Breton", --TLCHANGE
}
m["ca"] = {
"Katalan", --from Spanish "catalán"
7026,
"roa-ocr",
"Latn",
ancestors = "roa-oca",
sort_key = {remove_diacritics = c.grave .. c.acute .. c.diaer .. c.cedilla .. "·"},
standardChars = "AaÀàBbCcÇçDdEeÉéÈèFfGgHhIiÍíÏïJjLlMmNnOoÓóÒòPpQqRrSsTtUuÚúÜüVvXxYyZz·" .. c.punc,
english_name = "Catalan", --TLCHANGE
spanish_name = "Catalán" --TLCHANGE
}
m["ce"] = {
"Tsetseno", --TLCHANGE from Spanish "checheno"
33350,
"cau-vay",
"Cyrl, Latn, Arab",
translit = {
Cyrl = "cau-nec-translit",
Arab = "ar-translit",
},
override_translit = true,
display_text = {
Cyrl = s["cau-Cyrl-displaytext"]
},
entry_name = {
Cyrl = s["cau-Cyrl-entryname"],
Latn = s["cau-Latn-entryname"],
},
sort_key = {
Cyrl = {
from = {"аь", "гӏ", "ё", "кх", "къ", "кӏ", "оь", "пӏ", "тӏ", "уь", "хь", "хӏ", "цӏ", "чӏ", "юь", "яь"},
to = {"а" .. p[1], "г" .. p[1], "е" .. p[1], "к" .. p[1], "к" .. p[2], "к" .. p[3], "о" .. p[1], "п" .. p[1], "т" .. p[1], "у" .. p[1], "х" .. p[1], "х" .. p[2], "ц" .. p[1], "ч" .. p[1], "ю" .. p[1], "я" .. p[1]}
},
},
english_name = "Chechen", --TLCHANGE
spanish_name = "Checheno" --TLCHANGE
}
m["ch"] = {
"Tsamorro", --from Spanish "chamorro"
33262,
"poz",
"Latn",
sort_key = {
remove_diacritics = "'",
from = {"å", "ch", "ñ", "ng"},
to = {"a" .. p[1], "c" .. p[1], "n" .. p[1], "n" .. p[2]}
},
english_name = "Chamorro", --TLCHANGE
spanish_name = "Chamorro" --TLCHANGE
}
m["co"] = {
"Korso", --TLCHANGE from Spanish "corso"
33111,
"roa-itr",
"Latn",
sort_key = {
from = {"chj", "ghj", "sc", "sg"},
to = {"c" .. p[1], "g" .. p[1], "s" .. p[1], "s" .. p[2]}
},
standardChars = "AaÀàBbCcDdEeÈèFfGgHhIiÌìÏïJjLlMmNnOoÒòPpQqRrSsTtUuÙùÜüVvZz" .. c.punc,
english_name = "Corsican", --TLCHANGE
spanish_name = "Corso" --TLCHANGE
}
m["cr"] = {
"Cree",
33390,
"alg",
"Latn, Cans",
translit = {
Cans = "cr-translit"
},
english_name = "Cree", --TLCHANGE
}
m["cs"] = {
"Tseko", --from Spanish "checo"
9056,
"zlw",
"Latn",
ancestors = "cs-ear",
sort_key = {
from = {"á", "č", "ď", "é", "ě", "ch", "í", "ň", "ó", "ř", "š", "ť", "ú", "ů", "ý", "ž"},
to = {"a" .. p[1], "c" .. p[1], "d" .. p[1], "e" .. p[1], "e" .. p[2], "h" .. p[1], "i" .. p[1], "n" .. p[1], "o" .. p[1], "r" .. p[1], "s" .. p[1], "t" .. p[1], "u" .. p[1], "u" .. p[2], "y" .. p[1], "z" .. p[1]}
},
standardChars = "AaÁáBbCcČčDdĎďEeÉéĚěFfGgHhIiÍíJjKkLlMmNnŇňOoÓóPpRrŘřSsŠšTtŤťUuÚúŮůVvYyÝýZzŽž" .. c.punc,
english_name = "Czech", --TLCHANGE
spanish_name = "Checo" --TLCHANGE
}
m["cu"] = {
"Lumang Simbahang Eslavo", --TLCHANGE from Spanish "Antiguo eslavo eclesiástico"
35499,
"zls",
"Cyrs, Glag",
translit = {
Cyrs = "Cyrs-translit",
Glag = "Glag-translit"
},
entry_name = {
Cyrs = s["Cyrs-entryname"]
},
sort_key = {
Cyrs = s["Cyrs-sortkey"]
},
english_name = "Old Church Slavonic", --TLCHANGE
spanish_name = "Antiguo eslavo eclesiástico" --TLCHANGE
}
m["cv"] = {
"Tsuvasiyo", --TLCHANGE from Spanish "chuvasio"
33348,
"trk-ogr",
"Cyrl",
ancestors = "cv-mid",
translit = "cv-translit",
override_translit = true,
sort_key = {
from = {"ӑ", "ё", "ӗ", "ҫ", "ӳ"},
to = {"а" .. p[1], "е" .. p[1], "е" .. p[2], "с" .. p[1], "у" .. p[1]}
},
english_name = "Chuvash", --TLCHANGE
spanish_name = "Chuvasio" --TLCHANGE
}
m["cy"] = {
"Gales", --from Spanish "galés"
9309,
"cel-brw",
"Latn",
ancestors = "wlm",
sort_key = {
remove_diacritics = c.grave .. c.acute .. c.circ .. c.diaer .. "'",
from = {"ch", "dd", "ff", "ng", "ll", "ph", "rh", "th"},
to = {"c" .. p[1], "d" .. p[1], "f" .. p[1], "g" .. p[1], "l" .. p[1], "p" .. p[1], "r" .. p[1], "t" .. p[1]}
},
standardChars = "ÂâAaBbCcDdEeÊêFfGgHhIiÎîLlMmNnOoÔôPpRrSsTtUuÛûWwŴŵYyŶŷ" .. c.punc,
english_name = "Welsh", --TLCHANGE
spanish_name = "Galés" --TLCHANGE
}
m["da"] = {
"Danes", --from Spanish "danés"
9035,
"gmq-eas",
"Latn",
ancestors = "gmq-oda",
sort_key = {
remove_diacritics = c.grave .. c.acute .. c.circ .. c.tilde .. c.macron .. c.dacute .. c.caron .. c.cedilla,
remove_exceptions = {"å"},
from = {"æ", "ø", "å"},
to = {"z" .. p[1], "z" .. p[2], "z" .. p[3]}
},
standardChars = "AaBbDdEeFfGgHhIiJjKkLlMmNnOoPpRrSsTtUuVvYyÆæØøÅå" .. c.punc,
english_name = "Danish", --TLCHANGE
spanish_name = "Danés" --TLCHANGE
}
m["de"] = {
"Aleman", --from Spanish "alemán"
188,
"gmw-hgm",
"Latn, Latf, Brai",
ancestors = "gmh",
sort_key = {
Latn = s["de-Latn-sortkey"],
Latf = s["de-Latn-sortkey"],
},
standardChars = {
Latn = s["de-Latn-standardchars"],
Latf = s["de-Latn-standardchars"],
Brai = c.braille,
c.punc
},
is_official_kwf_name = "https://kwfdiksiyonaryo.ph/?query=Alem%C3%A1n", --TLCHANGE (Spanish first before English)
english_name = "German", --TLCHANGE
spanish_name = "Alemán" --TLCHANGE
}
m["dv"] = {
"Divehi", --from Spanish "divehi"
32656,
"inc-ins",
"Thaa, Diak",
translit = {
Thaa = "dv-translit",
Diak = "Diak-translit",
},
override_translit = true,
english_name = "Dhivehi", --TLCHANGE
spanish_name = "Divehi" --TLCHANGE
}
m["dz"] = {
"Dzongkha",
33081,
"sit-tib",
"Tibt",
ancestors = "xct",
translit = "Tibt-translit",
override_translit = true,
display_text = s["Tibt-displaytext"],
entry_name = s["Tibt-entryname"],
sort_key = "Tibt-sortkey",
english_name = "Dzongkha", --TLCHANGE
}
m["ee"] = {
"Ewe",
30005,
"alv-gbe",
"Latn",
sort_key = {
remove_diacritics = c.tilde,
from = {"ɖ", "dz", "ɛ", "ƒ", "gb", "ɣ", "kp", "ny", "ŋ", "ɔ", "ts", "ʋ"},
to = {"d" .. p[1], "d" .. p[2], "e" .. p[1], "f" .. p[1], "g" .. p[1], "g" .. p[2], "k" .. p[1], "n" .. p[1], "n" .. p[2], "o" .. p[1], "t" .. p[1], "v" .. p[1]}
},
english_name = "Ewe", --TLCHANGE
}
m["el"] = {
"Griyego", --from Spanish "griego"
9129,
"grk",
"Grek, Polyt, Brai",
ancestors = "el-kth",
translit = {
Grek = "el-translit",
Polyt = "grc-translit",
},
override_translit = true,
display_text = {
Grek = s["Grek-displaytext"],
Polyt = s["Polyt-displaytext"],
},
entry_name = {
Grek = s["Grek-entryname"],
Polyt = s["Polyt-entryname"],
},
sort_key = {
Grek = s["Grek-sortkey"],
Polyt = s["Polyt-sortkey"],
},
standardChars = {
Grek = "΅·ͺ΄ΑαΆάΒβΓγΔδΕεέΈΖζΗηΉήΘθΙιΊίΪϊΐΚκΛλΜμΝνΞξΟοΌόΠπΡρΣσςΤτΥυΎύΫϋΰΦφΧχΨψΩωΏώ",
Brai = c.braille,
c.punc
},
is_official_kwf_name = "https://kwfdiksiyonaryo.ph/?query=Griy%C3%A9go", --TLCHANGE (Spanish first before English)
english_name = "Greek", --TLCHANGE
spanish_name = "Griego" --TLCHANGE
}
m["en"] = {
"Ingles", --from Spanish "inglés"
1860,
"gmw-ang",
"Latn, Brai, Shaw, Dsrt", -- entries in Shaw or Dsrt might require prior discussion
wikimedia_codes = "en, simple",
ancestors = "en-ear",
sort_key = {
Latn = {
-- Many of these are needed for sorting language names.
remove_diacritics = "'\"%-%.,%s·ʻʼ" .. c.diacritics,
-- These are found in entry names.
from = {"[ɒæ🅱¢©ᴄðđəǝɜɡħʜıɨłŋɲøɔœꝑꝓꝕßʋ]"},
to = {{
["ɒ"] = "a", ["æ"] = "ae", ["🅱"] = "b", ["¢"] = "c", ["©"] = "c",
["ᴄ"] = "c", ["ð"] = "d", ["đ"] = "d", ["ə"] = "e", ["ǝ"] = "e",
["ɜ"] = "e", ["ɡ"] = "g", ["ħ"] = "h", ["ʜ"] = "h", ["ı"] = "i",
["ɨ"] = "i", ["ł"] = "l", ["ŋ"] = "n", ["ɲ"] = "n", ["ø"] = "o",
["ɔ"] = "o", ["œ"] = "oe", ["ꝑ"] = "p", ["ꝓ"] = "p", ["ꝕ"] = "p",
["ß"] = "ss", ["ʋ"] = "v",
}},
},
},
standardChars = {
Latn = "AaBbCcDdEeFfGgHhIiJjKkLlMmNnOoPpQqRrSsTtUuVvWwXxYyZz",
Brai = c.braille,
c.punc
},
is_official_kwf_name = "https://kwf.gov.ph/wp-content/uploads/MMP_Full.pdf#page=20", --TLCHANGE
english_name = "English", --TLCHANGE
spanish_name = "Inglés" --TLCHANGE
}
m["eo"] = {
"Esperanto",
143,
"art",
"Latn",
sort_key = {
remove_diacritics = c.grave .. c.acute,
from = {"ĉ", "ĝ", "ĥ", "ĵ", "ŝ", "ŭ"},
to = {"c" .. p[1], "g" .. p[1], "h" .. p[1], "j" .. p[1], "s" .. p[1], "u" .. p[1]}
},
standardChars = "AaBbCcĈĉDdEeFfGgĜĝHhĤĥIiJjĴĵKkLlMmNnOoPpRrSsŜŝTtUuŬŭVvZz" .. c.punc,
english_name = "Esperanto", --TLCHANGE
}
m["es"] = {
"Espanyol", --TLCHANGE this is confusing, KWF has "Espanyol", "Kastila", and "Español" as all translations of Spanish
1321,
"roa-cas",
"Latn, Brai",
ancestors = "es-ear",
sort_key = {
Latn = {
remove_exceptions = {"ñ"},
remove_diacritics = c.grave .. c.acute .. c.circ .. c.tilde .. c.macron .. c.diaer .. c.cedilla,
from = {"ª", "æ", "ñ", "º", "œ"},
to = {"a", "ae", "n" .. p[1], "o", "oe"}
},
},
standardChars = {
Latn = "AaÁáBbCcDdEeÉéFfGgHhIiÍíJjLlMmNnÑñOoÓóPpQqRrSsTtUuÚúÜüVvXxYyZz",
Brai = c.braille,
c.punc
},
is_official_kwf_name = "https://kwf.gov.ph/wp-content/uploads/MMP_Full.pdf#page=12", --TLCHANGE
english_name = "Spanish", --TLCHANGE
spanish_name = "Español" --TLCHANGE
}
m["et"] = {
"Estoniyo", --TLCHANGE from Spanish "estonio"
9072,
"urj-fin",
"Latn",
sort_key = {
from = {
"š", "ž", "õ", "ä", "ö", "ü", -- 2 chars
"z" -- 1 char
},
to = {
"s" .. p[1], "s" .. p[3], "w" .. p[1], "w" .. p[2], "w" .. p[3], "w" .. p[4],
"s" .. p[2]
}
},
standardChars = "AaBbDdEeFfGgHhIiJjKkLlMmNnOoPpRrSsTtUuVvÕõÄäÖöÜü" .. c.punc,
english_name = "Estonian", --TLCHANGE
spanish_name = "Estonio" --TLCHANGE
}
m["eu"] = {
"Euskera", --from Spanish "Euskera"
8752,
"euq",
"Latn",
sort_key = {
from = {"ç", "ñ"},
to = {"c" .. p[1], "n" .. p[1]}
},
standardChars = "AaBbDdEeFfGgHhIiJjKkLlMmNnÑñOoPpRrSsTtUuXxZz" .. c.punc,
english_name = "Basque", --TLCHANGE
spanish_name = "Euskera" --TLCHANGE
}
m["fa"] = {
"Persa", --TLCHANGE from Spanish "persa"
9168,
"ira-swi",
"fa-Arab, Hebr",
ancestors = "fa-cls",
display_text = {
Hebr = "Hebr-common",
},
entry_name = {
["fa-Arab"] = {
-- character "ۂ" code U+06C2 to "ه" and "هٔ" (U+0647 + U+0654) to "ه"; hamzatu l-waṣli to a regular alif
from = {"هٔ", "ٱ"}, -- character "ۂ" code U+06C2 to "ه"; hamzatu l-waṣli to a regular alif
to = {"ه", "ا"},
remove_diacritics = c.fathatan .. c.dammatan .. c.kasratan .. c.fatha .. c.damma .. c.kasra .. c.shadda .. c.sukun .. c.superalef,
},
Hebr = "Hebr-common",
},
sort_key = {
Hebr = "Hebr-common",
},
english_name = "Persian", --TLCHANGE
spanish_name = "Persa" --TLCHANGE
}
m["ff"] = {
"Fula",
33454,
"alv-fwo",
"Latn, Adlm",
english_name = "Fula", --TLCHANGE
}
m["fi"] = {
"Fines", --TLCHANGE from Spanish "finés"
1412,
"urj-fin",
"Latn",
display_text = {
from = {"'"},
to = {"’"}
},
entry_name = { -- used to indicate gemination of the next consonant
remove_diacritics = "ˣ",
from = {"’"},
to = {"'"},
},
sort_key = { -- [[Appendix:Finnish alphabet#Collation]] + "aͤ" and "oͤ" as historical variants of "ä" and "ö".
remove_diacritics = "':" .. c.diacritics,
remove_exceptions = {
"a[" .. c.ringabove .. c.diaer .. c.small_e .. "]", -- åäaͤ
"o[" .. c.diaer .. c.tilde .. c.dacute .. c.small_e .. "]", -- öõőoͤ
"u[" .. c.diaer .. c.dacute .. "]" -- üű
},
from = {"æ", "[ðđ]", "ł", "ŋ", "œ", "ß", "þ", "u[" .. c.diaer .. c.dacute .. "]", "å", "aͤ", "o[" .. c.tilde .. c.dacute .. c.small_e .. "]", "ø", "(.)['%-]"},
to = {"ae", "d", "l", "n", "oe", "ss", "th", "y", "z" .. p[1], "ä", "ö", "ö", "%1"}
},
standardChars = "AaBbDdEeFfGgHhIiJjKkLlMmNnOoPpRrSsTtUuVvYyÄäÖö" .. c.punc,
english_name = "Finnish", --TLCHANGE
spanish_name = "Finés" --TLCHANGE
}
m["fj"] = {
"Fiyiyano", --TLCHANGE from Spanish "fiyiano"
33295,
"poz-pcc",
"Latn",
english_name = "Fijian", --TLCHANGE
spanish_name = "Fiyiano" --TLCHANGE
}
m["fo"] = {
"Feroes", --TLCHANGE from Spanish "feroés"
25258,
"gmq-ins",
"Latn",
sort_key = {
from = {"á", "ð", "í", "ó", "ú", "ý", "æ", "ø"},
to = {"a" .. p[1], "d" .. p[1], "i" .. p[1], "o" .. p[1], "u" .. p[1], "y" .. p[1], "z" .. p[1], "z" .. p[2]}
},
standardChars = "AaÁáBbDdÐðEeFfGgHhIiÍíJjKkLlMmNnOoÓóPpRrSsTtUuÚúVvYyÝýÆæØø" .. c.punc,
english_name = "Faroese", --TLCHANGE
spanish_name = "Feroés" --TLCHANGE
}
m["fr"] = {
"Franses", --from Spanish "francés"
150,
"roa-oil",
"Latn, Brai",
display_text = {
Latn = {
from = {"'"},
to = {"’"}
},
},
entry_name = {
Latn = {
from = {"’"},
to = {"'"},
},
},
ancestors = "frm",
sort_key = {
Latn = s["roa-oil-sortkey"]
},
standardChars = {
Latn = "AaÀàÂâBbCcÇçDdEeÉéÈèÊêËëFfGgHhIiÎîÏïJjLlMmNnOoÔôŒœPpQqRrSsTtUuÙùÛûÜüVvXxYyZz",
Brai = c.braille,
c.punc
},
english_name = "French", --TLCHANGE
spanish_name = "Francés" --TLCHANGE
}
m["fy"] = {
"Kanlurang Frison",--TLCHANGE from Spanish "frisón occidental"
27175,
"gmw-fri",
"Latn",
sort_key = {
remove_diacritics = c.grave .. c.acute .. c.circ .. c.diaer,
from = {"y"},
to = {"i"}
},
standardChars = "AaâäàÆæBbCcDdEeéêëèFfGgHhIiïìYyỳJjKkLlMmNnOoôöòPpRrSsTtUuúûüùVvWwZz" .. c.punc,
english_name = "West Frisian", --TLCHANGE
spanish_name = "Frisón occidental" --TLCHANGE
}
m["ga"] = {
"Irlandes", --from Spanish "irlandés"
9142,
"cel-gae",
"Latn, Latg",
ancestors = "mga",
sort_key = {
remove_diacritics = c.acute,
from = {"ḃ", "ċ", "ḋ", "ḟ", "ġ", "ṁ", "ṗ", "ṡ", "ṫ"},
to = {"bh", "ch", "dh", "fh", "gh", "mh", "ph", "sh", "th"}
},
standardChars = "AaÁáBbCcDdEeÉéFfGgHhIiÍíLlMmNnOoÓóPpRrSsTtUuÚúVv" .. c.punc,
english_name = "Irish", --TLCHANGE
spanish_name = "Irlandés" --TLCHANGE
}
m["gd"] = {
"Gaeliko Eskoses", --TLCHANGE from Spanish "Gaélico escocés"
9314,
"cel-gae",
"Latn, Latg",
ancestors = "mga",
sort_key = {remove_diacritics = c.grave .. c.acute},
standardChars = "AaÀàBbCcDdEeÈèFfGgHhIiÌìLlMmNnOoÒòPpRrSsTtUuÙù" .. c.punc,
english_name = "Scottish Gaelic", --TLCHANGE
spanish_name = "Gaélico escocés" --TLCHANGE
}
m["gl"] = {
"Galyego", --from Spanish "gallego"
9307,
"roa-gap",
"Latn",
sort_key = {
remove_diacritics = c.acute,
from = {"ñ"},
to = {"n" .. p[1]}
},
standardChars = "AaÁáBbCcDdEeÉéFfGgHhIiÍíÏïLlMmNnÑñOoÓóPpQqRrSsTtUuÚúÜüVvXxZz" .. c.punc,
english_name = "Galician", --TLCHANGE
spanish_name = "Gallego" --TLCHANGE
}
m["gn"] = {
"Guwarani", --TLCHANGE from Spanish "guaraní"
35876,
"tup-gua",
"Latn",
english_name = "Guaraní", --TLCHANGE
spanish_name = "Guaraní" --TLCHANGE
}
m["gu"] = {
"Guyarati", --TLCHANGE from Spanish "guyaratí"
5137,
"inc-wes",
"Arab, Gujr",
ancestors = "inc-mgu",
translit = {
Gujr = "gu-translit",
},
entry_name = {
Arab = {remove_diacritics = c.fathatan .. c.dammatan .. c.kasratan .. c.fatha .. c.damma .. c.kasra .. c.kasra .. c.shadda .. c.sukun},
Gujr = {remove_diacritics = "઼"},
},
english_name = "Gujarati", --TLCHANGE
spanish_name = "Guyaratí" --TLCHANGE
}
m["gv"] = {
"Manes", --TLCHANGE from Spanish "manés"
12175,
"cel-gae",
"Latn",
ancestors = "mga",
sort_key = {remove_diacritics = c.cedilla .. "-"},
standardChars = "AaBbCcÇçDdEeFfGgHhIiJjKkLlMmNnOoPpQqRrSsTtUuVvWwYy" .. c.punc,
english_name = "Manx", --TLCHANGE
spanish_name = "Manés" --TLCHANGE
}
m["ha"] = {
"Hausa", --from Spanish "hausa"
56475,
"cdc-wst",
"Latn, Arab",
entry_name = {
Latn = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.tilde .. c.macron}
},
sort_key = {
Latn = {
from = {"ɓ", "b'", "ɗ", "d'", "ƙ", "k'", "sh", "ƴ", "'y"},
to = {"b" .. p[1], "b" .. p[2], "d" .. p[1], "d" .. p[2], "k" .. p[1], "k" .. p[2], "s" .. p[1], "y" .. p[1], "y" .. p[2]}
},
},
english_name = "Hausa", --TLCHANGE
spanish_name = "Hausa" --TLCHANGE
}
m["he"] = {
"Ebreyo", --from Spanish "hebreo"
9288,
"sem-can",
"Hebr, Phnx, Brai, Samr",
ancestors = "he-med",
display_text = {
Hebr = "Hebr-common",
},
entry_name = {
Hebr = "Hebr-common",
Samr = s["Samr-entryname"],
},
sort_key = {
Hebr = "Hebr-common",
Samr = s["Samr-sortkey"],
},
english_name = "Hebrew", --TLCHANGE
spanish_name = "Hebreo" --TLCHANGE
}
m["hi"] = {
"Hindi",
1568,
"inc-hnd",
"Deva, Kthi, Newa",
translit = {
Deva = "hi-translit"
},
standardChars = {
Deva = "अआइईउऊएऐओऔकखगघङचछजझञटठडढणतथदधनपफबभमयरलवशषसहत्रज्ञक्षक़ख़ग़ज़झ़ड़ढ़फ़काखागाघाङाचाछाजाझाञाटाठाडाढाणाताथादाधानापाफाबाभामायारालावाशाषासाहात्राज्ञाक्षाक़ाख़ाग़ाज़ाझ़ाड़ाढ़ाफ़ाकिखिगिघिङिचिछिजिझिञिटिठिडिढिणितिथिदिधिनिपिफिबिभिमियिरिलिविशिषिसिहित्रिज्ञिक्षिक़िख़िग़िज़िझ़िड़िढ़िफ़िकीखीगीघीङीचीछीजीझीञीटीठीडीढीणीतीथीदीधीनीपीफीबीभीमीयीरीलीवीशीषीसीहीत्रीज्ञीक्षीक़ीख़ीग़ीज़ीझ़ीड़ीढ़ीफ़ीकुखुगुघुङुचुछुजुझुञुटुठुडुढुणुतुथुदुधुनुपुफुबुभुमुयुरुलुवुशुषुसुहुत्रुज्ञुक्षुक़ुख़ुग़ुज़ुझ़ुड़ुढ़ुफ़ुकूखूगूघूङूचूछूजूझूञूटूठूडूढूणूतूथूदूधूनूपूफूबूभूमूयूरूलूवूशूषूसूहूत्रूज्ञूक्षूक़ूख़ूग़ूज़ूझ़ूड़ूढ़ूफ़ूकेखेगेघेङेचेछेजेझेञेटेठेडेढेणेतेथेदेधेनेपेफेबेभेमेयेरेलेवेशेषेसेहेत्रेज्ञेक्षेक़ेख़ेग़ेज़ेझ़ेड़ेढ़ेफ़ेकैखैगैघैङैचैछैजैझैञैटैठैडैढैणैतैथैदैधैनैपैफैबैभैमैयैरैलैवैशैषैसैहैत्रैज्ञैक्षैक़ैख़ैग़ैज़ैझ़ैड़ैढ़ैफ़ैकोखोगोघोङोचोछोजोझोञोटोठोडोढोणोतोथोदोधोनोपोफोबोभोमोयोरोलोवोशोषोसोहोत्रोज्ञोक्षोक़ोख़ोग़ोज़ोझ़ोड़ोढ़ोफ़ोकौखौगौघौङौचौछौजौझौञौटौठौडौढौणौतौथौदौधौनौपौफौबौभौमौयौरौलौवौशौषौसौहौत्रौज्ञौक्षौक़ौख़ौग़ौज़ौझ़ौड़ौढ़ौफ़ौक्ख्ग्घ्ङ्च्छ्ज्झ्ञ्ट्ठ्ड्ढ्ण्त्थ्द्ध्न्प्फ्ब्भ्म्य्र्ल्व्श्ष्स्ह्त्र्ज्ञ्क्ष्क़्ख़्ग़्ज़्झ़्ड़्ढ़्फ़्।॥०१२३४५६७८९॰",
c.punc
},
english_name = "Hindi", --TLCHANGE
}
m["ho"] = {
"Hiri Motu",
33617,
"crp",
"Latn",
ancestors = "meu",
english_name = "Hiri Motu", --TLCHANGE
}
m["ht"] = {
"Kriyolyo Haityano", --from Spanish "Criollo haitiano"
33491,
"crp",
"Latn",
ancestors = "ht-sdm",
sort_key = {
from = {
"oun", -- 3 chars
"an", "ch", "è", "en", "ng", "ò", "on", "ou", "ui" -- 2 chars
},
to = {
"o" .. p[4],
"a" .. p[1], "c" .. p[1], "e" .. p[1], "e" .. p[2], "n" .. p[1], "o" .. p[1], "o" .. p[2], "o" .. p[3], "u" .. p[1]
}
},
english_name = "Haitian Creole", --TLCHANGE
spanish_name = "Criollo haitiano" --TLCHANGE
}
m["hu"] = {
"Unggaro", --from Spanish "húngaro"
9067,
"urj-ugr",
"Latn, Hung",
ancestors = "ohu",
sort_key = {
Latn = {
from = {
"dzs", -- 3 chars
"á", "cs", "dz", "é", "gy", "í", "ly", "ny", "ó", "ö", "ő", "sz", "ty", "ú", "ü", "ű", "zs", -- 2 chars
},
to = {
"d" .. p[2],
"a" .. p[1], "c" .. p[1], "d" .. p[1], "e" .. p[1], "g" .. p[1], "i" .. p[1], "l" .. p[1], "n" .. p[1], "o" .. p[1], "o" .. p[2], "o" .. p[3], "s" .. p[1], "t" .. p[1], "u" .. p[1], "u" .. p[2], "u" .. p[3], "z" .. p[1],
}
},
},
standardChars = {
Latn = "AaÁáBbCcDdEeÉéFfGgHhIiÍíJjKkLlMmNnOoÓóÖöŐőPpQqRrSsTtUuÚúÜüŰűVvWwXxYyZz",
c.punc
},
english_name = "Hungarian", --TLCHANGE
spanish_name = "Húngaro" --TLCHANGE
}
m["hy"] = {
"Armenyo", --from Spanish "armenio"
8785,
"hyx",
"Armn, Brai",
ancestors = "axm",
translit = {
Armn = "Armn-translit"
},
override_translit = true,
entry_name = {
Armn = {
remove_diacritics = "՛՜՞՟",
from = {"եւ", "<sup>յ</sup>", "<sup>ի</sup>", "<sup>է</sup>", "յ̵", "ՙ", "՚"},
to = {"և", "յ", "ի", "է", "ֈ", "ʻ", "’"}
},
},
sort_key = {
Armn = {
from = {
"ու", "եւ", -- 2 chars
"և" -- 1 char
},
to = {
"ւ", "եվ",
"եվ"
}
},
},
english_name = "Armenian", --TLCHANGE
spanish_name = "Armenio" --TLCHANGE
}
m["hz"] = {
"Herero",
33315,
"bnt-swb",
"Latn",
english_name = "Herero", --TLCHANGE
}
m["ia"] = {
"Interlingua",
35934,
"art",
"Latn",
english_name = "Interlingua", --TLCHANGE
}
m["id"] = {
"Indones", --tanggap na pangalan na
9240,
"poz-mly",
"Latn",
ancestors = "ms",
standardChars = "AaBbCcDdEeFfGgHhIiJjKkLlMmNnOoPpQqRrSsTtUuVvWwXxYyZz" .. c.punc,
english_name = "Indonesian", --TLCHANGE
}
m["ie"] = {
"Interlingue",
35850,
"art",
"Latn",
type = "appendix-constructed",
entry_name = {remove_diacritics = c.grave .. c.acute .. c.circ},
english_name = "Interlingue", --TLCHANGE
}
m["ig"] = {
"Igbo",
33578,
"alv-igb",
"Latn",
entry_name = {remove_diacritics = c.grave .. c.acute .. c.macron},
sort_key = {
from = {"gb", "gh", "gw", "ị", "kp", "kw", "ṅ", "nw", "ny", "ọ", "sh", "ụ"},
to = {"g" .. p[1], "g" .. p[2], "g" .. p[3], "i" .. p[1], "k" .. p[1], "k" .. p[2], "n" .. p[1], "n" .. p[2], "n" .. p[3], "o" .. p[1], "s" .. p[1], "u" .. p[1]}
},
english_name = "Igbo", --TLCHANGE
}
m["ii"] = {
"Nuosu",
34235,
"tbq-nlo",
"Yiii",
translit = "ii-translit",
english_name = "Nuosu", --TLCHANGE
}
m["ik"] = {
"Inupiaq",
27183,
"esx-inu",
"Latn",
sort_key = {
from = {
"ch", "ġ", "dj", "ḷ", "ł̣", "ñ", "ng", "r̂", "sr", "zr", -- 2 chars
"ł", "ŋ", "ʼ" -- 1 char
},
to = {
"c" .. p[1], "g" .. p[1], "h" .. p[1], "l" .. p[1], "l" .. p[3], "n" .. p[1], "n" .. p[2], "r" .. p[1], "s" .. p[1], "z" .. p[1],
"l" .. p[2], "n" .. p[2], "z" .. p[2]
}
},
english_name = "Inupiaq", --TLCHANGE
}
m["io"] = {
"Ido",
35224,
"art",
"Latn",
english_name = "Ido", --TLCHANGE
}
m["is"] = {
"Islandes", --TLCHANGE from Spanish "islandés"
294,
"gmq-ins",
"Latn",
sort_key = {
from = {"á", "ð", "é", "í", "ó", "ú", "ý", "þ", "æ", "ö"},
to = {"a" .. p[1], "d" .. p[1], "e" .. p[1], "i" .. p[1], "o" .. p[1], "u" .. p[1], "y" .. p[1], "z" .. p[1], "z" .. p[2], "z" .. p[3]}
},
standardChars = "AaÁáBbDdÐðEeÉéFfGgHhIiÍíJjKkLlMmNnOoÓóPpRrSsTtUuÚúVvXxYyÝýÞþÆæÖö" .. c.punc,
english_name = "Icelandic", --TLCHANGE
spanish_name = "Islandés" --TLCHANGE
}
m["it"] = {
"Italyano", --from Spanish "italiano"
652,
"roa-itr",
"Latn",
ancestors = "roa-oit",
sort_key = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.diaer .. c.ringabove},
standardChars = "AaÀàBbCcDdEeÈèÉéFfGgHhIiÌìLlMmNnOoÒòPpQqRrSsTtUuÙùVvZz" .. c.punc,
english_name = "Italian", --TLCHANGE
spanish_name = "Italiano" --TLCHANGE
}
m["iu"] = {
"Inuktitut",
29921,
"esx-inu",
"Cans, Latn",
translit = {
Cans = "cr-translit"
},
override_translit = true,
english_name = "Inuktitut", --TLCHANGE
}
m["ja"] = {
"Hapones",
5287,
"jpx",
"Jpan, Latn, Brai",
ancestors = "ja-ear",
translit = s["jpx-translit"],
link_tr = true,
display_text = s["jpx-displaytext"],
entry_name = s["jpx-entryname"],
sort_key = s["jpx-sortkey"],
is_official_kwf_name = "https://kwf.gov.ph/wp-content/uploads/MMP_Full.pdf#page=32", --TLCHANGE
english_name = "Japanese", --TLCHANGE
}
m["jv"] = {
"Havanes", --TLCHANGE from Spanish "javanés"
33549,
"poz",
"Latn, Java",
ancestors = "kaw",
translit = {
Java = "jv-translit"
},
link_tr = true,
entry_name = {
Latn = {remove_diacritics = c.circ} -- Modern jv don't use ê
},
sort_key = {
Latn = {
from = {"å", "dh", "é", "è", "ng", "ny", "th"},
to = {"a" .. p[1], "d" .. p[1], "e" .. p[1], "e" .. p[2], "n" .. p[1], "n" .. p[2], "t" .. p[1]}
},
},
english_name = "Javanese", --TLCHANGE
spanish_name = "Javanés" --TLCHANGE
}
m["ka"] = {
"Heorhiyano", --from Spanish "georgiano"
8108,
"ccs-gzn",
"Geor, Geok, Hebr", -- Hebr is used to write Judeo-Georgian
ancestors = "ka-mid",
translit = {
Geor = "Geor-translit",
Geok = "Geok-translit",
},
override_translit = true,
display_text = {
Hebr = "Hebr-common",
},
entry_name = {
Geor = s["ka-entryname"],
Geok = s["ka-entryname"],
Hebr = "Hebr-common",
},
sort_key = {
Hebr = "Hebr-common",
},
english_name = "Georgian", --TLCHANGE
spanish_name = "Georgiano" --TLCHANGE
}
m["kg"] = {
"Kongo",
33702,
"bnt-kng",
"Latn",
english_name = "Kongo", --TLCHANGE
}
m["ki"] = {
"Kikuyu",
33587,
"bnt-kka",
"Latn",
english_name = "Kikuyu", --TLCHANGE
}
m["kj"] = {
"Kwanyama",
1405077,
"bnt-ova",
"Latn",
english_name = "Kwanyama", --TLCHANGE
}
m["kk"] = {
"Kazaho", --TLCHANGE from Spanish "kazajo"
9252,
"trk-kno",
"Cyrl, Latn, kk-Arab",
translit = {
Cyrl = {
from = {
"Ё", "ё", "Й", "й", "Нг", "нг", "Ӯ", "ӯ", -- 2 chars; are "Ӯ" and "ӯ" actually used?
"А", "а", "Ә", "ә", "Б", "б", "В", "в", "Г", "г", "Ғ", "ғ", "Д", "д", "Е", "е", "Ж", "ж", "З", "з", "И", "и", "К", "к", "Қ", "қ", "Л", "л", "М", "м", "Н", "н", "Ң", "ң", "О", "о", "Ө", "ө", "П", "п", "Р", "р", "С", "с", "Т", "т", "У", "у", "Ұ", "ұ", "Ү", "ү", "Ф", "ф", "Х", "х", "Һ", "һ", "Ц", "ц", "Ч", "ч", "Ш", "ш", "Щ", "щ", "Ъ", "ъ", "Ы", "ы", "І", "і", "Ь", "ь", "Э", "э", "Ю", "ю", "Я", "я", -- 1 char
},
to = {
"E", "e", "İ", "i", "Ñ", "ñ", "U", "u",
"A", "a", "Ä", "ä", "B", "b", "V", "v", "G", "g", "Ğ", "ğ", "D", "d", "E", "e", "J", "j", "Z", "z", "İ", "i", "K", "k", "Q", "q", "L", "l", "M", "m", "N", "n", "Ñ", "ñ", "O", "o", "Ö", "ö", "P", "p", "R", "r", "S", "s", "T", "t", "U", "u", "Ū", "ū", "Ü", "ü", "F", "f", "X", "x", "H", "h", "S", "s", "Ç", "ç", "Ş", "ş", "Ş", "ş", "", "", "Y", "y", "I", "ı", "", "", "É", "é", "Ü", "ü", "Ä", "ä",
}
}
},
-- override_translit = true,
sort_key = {
Cyrl = {
from = {"ә", "ғ", "ё", "қ", "ң", "ө", "ұ", "ү", "һ", "і"},
to = {"а" .. p[1], "г" .. p[1], "е" .. p[1], "к" .. p[1], "н" .. p[1], "о" .. p[1], "у" .. p[1], "у" .. p[2], "х" .. p[1], "ы" .. p[1]}
},
},
standardChars = {
Cyrl = "АаӘәБбВвГгҒғДдЕеЁёЖжЗзИиЙйКкҚқЛлМмНнҢңОоӨөПпРрСсТтУуҰұҮүФфХхҺһЦцЧчШшЩщЪъЫыІіЬьЭэЮюЯя",
c.punc
},
english_name = "Kazakh", --TLCHANGE
spanish_name = "Kazajo" --TLCHANGE
}
m["kl"] = {
"Groenlandes", --TLCHANGE from Spanish "groenlandés"
25355,
"esx-inu",
"Latn",
sort_key = {
from = {"æ", "ø", "å"},
to = {"z" .. p[1], "z" .. p[2], "z" .. p[3]}
},
english_name = "Greenlandic", --TLCHANGE
spanish_name = "Groenlandés" --TLCHANGE
}
m["km"] = {
"Hemer", --TLCHANGE from Spanish "jemer"
9205,
"mkh-kmr",
"Khmr",
ancestors = "xhm",
translit = "km-translit",
english_name = "Khmer", --TLCHANGE
spanish_name = "Jemer" --TLCHANGE
}
m["kn"] = {
"Kanares", --TLCHANGE from Spanish "canarés"
33673,
"dra-kan",
"Knda, Tutg",
ancestors = "dra-mkn",
translit = {
Knda = "kn-translit",
},
english_name = "Kannada", --TLCHANGE
spanish_name = "Canarés" --TLCHANGE
}
m["ko"] = {
"Koreano", --TLCHANGE official from KWF
9176,
"qfa-kor",
"Kore, Brai",
ancestors = "ko-ear",
translit = {
Kore = "ko-translit",
},
entry_name = {
Kore = s["Kore-entryname"],
},
is_official_kwf_name = "https://kwf.gov.ph/wp-content/uploads/MMP_Full.pdf#page=41", --TLCHANGE
english_name = "Korean", --TLCHANGE
}
m["kr"] = {
"Kanuri",
36094,
"ssa-sah",
"Latn, Arab",
-- the sortkey and entry_name are only for standard Kanuri; when dialectal entries get added, someone will have to work out how the dialects should be represented orthographically
entry_name = {
Latn = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.breve}
},
sort_key = {
Latn = {
from = {"ǝ", "ny", "ɍ", "sh"},
to = {"e" .. p[1], "n" .. p[1], "r" .. p[1], "s" .. p[1]}
},
},
english_name = "Kanuri", --TLCHANGE
}
m["ks"] = {
"Katsemir", --TLCHANGE
33552,
"inc-kas",
"ks-Arab, Deva, Shrd, Latn",
translit = {
["ks-Arab"] = "ks-Arab-translit",
Deva = "ks-Deva-translit",
Shrd = "Shrd-translit",
},
english_name = "Kashmiri", --TLCHANGE
spanish_name = "Cachemir", --TLCHANGE
}
-- "kv" IS TREATED AS "koi", "kpv", SEE WT:LT
m["kw"] = {
"Korniko", --TLCHANGE from Spanish "córnico"
25289,
"cel-brs",
"Latn",
ancestors = "cnx",
sort_key = {
from = {"ch"},
to = {"c" .. p[1]}
},
english_name = "Cornish", --TLCHANGE
spanish_name = "Córnico" --TLCHANGE
}
m["ky"] = {
"Kirgis", --from Spanish "kirguís"
9255,
"trk-kkp",
"Cyrl, Latn, Arab",
translit = {
Cyrl = "ky-translit"
},
override_translit = true,
sort_key = {
Cyrl = {
from = {"ё", "ң", "ө", "ү"},
to = {"е" .. p[1], "н" .. p[1], "о" .. p[1], "у" .. p[1]}
},
},
english_name = "Kyrgyz", --TLCHANGE
spanish_name = "Kirguís" --TLCHANGE
}
m["la"] = {
"Latin", -- official from KWF
397,
"itc-laf",
"Latn",
ancestors = "itc-ola",
display_text = {
Latn = s["itc-Latn-displaytext"]
},
entry_name = {
Latn = s["itc-Latn-entryname"]
},
sort_key = {
Latn = s["itc-Latn-sortkey"]
},
standardChars = {
Latn = "AaBbCcDdEeFfGgHhIiLlMmNnOoPpQqRrSsTtUuVvXx",
c.punc
},
is_official_kwf_name = "https://kwf.gov.ph/wp-content/uploads/MMP_Full.pdf#page=114", --TLCHANGE
english_name = "Latin", --TLCHANGE
}
m["lb"] = {
"Luxemburges", --TLCHANGE from Spanish "luxemburgués"
9051,
"gmw-hgm",
"Latn, Brai",
ancestors = "gmw-cfr",
sort_key = {
Latn = {
from = {"ä", "ë", "é"},
to = {"z" .. p[1], "z" .. p[2], "z" .. p[3]}
},
},
english_name = "Luxembourgish", --TLCHANGE
spanish_name = "Luxemburgués" --TLCHANGE
}
m["lg"] = {
"Luganda",
33368,
"bnt-nyg",
"Latn",
entry_name = {remove_diacritics = c.acute .. c.circ},
sort_key = {
from = {"ŋ"},
to = {"n" .. p[1]}
},
english_name = "Luganda", --TLCHANGE
}
m["li"] = {
"Limburges", --from Spanish "limburgués"
102172,
"gmw-frk",
"Latn",
ancestors = "dum",
english_name = "Limburgish", --TLCHANGE
spanish_name = "Limburgués" --TLCHANGE
}
m["ln"] = {
"Lingala",
36217,
"bnt-bmo",
"Latn",
sort_key = {
remove_diacritics = c.acute .. c.circ .. c.caron,
from = {"ɛ", "gb", "mb", "mp", "nd", "ng", "nk", "ns", "nt", "ny", "nz", "ɔ"},
to = {"e" .. p[1], "g" .. p[1], "m" .. p[1], "m" .. p[2], "n" .. p[1], "n" .. p[2], "n" .. p[3], "n" .. p[4], "n" .. p[5], "n" .. p[6], "n" .. p[7], "o" .. p[1]}
},
english_name = "Lingala", --TLCHANGE
}
m["lo"] = {
"Lao", --TLCHANGE
9211,
"tai-swe",
"Laoo",
translit = "lo-translit",
sort_key = "Laoo-sortkey",
standardChars = "0-9ກຂຄງຈຊຍດຕຖທນບປຜຝພຟມຢຣລວສຫອຮຯ-ໝ" .. c.punc,
english_name = "Lao", --TLCHANGE
}
m["lt"] = {
"Litwano", --from Spanish "lituano"
9083,
"bat-eas",
"Latn",
ancestors = "olt",
display_text = "lt-common",
entry_name = "lt-common",
sort_key = "lt-common",
standardChars = "AaĄąBbCcČčDdEeĘęĖėFfGgHhIiĮįYyJjKkLlMmNnOoPpRrSsŠšTtUuŲųŪūVvZzŽž" .. c.punc,
english_name = "Lithuanian", --TLCHANGE
spanish_name = "Lituano" --TLCHANGE
}
m["lu"] = {
"Luba-Katanga",
36157,
"bnt-lub",
"Latn",
english_name = "Luba-Katanga", --TLCHANGE
}
m["lv"] = {
"Leton", --from Spanish "letón"
9078,
"bat-eas",
"Latn",
entry_name = {
-- This attempts to convert vowels with tone marks to vowels either with or without macrons. Specifically, there should be no macrons if the vowel is part of a diphthong (including resonant diphthongs such pìrksts -> pirksts not #pīrksts). What we do is first convert the vowel + tone mark to a vowel + tilde in a decomposed fashion, then remove the tilde in diphthongs, then convert the remaining vowel + tilde sequences to macroned vowels, then delete any other tilde. We leave already-macroned vowels alone: Both e.g. ar and ār occur before consonants. FIXME: This still might not be sufficient.
from = {"([Ee])" .. c.cedilla, "[" .. c.grave .. c.circ .. c.tilde .."]", "([aAeEiIoOuU])" .. c.tilde .."?([lrnmuiLRNMUI])" .. c.tilde .. "?([^aAeEiIoOuU])", "([aAeEiIoOuU])" .. c.tilde .."?([lrnmuiLRNMUI])" .. c.tilde .."?$", "([iI])" .. c.tilde .. "?([eE])" .. c.tilde .. "?", "([aAeEiIuU])" .. c.tilde, c.tilde},
to = {"%1", c.tilde, "%1%2%3", "%1%2", "%1%2", "%1" .. c.macron}
},
sort_key = {
from = {"ā", "č", "ē", "ģ", "ī", "ķ", "ļ", "ņ", "š", "ū", "ž"},
to = {"a" .. p[1], "c" .. p[1], "e" .. p[1], "g" .. p[1], "i" .. p[1], "k" .. p[1], "l" .. p[1], "n" .. p[1], "s" .. p[1], "u" .. p[1], "z" .. p[1]}
},
standardChars = "AaĀāBbCcČčDdEeĒēFfGgĢģHhIiĪīJjKkĶķLlĻļMmNnŅņOoPpRrSsŠšTtUuŪūVvZzŽž" .. c.punc,
english_name = "Latvian", --TLCHANGE
spanish_name = "Letón" --TLCHANGE
}
m["mg"] = {
"Malgatse", --TLCHANGE from Spanish "malgache"
7930,
"poz-bre",
"Latn, Arab",
english_name = "Malagasy", --TLCHANGE
spanish_name = "Malgache" --TLCHANGE
}
m["mh"] = {
"Marshales", --from Spanish "marshalés"
36280,
"poz-mic",
"Latn",
sort_key = {
from = {"ā", "ļ", "m̧", "ņ", "n̄", "o̧", "ō", "ū"},
to = {"a" .. p[1], "l" .. p[1], "m" .. p[1], "n" .. p[1], "n" .. p[2], "o" .. p[1], "o" .. p[2], "u" .. p[1]}
},
english_name = "Marshallese", --TLCHANGE
spanish_name = "Marshalés" --TLCHANGE
}
m["mi"] = {
"Maori",
36451,
"poz-pep",
"Latn",
sort_key = {
remove_diacritics = c.macron,
from = {"ng", "wh"},
to = {"z" .. p[1], "z" .. p[2]}
},
english_name = "Maori", --TLCHANGE
}
m["mk"] = {
"Masedonyo", --from Spanish "macedonio"
9296,
"zls",
"Cyrl, Polyt",
ancestors = "cu",
translit = {
Cyrl = "mk-translit"
},
display_text = {
Polyt = s["Polyt-displaytext"]
},
entry_name = {
Cyrl = {
remove_diacritics = c.acute,
remove_exceptions = {"Ѓ", "ѓ", "Ќ", "ќ"}
},
Polyt = s["Polyt-entryname"],
},
sort_key = {
Cyrl = {
remove_diacritics = c.grave,
remove_exceptions = {"ѓ", "ќ"},
from = {"ѓ", "ѕ", "ј", "љ", "њ", "ќ", "џ"},
to = {"д" .. p[1], "з" .. p[1], "и" .. p[1], "л" .. p[1], "н" .. p[1], "т" .. p[1], "ч" .. p[1]}
},
Polyt = s["Polyt-sortkey"],
},
standardChars = {
Cyrl = "АаБбВвГгДдЃѓЕеЖжЗзЅѕИиЈјКкЛлЉљМмНнЊњОоПпРрСсТтЌќУуФфХхЦцЧчЏџШш",
c.punc
},
english_name = "Macedonian", --TLCHANGE
spanish_name = "Macedonio" --TLCHANGE
}
m["ml"] = {
"Malayalam",
36236,
"dra-mal",
"Mlym",
translit = "ml-translit",
override_translit = true,
english_name = "Malayalam", --TLCHANGE
}
m["mn"] = {
"Monggol", --from Spanish "mongol"
9246,
"xgn-cen",
"Cyrl, Mong, Latn, Brai",
ancestors = "cmg",
translit = {
Cyrl = "mn-translit",
Mong = "Mong-translit",
},
override_translit = true,
display_text = {
Mong = s["Mong-displaytext"]
},
entry_name = {
Cyrl = {remove_diacritics = c.grave .. c.acute},
Mong = s["Mong-entryname"],
},
sort_key = {
Cyrl = {
remove_diacritics = c.grave,
from = {"ё", "ө", "ү"},
to = {"е" .. p[1], "о" .. p[1], "у" .. p[1]}
},
},
standardChars = {
Cyrl = "АаБбВвГгДдЕеЁёЖжЗзИиЙйЛлМмНнОоӨөРрСсТтУуҮүХхЦцЧчШшЫыЬьЭэЮюЯя—",
Brai = c.braille,
c.punc
},
english_name = "Mongolian", --TLCHANGE
spanish_name = "Mongol" --TLCHANGE
}
-- "mo" IS TREATED AS "ro", SEE WT:LT
m["mr"] = {
"Marathi",
1571,
"inc-sou",
"Deva, Modi",
ancestors = "omr",
translit = {
Deva = "mr-translit",
Modi = "mr-Modi-translit",
},
entry_name = {
Deva = {
from = {"च़", "ज़", "झ़"},
to = {"च", "ज", "झ"}
},
},
english_name = "Marathi", --TLCHANGE
}
m["ms"] = {
"Malay",
9237,
"poz-mly",
"Latn, ms-Arab",
ancestors = "ms-cla",
standardChars = {
Latn = "AaBbCcDdEeFfGgHhIiJjKkLlMmNnOoPpQqRrSsTtUuVvWwXxYyZz",
c.punc
},
is_official_kwf_name = "https://kwfdiksiyonaryo.ph/?query=suwato", --TLCHANGE
english_name = "Malay", --TLCHANGE
}
m["mt"] = {
"Maltes", --from Spanish "maltés"
9166,
"sem-arb",
"Latn",
display_text = {
from = {"'"},
to = {"’"}
},
entry_name = {
from = {"’"},
to = {"'"},
},
ancestors = "sqr",
sort_key = {
from = {
"ċ", "ġ", "ż", -- Convert into PUA so that decomposed form does not get caught by the next step.
"([cgz])", -- Ensure "c" comes after "ċ", "g" comes after "ġ" and "z" comes after "ż".
"g" .. p[1] .. "ħ", -- "għ" after initial conversion of "g".
p[3], p[4], "ħ", "ie", p[5] -- Convert "ċ", "ġ", "ħ", "ie", "ż" into final output.
},
to = {
p[3], p[4], p[5],
"%1" .. p[1],
"g" .. p[2],
"c", "g", "h" .. p[1], "i" .. p[1], "z"
}
},
english_name = "Maltese", --TLCHANGE
spanish_name = "Maltes" --TLCHANGE
}
m["my"] = {
"Birmano", --from Spanish "birmano"
9228,
"tbq-brm",
"Mymr",
ancestors = "obr",
translit = "my-translit",
override_translit = true,
sort_key = {
from = {"ျ", "ြ", "ွ", "ှ", "ဿ"},
to = {"္ယ", "္ရ", "္ဝ", "္ဟ", "သ္သ"}
},
english_name = "Burmese", --TLCHANGE
spanish_name = "Birmano" --TLCHANGE
}
m["na"] = {
"Naurwano", --TLCHANGE from Spanish "nauruano"
13307,
"poz-mic",
"Latn",
english_name = "Nauruan", --TLCHANGE
spanish_name = "Nauruano" --TLCHANGE
}
m["nb"] = {
"Norwego Bokmål", --TLCHANGE from Spanish "noruego"
25167,
"gmq",
"Latn",
wikimedia_codes = "no",
ancestors = "gmq-mno, da", -- da as an (but not the) ancestor of nb was agreed on - do not change without discussion
sort_key = s["no-sortkey"],
standardChars = s["no-standardchars"],
english_name = "Norwegian Bokmål", --TLCHANGE
}
m["nd"] = {
"Hilagang Ndebele",
35613,
"bnt-ngu",
"Latn",
entry_name = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.macron .. c.caron},
english_name = "Northern Ndebele", --TLCHANGE
}
m["ne"] = {
"Nepali",
33823,
"inc-pah",
"Deva, Newa",
translit = {
Deva = "ne-translit"
},
english_name = "Nepali", --TLCHANGE
}
m["ng"] = {
"Ndonga",
33900,
"bnt-ova",
"Latn",
english_name = "Ndonga", --TLCHANGE
}
m["nl"] = {
"Nerlandes", --TLCHANGE from Spanish "neerlandés"
7411,
"gmw-frk",
"Latn, Brai",
ancestors = "dum",
sort_key = {
Latn = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.tilde .. c.diaer .. c.ringabove .. c.cedilla .. "'"},
},
standardChars = {
Latn = "AaBbCcDdEeFfGgHhIiJjKkLlMmNnOoPpQqRrSsTtUuVvWwXxYyZz",
Brai = c.braille,
c.punc
},
english_name = "Dutch", --TLCHANGE
spanish_name = "Neerlandés" --TLCHANGE
}
m["nn"] = {
"Norwego Nynorsk", --TLCHANGE from Spanish "noruego"
25164,
"gmq-wes",
"Latn",
ancestors = "gmq-mno",
entry_name = {
remove_diacritics = c.grave .. c.acute,
},
sort_key = s["no-sortkey"],
standardChars = s["no-standardchars"],
english_name = "Norwegian Nynorsk", --TLCHANGE
}
m["no"] = {
"Norwego", --from Spanish "noruego"
9043,
"gmq-wes",
"Latn",
ancestors = "gmq-mno",
sort_key = s["no-sortkey"],
standardChars = s["no-standardchars"],
english_name = "Norwegian", --TLCHANGE
spanish_name = "Noruego" --TLCHANGE
}
m["nr"] = {
"Katimugang Ndebele",
36785,
"bnt-ngu",
"Latn",
entry_name = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.macron .. c.caron},
english_name = "Southern Ndebele", --TLCHANGE
}
m["nv"] = {
"Navajo",
13310,
"apa",
"Latn, Brai",
sort_key = {
remove_diacritics = c.acute .. c.ogonek,
from = {
"chʼ", "tłʼ", "tsʼ", -- 3 chars
"ch", "dl", "dz", "gh", "hw", "kʼ", "kw", "sh", "tł", "ts", "zh", -- 2 chars
"ł", "ʼ" -- 1 char
},
to = {
"c" .. p[2], "t" .. p[2], "t" .. p[4],
"c" .. p[1], "d" .. p[1], "d" .. p[2], "g" .. p[1], "h" .. p[1], "k" .. p[1], "k" .. p[2], "s" .. p[1], "t" .. p[1], "t" .. p[3], "z" .. p[1],
"l" .. p[1], "z" .. p[2]
}
},
english_name = "Navajo", --TLCHANGE
}
m["ny"] = {
"Chichewa",
33273,
"bnt-nys",
"Latn",
entry_name = {remove_diacritics = c.acute .. c.circ},
sort_key = {
from = {"ng'"},
to = {"ng"}
},
english_name = "Chichewa", --TLCHANGE
}
m["oc"] = {
"Oksitano", --from Spanish "occitano"
14185,
"roa-ocr",
"Latn, Hebr",
ancestors = "pro",
display_text = {
Hebr = "Hebr-common",
},
entry_name = {
Hebr = "Hebr-common",
},
sort_key = {
Latn = {
remove_diacritics = c.grave .. c.acute .. c.diaer .. c.cedilla,
from = {"([lns])·h"},
to = {"%1h"}
},
Hebr = "Hebr-common",
},
english_name = "Occitan", --TLCHANGE
spanish_name = "Occitano" --TLCHANGE
}
m["oj"] = {
"Ojibwe",
33875,
"alg",
"Cans, Latn",
sort_key = {
Latn = {
from = {"aa", "ʼ", "ii", "oo", "sh", "zh"},
to = {"a" .. p[1], "h" .. p[1], "i" .. p[1], "o" .. p[1], "s" .. p[1], "z" .. p[1]}
},
},
english_name = "Ojibwe", --TLCHANGE
}
m["om"] = {
"Oromo",
33864,
"cus-eas",
"Latn, Ethi",
english_name = "Oromo", --TLCHANGE
}
m["or"] = {
"Odia",
33810,
"inc-eas",
"Orya",
ancestors = "inc-mor",
translit = "or-translit",
english_name = "Odia", --TLCHANGE
}
m["os"] = {
"Osetyo", --TLCHANGE from Spanish "osetio"
33968,
"xsc-sar",
"Cyrl, Geor, Latn",
ancestors = "oos",
translit = {
Cyrl = "os-translit",
Geor = "Geor-translit",
},
override_translit = true,
display_text = {
Cyrl = {
from = {"æ"},
to = {"ӕ"}
},
Latn = {
from = {"ӕ"},
to = {"æ"}
},
},
entry_name = {
Cyrl = {
remove_diacritics = c.grave .. c.acute,
from = {"æ"},
to = {"ӕ"}
},
Latn = {
from = {"ӕ"},
to = {"æ"}
},
},
sort_key = {
Cyrl = {
from = {"ӕ", "гъ", "дж", "дз", "ё", "къ", "пъ", "тъ", "хъ", "цъ", "чъ"},
to = {"а" .. p[1], "г" .. p[1], "д" .. p[1], "д" .. p[2], "е" .. p[1], "к" .. p[1], "п" .. p[1], "т" .. p[1], "х" .. p[1], "ц" .. p[1], "ч" .. p[1]}
},
},
english_name = "Ossetian", --TLCHANGE
spanish_name = "Osetio" --TLCHANGE
}
m["pa"] = {
"Punyabi", --TLCHANGE from Spanish "punyabí"
58635,
"inc-pan",
"Guru, pa-Arab",
ancestors = "inc-opa",
translit = {
Guru = "Guru-translit",
["pa-Arab"] = "pa-Arab-translit",
},
entry_name = {
["pa-Arab"] = {
remove_diacritics = c.fathatan .. c.dammatan .. c.kasratan .. c.fatha .. c.damma .. c.kasra .. c.shadda .. c.sukun .. c.nunghunna,
from = {"ݨ", "ࣇ"},
to = {"ن", "ل"}
},
},
english_name = "Punjabi", --TLCHANGE
spanish_name = "Punyabí" --TLCHANGE
}
m["pi"] = {
"Pali",
36727,
"inc-mid",
"Latn, Brah, Deva, Beng, Sinh, Mymr, Thai, Lana, Laoo, Khmr, Cakm", --and also Khom
ancestors = "sa",
translit = {
Brah = "Brah-translit",
Deva = "sa-translit",
Beng = "pi-translit",
Sinh = "si-translit",
Mymr = "pi-translit",
Thai = "pi-translit",
Lana = "pi-translit",
Laoo = "pi-translit",
Khmr = "pi-translit",
Cakm = "Cakm-translit",
},
entry_name = {
Thai = {
from = {"ึ", u(0xF700), u(0xF70F)}, -- FIXME: Not clear what's going on with the PUA characters here.
to = {"ิํ", "ฐ", "ญ"}
},
remove_diacritics = c.VS01
},
sort_key = { -- FIXME: This needs to be converted into the current standardized format.
from = {"ā", "ī", "ū", "ḍ", "ḷ", "m[" .. c.dotabove .. c.dotbelow .. "]", "ṅ", "ñ", "ṇ", "ṭ", "([เโ])([ก-ฮ])", "([ເໂ])([ກ-ຮ])", "ᩔ", "ᩕ", "ᩖ", "ᩘ", "([ᨭ-ᨱ])ᩛ", "([ᨷ-ᨾ])ᩛ", "ᩤ", u(0xFE00), u(0x200D)},
to = {"a~", "i~", "u~", "d~", "l~", "m~", "n~", "n~~", "n~~~", "t~", "%2%1", "%2%1", "ᩈ᩠ᩈ", "᩠ᩁ", "᩠ᩃ", "ᨦ᩠", "%1᩠ᨮ", "%1᩠ᨻ", "ᩣ"}
},
english_name = "Pali", --TLCHANGE
}
m["pl"] = {
"Polako", --from Spanish "polaco"
809,
"zlw-lch",
"Latn",
ancestors = "zlw-mpl",
sort_key = {
from = {"ą", "ć", "ę", "ł", "ń", "ó", "ś", "ź", "ż"},
to = {"a" .. p[1], "c" .. p[1], "e" .. p[1], "l" .. p[1], "n" .. p[1], "o" .. p[1], "s" .. p[1], "z" .. p[1], "z" .. p[2]}
},
standardChars = "AaĄąBbCcĆćDdEeĘęFfGgHhIiJjKkLlŁłMmNnŃńOoÓóPpRrSsŚśTtUuWwYyZzŹźŻż" .. c.punc,
english_name = "Polish", --TLCHANGE
spanish_name = "Polaco" --TLCHANGE
}
m["ps"] = {
"Pastun", --TLCHANGE from Spanish "pastún"
58680,
"ira-pat",
"ps-Arab",
entry_name = {remove_diacritics = c.fathatan .. c.dammatan .. c.kasratan .. c.fatha .. c.damma .. c.kasra .. c.shadda .. c.sukun .. c.zwarakay .. c.superalef},
english_name = "Pashto", --TLCHANGE
spanish_name = "Pastún" --TLCHANGE
}
m["pt"] = {
"Portuges", --from Spanish "portugués"
5146,
"roa-gap",
"Latn, Brai",
sort_key = {
Latn = {
remove_diacritics = c.grave .. c.acute .. c.circ .. c.tilde .. c.macron .. c.diaer .. c.cedilla,
from = {"ª", "æ", "º", "œ"},
to = {"a", "ae", "o", "oe"}
},
},
standardChars = {
Latn = "AaÁáÂâÃãBbCcÇçDdEeÉéÊêFfGgHhIiÍíJjLlMmNnOoÓóÔôÕõPpQqRrSsTtUuÚúVvXxZz",
Brai = c.braille,
c.punc
},
english_name = "Portuguese", --TLCHANGE
spanish_name = "Portugués" --TLCHANGE
}
m["qu"] = {
"Ketsuwa", --TLCHANGE from Spanish "quechua"
5218,
"qwe",
"Latn",
english_name = "Quechua", --TLCHANGE
spanish_name = "Quechua" --TLCHANGE
}
m["rm"] = {
"Romantse", --TLCHANGE from Spanish "Romanche"
13199,
"roa-rhe",
"Latn",
sort_key = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.diaer .. c.small_e},
english_name = "Romansch", --TLCHANGE
spanish_name = "Romanche" --TLCHANGE
}
m["ro"] = {
"Rumano", --from Spanish "rumano"
7913,
"roa-eas",
"Latn, Cyrl, Cyrs",
translit = {
Cyrl = "ro-translit"
},
sort_key = {
Latn = {
remove_diacritics = c.grave .. c.acute,
from = {"ă", "â", "î", "ș", "ț"},
to = {"a" .. p[1], "a" .. p[2], "i" .. p[1], "s" .. p[1], "t" .. p[1]}
},
Cyrl = {
from = {"ӂ"},
to = {"ж" .. p[1]}
},
},
standardChars = {
Latn = "AaĂăÂâBbCcDdEeFfGgHhIiÎîJjLlMmNnOoPpRrSsȘșTtȚțUuVvXxZz",
Cyrl = "АаБбВвГгДдЕеЖжӁӂЗзИиЙйКкЛлМмНнОоПпРрСсТтУуФфХхЦцЧчШшЫыЬьЭэЮюЯя",
c.punc
},
english_name = "Romanian", --TLCHANGE
spanish_name = "Rumano" --TLCHANGE
}
m["ru"] = {
"Ruso", --from Spanish "ruso"
7737,
"zle",
"Cyrl, Brai",
ancestors = "zle-mru",
translit = {
Cyrl = "ru-translit"
},
display_text = {
Cyrl = {
from = {"'"},
to = {"’"}
},
},
entry_name = {
Cyrl = {
remove_diacritics = c.grave .. c.acute .. c.diaer,
remove_exceptions = {"Ё", "ё", "Ѣ̈", "ѣ̈", "Я̈", "я̈"},
from = {"’"},
to = {"'"},
},
},
sort_key = {
Cyrl = {
remove_diacritics = c.grave .. c.acute .. c.diaer,
remove_exceptions = {"ё", "ѣ̈", "я̈"},
from = {
"ё", "ѣ̈", "я̈", -- 2 chars
"і", "ѣ", "ѳ", "ѵ" -- 1 char
},
to = {
"е" .. p[1], "ь" .. p[2], "я" .. p[1],
"и" .. p[1], "ь" .. p[1], "я" .. p[2], "я" .. p[3]
}
},
},
standardChars = {
Cyrl = "АаБбВвГгДдЕеЁёЖжЗзИиЙйКкЛлМмНнОоПпРрСсТтУуФфХхЦцЧчШшЩщЪъЫыЬьЭэЮюЯя—",
Brai = c.braille,
(c.punc:gsub("'", "")) -- Exclude apostrophe.
},
english_name = "Russian", --TLCHANGE
spanish_name = "Ruso" --TLCHANGE
}
m["rw"] = {
"Rwanda-Rundi",
3217514,
"bnt-glb",
"Latn",
entry_name = {remove_diacritics = c.acute .. c.circ .. c.macron .. c.caron},
english_name = "Rwanda-Rundi", --TLCHANGE
}
m["sa"] = {
"Sanskrit", --TLCHANGE it's "Sanskrit" according to KWF
11059,
"inc",
"as-Beng, Bali, Beng, Bhks, Brah, Mymr, xwo-Mong, Deva, Gujr, Guru, Gran, Hani, Java, Kthi, Knda, Kawi, Khar, Khmr, Laoo, Mlym, mnc-Mong, Marc, Modi, Mong, Nand, Newa, Orya, Phag, Ranj, Saur, Shrd, Sidd, Sinh, Soyo, Lana, Takr, Taml, Tang, Telu, Thai, Tibt, Tutg, Tirh, Zanb", --and also Khom; script codes sorted by canonical name rather than code for [[MOD:sa-convert]]
translit = {
Beng = "sa-Beng-translit",
["as-Beng"] = "sa-Beng-translit",
Brah = "Brah-translit",
Deva = "sa-translit",
Gujr = "sa-Gujr-translit",
Guru = "sa-Guru-translit",
Java = "sa-Java-translit",
Kthi = "sa-Kthi-translit",
Khmr = "pi-translit",
Knda = "sa-Knda-translit",
Lana = "pi-translit",
Laoo = "pi-translit",
Mlym = "sa-Mlym-translit",
Modi = "sa-Modi-translit",
Mong = "Mong-translit",
["mnc-Mong"] = "mnc-translit",
["xwo-Mong"] = "xal-translit",
Mymr = "pi-translit",
Orya = "sa-Orya-translit",
Shrd = "Shrd-translit",
Sidd = "Sidd-translit",
Sinh = "si-translit",
Taml = "sa-Taml-translit",
Telu = "sa-Telu-translit",
Thai = "pi-translit",
Tibt = "Tibt-translit",
},
display_text = {
Mong = s["Mong-displaytext"],
Tibt = s["Tibt-displaytext"],
},
entry_name = {
Mong = s["Mong-entryname"],
Tibt = s["Tibt-entryname"],
Thai = {
from = {"ึ", u(0xF700), u(0xF70F)}, -- FIXME: Not clear what's going on with the PUA characters here.
to = {"ิํ", "ฐ", "ญ"}
},
remove_diacritics = c.VS01 .. c.udatta .. c.anudatta
},
sort_key = {
Tibt = "Tibt-sortkey",
{ -- FIXME: This needs to be converted into the current standardized format.
from = {"ā", "ī", "ū", "ḍ", "ḷ", "ḹ", "m[" .. c.dotabove .. c.dotbelow .. "]", "ṅ", "ñ", "ṇ", "ṛ", "ṝ", "ś", "ṣ", "ṭ", "([เโไ])([ก-ฮ])", "([ເໂໄ])([ກ-ຮ])", "ᩔ", "ᩕ", "ᩖ", "ᩘ", "([ᨭ-ᨱ])ᩛ", "([ᨷ-ᨾ])ᩛ", "ᩤ", u(0xFE00), u(0x200D)},
to = {"a~", "i~", "u~", "d~", "l~", "l~~", "m~", "n~", "n~~", "n~~~", "r~", "r~~", "s~", "s~~", "t~", "%2%1", "%2%1", "ᩈ᩠ᩈ", "᩠ᩁ", "᩠ᩃ", "ᨦ᩠", "%1᩠ᨮ", "%1᩠ᨻ", "ᩣ"},
},
},
is_official_kwf_name = "https://kwfdiksiyonaryo.ph/?query=S%C3%A1nskrit", --TLCHANGE
english_name = "Sanskrit", --TLCHANGE
}
m["sc"] = {
"Sardo", --TLCHANGE from Spanish "sardo"
33976,
"roa-sou",
"Latn",
english_name = "Sardinian", --TLCHANGE
spanish_name = "Sardo" --TLCHANGE
}
m["sd"] = {
"Sindi", --TLCHANGE from Spanish "sindi"
33997,
"inc-snd",
"sd-Arab, Deva, Sind, Khoj",
translit = {
Sind = "Sind-translit"
},
entry_name = {
["sd-Arab"] = {
remove_diacritics = c.kashida .. c.fathatan .. c.dammatan .. c.kasratan .. c.fatha .. c.damma .. c.kasra .. c.shadda .. c.sukun .. c.superalef,
from = {"ٱ"},
to = {"ا"}
},
},
english_name = "Sindhi", --TLCHANGE
spanish_name = "Sindi" --TLCHANGE
}
m["se"] = {
"Hilagang Sami",
33947,
"smi",
"Latn",
display_text = {
from = {"'"},
to = {"ˈ"}
},
entry_name = {remove_diacritics = c.macron .. c.dotbelow .. "'ˈ"},
sort_key = {
from = {"á", "č", "đ", "ŋ", "š", "ŧ", "ž"},
to = {"a" .. p[1], "c" .. p[1], "d" .. p[1], "n" .. p[1], "s" .. p[1], "t" .. p[1], "z" .. p[1]}
},
standardChars = "AaÁáBbCcČčDdĐđEeFfGgHhIiJjKkLlMmNnŊŋOoPpRrSsŠšTtŦŧUuVvZzŽž" .. c.punc,
english_name = "Northern Sami", --TLCHANGE
}
m["sg"] = {
"Sango",
33954,
"crp",
"Latn",
ancestors = "ngb",
english_name = "Sango", --TLCHANGE
}
m["sh"] = {
"Serbokroata", --TLCHANGE from Spanish "Serbocroata"
9301,
"zls",
"Latn, Cyrl, Glag",
ietf_subtag = "hbs", -- ISO 639-3 code, since "sh" is deprecated from ISO 639-1
wikimedia_codes = "sh, bs, hr, sr",
entry_name = {
Latn = {
remove_diacritics = c.grave .. c.acute .. c.tilde .. c.macron .. c.dgrave .. c.invbreve,
remove_exceptions = {"Ć", "ć", "Ś", "ś", "Ź", "ź"}
},
Cyrl = {
remove_diacritics = c.grave .. c.acute .. c.tilde .. c.macron .. c.dgrave .. c.invbreve,
remove_exceptions = {"З́", "з́", "С́", "с́"}
},
},
sort_key = {
Latn = {
remove_diacritics = c.grave .. c.acute .. c.tilde .. c.macron .. c.dgrave .. c.invbreve,
remove_exceptions = {"ć", "ś", "ź"},
from = {"č", "ć", "dž", "đ", "lj", "nj", "š", "ś", "ž", "ź"},
to = {"c" .. p[1], "c" .. p[2], "d" .. p[1], "d" .. p[2], "l" .. p[1], "n" .. p[1], "s" .. p[1], "s" .. p[2], "z" .. p[1], "z" .. p[2]}
},
Cyrl = {
remove_diacritics = c.grave .. c.acute .. c.tilde .. c.macron .. c.dgrave .. c.invbreve,
remove_exceptions = {"з́", "с́"},
from = {"ђ", "з́", "ј", "љ", "њ", "с́", "ћ", "џ"},
to = {"д" .. p[1], "з" .. p[1], "и" .. p[1], "л" .. p[1], "н" .. p[1], "с" .. p[1], "т" .. p[1], "ч" .. p[1]}
},
},
standardChars = {
Latn = "AaBbCcČčĆćDdĐđEeFfGgHhIiJjKkLlMmNnOoPpRrSsŠšTtUuVvZzŽž",
Cyrl = "АаБбВвГгДдЂђЕеЖжЗзИиЈјКкЛлЉљМмНнЊњОоПпРрСсТтЋћУуФфХхЦцЧчЏџШш",
c.punc
},
english_name = "Serbo-Croatian", --TLCHANGE
spanish_name = "Serbocroata" --TLCHANGE
}
m["si"] = {
"Singgales", --from Spanish "cingalés"
13267,
"inc-ins",
"Sinh",
translit = "si-translit",
override_translit = true,
english_name = "Sinhalese", --TLCHANGE
spanish_name = "Singalés" --TLCHANGE
}
m["sk"] = {
"Eslovako", --TLCHANGE from Spanish "eslovaco"
9058,
"zlw",
"Latn",
ancestors = "zlw-osk",
sort_key = {remove_diacritics = c.acute .. c.circ .. c.diaer .. c.caron},
standardChars = "AaÁáÄäBbCcČčDdĎďEeÉéFfGgHhIiÍíJjKkLlĹ弾MmNnŇňOoÓóÔôPpRrŔŕSsŠšTtŤťUuÚúVvYyÝýZzŽž" .. c.punc,
english_name = "Slovak", --TLCHANGE
spanish_name = "Eslovaco" --TLCHANGE
}
m["sl"] = {
"Esloveno", --TLCHANGE from Spanish "esloveno"
9063,
"zls",
"Latn",
entry_name = {
remove_diacritics = c.grave .. c.acute .. c.circ .. c.macron .. c.dgrave .. c.invbreve .. c.dotbelow,
remove_exceptions = {"Ć", "ć", "Ǵ", "ǵ", "Ś", "ś", "Ź", "ź"},
from = {"Ə", "ə", "Ł", "ł"},
to = {"E", "e", "L", "l"},
},
sort_key = {
remove_diacritics = c.grave .. c.acute .. c.circ .. c.tilde .. c.macron .. c.dotabove .. c.ringabove .. c.dgrave .. c.invbreve .. c.dotbelow .. c.ringbelow .. c.ogonek,
remove_exceptions = {"ć", "ǵ", "ś", "ź"},
from = {"ä", "č", "ć", "đ", "ə", "ë", "ǧ", "ǵ", "ï", "ł", "ö", "š", "ś", "ü", "ž", "ź"},
to = {"a" .. p[1], "c" .. p[1], "c" .. p[2], "d" .. p[1], "e", "e" .. p[1], "g" .. p[1], "g" .. p[2], "i" .. p[1], "l", "o" .. p[1], "s" .. p[1], "s" .. p[2], "u" .. p[1], "z" .. p[1], "z" .. p[2]},
},
standardChars = "AaBbCcČčDdEeFfGgHhIiJjKkLlMmNnOoPpRrSsŠšTtUuVvZzŽž" .. c.punc,
english_name = "Slovene", --TLCHANGE
spanish_name = "Esloveno" --TLCHANGE
}
m["sm"] = {
"Samoano", --from Spanish "samoano"
34011,
"poz-pnp",
"Latn",
english_name = "Samoan", --TLCHANGE
spanish_name = "Samoano" --TLCHANGE
}
m["sn"] = {
"Shona",
34004,
"bnt-sho",
"Latn",
entry_name = {remove_diacritics = c.acute},
english_name = "Shona", --TLCHANGE
}
m["so"] = {
"Somali",
13275,
"cus-som",
"Latn, Arab, Osma",
entry_name = {
Latn = {remove_diacritics = c.grave .. c.acute .. c.circ}
},
english_name = "Somali", --TLCHANGE
}
m["sq"] = {
"Albanes", --from Spanish "albanés"
8748,
"sqj",
"Latn, Grek, ota-Arab, Elba, Todr, Vith",
translit = {
Elba = "Elba-translit",
},
display_text = {
Grek = s["Grek-displaytext"],
},
entry_name = {
Latn = {
remove_diacritics = c.acute,
from = {'^[ie] (%w)', '^të (%w)'}, to = {'%1', '%1'},
},
Grek = { -- Diacritic removal from Grek-entryname excluded.
from = s["Grek-entryname"].from,
to = s["Grek-entryname"].to,
},
},
sort_key = {
Latn = {
remove_diacritics = c.acute .. c.circ .. c.tilde .. c.breve .. c.caron,
from = {'^[ie] (%w)', '^të (%w)', 'ç', 'dh', 'ë', 'gj', 'll', 'nj', 'rr', 'sh', 'th', 'xh', 'zh'},
to = {'%1', '%1', 'c'..p[1], 'd'..p[1], 'e'..p[1], 'g'..p[1], 'l'..p[1], 'n'..p[1], 'r'..p[1], 's'..p[1], 't'..p[1], 'x'..p[1], 'z'..p[1]},
}
-- TODO: Grek
},
standardChars = {
Latn = "AaBbCcÇçDdEeËëFfGgHhIiJjKkLlMmNnOoPpQqRrSsTtUuVvXxYyZz",
c.punc
},
english_name = "Albanian", --TLCHANGE
spanish_name = "Albanés" --TLCHANGE
}
m["ss"] = {
"Suwazi", --from Spanish "suazi"
34014,
"bnt-ngu",
"Latn",
entry_name = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.macron .. c.caron},
english_name = "Swazi", --TLCHANGE
spanish_name = "Suazi" --TLCHANGE
}
m["st"] = {
"Sesoto", --TLCHANGE from Spanish "Sesoto"
34340,
"bnt-sts",
"Latn",
entry_name = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.macron .. c.caron},
english_name = "Sotho", --TLCHANGE
spanish_name = "Sesoto" --TLCHANGE
}
m["su"] = {
"Sondanes", --TLCHANGE from Spanish "sondanés"
34002,
"poz-msa",
"Latn, Sund, Arab",
ancestors = "osn",
translit = {
Sund = "su-translit"
},
english_name = "Sundanese", --TLCHANGE
spanish_name = "Sondanés" --TLCHANGE
}
m["sv"] = {
"Suweko", --from Spanish "sueco"
9027,
"gmq-eas",
"Latn",
ancestors = "gmq-osw-lat",
sort_key = {
remove_diacritics = c.grave .. c.acute .. c.circ .. c.tilde .. c.macron .. c.dacute .. c.caron .. c.cedilla .. "':",
remove_exceptions = {"å"},
from = {"ø", "æ", "œ", "ß", "å", "aͤ", "oͤ"},
to = {"o", "ae", "oe", "ss", "z" .. p[1], "ä", "ö"}
},
standardChars = "AaBbCcDdEeFfGgHhIiJjKkLlMmNnOoPpRrSsTtUuVvXxYyÅåÄäÖö" .. c.punc,
english_name = "Swedish", --TLCHANGE
spanish_name = "Sueco" --TLCHANGE
}
m["sw"] = {
"Suwahili", --TLCHANGE from Spanish "suajili"
7838,
"bnt-swh",
"Latn, Arab",
sort_key = {
Latn = {
from = {"ng'"},
to = {"ng" .. p[1]}
},
},
english_name = "Swahili", --TLCHANGE
spanish_name = "Suajili" --TLCHANGE
}
m["ta"] = {
"Tamil",
5885,
"dra-tam",
"Taml",
ancestors = "ta-mid",
translit = "ta-translit",
override_translit = true,
english_name = "Tamil", --TLCHANGE
}
m["te"] = {
"Telugu",
8097,
"dra-tel",
"Telu",
translit = "te-translit",
override_translit = true,
english_name = "Telugu", --TLCHANGE
}
m["tg"] = {
"Tayiko", --from Spanish "tayiko"
9260,
"ira-swi",
"Cyrl, fa-Arab, Latn",
ancestors = "fa-cls",
translit = {
Cyrl = "tg-translit"
},
override_translit = true,
entry_name = {
Cyrl = s["tg-entryname"],
Latn = s["tg-entryname"],
},
sort_key = {
Cyrl = {
from = {"ғ", "ё", "ӣ", "қ", "ӯ", "ҳ", "ҷ"},
to = {"г" .. p[1], "е" .. p[1], "и" .. p[1], "к" .. p[1], "у" .. p[1], "х" .. p[1], "ч" .. p[1]}
},
},
english_name = "Tajik", --TLCHANGE
spanish_name = "Tayiko" --TLCHANGE
}
m["th"] = {
"Tailandes", --from Spanish "tailandés"
9217,
"tai-swe",
"Thai, Khomt, Brai",
translit = {
Thai = "th-translit"
},
sort_key = {
Thai = "Thai-sortkey"
},
english_name = "Thai", --TLCHANGE
spanish_name = "Tailandés" --TLCHANGE
}
m["ti"] = {
"Tigriña", --TLCHANGE from Spanish tigriña
34124,
"sem-eth",
"Ethi",
translit = "Ethi-translit",
english_name = "Tigrinya", --TLCHANGE
spanish_name = "Tigriña" --TLCHANGE
}
m["tk"] = {
"Turkomano", --TLCHANGE from Spanish "turcomano"
9267,
"trk-ogz",
"Latn, Cyrl, Arab",
entry_name = {
Latn = s["tk-entryname"],
Cyrl = s["tk-entryname"],
},
sort_key = {
Latn = {
from = {"ç", "ä", "ž", "ň", "ö", "ş", "ü", "ý"},
to = {"c" .. p[1], "e" .. p[1], "j" .. p[1], "n" .. p[1], "o" .. p[1], "s" .. p[1], "u" .. p[1], "y" .. p[1]}
},
Cyrl = {
from = {"ё", "җ", "ң", "ө", "ү", "ә"},
to = {"е" .. p[1], "ж" .. p[1], "н" .. p[1], "о" .. p[1], "у" .. p[1], "э" .. p[1]}
},
},
english_name = "Turkmen", --TLCHANGE
spanish_name = "Turcomano" --TLCHANGE
}
m["tl"] = {
"Tagalog",
34057,
"phi",
"Latn, Tglg",
translit = {
Tglg = "tl-translit"
},
override_translit = true,
entry_name = {
Latn = {remove_diacritics = c.grave .. c.acute .. c.circ}
},
standardChars = {
Latn = "AaBbKkDdEeGgHhIiLlMmNnOoPpRrSsTtUuWwYy",
c.punc
},
sort_key = {
Latn = "tl-sortkey",
},
is_official_kwf_name = "https://kwfwikaatkultura.ph/tagalog-2/", --TLCHANGE
english_name = "Tagalog", --TLCHANGE
}
m["tn"] = {
"Setswana", --TLCHANGE from Spanish "Setsuana"
34137,
"bnt-sts",
"Latn",
english_name = "Tswana", --TLCHANGE
spanish_name = "Setsuana" --TLCHANGE
}
m["to"] = {
"Tonggano", --from Spanish "tongano"
34094,
"poz-ton",
"Latn",
entry_name = {remove_diacritics = c.acute},
sort_key = {remove_diacritics = c.macron},
english_name = "Tongan", --TLCHANGE
spanish_name = "Tongano" --TLCHANGE
}
m["tr"] = {
"Turko", --from Spanish "turco"
256,
"trk-ogz",
"Latn",
ancestors = "ota",
dotted_dotless_i = true,
sort_key = {
from = {
-- Ignore circumflex, but account for capital Î wrongly becoming ı + circ due to dotted dotless I logic.
"ı" .. c.circ, c.circ,
"i", -- Ensure "i" comes after "ı".
"ç", "ğ", "ı", "ö", "ş", "ü"
},
to = {
"i", "",
"i" .. p[1],
"c" .. p[1], "g" .. p[1], "i", "o" .. p[1], "s" .. p[1], "u" .. p[1]
}
},
standardChars = "AaÂâBbCcÇçDdEeFfGgĞğHhIıİiÎîJjKkLlMmNnOoÖöPpRrSsŞşTtUuÛûÜüVvYyZz" .. c.punc,
english_name = "Turkish", --TLCHANGE
spanish_name = "Turco" --TLCHANGE
}
m["ts"] = {
"Tsongga", --from Spanish "tsonga"
34327,
"bnt-tsr",
"Latn",
english_name = "Tsonga", --TLCHANGE
spanish_name = "Tsonga" --TLCHANGE
}
m["tt"] = {
"Tartaro", --from Spanish "tártaro"
25285,
"trk-kbu",
"Cyrl, Latn, tt-Arab",
translit = {
Cyrl = "tt-translit"
},
override_translit = true,
dotted_dotless_i = true,
sort_key = {
Cyrl = {
from = {"ә", "ў", "ғ", "ё", "җ", "қ", "ң", "ө", "ү", "һ"},
to = {"а" .. p[1], "в" .. p[1], "г" .. p[1], "е" .. p[1], "ж" .. p[1], "к" .. p[1], "н" .. p[1], "о" .. p[1], "у" .. p[1], "х" .. p[1]}
},
Latn = {
from = {
"i", -- Ensure "i" comes after "ı".
"ä", "ə", "ç", "ğ", "ı", "ñ", "ŋ", "ö", "ɵ", "ş", "ü"
},
to = {
"i" .. p[1],
"a" .. p[1], "a" .. p[2], "c" .. p[1], "g" .. p[1], "i", "n" .. p[1], "n" .. p[2], "o" .. p[1], "o" .. p[2], "s" .. p[1], "u" .. p[1]
}
},
},
english_name = "Tatar", --TLCHANGE
spanish_name = "Tártaro" --TLCHANGE
}
-- "tw" IS TREATED AS "ak", SEE WT:LT
m["ty"] = {
"Tahityano", --TLCHANGE from Spanish "tahitiano"
34128,
"poz-pep",
"Latn",
english_name = "Tahitian", --TLCHANGE
spanish_name = "Tahitiano" --TLCHANGE
}
m["ug"] = {
"Wigur", --TLCHANGE from Spanish "uigur"
13263,
"trk-kar",
"ug-Arab, Latn, Cyrl",
ancestors = "chg",
translit = {
["ug-Arab"] = "ug-translit",
Cyrl = "ug-translit",
},
override_translit = true,
english_name = "Uyghur", --TLCHANGE
spanish_name = "Uigur" --TLCHANGE
}
m["uk"] = {
"Ukranyano", --from Spanish "ucraniano"
8798,
"zle",
"Cyrl",
ancestors = "zle-ouk",
translit = "uk-translit",
entry_name = {remove_diacritics = c.grave .. c.acute},
sort_key = {
remove_diacritics = c.grave .. c.acute,
from = {
"ї", -- 2 chars
"ґ", "є", "і" -- 1 char
},
to = {
"и" .. p[2],
"г" .. p[1], "е" .. p[1], "и" .. p[1]
}
},
standardChars = "АаБбВвГгДдЕеЄєЖжЗзИиІіЇїЙйКкЛлМмНнОоПпРрСсТтУуФфХхЦцЧчШшЩщЬьЮюЯя" .. c.punc:gsub("'", ""), -- Exclude apostrophe.
english_name = "Ukrainian", --TLCHANGE
spanish_name = "Ucraniano" --TLCHANGE
}
m["ur"] = {
"Urdu",
1617,
"inc-hnd",
"ur-Arab, Hebr",
translit = {
["ur-Arab"] = "ur-translit"
},
display_text = {
Hebr = "Hebr-common",
},
entry_name = {
["ur-Arab"] = {
-- character "ۂ" code U+06C2 to "ه" and "هٔ" (U+0647 + U+0654) to "ه"; hamzatu l-waṣli to a regular alif
from = {"هٔ", "ۂ", "ٱ"},
to = {"ہ", "ہ", "ا"},
remove_diacritics = c.fathatan .. c.dammatan .. c.kasratan .. c.fatha .. c.damma .. c.kasra .. c.shadda .. c.sukun .. c.nunghunna .. c.superalef
},
Hebr = "Hebr-common",
},
sort_key = {
Hebr = "Hebr-common",
},
standardChars = {
["ur-Arab"] = "ایببپتثجچحخدذرزژسشصضطظعغفقکگلࣇڷمنݨوؤہھئٹڈڑآے",
c.punc,
},
english_name = "Urdu", --TLCHANGE
}
m["uz"] = {
"Uzbeko", --TLCHANGE from Spanish "uzbeko"
9264,
"trk-kar",
"Latn, Cyrl, fa-Arab",
ancestors = "chg",
translit = {
Cyrl = "uz-translit"
},
sort_key = {
Latn = {
from = {"oʻ", "gʻ", "sh", "ch", "ng"},
to = {"z" .. p[1], "z" .. p[2], "z" .. p[3], "z" .. p[4], "z" .. p[5]}
},
Cyrl = {
from = {"ё", "ў", "қ", "ғ", "ҳ"},
to = {"е" .. p[1], "я" .. p[1], "я" .. p[2], "я" .. p[3], "я" .. p[4]}
},
},
english_name = "Uzbek", --TLCHANGE
spanish_name = "Uzbeko" --TLCHANGE
}
m["ve"] = {
"Venda", --TLCHANGE from Spanish "venda"
32704,
"bnt-bso",
"Latn",
english_name = "Venda", --TLCHANGE
spanish_name = "Venda" --TLCHANGE
}
m["vi"] = {
"Viyetnamita", --TLCHANGE
9199,
"mkh-vie",
"Latn, Hani",
ancestors = "mkh-mvi",
sort_key = {
Latn = "vi-sortkey",
Hani = "Hani-sortkey",
},
english_name = "Vietnamese", --TLCHANGE
spanish_name = "Vietnamita", --TLCHANGE
}
m["vo"] = {
"Volapük",
36986,
"art",
"Latn",
english_name = "Volapük", --TLCHANGE
}
m["wa"] = {
"Valon", --TLCHANGE from Spanish "valón"
34219,
"roa-oil",
"Latn",
sort_key = s["roa-oil-sortkey"],
english_name = "Walloon", --TLCHANGE
spanish_name = "Valón" --TLCHANGE
}
m["wo"] = {
"Wolof", --from Spanish "wólof"
34257,
"alv-fwo",
"Latn, Arab, Gara",
english_name = "Wolof", --TLCHANGE
spanish_name = "Wólof" --TLCHANGE
}
m["xh"] = {
"Xhosa", --mahirap dagliang ireispel
13218,
"bnt-ngu",
"Latn",
entry_name = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.macron .. c.caron},
english_name = "Xhosa", --TLCHANGE
}
m["yi"] = {
"Yidis", --from Spanish "Yidis"
8641,
"gmw-hgm",
"Hebr, Latn",
ancestors = "gmh",
translit = {
Hebr = "yi-translit",
},
display_text = {
Hebr = "Hebr-common",
},
entry_name = {
Hebr = "Hebr-common",
},
sort_key = {
Hebr = "Hebr-common",
},
english_name = "Yiddish", --TLCHANGE
spanish_name = "Yidis" --TLCHANGE
}
m["yo"] = {
"Yoruba",
34311,
"alv-yor",
"Latn, Arab",
entry_name = {
Latn = {remove_diacritics = c.grave .. c.acute .. c.macron}
},
sort_key = {
Latn = {
from = {"ẹ", "ɛ", "gb", "ị", "kp", "ọ", "ɔ", "ṣ", "sh", "ụ"},
to = {"e" .. p[1], "e" .. p[1], "g" .. p[1], "i" .. p[1], "k" .. p[1], "o" .. p[1], "o" .. p[1], "s" .. p[1], "s" .. p[1], "u" .. p[1]}
},
},
english_name = "Yoruba", --TLCHANGE
}
m["za"] = {
"Zhuang",
13216,
"tai",
"Latn, Hani",
sort_key = {
Latn = "za-sortkey",
Hani = "Hani-sortkey",
},
english_name = "Zhuang", --TLCHANGE
}
m["zh"] = {
"Tsino", --from Spanish "chino"
7850,
"zhx",
"Hants, Latn, Bopo, Nshu, Brai",
ancestors = "ltc",
generate_forms = "zh-generateforms",
translit = {
Hani = "zh-translit",
Bopo = "zh-translit",
},
sort_key = {
Hani = "Hani-sortkey"
},
is_official_kwf_name = "https://kwfdiksiyonaryo.ph/?query=Ts%C3%ADno", --TLCHANGE
english_name = "Chinese", --TLCHANGE
spanish_name = "Chino" --TLCHANGE
}
m["zu"] = {
"Zulu", --from Spanish "zulú"
10179,
"bnt-ngu",
"Latn",
entry_name = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.macron .. c.caron},
english_name = "Zulu", --TLCHANGE
spanish_name = "Zulú" --TLCHANGE
}
return require("Module:languages").finalizeData(m, "language")