Linguifex

Module:languages/data/exceptional: Difference between revisions

← Older edit
No edit summary
Melinoë (talk | contribs)
5,954 edits
No edit summary
 
(40 intermediate revisions by 5 users not shown)
Line 12: Line 12:


local m = {}
local m = {}
m["lhaz"] = {
"Lhazareen",
nil,
"plai",
"Latn",
ancestors = "pls-pro",
type = "conlang"
}
m["meer"] = {
"Meereenese Valyrian",
nil,
"conlang-fam",
"Latn",
ancestors = "qhv",
type = "conlang"
}
m["asta"] = {
"Astapori Valyrian",
nil,
"conlang-fam",
"Latn",
ancestors = "qhv",
type = "conlang"
}
m["ghis"] = {
"Ghiscari",
nil,
"conlang-fam",
"Latn",
type = "conlang"
}
m["assh"] = {
"Asshai'i",
nil,
"conlang-fam",
"Latn",
type = "conlang"
}


m["estu"] = {                   
m["estu"] = {                   
Line 99: Line 142:
"Afrihili",
"Afrihili",
384707,
384707,
"art",
"conlang-fam",
"Latn",
"Latn",
}
}
Line 138: Line 181:
"Proto-Alopian",
"Proto-Alopian",
nil,
nil,
"art",
"conlang-fam",
"Latn",
"Latn",
sort_key = {
sort_key = {
Line 175: Line 218:
"Bolak",
"Bolak",
2909283,
2909283,
"art",
"conlang-fam",
"Latn",
"Latn",
}
}
Line 182: Line 225:
"Black Speech",
"Black Speech",
686210,
686210,
"art",
"conlang-fam",
"Latn, Teng",
"Latn, Teng",
}
}
Line 189: Line 232:
"Communicationssprache",
"Communicationssprache",
35227,
35227,
"art",
"conlang-fam",
"Latn",
"Latn",
}
m["art-dtk"] = {
"Dothraki",
2914733,
"art",
"Latn",
}
}


Line 203: Line 239:
"Eloi",
"Eloi",
nil,
nil,
"art",
"conlang-fam",
"Latn",
"Latn",
}
}
Line 210: Line 246:
"Goa'uld",
"Goa'uld",
19823,
19823,
"art",
"conlang-fam",
"Latn, Egyp, Mero",
"Latn, Egyp, Mero",
}
}
Line 217: Line 253:
"Lapine",
"Lapine",
6488195,
6488195,
"art",
"conlang-fam",
"Latn",
"Latn",
}
}
Line 224: Line 260:
"Mandalorian",
"Mandalorian",
54289,
54289,
"art",
"conlang-fam",
"Latn",
"Latn",
}
}
Line 231: Line 267:
"Mundolinco",
"Mundolinco",
851355,
851355,
"art",
"conlang-fam",
"Latn",
"Latn",
}
}
Line 238: Line 274:
"Na'vi",
"Na'vi",
316939,
316939,
"art",
"conlang-fam",
"Latn",
"Latn",
}
}
Line 245: Line 281:
"Noxilo",
"Noxilo",
nil,
nil,
"art",
"conlang-fam",
"Latn",
"Latn",
type = "conlang",
type = "conlang",
Line 255: Line 291:
"ǂA Ṇṵĩ",
"ǂA Ṇṵĩ",
nil,
nil,
"art",
"conlang-fam",
"Latn",
"Latn",
sort_key = {
sort_key = {
Line 296: Line 332:
"Unas",
"Unas",
nil,
nil,
"art",
"conlang-fam",
"Latn",
"Latn",
type = "conlang",
type = "conlang",
Line 308: Line 344:
ancestors = "mish-pro, ine-pro",
ancestors = "mish-pro, ine-pro",
type = "reconstructed,conlang",
type = "reconstructed,conlang",
}
m["aoka"] = {
"Ah Oka",
nil,
"sntl",
"Latn",
ancestors="sntl-pro, hauh",
type = "conlang"
}
}


Line 313: Line 358:
"Kotava",
"Kotava",
1377116,
1377116,
"art",
"conlang-fam",
"Latn",
"Latn",
}
}
Line 320: Line 365:
"Proto-Axwan",
"Proto-Axwan",
nil,
nil,
"art",
"conlang-fam",
"Latn",
"Latn",
type = "reconstructed,conlang",
type = "reconstructed,conlang",
Line 346: Line 391:
"Bemé",
"Bemé",
nil,
nil,
"art",
"conlang-fam",
"Latn",
"Latn",
type = "conlang"
type = "conlang"
Line 382: Line 427:
"Gwaxol",
"Gwaxol",
nil,
nil,
"wasc",
"wasc-fam",
"Latn",
"Latn",
ancestors = "wasc, nent-pro",
ancestors = "wasc, nent-pro",
Line 394: Line 439:
to = {"¹", "²", "³", "⁴", "⁵", "⁶"},
to = {"¹", "²", "³", "⁴", "⁵", "⁶"},
}
}
}
m["hauh"] = {
"Hau-Hau",
nil,
"sntl",
"Latn",
ancestors="sntl-pro",
type = "conlang"
}
}


Line 408: Line 462:
"Hazulacanol",
"Hazulacanol",
nil,
nil,
"wasc",
"wasc-fam",
"Latn",
"Latn",
ancestors = "wasc",
ancestors = "wasc",
type = "conlang",
type = "conlang",
}
}


m["xodc"] = {  
m["xodc"] = {  
"Xodec",
"Xodec",
nil,
nil,
"wasc",
"wasc-fam",
"Latn",
"Latn",
ancestors = "hzlc",
ancestors = "hzlc",
Line 428: Line 481:
"North Xodec",
"North Xodec",
nil,
nil,
"wasc",
"wasc-fam",
"Latn",
"Latn",
ancestors = "xodc, hzlc",
ancestors = "xodc, hzlc",
Line 445: Line 498:
"Kilīmos-sāîl",
"Kilīmos-sāîl",
nil,
nil,
"wasc",
"wasc-fam",
"Latn",
"Latn",
ancestors = "wasc",
ancestors = "wasc",
Line 454: Line 507:
"Knrawi",
"Knrawi",
nil,
nil,
"art",
"conlang-fam",
"Latn",
"Latn, Wacg",
type = "conlang",
type = "conlang",
}
}
Line 471: Line 524:
"Central Isles Creole",
"Central Isles Creole",
nil,
nil,
"art",
"conlang-fam",
"Latn",
"Latn",
ancestors = "knra, qsc",
ancestors = "knra, qsc",
Line 480: Line 533:
"Maahaat",
"Maahaat",
nil,
nil,
"slaq",
"slaq-fam",
"Latn",
"Latn",
ancestors = "slaq-pro",
ancestors = "slaq-pro",
Line 489: Line 542:
"Maazha",
"Maazha",
nil,
nil,
"slaq",
"slaq-fam",
"Latn",
"Latn",
ancestors = "slaq-pro",
ancestors = "slaq-pro",
Line 506: Line 559:
"Naedzur",
"Naedzur",
nil,
nil,
"art",
"conlang-fam",
"Latn",
"Latn",
ancestors = "naedz-old",
ancestors = "naedz-old",
Line 515: Line 568:
"Old Naedzur",
"Old Naedzur",
nil,
nil,
"art",
"conlang-fam",
"Latn",
"Latn",
type = "conlang",
type = "conlang",
Line 523: Line 576:
"Nentammmi",
"Nentammmi",
nil,
nil,
"art",
"conlang-fam",
"Latn",
"Latn",
type = "reconstructed,conlang",
type = "reconstructed,conlang",
Line 540: Line 593:
"Misa Okan",
"Misa Okan",
nil,
nil,
"art",
"conlang-fam",
"Latn",
"Latn",
type = "conlang",
type = "conlang",
Line 548: Line 601:
"Po Po",
"Po Po",
nil,
nil,
"art",
"conlang-fam",
"Latn",
"Latn",
type = "conlang",
type = "conlang",
Line 565: Line 618:
"Sokya",
"Sokya",
nil,
nil,
"wasc",
"wasc-fam",
"Latn",
"Latn",
ancestors = "qsc",
ancestors = "qsc",
Line 574: Line 627:
"Rokadong",
"Rokadong",
nil,
nil,
"art",
"conlang-fam",
"Roka",
"Roka",
ancestors = "annen",
ancestors = "annen",
Line 583: Line 636:
"Ankistran substrate",
"Ankistran substrate",
nil,
nil,
"art",
"conlang-fam",
"Latn",
"Latn",
type = "conlang",
type = "conlang",
Line 591: Line 644:
"Kairitelan",
"Kairitelan",
nil,
nil,
"art",
"conlang-fam",
"Latn",
"Latn",
ancestors = "annen",
ancestors = "annen",
Line 600: Line 653:
"Liðakuin",
"Liðakuin",
nil,
nil,
"art",
"conlang-fam",
"Latn",
"Latn",
ancestors = "anldk-old",
ancestors = "anldk-old",
Line 609: Line 662:
"Debazi",
"Debazi",
nil,
nil,
"art",
"conlang-fam",
"Latn",
"Latn",
ancestors = "anmnk",
ancestors = "anmnk",
Line 618: Line 671:
"Old Liðakuin",
"Old Liðakuin",
nil,
nil,
"art",
"conlang-fam",
"Latn",
"Latn",
ancestors = "anwgs",
ancestors = "anwgs",
Line 627: Line 680:
"Classical Munkai",
"Classical Munkai",
nil,
nil,
"art",
"conlang-fam",
"Latn",
"Latn",
ancestors = "anpmk",
ancestors = "anpmk",
Line 636: Line 689:
"Proto-Munkai",
"Proto-Munkai",
nil,
nil,
"art",
"conlang-fam",
"Latn",
"Latn",
ancestors = "anplm",
ancestors = "anplm",
Line 645: Line 698:
"Proto-Leyen-Mangellian",
"Proto-Leyen-Mangellian",
nil,
nil,
"art",
"conlang-fam",
"Latn",
"Latn",
type = "conlang",
type = "conlang",
Line 653: Line 706:
"Proto-Nenta",
"Proto-Nenta",
nil,
nil,
"art",
"conlang-fam",
"Latn",
"Latn",
type = "conlang",
type = "conlang",
Line 661: Line 714:
"Proto-West-Gomensayan",
"Proto-West-Gomensayan",
nil,
nil,
"art",
"conlang-fam",
"Latn",
"Latn",
type = "conlang",
type = "conlang",
Line 669: Line 722:
"Hatzonian",
"Hatzonian",
nil,
nil,
"art",
"conlang-fam",
"Latn",
"Latn",
ancestors = "ankar",
ancestors = "ankar",
Line 678: Line 731:
"Common Kardonian",
"Common Kardonian",
nil,
nil,
"art",
"conlang-fam",
"Latn",
"Latn",
ancestors = "ankar",
ancestors = "ankar",
Line 687: Line 740:
"Speodan",
"Speodan",
nil,
nil,
"art",
"conlang-fam",
"Latn",
"Latn",
ancestors = "ankar",
ancestors = "ankar",
Line 696: Line 749:
"Calubian",
"Calubian",
nil,
nil,
"art",
"conlang-fam",
"Latn",
"Latn",
ancestors = "ankar",
ancestors = "ankar",
Line 705: Line 758:
"Dyamantian",
"Dyamantian",
nil,
nil,
"art",
"conlang-fam",
"Latn",
"Latn",
ancestors = "ankar",
ancestors = "ankar",
Line 714: Line 767:
"Middle Kardonian",
"Middle Kardonian",
nil,
nil,
"art",
"conlang-fam",
"Latn",
"Latn",
type = "conlang",
type = "conlang",
Line 790: Line 843:
}
}


m["elva"] = {
m["thus"] = {
"Elvarri",
"Thustani",
"lxel, lxel-nor",
nil,
"art",
"qfa-iso",
"Latn",
"Latn",
ancestors = "lxel-pro,lxel-nor-pro,elva-ear",
ancestors = "thus-old",
type="conlang"
type = "conlang"
}
}


m["elva-ear"] = {
m["thus-old"] = {
"Early Elvarri",
"Old Thustani",
nil,
"qfa-iso",
"Latn",
type = "conlang"
}
 
 
m["elva"] = {
"Elvarri",
"lxel, lxel-nor",
"conlang-fam",
"Latn",
ancestors = "lxel-pro,lxel-nor-pro,elva-ear",
type="conlang"
}
 
m["elva-ear"] = {
"Early Elvarri",
"lxel, lxel-nor",
"lxel, lxel-nor",
"art",
"conlang-fam",
"Latn",
"Latn",
ancestors = "lxel-pro,lxel-nor-pro",
ancestors = "lxel-pro,lxel-nor-pro",
type="conlang"
}
m["sadl"] = {
"Sadling",
"lxel, lxel-sou",
"conlang-fam",
"Latn",
ancestors = "lxel-pro, lxel-sou-pro",
type="conlang"
type="conlang"
}
}
Line 814: Line 894:
"Latn, Runr",
"Latn, Runr",
ancestors = "gem-pro",
ancestors = "gem-pro",
type = "conlang",
}
m["cacr"] = {
"Cabot Creole",
nil,
"iro-nor, iro",
"Latn",
    sort_key = {
        from = {"%-"},
        to = {""},
    },
    display_text = {
    from = {"^(.+):"}, -- colon, except if beginning with it
    to = {"%1꞉"}, --modifier letter colon
    },
ancestors = "iro-pro, iro-nor-pro",
type = "conlang",
type = "conlang",
}
}
Line 842: Line 939:
ancestors = "vdnc-pro",
ancestors = "vdnc-pro",
type = "conlang",
type = "conlang",
}
m["gnym"] = {
"Ganymedian",
nil,
"conlang-fam",
"Latn",
type = "conlang"
}
}


Line 866: Line 971:
"Jokelang 2",
"Jokelang 2",
nil,
nil,
"art",
"conlang-fam",
"Latn",
"Latn",
type = "conlang",
type = "conlang",
Line 903: Line 1,008:
"Kílta",
"Kílta",
nil,
nil,
"art",
"conlang-fam",
"Latn",
"Latn",
sort_key = {
sort_key = {
Line 936: Line 1,041:
nil,
nil,
"lxel-nor,lxel",
"lxel-nor,lxel",
"Latn",
sort_key = {
from = {"[-*·]"},
to =  {""},
remove_diacritics = c.macron .. c.breve,
},
ancestors="lxel-pro",
type = "reconstructed,conlang",
}
m["lxel-sou-pro"] = {
"Proto–South Luxelvic",
nil,
"lxel-sou,lxel",
"Latn",
"Latn",
sort_key = {
sort_key = {
Line 1,029: Line 1,147:
"Nawuhu",
"Nawuhu",
nil,
nil,
"art",
"conlang-fam",
"Latn",
"Latn",
type = "conlang",
type = "conlang",
Line 1,046: Line 1,164:
"Pine",
"Pine",
nil,
nil,
"art",
"conlang-fam",
"Teul, Tugv",
"Teul, Tugv",
entry_name = {
entry_name = {
from = {"‧"},
from = {"‧$", "‧"},
to = {""},
to = {"-", ""},
},
},
sort_key = {
sort_key = {
remove_diacritics = c.hook,
remove_diacritics = c.hook,
from = {"%-"},
to = {""},
},
},
type = "conlang",
type = "conlang",
Line 1,064: Line 1,184:
"Old Ponish",
"Old Ponish",
nil,
nil,
"art",
"conlang-fam",
"Latn",
"Latn",
ancestors = "gmw-pro",
ancestors = "gmw-pro",
Line 1,073: Line 1,193:
"Ponish",
"Ponish",
nil,
nil,
"art",
"conlang-fam",
"Latn",
"Latn",
ancestors = "old-pnsh",
ancestors = "old-pnsh",
Line 1,082: Line 1,202:
"Sekhulla",
"Sekhulla",
nil,
nil,
"wasc",
"wasc-fam",
"Latn",
"Latn",
ancestors = "wasc",
ancestors = "wasc",
Line 1,125: Line 1,245:
"Proto-Slaq",
"Proto-Slaq",
nil,
nil,
"art",
"conlang-fam",
"Latn",
"Latn",
type = "reconstructed,conlang",
type = "reconstructed,conlang",
Line 1,151: Line 1,271:
"Toki Pona",
"Toki Pona",
36846,
36846,
"art",
"conlang-fam",
"Latn",
"Latn",
type = "conlang",
type = "conlang",
Line 1,159: Line 1,279:
"Uchee",
"Uchee",
nil,
nil,
"slaq",
"slaq-fam",
"Latn",
"Latn",
ancestors = "slaq-pro",
ancestors = "slaq-pro",
Line 1,176: Line 1,296:
"Urka",
"Urka",
nil,
nil,
"slaq",
"slaq-fam",
"Latn",
"Latn",
ancestors = "slaq-pro",
ancestors = "slaq-pro",
Line 1,197: Line 1,317:
"Wascotl",
"Wascotl",
nil,
nil,
"art",
"conlang-fam",
"Latn",
"Latn",
type = "reconstructed,conlang",
type = "reconstructed,conlang",
Line 1,205: Line 1,325:
"Wedge",
"Wedge",
nil,
nil,
"art",
"conlang-fam",
"Latn",
"Latn",
type="conlang",
type="conlang",
Line 1,213: Line 1,333:
"Chiingimec",
"Chiingimec",
nil,
nil,
"art",
"conlang-fam",
"Cyrl",
"Cyrl",
translit = "xchc-translit",
translit = "xchc-translit",
Line 1,322: Line 1,442:
"Proto-Plains",
"Proto-Plains",
nil,
nil,
"art",
"conlang-fam",
"Latn",
"Latn",
type = "reconstructed,conlang"
type = "reconstructed,conlang"
Line 1,366: Line 1,486:
"Qut",  
"Qut",  
nil,
nil,
"art",
"conlang-fam",
"Latn",
"Latn",
type = "conlang",
type = "conlang",
Line 1,577: Line 1,697:
     ancestors = "vhus, phus, non, gem-pro",
     ancestors = "vhus, phus, non, gem-pro",
     type = "conlang",
     type = "conlang",
}
m["sdno"] = {                         
    "Sudrey Norse",                       
    nil,                         
    "gem",                       
    "Latn",
    ancestors = "non, gem-pro",
    type = "conlang",
    sort_key = {remove_diacritics = c.grave .. c.acute},
    standard_chars = "AaÀàBbCcDdEeÈèFfGgHhIiÌìLlMmNnOoÒòPpRrSsTtUuÙùVv" .. c.punc,
}
}


Line 1,584: Line 1,715:
     "gem",                         
     "gem",                         
     "Latn",
     "Latn",
     ancestors = "non, gem-pro",
     ancestors = "sdno, non, gem-pro",
     type = "conlang",
     type = "conlang",
     translit = "snon-translit"
     sort_key = {remove_diacritics = c.grave .. c.acute},
    standard_chars = "AaÀàBbCcDdEeÈèFfGgHhIiÌìLlMmNnOoÒòPpRrSsTtUuÙùVvZz" .. c.punc,
}
}


Line 2,214: Line 2,346:
"nic-grs",
"nic-grs",
"Latn",
"Latn",
entry_name = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.tilde .. c.macron},
strip_diacritics = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.tilde .. c.macron},
}
}


m["alv-bgu"] = {
m["alv-bgu"] = {
"Baïnounk Gubëeher",
"Bainouk Gubeeher",
17002646,
17002646,
"alv-bny",
"alv-bny",
Line 2,395: Line 2,527:
"Adûni",
"Adûni",
1232159,
1232159,
"art",
"conlang-fam",
"Latn",
"Latn",
type = "appendix-constructed",
type = "appendix-constructed",
Line 2,403: Line 2,535:
"Belter Creole",
"Belter Creole",
108055510,
108055510,
"art",
"conlang-fam",
"Latn",
"Latn",
type = "appendix-constructed",
type = "appendix-constructed",
Line 2,416: Line 2,548:
"Bolak",
"Bolak",
2909283,
2909283,
"art",
"conlang-fam",
"Latn",
"Latn",
type = "appendix-constructed",
type = "appendix-constructed",
Line 2,424: Line 2,556:
"Black Speech",
"Black Speech",
686210,
686210,
"art",
"conlang-fam",
"Latn, Teng",
"Latn, Teng",
type = "appendix-constructed",
type = "appendix-constructed",
Line 2,432: Line 2,564:
"Communicationssprache",
"Communicationssprache",
35227,
35227,
"art",
"conlang-fam",
"Latn",
"Latn",
type = "appendix-constructed",
type = "appendix-constructed",
Line 2,440: Line 2,572:
"Dothraki",
"Dothraki",
2914733,
2914733,
"art",
"conlang-fam",
"Latn",
"Latn",
type = "appendix-constructed",
type = "appendix-constructed",
Line 2,448: Line 2,580:
"Eloi",
"Eloi",
nil,
nil,
"art",
"conlang-fam",
"Latn",
"Latn",
type = "appendix-constructed",
type = "appendix-constructed",
Line 2,456: Line 2,588:
"Goa'uld",
"Goa'uld",
19823,
19823,
"art",
"conlang-fam",
"Latn, Egyp, Mero",
"Latn, Egyp, Mero",
type = "appendix-constructed",
type = "appendix-constructed",
Line 2,464: Line 2,596:
"Lapine",
"Lapine",
6488195,
6488195,
"art",
"conlang-fam",
"Latn",
"Latn",
type = "appendix-constructed",
type = "appendix-constructed",
Line 2,472: Line 2,604:
"Mandalorian",
"Mandalorian",
54289,
54289,
"art",
"conlang-fam",
"Latn",
"Latn",
type = "appendix-constructed",
type = "appendix-constructed",
Line 2,480: Line 2,612:
"Mundolinco",
"Mundolinco",
851355,
851355,
"art",
"conlang-fam",
"Latn",
"Latn",
type = "appendix-constructed",
type = "appendix-constructed",
Line 2,488: Line 2,620:
"Naʼvi",
"Naʼvi",
316939,
316939,
"art",
"conlang-fam",
"Latn",
"Latn",
type = "appendix-constructed",
type = "appendix-constructed",
}
}


m["art-vlh"] = {
m["ath-nic"] = {
"High Valyrian",
64483808,
"art",
"Latn",
type = "appendix-constructed",
}
 
m["ath-nic"] = {
"Nicola",
"Nicola",
20609,
20609,
Line 2,593: Line 2,717:
"Little Swanport",
"Little Swanport",
6652138,
6652138,
nil,
"qfa-unc",
"Latn",
"Latn",
}
}
Line 2,997: Line 3,121:
"bnt-ngu",
"bnt-ngu",
"Latn",
"Latn",
entry_name = {remove_diacritics = c.grave .. c.acute},
strip_diacritics = {remove_diacritics = c.grave .. c.acute},
}
}


Line 3,007: Line 3,131:
type = "reconstructed",
type = "reconstructed",
sort_key = "bnt-pro-sortkey",
sort_key = "bnt-pro-sortkey",
}
m["bnt-sab-pro"] = {
"Proto-Sabaki",
nil, -- Q2209395 is the code for the Sabaki family
"bnt-sab",
"Latn",
type = "reconstructed",
}
}


Line 3,168: Line 3,300:
"Latn",
"Latn",
type = "reconstructed",
type = "reconstructed",
entry_name = {
strip_diacritics = {
from = {"q̣", "p̣", "ʓ", "ċ"},
from = {"q̣", "p̣", "ʓ", "ċ"},
to = {"q̇", "ṗ", "ʒ", "c̣"}
to = {"q̇", "ṗ", "ʒ", "c̣"}
Line 3,180: Line 3,312:
"Latn",
"Latn",
type = "reconstructed",
type = "reconstructed",
entry_name = {
strip_diacritics = {
from = {"q̣", "p̣", "ʓ", "ċ"},
from = {"q̣", "p̣", "ʓ", "ċ"},
to = {"q̇", "ṗ", "ʒ", "c̣"}
to = {"q̇", "ṗ", "ʒ", "c̣"}
Line 3,223: Line 3,355:
"cel-bry",
"cel-bry",
"Latn, Polyt",
"Latn, Polyt",
translit = {
Polyt = "grc-translit",
},
display_text = {
Polyt = s["Polyt-displaytext"],
},
entry_name = {
Polyt = s["Polyt-entryname"],
},
sort_key = {
sort_key = {
Latn = "cel-bry-pro-sortkey",
Latn = "cel-bry-pro-sortkey",
Polyt = s["Polyt-sortkey"],
},
},
-- Polyt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]]
}
}


Line 3,243: Line 3,366:
"cel",
"cel",
"Latn, Polyt, Ital",
"Latn, Polyt, Ital",
translit = {
strip_diacritics = {
Polyt = "grc-translit",
Ital = "Ital-translit"
},
display_text = {
Polyt = s["Polyt-displaytext"],
},
entry_name = {
Latn = {remove_diacritics = c.macron .. c.breve .. c.diaer},
Latn = {remove_diacritics = c.macron .. c.breve .. c.diaer},
Polyt = s["Polyt-entryname"],
},
},
sort_key = {
sort_key = {
Latn = "cel-bry-pro-sortkey",
Latn = "cel-bry-pro-sortkey",
Polyt = s["Polyt-sortkey"],
},
},
-- Ital translit in [[Module:scripts/data]]
-- Polyt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]]
}
}


Line 3,453: Line 3,569:
"Mlym, Knda",
"Mlym, Knda",
ancestors = "ml, tcy",
ancestors = "ml, tcy",
translit = {
-- Knda translit in [[Module:scripts/data]]
Mlym = "ml-translit",
-- Mlym translit in [[Module:scripts/data]]
Knda = "kn-translit",
},
}
}


Line 3,472: Line 3,586:
"dra-kan",
"dra-kan",
"Knda",
"Knda",
translit = "kn-translit",
-- Knda translit in [[Module:scripts/data]]
}
}


Line 3,488: Line 3,602:
"dra-kan",
"dra-kan",
"Knda",
"Knda",
translit = "kn-translit",
-- Knda translit in [[Module:scripts/data]]
}
}


Line 3,532: Line 3,646:


m["egx-dem"] = {
m["egx-dem"] = {
"Demotic",
"Demotic Egyptian",
36765,
36765,
"egx",
"egx",
"Latn, Egyd, Polyt",
"Latn, Egyd, Polyt",
translit = {
Polyt = "grc-translit",
},
display_text = {
Polyt = s["Polyt-displaytext"],
},
entry_name = {
Polyt = s["Polyt-entryname"],
},
sort_key = {
sort_key = {
Latn = {
Latn = {
Line 3,551: Line 3,656:
to = {p[1], p[2], p[3], p[4], p[5], p[6], p[7], p[8], p[9], p[10], p[11], p[12], p[13], p[15], p[16], p[16], p[17], p[14], p[19], p[18], p[20], p[21], p[22], p[23], p[24], p[23], p[25], p[26], p[26]}
to = {p[1], p[2], p[3], p[4], p[5], p[6], p[7], p[8], p[9], p[10], p[11], p[12], p[13], p[15], p[16], p[16], p[17], p[14], p[19], p[18], p[20], p[21], p[22], p[23], p[24], p[23], p[25], p[26], p[26]}
},
},
Polyt = s["Polyt-sortkey"],
},
},
-- Polyt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]]
}
}


Line 3,711: Line 3,816:
"gmq-eas",
"gmq-eas",
"Latn, Runr",
"Latn, Runr",
entry_name = {remove_diacritics = c.macron},
strip_diacritics = {remove_diacritics = c.macron},
}
}


Line 3,727: Line 3,832:
"gmq-eas",
"gmq-eas",
"Latn, Runr",
"Latn, Runr",
entry_name = {remove_diacritics = c.macron},
strip_diacritics = {remove_diacritics = c.macron},
}
}


Line 3,851: Line 3,956:


m["gn-cls"] = {
m["gn-cls"] = {
"Classical Guaraní",
"Classical Guarani",
17478065,
17478065,
"tup-gua",
"gn",
"Latn",
"Latn",
ancestors = "gn",
}
}


Line 3,867: Line 3,971:
Grek = "el-translit",
Grek = "el-translit",
},
},
display_text = {
-- Grek display_text, strip_diacritics, sort_key in [[Module:scripts/data]]
Grek = s["Grek-displaytext"],
},
entry_name = {
Grek = s["Grek-entryname"],
},
sort_key = {
Grek = s["Grek-sortkey"],
},
}
}


Line 3,887: Line 3,983:
Grek = "el-translit",
Grek = "el-translit",
},
},
display_text = {
-- Grek display_text, strip_diacritics, sort_key in [[Module:scripts/data]]
Grek = s["Grek-displaytext"],
},
entry_name = {
Grek = s["Grek-entryname"],
},
sort_key = {
Grek = s["Grek-sortkey"],
},
}
}


Line 3,909: Line 3,997:
},
},
override_translit = true,
override_translit = true,
display_text = {
strip_diacritics = {
Grek = s["Grek-displaytext"],
},
entry_name = {
Cyrl = {remove_diacritics = c.acute},
Cyrl = {remove_diacritics = c.acute},
Grek = s["Grek-entryname"],
},
sort_key = {
Grek = s["Grek-sortkey"],
},
},
-- Grek display_text, strip_diacritics, sort_key in [[Module:scripts/data]]
}
}


Line 3,932: Line 4,014:
remove_diacritics = c.grave .. c.acute .. c.macron .. c.breve .. c.caron
remove_diacritics = c.grave .. c.acute .. c.macron .. c.breve .. c.caron
}},
}},
-- Polyt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]]
-- NOTE: formerly no translit specified for Polyt; presumably an accidental omission; if not, set Polyt = false in
-- the translit section
}
}


m["hmn-pro"] = {
m["hmn-pro"] = {
"Proto-Hmong",
"Proto-Hmongic",
116773210,
116773210,
"hmn",
"hmn",
Line 3,943: Line 4,028:


m["hmx-mie-pro"] = {
m["hmx-mie-pro"] = {
"Proto-Mien",
"Proto-Mienic",
116773229,
116773229,
"hmx-mie",
"hmx-mie",
Line 3,998: Line 4,083:
translit = {
translit = {
Deva = "sa-translit",
Deva = "sa-translit",
Shrd = "Shrd-translit",
-- Shrd translit in [[Module:scripts/data]]
Sidd = "Sidd-translit",
-- Sidd translit in [[Module:scripts/data]]
},
},
}
}
Line 4,010: Line 4,095:
ancestors = "sa",
ancestors = "sa",
translit = {
translit = {
Brah = "Brah-translit",
-- Brah translit in [[Module:scripts/data]]
Khar = "Khar-translit",
Khar = "Khar-translit",
},
},
}
m["inc-dng-pro"] = {
"Proto-Dangari",
nil,
"inc-dng",
"Latn",
type = "reconstructed",
}
}


Line 4,020: Line 4,113:
"inc-bas",
"inc-bas",
"Brah, Sidd",
"Brah, Sidd",
translit = {
-- Brah, Sidd translit in [[Module:scripts/data]]
Brah = "Brah-translit",
}
Sidd = "Sidd-translit",
},
}


m["inc-kho"] = {
m["inc-kho"] = {
Line 4,090: Line 4,180:
"inc-hie",
"inc-hie",
"Deva, Kthi, ur-Arab",
"Deva, Kthi, ur-Arab",
entry_name = {
strip_diacritics = {
from = {"هٔ", "ۂ"}, -- character "ۂ" code U+06C2 to "ه" and "هٔ"‎ (U+0647 + U+0654) to "ه"
from = {"هٔ", "ۂ"}, -- character "ۂ" code U+06C2 to "ه" and "هٔ" (U+0647 + U+0654) to "ه"
to = {"ہ", "ہ"},
to = {"ہ", "ہ"},
remove_diacritics = c.fathatan .. c.dammatan .. c.kasratan .. c.fatha .. c.damma .. c.kasra .. c.shadda .. c.sukun .. c.nunghunna .. c.superalef
remove_diacritics = c.fathatan .. c.dammatan .. c.kasratan .. c.fatha .. c.damma .. c.kasra .. c.shadda .. c.sukun .. c.nunghunna .. c.superalef
Line 4,122: Line 4,212:
"inc-hiw",
"inc-hiw",
"Deva, ur-Arab",
"Deva, ur-Arab",
entry_name = {
strip_diacritics = {
from = {"هٔ", "ۂ"}, -- character "ۂ" code U+06C2 to "ه" and "هٔ"‎ (U+0647 + U+0654) to "ه"
from = {"هٔ", "ۂ"}, -- character "ۂ" code U+06C2 to "ه" and "هٔ" (U+0647 + U+0654) to "ه"
to = {"ہ", "ہ"},
to = {"ہ", "ہ"},
remove_diacritics = c.fathatan .. c.dammatan .. c.kasratan .. c.fatha .. c.damma .. c.kasra .. c.shadda .. c.sukun .. c.nunghunna .. c.superalef
remove_diacritics = c.fathatan .. c.dammatan .. c.kasratan .. c.fatha .. c.damma .. c.kasra .. c.shadda .. c.sukun .. c.nunghunna .. c.superalef
Line 4,149: Line 4,239:
["pa-Arab"] = "pa-Arab-translit",
["pa-Arab"] = "pa-Arab-translit",
},
},
entry_name = {remove_diacritics = c.fathatan .. c.dammatan .. c.kasratan .. c.fatha .. c.damma .. c.kasra .. c.shadda .. c.sukun},
strip_diacritics = {remove_diacritics = c.fathatan .. c.dammatan .. c.kasratan .. c.fatha .. c.damma .. c.kasra .. c.shadda .. c.sukun},
}
}


Line 4,192: Line 4,282:
"ine",
"ine",
"Polyt",
"Polyt",
translit = "grc-translit",
-- Polyt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]]
display_text = s["Polyt-displaytext"],
entry_name = s["Polyt-entryname"],
sort_key = s["Polyt-sortkey"],
}
}


Line 4,223: Line 4,310:
"xme",
"xme",
"Polyt, Latn",
"Polyt, Latn",
translit = {
-- Polyt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]]
Polyt = "grc-translit",
},
display_text = {
Polyt = s["Polyt-displaytext"],
},
entry_name = {
Polyt = s["Polyt-entryname"],
},
sort_key = {
Polyt = s["Polyt-sortkey"],
},
}
}


Line 4,250: Line 4,326:
"fa-Arab, Latn, Hebr",
"fa-Arab, Latn, Hebr",
ancestors = "xme-mid",
ancestors = "xme-mid",
-- Hebr display_text, strip_diacritics, sort_key in [[Module:scripts/data]]
}
}


Line 4,460: Line 4,537:
"itc-sbl",
"itc-sbl",
"Ital, Polyt, Latn",
"Ital, Polyt, Latn",
translit = {
-- Ital translit in [[Module:scripts/data]] (NOTE: formerly not present, probably an accidental omission)
Polyt = "grc-translit",
-- Polyt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]]
},
display_text = {
Polyt = s["Polyt-displaytext"],
},
entry_name = {
Polyt = s["Polyt-entryname"],
},
sort_key = {
Polyt = s["Polyt-sortkey"],
},
}
}


Line 4,482: Line 4,549:
translit = s["jpx-translit"],
translit = s["jpx-translit"],
display_text = s["jpx-displaytext"],
display_text = s["jpx-displaytext"],
entry_name = s["jpx-entryname"],
strip_diacritics = s["jpx-stripdiacritics"],
sort_key = s["jpx-sortkey"],
sort_key = s["jpx-sortkey"],
}
}
Line 4,571: Line 4,638:
ancestors = "okm",
ancestors = "okm",
translit = "okm-translit",
translit = "okm-translit",
entry_name = s["Kore-entryname"],
-- Kore strip_diacritics in [[Module:scripts/data]]
}
}


Line 4,623: Line 4,690:
"Idiom Neutral",
"Idiom Neutral",
35847,
35847,
"art",
"conlang-fam",
"Latn",
"Latn",
type = "appendix-constructed",
type = "appendix-constructed",
Line 4,676: Line 4,743:
nil,
nil,
"Phnx",
"Phnx",
-- Phnx translit in [[Module:scripts/data]] (NOTE: not present before, presumably an accidental omission)
}
}


Line 5,306: Line 5,374:
}
}


m["nds-de"] = {
m["ngf-bin-pro"] = {
"German Low German",
"Proto-Binanderean",
25433,
137881672,
"gmw-lgm",
"ngf-bin",
"Latn",
"Latn",
ancestors = "nds",
type = "reconstructed",
ietf_subtag = "nds-DE", -- should we make this the actual code?
wikimedia_codes = "nds",
}
 
m["nds-nl"] = {
"Dutch Low Saxon",
516137,
"gmw-lgm",
"Latn",
ancestors = "nds",
ietf_subtag = "nds-NL", -- should we make this the actual code?
wikimedia_codes = "nds-nl",
}
}


Line 5,452: Line 5,508:
"Latn",
"Latn",
type = "reconstructed",
type = "reconstructed",
}
m["njo-jgl"] = {
"Chungli Ao",
55607615,
"sit-aao",
"Latn",
}
}


Line 5,519: Line 5,582:
m["omq-sjq"] = {
m["omq-sjq"] = {
"San Juan Quiahije Chatino",
"San Juan Quiahije Chatino",
17003130,
138330751,
"omq-cha",
"omq-cha",
"Latn",
"Latn",
Line 5,539: Line 5,602:


m["omq-tri-pro"] = {
m["omq-tri-pro"] = {
"Proto-Trique",
"Proto-Triqui",
116773817,
116773817,
"omq-tri",
"omq-tri",
Line 5,602: Line 5,665:
}
}


m["paa-kom"] = {
m["paa-kmn"] = {
"Kómnzo",
"Kómnzo",
18344310,
18344310,
"paa-yam",
"paa-wko",
"Latn",
"Latn",
}
}
Line 5,612: Line 5,675:
"Kuwani",
"Kuwani",
6449056,
6449056,
"paa",
"qfa-unc", -- poorly attested, possibly the same as or related to Kalabra
"Latn",
"Latn",
}
m["paa-lei"] = {
"Leitre",
85776228,
"paa-isk",
}
}


Line 5,627: Line 5,696:
"Nungon",
"Nungon",
128807788,
128807788,
"paa",
"ngf-ynu",
"Latn",
"Latn",
}
}
Line 6,013: Line 6,082:
3094838,
3094838,
"roa-git",
"roa-git",
ancestors = "pms-old",
"Latn",
"Latn",
}
}
Line 6,021: Line 6,091:
"roa-git",
"roa-git",
"Latn",
"Latn",
ancestors = "pms-old",
}
}


Line 6,065: Line 6,136:
"roa-gap",
"roa-gap",
"Latn",
"Latn",
entry_name = {remove_diacritics = c.grave .. c.acute .. c.circ},
strip_diacritics = {remove_diacritics = c.grave .. c.acute .. c.circ},
}
}


Line 6,116: Line 6,187:
"Baenan",
"Baenan",
3401998,
3401998,
nil,
"qfa-unc", -- extinct, poorly attested; only known through 9 words
"Latn",
"Latn",
}
}
Line 6,123: Line 6,194:
"Bagua",
"Bagua",
5390321,
5390321,
nil,
"qfa-unc", -- extinct, poorly attested; possibly Cariban
"Latn",
"Latn",
}
}
Line 6,145: Line 6,216:
"Cacán",
"Cacán",
945482,
945482,
nil,
"qfa-unc", -- extinct, poorly attested; no consensus on classification
"Latn",
"Latn",
}
}
Line 6,182: Line 6,253:
"Chirino",
"Chirino",
5390321,
5390321,
nil,
"qfa-unc", -- extinct, only four words known; possibly related to Candoshi-Shapra (cbu)
"Latn",
"Latn",
}
}
Line 6,225: Line 6,296:
"Comechingon",
"Comechingon",
6644203,
6644203,
nil,
"qfa-unc", -- extinct, poorly attested; no consensus on classification
"Latn",
"Latn",
}
}
Line 6,232: Line 6,303:
"Chono",
"Chono",
5104704,
5104704,
nil,
"qfa-unc", -- extinct, poorly attested; no consensus on classification, possibly spurious
"Latn",
"Latn",
}
}
Line 6,239: Line 6,310:
"Cañari",
"Cañari",
5055572,
5055572,
nil,
"qfa-unc", -- extinct, poorly attested; possibly Chimuan or Barbacoan
"Latn",
"Latn",
}
}
Line 6,260: Line 6,331:
"Copallén",
"Copallén",
5390321,
5390321,
nil,
"qfa-unc", -- extinct, only four words attested; possibly Cholonan
"Latn",
"Latn",
}
}
Line 6,274: Line 6,345:
"Catuquinaru",
"Catuquinaru",
16858455,
16858455,
nil,
"qfa-unc", -- extinct, poorly attested; vocabulary does not resemble other languages
"Latn",
"Latn",
}
}
Line 6,281: Line 6,352:
"Culli",
"Culli",
2879660,
2879660,
nil,
"qfa-unc", -- extinct, poorly attested; often considered an isolate
"Latn",
"Latn",
}
}
Line 6,288: Line 6,359:
"Cueva",
"Cueva",
5192644,
5192644,
nil,
"qfa-unc", -- extinct, poorly attested; possibly Chocoan
"Latn",
"Latn",
}
}
Line 6,295: Line 6,366:
"Esmeralda",
"Esmeralda",
3058083,
3058083,
nil,
"qfa-unc", -- extinct, poorly attested; possibly related to Yaruro
"Latn",
"Latn",
}
}
Line 6,309: Line 6,380:
"Gamela",
"Gamela",
5403661,
5403661,
nil,
"qfa-unc", -- extinct, poorly attested; possibly an isolate
"Latn",
"Latn",
}
}
Line 6,323: Line 6,394:
"Guamo",
"Guamo",
5613495,
5613495,
nil,
"qfa-unc", -- extinct; "Kaufman (1990) finds a connection with the Chapacuran languages convincing." [Wikipedia] Considered an isolate by Campbell (2024).
"Latn",
"Latn",
}
}
Line 6,373: Line 6,444:
"Katembri",
"Katembri",
6375925,
6375925,
nil,
"qfa-unc", -- extinct, poorly attested; "Kaufman (1990) has linked it with the nearly extinct Taruma, although this has not been accepted by other scholars." [Wikipedia]
"Latn",
"Latn",
}
}
Line 6,380: Line 6,451:
"Malalí",
"Malalí",
6741212,
6741212,
nil,
"sai-mje", -- considered the most divergent Maxakalían language (a subdivision of Macro-Jê), for which we have no entry
"Latn",
"Latn",
}
}
Line 6,387: Line 6,458:
"Maratino",
"Maratino",
6755055,
6755055,
nil,
"qfa-unc", -- extinct, poorly attested; possibly Uto-Aztecan
"Latn",
"Latn",
}
}
Line 6,394: Line 6,465:
"Matanawi",
"Matanawi",
6786047,
6786047,
nil,
"qfa-unc", -- extinct; either an isolate or distantly related to the Muran languages; Campbell (2024) lists it as an isolate, Glottolog gives it as unclassified
"Latn",
"Latn",
}
}
Line 6,401: Line 6,472:
"Mocana",
"Mocana",
3402048,
3402048,
nil,
"qfa-unc", -- extinct, poorly attested; given as part of the Malibu languages (geographic grouping; not a clade)
"Latn",
"Latn",
}
}
Line 6,422: Line 6,493:
"Malibu",
"Malibu",
3402048,
3402048,
nil,
"qfa-unc", -- extinct, poorly attested; given as part of the Malibu languages (geographic grouping; not a clade)
"Latn",
"Latn",
}
}
Line 6,436: Line 6,507:
"Mucuchí",
"Mucuchí",
6931290,
6931290,
nil,
nil, -- generally considered Timotean, for which we have no entry
"Latn",
"Latn",
}
}
Line 6,450: Line 6,521:
"Muzo",
"Muzo",
6644203,
6644203,
nil,
"qfa-unc", -- extinct language of Colombia, poorly attested; may be Pijao (Cariban)
"Latn",
"Latn",
}
}
Line 6,457: Line 6,528:
"Maynas",
"Maynas",
16919393,
16919393,
nil,
"sai-cah", -- per Campbell (2024); formerly considered unclassified
"Latn",
"Latn",
}
}
Line 6,464: Line 6,535:
"Natú",
"Natú",
9006749,
9006749,
nil,
"qfa-unc", -- extinct, poorly attested; "only Greenberg dares to classify [it]".[Wikipedia, quoting Moseley, Christopher; Asher, R. E.; Tait, Mary (1994), Atlas of the world's languages]
"Latn",
"Latn",
}
}
Line 6,493: Line 6,564:
"Palta",
"Palta",
3042978,
3042978,
nil,
"qfa-unc", -- extinct, unclassified; possibly Chicham
"Latn",
"Latn",
}
}
Line 6,507: Line 6,578:
"Paratió",
"Paratió",
16890038,
16890038,
nil,
"qfa-unc", -- extinct, poorly attested; possibly Xukuruan
"Latn",
}
 
m["sai-peb"] = {
"Peba",
3373890,
"sai-pey",
"Latn",
"Latn",
}
}
Line 6,514: Line 6,592:
"Panzaleo",
"Panzaleo",
3123275,
3123275,
nil,
"qfa-unc", -- extinct, unclassified; possibly Paezan
"Latn",
"Latn",
}
}
Line 6,521: Line 6,599:
"Puruhá",
"Puruhá",
3410994,
3410994,
nil,
"qfa-unc", -- extinct, poorly attested; possibly in a famil with Cañari
"Latn",
"Latn",
}
}
Line 6,528: Line 6,606:
"Patagón",
"Patagón",
128807870,
128807870,
nil,
"sai-tar", -- extinct, only known from 4 words, which suggest Cariban lineage (Campbell 2024)
"Latn",
"Latn",
}
}
Line 6,556: Line 6,634:
"Quimbaya",
"Quimbaya",
7272043,
7272043,
nil,
"qfa-unc", -- extinct, might not exist; few known words
"Latn",
"Latn",
}
}
Line 6,570: Line 6,648:
"Rabona",
"Rabona",
6644203,
6644203,
nil,
"qfa-unc", -- extinct, poorly attested, mostly plant names; possibly Candoshi-Shapra
"Latn",
"Latn",
}
}
Line 6,577: Line 6,655:
"Ramanos",
"Ramanos",
16902824,
16902824,
nil,
"qfa-unc", -- extinct, poorly attested, possibly an isolate; per Glottolog: "the minuscule wordlist ... shows no convincing resemblances to surrounding languages"
"Latn",
"Latn",
}
}
Line 6,584: Line 6,662:
"Sácata",
"Sácata",
5390321,
5390321,
nil,
"qfa-unc", -- extinct, only 3 words known; possibly Candoshí or Arawakan
"Latn",
"Latn",
}
}
Line 6,591: Line 6,669:
"Sanaviron",
"Sanaviron",
16895999,
16895999,
nil,
"qfa-unc", -- extinct, unclassified; no consensus on classification
"Latn",
"Latn",
}
}
Line 6,605: Line 6,683:
"Sechura",
"Sechura",
7442912,
7442912,
nil,
"qfa-unc", -- extinct, poorly attested; possibly Catacaoan
"Latn",
"Latn",
}
}
Line 6,612: Line 6,690:
"Sinúfana",
"Sinúfana",
7525275,
7525275,
nil,
"qfa-unc", -- moribund, poorly attested; possibly Chocoan
"Latn",
"Latn",
}
}
Line 6,627: Line 6,705:
"Tabancale",
"Tabancale",
5390321,
5390321,
nil,
"qfa-unc", -- extinct, only 5 words known; no obvious connections, might be an isolate
"Latn",
"Latn",
}
}
Line 6,634: Line 6,712:
"Tallán",
"Tallán",
16910468,
16910468,
nil,
"qfa-unc", -- extinct, poorly attested; might be Catacaoan
"Latn",
"Latn",
}
}
Line 6,656: Line 6,734:
"Teushen",
"Teushen",
3519243,
3519243,
nil,
"qfa-unc", -- probably extinct by the 1950's; possibly Chonan
"Latn",
"Latn",
}
}
Line 6,663: Line 6,741:
"Timote",
"Timote",
7806995,
7806995,
nil,
nil, -- possibly in a small Timotean family
"Latn",
"Latn",
}
}
Line 6,677: Line 6,755:
"Tarairiú",
"Tarairiú",
7685313,
7685313,
nil,
"qfa-unc", -- extinct, too poorly attested to classify
"Latn",
"Latn",
}
}
Line 6,684: Line 6,762:
"Waitaká",
"Waitaká",
16918610,
16918610,
nil,
"qfa-unc", -- extinct, possibly Purian
"Latn",
"Latn",
}
}
Line 6,713: Line 6,791:
"Xocó",
"Xocó",
12953620,
12953620,
nil,
"qfa-unc", -- extinct and poorly attested; not clear if one or three languages
"Latn",
"Latn",
}
}
Line 6,748: Line 6,826:
"Yurumanguí",
"Yurumanguí",
1281291,
1281291,
nil,
"qfa-unc", -- extinct, too poorly attested to classify
"Latn",
"Latn",
}
}
Line 6,829: Line 6,907:
"sem-can",
"sem-can",
"Phnx",
"Phnx",
translit = "Phnx-translit",
-- Phnx translit in [[Module:scripts/data]]
}
}


Line 6,852: Line 6,930:
"sem-cen",
"sem-cen",
"Narb",
"Narb",
translit = "Narb-translit",
-- Narb translit in [[Module:scripts/data]]
}
}


Line 6,860: Line 6,938:
"sem-cen",
"sem-cen",
"Narb",
"Narb",
translit = "Narb-translit",
-- Narb translit in [[Module:scripts/data]]
}
}


Line 6,868: Line 6,946:
"sem-cen",
"sem-cen",
"Narb",
"Narb",
translit = "Narb-translit",
-- Narb translit in [[Module:scripts/data]]
}
}


Line 6,876: Line 6,954:
"sem-cen",
"sem-cen",
"Narb",
"Narb",
translit = "Narb-translit",
-- Narb translit in [[Module:scripts/data]]
}
}


Line 6,899: Line 6,977:
"sem-cen",
"sem-cen",
"Narb",
"Narb",
translit = "Narb-translit",
-- Narb translit in [[Module:scripts/data]]
}
 
m["sem-sam"] = {
"Samalian",
85847147,
"sem-nwe",
"Phnx",
-- Phnx translit in [[Module:scripts/data]]
}
}


Line 6,907: Line 6,993:
"sem-osa",
"sem-osa",
"Sarb",
"Sarb",
translit = "Sarb-translit",
-- Sarb translit in [[Module:scripts/data]]
}
}


Line 6,915: Line 7,001:
"sem-cen",
"sem-cen",
"Narb",
"Narb",
translit = "Narb-translit",
-- Narb translit in [[Module:scripts/data]]
}
}


Line 6,923: Line 7,009:
"sem-cen",
"sem-cen",
"Narb",
"Narb",
translit = "Narb-translit",
-- Narb translit in [[Module:scripts/data]]
}
}


Line 6,978: Line 7,064:
"sit-tan",
"sit-tan",
"Latn, Tibt",
"Latn, Tibt",
translit = {Tibt = "Tibt-translit"},
override_translit = true,
override_translit = true,
display_text = {Tibt = s["Tibt-displaytext"]},
-- Tibt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]]
entry_name = {Tibt = s["Tibt-entryname"]},
sort_key = {Tibt = "Tibt-sortkey"},
}
}


Line 7,178: Line 7,261:
"Latn",
"Latn",
type = "reconstructed",
type = "reconstructed",
entry_name = {
strip_diacritics = {
remove_diacritics = c.grave .. c.acute .. c.tilde .. c.macron .. c.dgrave .. c.invbreve,
remove_diacritics = c.grave .. c.acute .. c.tilde .. c.macron .. c.dgrave .. c.invbreve,
remove_exceptions = {'ś'},
remove_exceptions = {'ś'},
Line 7,238: Line 7,321:
"Latn",
"Latn",
type = "reconstructed",
type = "reconstructed",
}
m["syd-fne"] = {
"Forest Nenets",
1295107,
"syd",
"Cyrl",
translit = "syd-fne-translit",
entry_name = {remove_diacritics = c.grave .. c.acute .. c.macron .. c.breve .. c.dotabove},
}
}


Line 7,371: Line 7,445:
"trk-ssb",
"trk-ssb",
"Latn, Cyrl, Mong",
"Latn, Cyrl, Mong",
translit = {Mong = "Mong-translit"},
-- Mong translit, display_text and strip_diacritics in [[Module:scripts/data]]
display_text = {Mong = s["Mong-displaytext"]},
entry_name = {Mong = s["Mong-entryname"]},
}
}


Line 7,382: Line 7,454:
"trk-ogz",
"trk-ogz",
"ota-Arab",
"ota-Arab",
entry_name = {["ota-Arab"] = "ar-entryname"},
strip_diacritics = {["ota-Arab"] = "ar-stripdiacritics"},
}
}


Line 7,390: Line 7,462:
"trk-ogz",
"trk-ogz",
"ota-Arab",
"ota-Arab",
entry_name = {["ota-Arab"] = "ar-entryname"},
strip_diacritics = {["ota-Arab"] = "ar-stripdiacritics"},
ancestors = "trk-eog",
ancestors = "trk-eog",
}
}
Line 7,400: Line 7,472:
"Latn",
"Latn",
type = "reconstructed",
type = "reconstructed",
standardChars = {
standard_chars = {
Latn = " ()-abdegiklmnoprstuxyzïöüāčēīĺŋōŕšūǖȫẹ" .. c.macron,
Latn = " ()-abdegiklmnoprstuxyzïöüāčēīĺŋōŕšūǖȫẹ" .. c.macron,
}
}
Line 7,433: Line 7,505:
"tut",
"tut",
"Latn",
"Latn",
type = "reconstructed",
type = "reconstructed"
}
}


Line 7,492: Line 7,564:
"Old Komi",
"Old Komi",
86679962,
86679962,
"urj-prm",
"kv",
"Perm, Cyrs",
"Perm, Cyrs",
translit = "urj-koo-translit",
translit = "urj-koo-translit",
sort_key = {Cyrs = s["Cyrs-sortkey"]},
-- Cyrs strip_diacritics, sort_key in [[Module:scripts/data]]; previously, Cyrs strip_diacritics not present
}
}


Line 7,509: Line 7,581:
"Komi-Yazva",
"Komi-Yazva",
2365210,
2365210,
"urj-prm",
"kv",
"Cyrl",
"Cyrl",
translit = "kv-translit",
translit = "kv-translit",
override_translit = true,
override_translit = true,
entry_name = {remove_diacritics = c.acute},
strip_diacritics = {remove_diacritics = c.acute},
}
}


Line 7,583: Line 7,655:


m["yok-gsy"] = {
m["yok-gsy"] = {
"Gashowu",
"Gashowu Yokuts",
3098708,
3098708,
"yok",
"yok",
Line 7,604: Line 7,676:


m["yok-ply"] = {
m["yok-ply"] = {
"Palewyami",
"Palewyami Yokuts",
2387391,
2387391,
"yok",
"yok",
Line 7,630: Line 7,702:
"Latn",
"Latn",
type = "reconstructed",
type = "reconstructed",
}
m["yrk-for"] = {
"Forest Nenets",
1295107,
"yrk",
"Cyrl",
translit = "yrk-for-translit",
strip_diacritics = {remove_diacritics = c.grave .. c.acute .. c.macron .. c.breve .. c.dotabove},
}
m["yrk-tun"] = {
"Tundra Nenets",
36452,
"yrk",
"Cyrl",
strip_diacritics = {
from = {"ӑ", "а̄", "э̇", "ӣ", "ы̄", "ӯ", "ю̄", "я̆", "я̄"},
to = {"а", "а", "э", "и", "ы", "у", "ю", "я", "я"},
},
translit = "yrk-tun-translit",
}
}


Line 7,675: Line 7,768:
"Cyrs, Glag",
"Cyrs, Glag",
translit = {Cyrs = "Cyrs-translit", Glag = "Glag-translit"},
translit = {Cyrs = "Cyrs-translit", Glag = "Glag-translit"},
entry_name = {Cyrs = s["Cyrs-entryname"]},
-- Cyrs strip_diacritics, sort_key in [[Module:scripts/data]]
sort_key = {Cyrs = s["Cyrs-sortkey"]},
}
}


Line 7,689: Line 7,781:
Arab = "zle-ort-Arab-translit",
Arab = "zle-ort-Arab-translit",
},
},
entry_name = {
strip_diacritics = {
remove_diacritics = s["Cyrs-entryname"].remove_diacritics,
Cyrs = {
remove_exceptions = {"Ї", "ї"},
remove_diacritics = m_langdata.chars_substitutions["Cyrs_remove_diacritics"],
Arab = "ar-entryname",
remove_exceptions = {"Ї", "ї"},
},
Arab = "ar-stripdiacritics",
},
},
sort_key = s["Cyrs-sortkey"],
-- Cyrs sort_key in [[Module:scripts/data]]
}
}


Line 7,707: Line 7,801:
Glag = "Glag-translit"
Glag = "Glag-translit"
},
},
entry_name = {
-- Cyrs strip_diacritics, sort_key in [[Module:scripts/data]]
Cyrs = s["Cyrs-entryname"]
},
sort_key = {
Cyrs = s["Cyrs-sortkey"]
},
}
}


Line 7,727: Line 7,816:
"zlw-lch",
"zlw-lch",
"Latn",
"Latn",
entry_name = {remove_diacritics = c.ringabove},
strip_diacritics = {remove_diacritics = c.ringabove},
}
}


Line 7,742: Line 7,831:
"zlw-pom",
"zlw-pom",
"Latn",
"Latn",
entry_name = {remove_diacritics = c.macron .. c.breve},
strip_diacritics = {remove_diacritics = c.macron .. c.breve},
}
}


return require("Module:languages").finalizeData(m, "language")
return require("Module:languages").finalizeData(m, "language")
Retrieved from "https://linguifex.com/wiki/Module:languages/data/exceptional"