Модул:languages/data/2
< Модул:languages | data
Ин модул дорои таърифҳо ва метамаълумот барои коди дуҳарфӣ. Барои маълумоти бештар Wiktionary:Language нигаред.
Ин модули бояд бевосита дар дигар модул ё қолаб истифода шавад. Маълумот бояд тавассути Модул:languages дастрас карда шавад. Барои мувофиқати маълумоти иловагӣ ба Модул:languages/data/2/extra нигаред.
local m_lang = require("Module:languages")
local m_langdata = require("Module:languages/data")
local u = require("Module:string utilities").char
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["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
local m = {}
m["aa"] = {
"афарӣ",
27811,
"cus-eas",
"Latn, Ethi",
entry_name = {Latn = {remove_diacritics = c.acute}},
}
m["ab"] = {
"абхозӣ",
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],
"",
}
},
},
}
m["ae"] = {
"авестоӣ",
29572,
"ira-cen",
"Avst, Gujr",
translit = {Avst = "Avst-translit"},
wikipedia_article = "Avestan",
}
m["af"] = {
"африқоӣ",
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]}
}
},
}
m["ak"] = {
"аканӣ",
28026,
"alv-ctn",
"Latn",
}
m["am"] = {
"амҳарӣ",
28244,
"sem-eth",
"Ethi",
translit = "Ethi-translit",
}
m["an"] = {
"арагонӣ",
8765,
"roa-ibe",
"Latn",
ancestors = "roa-oan",
}
m["ar"] = {
"арабӣ",
13955,
"sem-arb",
"Arab, Hebr, Syrc, Brai",
translit = {Arab = "ar-translit"},
entry_name = {Arab = "ar-entryname"},
-- put Judeo-Arabic (Hebrew-script Arabic) under the category header
-- U+FB21 HEBREW LETTER WIDE ALEF so that it sorts after Arabic script titles
sort_key = {
Hebr = {
from = {"^%f[" .. u(0x5D0) .. "-" .. u(0x5EA) .. "]"},
to = {u(0xFB21)},
},
},
}
m["as"] = {
"асамизӣ",
29401,
"inc-bas",
"as-Beng",
ancestors = "inc-mas",
translit = "as-translit",
}
m["av"] = {
"аварӣ",
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]}
},
},
}
m["ay"] = {
"аймараӣ",
4627,
"sai-aym",
"Latn",
}
m["az"] = {
"озарбойҷонӣ",
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]}
},
},
}
m["ba"] = {
"бошқирдӣ",
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]}
},
}
m["be"] = {
"белорусӣ",
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.
},
}
m["bg"] = {
"булғорӣ",
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]"},
},
standardChars = "АаБбВвГгДдЕеЖжЗзИиЙйКкЛлМмНнОоПпРрСсТтУуФфХхЦцЧчШшЩщЪъЬьЮюЯя" .. c.punc,
}
m["bh"] = {
"бҳоҷпурӣ",
135305,
"inc-eas",
"Deva",
}
m["bi"] = {
"бислама",
35452,
"crp",
"Latn",
ancestors = "en",
}
m["bm"] = {
"бамбара",
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]}
},
},
}
m["bn"] = {
"банголӣ",
9610,
"inc-bas",
"Beng, Newa",
ancestors = "inc-mbn",
translit = {Beng = "bn-translit"},
}
m["bo"] = {
"тибетӣ",
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",
}
m["br"] = {
"бретонӣ",
12107,
"cel-brs",
"Latn",
ancestors = "xbm",
sort_key = {
from = {"ch", "c['ʼ’]h"},
to = {"c" .. p[1], "c" .. p[2]}
},
}
m["ca"] = {
"каталанӣ",
7026,
"roa-ocr",
"Latn",
ancestors = "roa-oca",
sort_key = {
remove_diacritics = c.grave .. c.acute .. c.diaer .. c.cedilla,
from = {"l·l"},
to = {"ll"}
},
standardChars = "AaÀàBbCcÇçDdEeÉéÈèFfGgHhIiÍíÏïJjLlMmNnOoÓóÒòPpQqRrSsTtUuÚúÜüVvXxYyZz·" .. c.punc,
}
m["ce"] = {
"чеченӣ",
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]}
},
},
}
m["ch"] = {
"чаморро",
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]}
},
}
m["co"] = {
"корсиканӣ",
33111,
"roa-itd",
"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,
}
m["cr"] = {
"кри",
33390,
"alg",
"Latn, Cans",
translit = {Cans = "cr-translit"},
}
m["cs"] = {
"чехӣ",
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,
}
m["cu"] = {
"славянии бостонӣ",
35499,
"zls",
"Cyrs, Glag",
translit = {Cyrs = "Cyrs-translit", Glag = "Glag-translit"},
entry_name = {Cyrs = s["Cyrs-entryname"]},
sort_key = {Cyrs = s["Cyrs-sortkey"]},
}
m["cv"] = {
"чувашӣ",
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]}
},
}
m["cy"] = {
"уэлсӣ",
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,
}
m["da"] = {
"даниягӣ",
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,
}
m["de"] = {
"олмонӣ",
188,
"gmw-hgm",
"Latn, Latf",
ancestors = "gmh",
sort_key = {
remove_diacritics = c.grave .. c.acute .. c.circ .. c.diaer .. c.ringabove,
from = {"æ", "œ", "ß"},
to = {"ae", "oe", "ss"}
},
standardChars = "AaÄäBbCcDdEeFfGgHhIiJjKkLlMmNnOoÖöPpQqRrSsẞßTtUuÜüVvWwXxYyZz" .. c.punc,
}
m["dv"] = {
"малдивӣ",
32656,
"inc-ins",
"Thaa, Diak",
translit = {
Thaa = "dv-translit",
Diak = "Diak-translit",
},
override_translit = true,
}
m["dz"] = {
"дзонгкӣ",
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",
}
m["ee"] = {
"эве",
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]}
},
}
m["el"] = {
"юнонӣ",
9129,
"grk",
"Grek, Polyt, Brai",
ancestors = "el-kth",
translit = {
Grek = "el-translit",
Polyt = "grc-translit",
},
override_translit = true,
entry_name = {
Grek = {remove_diacritics = c.caron .. c.diaerbelow .. c.brevebelow},
Polyt = s["Polyt-entryname"],
},
sort_key = {
Grek = s["Grek-sortkey"],
Polyt = s["Grek-sortkey"],
},
standardChars = {
Grek = "΅·ͺ΄ΑαΆάΒβΓγΔδΕεέΈΖζΗηΉήΘθΙιΊίΪϊΐΚκΛλΜμΝνΞξΟοΌόΠπΡρΣσςΤτΥυΎύΫϋΰΦφΧχΨψΩωΏώ",
Brai = c.braille,
c.punc
},
}
m["en"] = {
"англисӣ",
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 = "'\"%-%.,%sʻʼ" .. c.diacritics,
-- These are found in entry names.
from = {"æ", "🅱", "[¢©ᴄ]", "[ðđ]", "[əǝ]", "[ħʜ]", "ɨ", "ł", "[ŋɲ]", "[øɔ]", "œ", "ꝓ", "ß", "ʋ"},
to = {"ae", "b", "c", "d", "e", "h", "i", "l", "n", "o", "oe", "p", "ss", "v"}
},
},
standardChars = {
Latn = "AaBbCcDdEeFfGgHhIiJjKkLlMmNnOoPpQqRrSsTtUuVvWwXxYyZz",
Brai = c.braille,
c.punc
},
}
m["eo"] = {
"эсперанто",
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,
}
m["es"] = {
"испанӣ",
1321,
"roa-ibe",
"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
},
}
m["et"] = {
"эстонӣ",
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,
}
m["eu"] = {
"баскӣ",
8752,
"euq",
"Latn",
sort_key = {
from = {"ç", "ñ"},
to = {"c" .. p[1], "n" .. p[1]}
},
standardChars = "AaBbDdEeFfGgHhIiJjKkLlMmNnÑñOoPpRrSsTtUuXxZz" .. c.punc,
}
m["fa"] = {
"форсӣ",
9168,
"ira-swi",
"fa-Arab, Hebr",
ancestors = "fa-cls",
entry_name = {
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,
},
-- put Judeo-Persian (Hebrew-script Persian) under the category header
-- U+FB21 HEBREW LETTER WIDE ALEF so that it sorts after Arabic script titles
sort_key = {
Hebr = {
from = {"^%f[" .. u(0x5D0) .. "-" .. u(0x5EA) .. "]"},
to = {u(0xFB21)},
},
},
}
m["ff"] = {
"фула",
33454,
"alv-fwo",
"Latn, Adlm",
}
m["fi"] = {
"финӣ",
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", "ð", "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,
}
m["fj"] = {
"фиҷи",
33295,
"poz-pcc",
"Latn",
}
m["fo"] = {
"фарерӣ",
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,
}
m["fr"] = {
"фаронсавӣ",
150,
"roa-oil",
"Latn, Brai",
display_text = {
from = {"'"},
to = {"’"}
},
entry_name = {
from = {"’"},
to = {"'"},
},
ancestors = "frm",
sort_key = {Latn = s["roa-oil-sortkey"]},
standardChars = {
Latn = "AaÀàÂâBbCcÇçDdEeÉéÈèÊêËëFfGgHhIiÎîÏïJjLlMmNnOoÔôŒœPpQqRrSsTtUuÙùÛûÜüVvXxYyZz",
Brai = c.braille,
c.punc
},
}
m["fy"] = {
"фризии ғарбӣ",
27175,
"gmw-fri",
"Latn",
sort_key = {
remove_diacritics = c.grave .. c.acute .. c.circ .. c.diaer,
from = {"y"},
to = {"i"}
},
standardChars = "AaâäàÆæBbCcDdEeéêëèFfGgHhIiïìYyỳJjKkLlMmNnOoôöòPpRrSsTtUuúûüùVvWwZz" .. c.punc,
}
m["ga"] = {
"ирландӣ",
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,
}
m["gd"] = {
"голики шотландӣ",
9314,
"cel-gae",
"Latn, Latg",
ancestors = "mga",
sort_key = {remove_diacritics = c.grave .. c.acute},
standardChars = "AaÀàBbCcDdEeÈèFfGgHhIiÌìLlMmNnOoÒòPpRrSsTtUuÙù" .. c.punc,
}
m["gl"] = {
"галисиягӣ",
9307,
"roa-ibe",
"Latn",
ancestors = "roa-opt",
sort_key = {
remove_diacritics = c.acute,
from = {"ñ"},
to = {"n" .. p[1]}
},
standardChars = "AaÁáBbCcDdEeÉéFfGgHhIiÍíÏïLlMmNnÑñOoÓóPpQqRrSsTtUuÚúÜüVvXxZz" .. c.punc,
}
m["gn"] = {
"гуаранӣ",
35876,
"tup-gua",
"Latn",
}
m["gu"] = {
"гуҷаротӣ",
5137,
"inc-wes",
"Arab, Gujr",
ancestors = "inc-mgu",
translit = {
Gujr = "gu-translit",
},
entry_name = {
remove_diacritics = c.fathatan .. c.dammatan .. c.kasratan .. c.fatha .. c.damma .. c.kasra .. c.kasra .. c.shadda .. c.sukun .. "઼"
},
}
m["gv"] = {
"манска",
12175,
"cel-gae",
"Latn",
ancestors = "mga",
sort_key = {remove_diacritics = c.cedilla .. "-"},
standardChars = "AaBbCcÇçDdEeFfGgHhIiJjKkLlMmNnOoPpQqRrSsTtUuVvWwYy" .. c.punc,
}
m["ha"] = {
"ҳаузаӣ",
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]}
},
},
}
m["he"] = {
"ибрӣ",
9288,
"sem-can",
"Hebr, Phnx, Brai",
ancestors = "he-med",
entry_name = {Hebr = {remove_diacritics = u(0x0591) .. "-" .. u(0x05BD) .. u(0x05BF) .. "-" .. u(0x05C5) .. u(0x05C7) .. c.CGJ}},
}
m["hi"] = {
"ҳиндӣ",
1568,
"inc-hnd",
"Deva, Kthi, Newa",
translit = {Deva = "hi-translit"},
standardChars = {
Deva = "अआइईउऊएऐओऔकखगघङचछजझञटठडढणतथदधनपफबभमयरलवशषसहत्रज्ञक्षक़ख़ग़ज़झ़ड़ढ़फ़काखागाघाङाचाछाजाझाञाटाठाडाढाणाताथादाधानापाफाबाभामायारालावाशाषासाहात्राज्ञाक्षाक़ाख़ाग़ाज़ाझ़ाड़ाढ़ाफ़ाकिखिगिघिङिचिछिजिझिञिटिठिडिढिणितिथिदिधिनिपिफिबिभिमियिरिलिविशिषिसिहित्रिज्ञिक्षिक़िख़िग़िज़िझ़िड़िढ़िफ़िकीखीगीघीङीचीछीजीझीञीटीठीडीढीणीतीथीदीधीनीपीफीबीभीमीयीरीलीवीशीषीसीहीत्रीज्ञीक्षीक़ीख़ीग़ीज़ीझ़ीड़ीढ़ीफ़ीकुखुगुघुङुचुछुजुझुञुटुठुडुढुणुतुथुदुधुनुपुफुबुभुमुयुरुलुवुशुषुसुहुत्रुज्ञुक्षुक़ुख़ुग़ुज़ुझ़ुड़ुढ़ुफ़ुकूखूगूघूङूचूछूजूझूञूटूठूडूढूणूतूथूदूधूनूपूफूबूभूमूयूरूलूवूशूषूसूहूत्रूज्ञूक्षूक़ूख़ूग़ूज़ूझ़ूड़ूढ़ूफ़ूकेखेगेघेङेचेछेजेझेञेटेठेडेढेणेतेथेदेधेनेपेफेबेभेमेयेरेलेवेशेषेसेहेत्रेज्ञेक्षेक़ेख़ेग़ेज़ेझ़ेड़ेढ़ेफ़ेकैखैगैघैङैचैछैजैझैञैटैठैडैढैणैतैथैदैधैनैपैफैबैभैमैयैरैलैवैशैषैसैहैत्रैज्ञैक्षैक़ैख़ैग़ैज़ैझ़ैड़ैढ़ैफ़ैकोखोगोघोङोचोछोजोझोञोटोठोडोढोणोतोथोदोधोनोपोफोबोभोमोयोरोलोवोशोषोसोहोत्रोज्ञोक्षोक़ोख़ोग़ोज़ोझ़ोड़ोढ़ोफ़ोकौखौगौघौङौचौछौजौझौञौटौठौडौढौणौतौथौदौधौनौपौफौबौभौमौयौरौलौवौशौषौसौहौत्रौज्ञौक्षौक़ौख़ौग़ौज़ौझ़ौड़ौढ़ौफ़ौक्ख्ग्घ्ङ्च्छ्ज्झ्ञ्ट्ठ्ड्ढ्ण्त्थ्द्ध्न्प्फ्ब्भ्म्य्र्ल्व्श्ष्स्ह्त्र्ज्ञ्क्ष्क़्ख़्ग़्ज़्झ़्ड़्ढ़्फ़्।॥०१२३४५६७८९॰",
c.punc
},
}
m["ho"] = {
"хири моту",
33617,
"crp",
"Latn",
ancestors = "meu",
}
m["ht"] = {
"гаитии креолӣ",
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]
}
},
}
m["hu"] = {
"маҷорӣ",
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
},
}
m["hy"] = {
"арманӣ",
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"
}
},
},
}
m["hz"] = {
"ҳереро",
33315,
"bnt-swb",
"Latn",
}
m["ia"] = {
"интерлингва",
35934,
"art",
"Latn",
}
m["id"] = {
"индонезӣ",
9240,
"poz-mly",
"Latn",
ancestors = "ms",
standardChars = "AaBbCcDdEeFfGgHhIiJjKkLlMmNnOoPpQqRrSsTtUuVvWwXxYyZz" .. c.punc,
}
m["ie"] = {
"окцидентал",
35850,
"art",
"Latn",
type = "appendix-constructed",
entry_name = {remove_diacritics = c.grave .. c.acute .. c.circ},
}
m["ig"] = {
"игбо",
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]}
},
}
m["ii"] = {
"нуосу",
34235,
"tbq-nlo",
"Yiii",
translit = "ii-translit",
}
m["ik"] = {
"инупиак",
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]
}
},
}
m["io"] = {
"идо",
35224,
"art",
"Latn",
}
m["is"] = {
"исландӣ",
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,
}
m["it"] = {
"итолиявӣ",
652,
"roa-itd",
"Latn",
ancestors = "roa-oit",
sort_key = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.diaer .. c.ringabove},
standardChars = "AaÀàBbCcDdEeÈèÉéFfGgHhIiÌìLlMmNnOoÒòPpQqRrSsTtUuÙùVvZz" .. c.punc,
}
m["iu"] = {
"инуктитутӣ",
29921,
"esx-inu",
"Cans, Latn",
translit = {Cans = "cr-translit"},
override_translit = true,
}
m["ja"] = {
"ҷопонӣ",
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"],
}
m["jv"] = {
"ҷаванизӣ",
33549,
"poz",
"Latn, Java",
ancestors = "kaw",
translit = {Java = "jv-translit"},
link_tr = true,
entry_name = {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]}
},
},
}
m["ka"] = {
"гурҷӣ",
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,
entry_name = {remove_diacritics = c.circ},
}
m["kg"] = {
"конго",
33702,
"bnt-kng",
"Latn",
}
m["ki"] = {
"кикую",
33587,
"bnt-kka",
"Latn",
}
m["kj"] = {
"кваньяма",
1405077,
"bnt-ova",
"Latn",
}
m["kk"] = {
"қазоқӣ",
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
},
}
m["kl"] = {
"гринландӣ",
25355,
"esx-inu",
"Latn",
sort_key = {
from = {"æ", "ø", "å"},
to = {"z" .. p[1], "z" .. p[2], "z" .. p[3]}
}
}
m["km"] = {
"кҳмерӣ",
9205,
"mkh-kmr",
"Khmr",
ancestors = "xhm",
translit = "km-translit",
}
m["kn"] = {
"каннада",
33673,
"dra-kan",
"Knda, Tutg",
ancestors = "dra-mkn",
translit = "kn-translit",
}
m["ko"] = {
"кореягӣ",
9176,
"qfa-kor",
"Kore, Brai",
ancestors = "ko-ear",
translit = {Kore = "ko-translit"},
entry_name = {Kore = s["Kore-entryname"]},
}
m["kr"] = {
"канурӣ",
36094,
"ssa-sah",
"Latn, Arab",
entry_name = {Latn = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.breve}}, -- 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
sort_key = {
Latn = {
from = {"ǝ", "ny", "ɍ", "sh"},
to = {"e" .. p[1], "n" .. p[1], "r" .. p[1], "s" .. p[1]}
},
},
}
m["ks"] = {
"кашмирӣ",
33552,
"inc-kas",
"ks-Arab, Deva, Shrd, Latn",
translit = {
["ks-Arab"] = "ks-Arab-translit",
Deva = "ks-Deva-translit",
Shrd = "Shrd-translit",
},
}
-- "kv" IS TREATED AS "koi", "kpv", SEE WT:LT
m["kw"] = {
"корнӣ",
25289,
"cel-brs",
"Latn",
ancestors = "cnx",
sort_key = {
from = {"ch"},
to = {"c" .. p[1]}
},
}
m["ky"] = {
"қирғизӣ",
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]}
},
},
}
m["la"] = {
"лотинӣ",
397,
"itc",
"Latn, Ital",
ancestors = "itc-ola",
entry_name = {Latn = {remove_diacritics = c.macron .. c.breve .. c.diaer .. c.dinvbreve}},
sort_key = {
remove_diacritics = c.circ .. c.tilde .. c.macron .. c.diaer .. c.zigzag .. c.dmacron .. c.dtilde .. c.small_a .. c.small_e .. c.small_i .. c.small_o .. c.small_u, -- Medieval abbreviations.
Latn = {
from = {"æ", "œ", "[ꝑꝓ]"},
to = {"ae", "oe", "p"}
},
},
standardChars = {
Latn = "AaBbCcDdEeFfGgHhIiLlMmNnOoPpQqRrSsTtUuVvXxZz",
c.punc
},
}
m["lb"] = {
"люксембургӣ",
9051,
"gmw-hgm",
"Latn",
ancestors = "gmw-cfr",
sort_key = {
from = {"ä", "ë", "é"},
to = {"z" .. p[1], "z" .. p[2], "z" .. p[3]}
},
}
m["lg"] = {
"луганда",
33368,
"bnt-nyg",
"Latn",
entry_name = {remove_diacritics = c.acute .. c.circ},
sort_key = {
from = {"ŋ"},
to = {"n" .. p[1]}
},
}
m["li"] = {
"лимбургӣ",
102172,
"gmw-frk",
"Latn",
ancestors = "dum",
}
m["ln"] = {
"лингала",
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]}
},
}
m["lo"] = {
"лаосӣ",
9211,
"tai-swe",
"Laoo",
translit = "lo-translit",
sort_key = "Laoo-sortkey",
standardChars = "0-9ກຂຄງຈຊຍດຕຖທນບປຜຝພຟມຢຣລວສຫອຮຯ-ໝ" .. c.punc,
}
m["lt"] = {
"литвонӣ",
9083,
"bat-eas",
"Latn",
ancestors = "olt",
entry_name = {remove_diacritics = c.grave .. c.acute .. c.tilde},
sort_key = {
from = {"ą", "č", "ę", "ė", "į", "y", "š", "ų", "ū", "ž"},
to = {"a" .. p[1], "c" .. p[1], "e" .. p[1], "e" .. p[2], "i" .. p[1], "i" .. p[2], "s" .. p[1], "u" .. p[1], "u" .. p[2], "z" .. p[1]}
},
standardChars = "AaĄąBbCcČčDdEeĘęĖėFfGgHhIiĮįYyJjKkLlMmNnOoPpRrSsŠšTtUuŲųŪūVvZzŽž" .. c.punc,
}
m["lu"] = {
"люба-катанга",
36157,
"bnt-lub",
"Latn",
}
m["lv"] = {
"латышӣ",
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,
}
m["mg"] = {
"малагашкӣ",
7930,
"poz-bre",
"Latn",
}
m["mh"] = {
"маршалӣ",
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]}
},
}
m["mi"] = {
"маорӣ",
36451,
"poz-pep",
"Latn",
sort_key = {
remove_diacritics = c.macron,
from = {"ng", "wh"},
to = {"z" .. p[1], "z" .. p[2]}
},
}
m["mk"] = {
"мақдунӣ",
9296,
"zls",
"Cyrl, Grek",
ancestors = "cu",
translit = {Cyrl = "mk-translit"},
entry_name = {Cyrl = {
remove_diacritics = c.acute,
remove_exceptions = {"Ѓ", "ѓ", "Ќ", "ќ"}
}},
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]}
}},
standardChars = {
Cyrl = "АаБбВвГгДдЃѓЕеЖжЗзЅѕИиЈјКкЛлЉљМмНнЊњОоПпРрСсТтЌќУуФфХхЦцЧчЏџШш",
c.punc
},
}
m["ml"] = {
"малаяламӣ",
36236,
"dra-mal",
"Mlym",
translit = "ml-translit",
override_translit = true,
}
m["mn"] = {
"муғулӣ",
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
},
}
-- "mo" IS TREATED AS "ro", SEE WT:LT
m["mr"] = {
"маротҳӣ",
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"}
},
},
}
m["ms"] = {
"малайӣ",
9237,
"poz-mly",
"Latn, ms-Arab",
ancestors = "ms-cla",
standardChars = {
Latn = "AaBbCcDdEeFfGgHhIiJjKkLlMmNnOoPpQqRrSsTtUuVvWwXxYyZz",
c.punc
},
}
m["mt"] = {
"малтӣ",
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"
}
},
}
m["my"] = {
"бирмаӣ",
9228,
"tbq-brm",
"Mymr",
ancestors = "obr",
translit = "my-translit",
override_translit = true,
sort_key = {
from = {"ျ", "ြ", "ွ", "ှ", "ဿ"},
to = {"္ယ", "္ရ", "္ဝ", "္ဟ", "သ္သ"}
},
}
m["na"] = {
"науруанӣ",
13307,
"poz-mic",
"Latn",
}
m["nb"] = {
"норвегӣ (букмол)",
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"],
}
m["nd"] = {
"ндебелеи шимолӣ",
35613,
"bnt-ngu",
"Latn",
entry_name = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.macron .. c.caron},
}
m["ne"] = {
"неполӣ",
33823,
"inc-pah",
"Deva, Newa",
translit = {Deva = "ne-translit"},
}
m["ng"] = {
"ндонга",
33900,
"bnt-ova",
"Latn",
}
m["nl"] = {
"нидерландӣ",
7411,
"gmw-frk",
"Latn, Brai",
ancestors = "dum",
sort_key = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.tilde .. c.diaer .. c.ringabove .. c.cedilla .. "'"},
standardChars = {
Latn = "AaBbCcDdEeFfGgHhIiJjKkLlMmNnOoPpQqRrSsTtUuVvWwXxYyZz",
Brai = c.braille,
c.punc
},
}
m["nn"] = {
"норвегӣ (нюнорск)",
25164,
"gmq-wes",
"Latn",
ancestors = "gmq-mno",
entry_name = {
remove_diacritics = c.grave .. c.acute,
},
sort_key = s["no-sortkey"],
standardChars = s["no-standardchars"],
}
m["no"] = {
"норвегӣ",
9043,
"gmq-wes",
"Latn",
ancestors = "gmq-mno",
sort_key = s["no-sortkey"],
standardChars = s["no-standardchars"],
}
m["nr"] = {
"ндебелеи ҷанубӣ",
36785,
"bnt-ngu",
"Latn",
entry_name = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.macron .. c.caron},
}
m["nv"] = {
"навахо",
13310,
"apa",
"Latn",
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]
}
},
}
m["ny"] = {
"нянджа",
33273,
"bnt-nys",
"Latn",
entry_name = {remove_diacritics = c.acute .. c.circ},
sort_key = {
from = {"ng'"},
to = {"ng"}
},
}
m["oc"] = {
"окситанӣ",
14185,
"roa-ocr",
"Latn, Hebr",
ancestors = "pro",
sort_key = {
Latn = {
remove_diacritics = c.grave .. c.acute .. c.diaer .. c.cedilla,
from = {"([lns])·h"},
to = {"%1h"}
},
},
}
m["oj"] = {
"оҷибве",
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]}
},
},
}
m["om"] = {
"оромо",
33864,
"cus-eas",
"Latn, Ethi",
}
m["or"] = {
"ория",
33810,
"inc-eas",
"Orya",
ancestors = "inc-mor",
translit = "or-translit",
}
m["os"] = {
"осетӣ",
33968,
"xsc",
"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]}
},
},
}
m["pa"] = {
"пунҷобӣ",
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"}
},
},
}
m["pi"] = {
"палӣ",
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", "ᩣ"}
},
}
m["pl"] = {
"лаҳистонӣ",
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,
}
m["ps"] = {
"пашту",
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.superalef},
}
m["pt"] = {
"португалӣ",
5146,
"roa-ibe",
"Latn, Brai",
ancestors = "roa-opt",
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
},
}
m["qu"] = {
"кечваӣ",
5218,
"qwe",
"Latn",
}
m["rm"] = {
"ретороманӣ",
13199,
"roa-rhe",
"Latn",
sort_key = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.diaer .. c.small_e},
}
m["ro"] = {
"руминӣ",
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
},
}
m["ru"] = {
"русӣ",
7737,
"zle",
"Cyrl, Brai",
ancestors = "zle-mru",
translit = {Cyrl = "ru-translit"},
display_text = {
from = {"'"},
to = {"’"}
},
entry_name = {
remove_diacritics = c.grave .. c.acute .. c.diaer,
remove_exceptions = {"Ё", "ё", "Ѣ̈", "ѣ̈", "Я̈", "я̈"},
from = {"’"},
to = {"'"},
},
sort_key = {
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.
},
}
m["rw"] = {
"куечува",
3217514,
"bnt-glb",
"Latn",
entry_name = {remove_diacritics = c.acute .. c.circ .. c.macron .. c.caron},
}
m["sa"] = {
"санскритӣ",
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", "ᩣ"},
},
},
}
m["sc"] = {
"сардинӣ",
33976,
"roa",
"Latn",
}
m["sd"] = {
"синдӣ",
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"}
},
},
}
m["se"] = {
"самии шимолӣ",
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,
}
m["sg"] = {
"санго",
33954,
"crp",
"Latn",
ancestors = "ngb",
}
m["sh"] = {
"сербу хорватӣ",
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
},
}
m["si"] = {
"сингалӣ",
13267,
"inc-ins",
"Sinh",
translit = "si-translit",
override_translit = true,
}
m["sk"] = {
"словакӣ",
9058,
"zlw",
"Latn",
ancestors = "zlw-osk",
sort_key = {remove_diacritics = c.acute .. c.circ .. c.diaer .. c.caron},
standardChars = "AaÁáÄäBbCcČčDdĎďEeFfGgHhIiÍíJjKkLlĹ弾MmNnŇňOoÔôPpRrŔŕSsŠšTtŤťUuÚúVvYyÝýZzŽž" .. c.punc,
}
m["sl"] = {
"словенӣ",
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,
}
m["sm"] = {
"самоаӣ",
34011,
"poz-pnp",
"Latn",
}
m["sn"] = {
"шонаӣ",
34004,
"bnt-sho",
"Latn",
entry_name = {remove_diacritics = c.acute},
}
m["so"] = {
"сомалӣ",
13275,
"cus-som",
"Latn, Arab, Osma",
entry_name = {Latn = {remove_diacritics = c.grave .. c.acute .. c.circ}},
}
m["sq"] = {
"албанӣ",
8748,
"sqj",
"Latn, Grek, ota-Arab, Elba, Todr, Vith",
translit = {Elba = "Elba-translit"},
entry_name = {Latn = {
remove_diacritics = c.acute,
from = {'^[ie] (%w)', '^të (%w)'}, to = {'%1', '%1'},
}},
sort_key = {Latn = {
remove_diacritics = c.acute .. c.circ .. c.tilde .. c.breve .. c.caron,
from = {'ç', 'dh', 'ë', 'gj', 'll', 'nj', 'rr', 'sh', 'th', 'xh', 'zh'},
to = {'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]},
}},
standardChars = {
Latn = "AaBbCcÇçDdEeËëFfGgHhIiJjKkLlMmNnOoPpQqRrSsTtUuVvXxYyZz",
c.punc
},
}
m["ss"] = {
"свазӣ",
34014,
"bnt-ngu",
"Latn",
entry_name = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.macron .. c.caron},
}
m["st"] = {
"сотои ҷанубӣ",
34340,
"bnt-sts",
"Latn",
entry_name = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.macron .. c.caron},
}
m["su"] = {
"сунданизӣ",
34002,
"poz-msa",
"Latn, Sund",
ancestors = "osn",
translit = {Sund = "su-translit"},
}
m["sv"] = {
"шведӣ",
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,
}
m["sw"] = {
"суаҳилӣ",
7838,
"bnt-swh",
"Latn, Arab",
sort_key = {
Latn = {
from = {"ng'"},
to = {"ng" .. p[1]}
},
},
}
m["ta"] = {
"тамилӣ",
5885,
"dra-tam",
"Taml",
ancestors = "ta-mid",
translit = "ta-translit",
override_translit = true,
}
m["te"] = {
"телугу",
8097,
"dra-tel",
"Telu",
translit = "te-translit",
override_translit = true,
}
m["tg"] = {
"тоҷикӣ",
9260,
"ira-swi",
"Cyrl, fa-Arab, Latn",
ancestors = "fa-cls",
translit = {Cyrl = "tg-translit"},
override_translit = true,
entry_name = {remove_diacritics = c.grave .. c.acute},
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]}
},
},
}
m["th"] = {
"таиландӣ",
9217,
"tai-swe",
"Thai, Brai", --and also Khom
translit = {Thai = "th-translit"},
sort_key = {Thai = "Thai-sortkey"},
}
m["ti"] = {
"тигриня",
34124,
"sem-eth",
"Ethi",
translit = "Ethi-translit",
}
m["tk"] = {
"туркменӣ",
9267,
"trk-ogz",
"Latn, Cyrl, Arab",
entry_name = {remove_diacritics = c.macron},
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]}
},
},
}
m["tl"] = {
"тагалӣ",
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",
},
}
m["tn"] = {
"тсвана",
34137,
"bnt-sts",
"Latn",
}
m["to"] = {
"тонганӣ",
34094,
"poz-ton",
"Latn",
entry_name = {remove_diacritics = c.acute},
sort_key = {remove_diacritics = c.macron},
}
m["tr"] = {
"туркӣ",
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,
}
m["ts"] = {
"тсонга",
34327,
"bnt-tsr",
"Latn",
}
m["tt"] = {
"тоторӣ",
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]
}
},
},
}
-- "tw" IS TREATED AS "ak", SEE WT:LT
m["ty"] = {
"таитиӣ",
34128,
"poz-pep",
"Latn",
}
m["ug"] = {
"уйғурӣ",
13263,
"trk-kar",
"ug-Arab, Latn, Cyrl",
ancestors = "chg",
translit = {
["ug-Arab"] = "ug-translit",
Cyrl = "ug-translit",
},
override_translit = true,
}
m["uk"] = {
"украинӣ",
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.
}
m["ur"] = {
"урду",
1617,
"inc-hnd",
"ur-Arab,Hebr",
translit = {["ur-Arab"] = "ur-translit"},
entry_name = {
-- 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
},
-- put Judeo-Urdu (Hebrew-script Urdu) under the category header
-- U+FB21 HEBREW LETTER WIDE ALEF so that it sorts after Arabic script titles
sort_key = {
from = {"^%f[" .. u(0x5D0) .. "-" .. u(0x5EA) .. "]"},
to = {u(0xFB21)},
},
standardChars = "ایببپتثجچحخدذرزژسشصضطظعغفقکگلࣇڷمنݨوؤہھئٹڈڑآے" .. c.punc,
}
m["uz"] = {
"ӯзбакӣ",
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]}
},
},
}
m["ve"] = {
"венда",
32704,
"bnt-bso",
"Latn",
}
m["vi"] = {
"ветнамӣ",
9199,
"mkh-vie",
"Latn, Hani",
ancestors = "mkh-mvi",
sort_key = {
Latn = "vi-sortkey",
Hani = "Hani-sortkey",
},
}
m["vo"] = {
"волапyкӣ",
36986,
"art",
"Latn",
}
m["wa"] = {
"валлонӣ",
34219,
"roa-oil",
"Latn",
sort_key = s["roa-oil-sortkey"],
}
m["wo"] = {
"волофӣ",
34257,
"alv-fwo",
"Latn, Arab, Gara",
}
m["xh"] = {
"коса",
13218,
"bnt-ngu",
"Latn",
entry_name = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.macron .. c.caron},
}
m["yi"] = {
"идиш",
8641,
"gmw-hgm",
"Hebr",
ancestors = "gmh",
translit = "yi-translit",
sort_key = {
from = {"א[ַָ]", "בּ", "ו[ֹּ]", "יִ", "ײַ", "פֿ"},
to = {"א", "ב", "ו", "י", "יי", "פ"}
},
}
m["yo"] = {
"ёрубаӣ",
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]}
},
},
}
m["za"] = {
"чжуанӣ",
13216,
"tai",
"Latn, Hani",
sort_key = {
Latn = "za-sortkey",
Hani = "Hani-sortkey",
},
}
m["zh"] = {
"чинӣ",
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"},
}
m["zu"] = {
"зулугӣ",
10179,
"bnt-ngu",
"Latn",
entry_name = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.macron .. c.caron},
}
return m_lang.finalizeLanguageData(m_lang.addDefaultTypes(m, true))