Linguifex

Module:languages/data/3/a: Difference between revisions

← Older edit
m 1 revision imported
m 1 revision imported
 
(One intermediate revision by one other user not shown)
Line 30: Line 30:
"Ari",
"Ari",
1811224,
1811224,
"paa-pag",
"ngf-gsu",
"Latn",
"Latn",
}
}
Line 37: Line 37:
"Amal",
"Amal",
56708,
56708,
"paa-iwm",
"paa-sep",
"Latn",
"Latn",
}
}


-- "aae" IS TREATED AS "sq", SEE WT:LT
-- "aae" is treated as "sq", see [[WT:LT]]


m["aaf"] = {
m["aaf"] = {
Line 48: Line 48:
"dra-mal",
"dra-mal",
"Mlym",
"Mlym",
-- Mlym translit in [[Module:scripts/data]] (NOTE: not present before, presumably an accidental omission)
}
}


Line 53: Line 54:
"Ambrak",
"Ambrak",
4741706,
4741706,
"qfa-tor",
"paa-pal",
"Latn",
"Latn",
}
}
Line 60: Line 61:
"Abu'",
"Abu'",
4670715,
4670715,
"qfa-tor",
"paa-ara",
"Latn",
"Latn",
}
}
Line 74: Line 75:
"Ankave",
"Ankave",
3446690,
3446690,
"ngf",
"ngf-ata",
"Latn",
"Latn",
}
}
Line 93: Line 94:


m["aap"] = {
m["aap"] = {
"Pará Arára",
"Arára (Pará)",
56807,
56807,
"sai-pek",
"sai-pek",
Line 113: Line 114:
}
}


-- "aat" IS TREATED AS "sq", SEE WT:LT
-- "aat" is treated as "sq", see [[WT:LT]]


m["aau"] = {
m["aau"] = {
"Abau",
"Abau",
3073568,
3073568,
"paa-spk",
"paa-sep",
"Latn",
"Latn",
}
}
Line 130: Line 131:


m["aax"] = {
m["aax"] = {
"Mandobo Atas",
"Upper Mandobo",
12636156,
12636156,
"ngf",
"ngf-dum",
"Latn",
"Latn",
}
}
Line 188: Line 189:
"Abaga",
"Abaga",
3507954,
3507954,
"paa-kag",
"ngf-kya",
"Latn",
"Latn",
}
}
Line 197: Line 198:
"sem-arb",
"sem-arb",
"Arab",
"Arab",
entry_name = "ar-entryname",
strip_diacritics = "ar-stripdiacritics",
}
}


Line 261: Line 262:
Cyrl = s["cau-Cyrl-displaytext"]
Cyrl = s["cau-Cyrl-displaytext"]
},
},
entry_name = {
strip_diacritics = {
Cyrl = s["cau-Cyrl-entryname"],
Cyrl = s["cau-Cyrl-stripdiacritics"],
Latn = s["cau-Latn-entryname"],
Latn = s["cau-Latn-stripdiacritics"],
},
},
sort_key = {
sort_key = {
Line 279: Line 280:
}
}


m["abr"] = {
-- "abr" Abron is treated as "ak" Akan, see [[WT:LT]]
"Abron",
34831,
"alv-ctn",
"Latn",
ancestors = "ak",
}


m["abs"] = {
m["abs"] = {
Line 298: Line 293:
"Ambulas",
"Ambulas",
3508015,
3508015,
"paa-spk",
"paa-nnd",
"Latn",
"Latn",
}
}
Line 314: Line 309:
"sem-arb",
"sem-arb",
"Arab",
"Arab",
entry_name = "ar-entryname",
strip_diacritics = "ar-stripdiacritics",
}
}


Line 320: Line 315:
"Pal",
"Pal",
7126121,
7126121,
"ngf-mad",
"ngf-omo",
"Latn",
"Latn",
}
}
Line 334: Line 329:
"Aneme Wake",
"Aneme Wake",
3508107,
3508107,
"ngf",
"ngf-yar",
"Latn",
"Latn",
}
}
Line 341: Line 336:
"Abui",
"Abui",
2822110,
2822110,
"qfa-tap",
"paa-alp",
"Latn",
"Latn",
}
}
Line 371: Line 366:
"cmc",
"cmc",
"Latn, ms-Arab",
"Latn, ms-Arab",
standardChars = {
standard_chars = {
Latn = "AaBbCcDdEeÉéÈèËëFfGgHhIiJjKkLlMmNnOoÔôÖöPpQqRrSsTtUuVvWwXxYyZz", -- current orthography (not yet add Arab)
Latn = "AaBbCcDdEeÉéÈèËëFfGgHhIiJjKkLlMmNnOoÔôÖöPpQqRrSsTtUuVvWwXxYyZz", -- current orthography (not yet add Arab)
c.punc
c.punc
Line 409: Line 404:
56232,
56232,
"sem-arb",
"sem-arb",
"Arab",
"Arab, Hebr",
entry_name = "ar-entryname",
strip_diacritics = {
Arab = "ar-stripdiacritics",
},
-- Hebr display_text, strip_diacritics, sort_key in [[Module:scripts/data]]
}
}


Line 460: Line 458:
"sem-arb",
"sem-arb",
"Arab",
"Arab",
entry_name = "ar-entryname",
strip_diacritics = "ar-stripdiacritics",
}
}


Line 468: Line 466:
"sem-arb",
"sem-arb",
"Arab",
"Arab",
entry_name = "ar-entryname",
strip_diacritics = "ar-stripdiacritics",
}
}


Line 477: Line 475:
"Latn, Grek",
"Latn, Grek",
ancestors = "acm",
ancestors = "acm",
display_text = {
strip_diacritics = {
Grek = s["Grek-displaytext"]
},
entry_name = {
Latn = {remove_diacritics = c.grave .. c.acute .. c.breve},
Latn = {remove_diacritics = c.grave .. c.acute .. c.breve},
Grek = s["Grek-entryname"]
},
sort_key = {
Grek = s["Grek-sortkey"]
},
},
standardChars = {
-- Grek display_text, strip_diacritics, sort_key in [[Module:scripts/data]]
standard_chars = {
Latn = "AaBbCcDdΔδEeFfGgĠġĊċIiJjKkLlMmNnOoPpΘθRrSsTtUuVvWwXxYyZzŞş",
Latn = "AaBbCcDdΔδEeFfGgĠġĊċIiJjKkLlMmNnOoPpΘθRrSsTtUuVvWwXxYyZzŞş",
c.punc
c.punc
Line 507: Line 499:
}
}


m["adb"] = { -- rename or remove, see RFM
m["adb"] = {
"Adabe",
"Atauran",
36872,
125421255,
nil,
"poz-cet",
"Latn",
"Latn",
}
}
Line 533: Line 525:
"sem-arb",
"sem-arb",
"Arab",
"Arab",
entry_name = "ar-entryname",
strip_diacritics = "ar-stripdiacritics",
}
}


Line 539: Line 531:
"Andegerebinha",
"Andegerebinha",
3508123,
3508123,
"aus-pam",
"aus-rnd",
"Latn",
"Latn",
}
}
Line 574: Line 566:
"Adang",
"Adang",
3398276,
3398276,
"qfa-tap",
"paa-alp",
"Latn",
"Latn",
}
}
Line 581: Line 573:
"Abu",
"Abu",
56659,
56659,
"paa-ram",
"paa-por",
"Latn",
"Latn",
}
}
Line 591: Line 583:
"Tibt",
"Tibt",
ancestors = "dz",
ancestors = "dz",
translit = "Tibt-translit",
override_translit = true,
override_translit = true,
display_text = s["Tibt-displaytext"],
-- Tibt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]]
entry_name = s["Tibt-entryname"],
sort_key = "Tibt-sortkey",
}
}


Line 643: Line 632:


m["ady"] = {
m["ady"] = {
"Adyghe",
"West Circassian",
27776,
27776,
"cau-cir",
"cau-cir",
Line 655: Line 644:
Cyrl = s["cau-Cyrl-displaytext"]
Cyrl = s["cau-Cyrl-displaytext"]
},
},
entry_name = {
strip_diacritics = {
Cyrl = s["cau-Cyrl-entryname"],
Cyrl = s["cau-Cyrl-stripdiacritics"],
Latn = s["cau-Latn-entryname"],
Latn = s["cau-Latn-stripdiacritics"],
},
},
sort_key = {
sort_key = {
Line 694: Line 683:
"sem-arb",
"sem-arb",
"Arab",
"Arab",
entry_name = "ar-entryname",
strip_diacritics = "ar-stripdiacritics",
}
}


Line 748: Line 737:
"Eastern Arrernte",
"Eastern Arrernte",
10728232,
10728232,
"aus-pam",
"aus-rnd",
"Latn",
"Latn",
}
}
Line 769: Line 758:
"Ambakich",
"Ambakich",
56642,
56642,
"paa-ram",
"paa-eke",
"Latn",
"Latn",
}
}
Line 776: Line 765:
"Amele",
"Amele",
3508025,
3508025,
"ngf-mad",
"ngf-gum",
"Latn",
"Latn",
}
}
Line 783: Line 772:
"Aeka",
"Aeka",
16110528,
16110528,
"ngf",
"ngf-oro",
"Latn",
"Latn",
}
}
Line 792: Line 781:
"sem-arb",
"sem-arb",
"Arab",
"Arab",
entry_name = "ar-entryname",
strip_diacritics = "ar-stripdiacritics",
}
}


Line 826: Line 815:
"Akrukay",
"Akrukay",
57003,
57003,
"paa-ram",
"paa-tam",
"Latn",
"Latn",
}
}
Line 883: Line 872:
"Obokuitai",
"Obokuitai",
7075258,
7075258,
"paa-lkp",
"paa-clp",
"Latn",
"Latn",
}
}
Line 911: Line 900:
"Agarabi",
"Agarabi",
3399642,
3399642,
"paa-kag",
"ngf-gau",
"Latn",
"Latn",
}
}
Line 918: Line 907:
"Angal",
"Angal",
10951553,
10951553,
"paa-eng",
"ngf-ank",
"Latn",
"Latn",
}
}
Line 932: Line 921:
"Angor",
"Angor",
3508100,
3508100,
"paa",
"paa-sng",
"Latn",
"Latn",
}
}
Line 967: Line 956:
"Fembe",
"Fembe",
372927,
372927,
"ngf",
"ngf-est",
"Latn",
"Latn",
}
}
Line 974: Line 963:
"Angaataha",
"Angaataha",
3508001,
3508001,
"ngf",
"ngf-ang",
"Latn",
"Latn",
}
}
Line 988: Line 977:
"Tainae",
"Tainae",
7676186,
7676186,
"ngf",
"ngf-taa",
"Latn",
"Latn",
}
}
Line 1,049: Line 1,038:
override_translit = true,
override_translit = true,
display_text = s["cau-Cyrl-displaytext"],
display_text = s["cau-Cyrl-displaytext"],
entry_name = s["cau-Cyrl-entryname"],
strip_diacritics = s["cau-Cyrl-stripdiacritics"],
sort_key = {
sort_key = {
from = {"аь", "гъ", "гь", "гӏ", "дж", "ё", "къ", "кь", "кӏ", "оь", "пӏ", "тӏ", "уь", "хъ", "хь", "хӏ", "цӏ", "чӏ"},
from = {"аь", "гъ", "гь", "гӏ", "дж", "ё", "къ", "кь", "кӏ", "оь", "пӏ", "тӏ", "уь", "хъ", "хь", "хӏ", "цӏ", "чӏ"},
Line 1,094: Line 1,083:
"Aghu",
"Aghu",
3436645,
3436645,
"ngf",
"ngf-awy",
"Latn",
"Latn",
}
}


m["ahi"] = {
m["ahi"] = {
"Tiagbamrin Aizi",
"Tiagba",
3400073,
3400073,
"kro-aiz",
"kro-aiz",
Line 1,126: Line 1,115:


m["ahm"] = {
m["ahm"] = {
"Mobumrin Aizi",
"Mobu",
35967,
35967,
"kro-aiz",
"kro-aiz",
Line 1,148: Line 1,137:


m["ahp"] = {
m["ahp"] = {
"Aproumu Aizi",
"Apro",
34810,
34810,
"alv-kwa",
"alv-kwa",
Line 1,194: Line 1,183:
"Ainbai",
"Ainbai",
3332149,
3332149,
"paa-brd",
"paa-bew",
"Latn",
"Latn",
}
}
Line 1,215: Line 1,204:
"Agi",
"Agi",
3331491,
3331491,
"qfa-tor",
"paa-wpa",
"Latn",
"Latn",
}
}
Line 1,243: Line 1,232:
"Syrc",
"Syrc",
translit = "aii-translit",
translit = "aii-translit",
entry_name = "Syrc-entryname",
strip_diacritics = "Syrc-stripdiacritics",
}
}


Line 1,251: Line 1,240:
"sem-nna",
"sem-nna",
"Hebr",
"Hebr",
-- Hebr display_text, strip_diacritics, sort_key in [[Module:scripts/data]]
}
}


Line 1,263: Line 1,253:
"Aimele",
"Aimele",
3327418,
3327418,
"ngf",
"ngf-bos",
"Latn",
"Latn",
}
}
Line 1,290: Line 1,280:
"Mymr",
"Mymr",
translit = "aio-phk-translit",
translit = "aio-phk-translit",
entry_name = {remove_diacritics = c.VS01},
display_text = s["aio-displaytext"],
strip_diacritics = s["aio-stripdiacritics"],
}
}


Line 1,296: Line 1,287:
"Burumakok",
"Burumakok",
5000984,
5000984,
"ngf-okk",
"ngf-wok",
"Latn",
"Latn",
}
}
Line 1,303: Line 1,294:
"Airoran",
"Airoran",
3321131,
3321131,
"paa-tkw",
"paa-saa",
"Latn",
"Latn",
}
}
Line 1,336: Line 1,327:


m["aja"] = {
m["aja"] = {
"Aja",
"Aja (East Africa)",
3237491,
3237491,
"csu-bkr",
"csu-bkr",
Line 1,343: Line 1,334:


m["ajg"] = {
m["ajg"] = {
"Adja",
"Aja (West Africa)",
35035,
35035,
"alv-gbe",
"alv-gbe",
Line 1,368: Line 1,359:
"sem-arb",
"sem-arb",
"Arab",
"Arab",
entry_name = "ar-entryname",
strip_diacritics = "ar-stripdiacritics",
}
}


Line 1,396: Line 1,387:
"Mpur",
"Mpur",
3327139,
3327139,
"paa-wpa",
"qfa-iso", -- Papuan; based on Palmer (2018), Ethnologue and Glottolog
"Latn",
"Latn",
}
}
Line 1,431: Line 1,422:
"Angal Heneng",
"Angal Heneng",
10950354,
10950354,
"paa-eng",
"ngf-ank",
"Latn",
"Latn",
}
}
Line 1,438: Line 1,429:
"Aiome",
"Aiome",
56735,
56735,
"paa",
"paa-aia",
"Latn",
"Latn",
}
}
Line 1,487: Line 1,478:
"Ak",
"Ak",
56654,
56654,
"paa",
"paa-sep",
"Latn",
"Latn",
}
}
Line 1,527: Line 1,518:
override_translit = true,
override_translit = true,
display_text = s["cau-Cyrl-displaytext"],
display_text = s["cau-Cyrl-displaytext"],
entry_name = s["cau-Cyrl-entryname"],
strip_diacritics = s["cau-Cyrl-stripdiacritics"],
}
}


Line 1,583: Line 1,574:
27210,
27210,
"esx",
"esx",
"Latn",
"Latn, Cyrl",
}
}


Line 1,626: Line 1,617:
"dra-mal",
"dra-mal",
"Mlym",
"Mlym",
-- Mlym translit in [[Module:scripts/data]] (NOTE: not present before, presumably an accidental omission)
}
}


-- "aln" IS TREATED AS "sq", SEE WT:LT
-- "aln" is treated as "sq", see [[WT:LT]]


m["alm"] = {
m["alm"] = {
Line 1,664: Line 1,656:
"qfa-ckn",
"qfa-ckn",
"Cyrl",
"Cyrl",
entry_name = {
strip_diacritics = {
from = {"['’]"},
from = {"['’]"},
to = {"ʼ"}
to = {"ʼ"}
Line 1,703: Line 1,695:
"Amol",
"Amol",
3504260,
3504260,
"qfa-tor",
"paa-pal",
"Latn",
"Latn",
}
}
Line 1,710: Line 1,702:
"Alyawarr",
"Alyawarr",
3327389,
3327389,
"aus-pam",
"aus-rnd",
"Latn",
"Latn",
}
}
Line 1,753: Line 1,745:
35764,
35764,
"omv-aro",
"omv-aro",
"Latn",
"Latn, Ethi",
sort_key = "amf-utilities"
sort_key = "amf-utilities"
}
}
Line 1,795: Line 1,787:
"Ama",
"Ama",
3446626,
3446626,
"qfa-mal",
"paa-lma",
"Latn",
"Latn",
}
}
Line 1,802: Line 1,794:
"Amanab",
"Amanab",
3327399,
3327399,
"paa-brd",
"paa-war",
"Latn",
"Latn",
}
}
Line 1,816: Line 1,808:
"Alamblak",
"Alamblak",
56688,
56688,
"paa",
"paa-sep",
"Latn",
"Latn",
}
}
Line 1,841: Line 1,833:
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 1,848: Line 1,840:
"Amto",
"Amto",
56517,
56517,
"paa-asa",
"paa-amu",
"Latn",
"Latn",
}
}
Line 1,871: Line 1,863:
"sem-arw",
"sem-arw",
"Armi, Syrc, Latn",
"Armi, Syrc, Latn",
entry_name = {
strip_diacritics = {
Syrc = "Syrc-entryname"
Syrc = "Syrc-stripdiacritics"
},
},
}
}
Line 1,879: Line 1,871:
"Anmatyerre",
"Anmatyerre",
10412317,
10412317,
"aus-pam",
"aus-rnd",
"Latn",
"Latn",
}
}
Line 1,947: Line 1,939:
Runr = "Runr-translit"
Runr = "Runr-translit"
},
},
entry_name = {
strip_diacritics = {
Latn = {
Latn = {
remove_diacritics = c.acute .. c.macron .. c.dotabove,
remove_diacritics = c.acute .. c.circ .. c.macron .. c.breve .. c.dotabove .. c.diaer .. c.dotbelow,
from = {"Ƿ", "ƿ"},
from = {"[Ƿƿ]"},
to = {"W", "w"}
to = {{
["Ƿ"] = "W", ["ƿ"] = "w",
}},
},
},
},
},
sort_key = {
sort_key = {
Latn = {
Latn = {
remove_diacritics = c.acute .. c.macron .. c.dotabove,
remove_diacritics = c.acute .. c.circ .. c.macron .. c.breve .. c.dotabove .. c.diaer .. c.dotbelow,
from = {"æ", "ð", "þ", "ƿ"},
from = {"[æƀꝺðꝼᵹȝłœꞃꞅꞇþꝥꝧƿ]"},
to = {"ae", "t" .. p[1], "t" .. p[2], "w" .. p[1]}
to = {{
["æ"] = "ae", ["ƀ"] = "b", ["ꝺ"] = "d", ["ð"] = "d" .. p[1], ["ꝼ"] = "f",
["ᵹ"] = "g", ["ȝ"] = "g" .. p[1], ["ł"] = "l", ["œ"] = "oe", ["ꞃ"] = "r",
["ꞅ"] = "s", ["ꞇ"] = "t", ["þ"] = "t" .. p[1], ["ꝥ"] = "t" .. p[1],
["ꝧ"] = "t" .. p[1], ["ƿ"] = "w",
}},
},
},
},
},
standardChars = {
standard_chars = {
Latn = "AaÆæBbCcDdEeFfGgHhIiLlMmNnOoŒœPpRrSsTtUuWwXxYyÐðÞþ",
Latn = "AaÆæBbCcDdÐðEeFfGgHhIiLlMmNnOoŒœPpRrSsTtÞþUuWwXxYy",
c.punc,
c.punc,
},
},
Line 1,970: Line 1,969:
"Nend",
"Nend",
6991554,
6991554,
"ngf-mad",
"ngf-wso",
"Latn",
"Latn",
}
}
Line 1,982: Line 1,981:
override_translit = true,
override_translit = true,
display_text = s["cau-Cyrl-displaytext"],
display_text = s["cau-Cyrl-displaytext"],
entry_name = s["cau-Cyrl-entryname"],
strip_diacritics = s["cau-Cyrl-stripdiacritics"],
}
}


Line 1,988: Line 1,987:
"Anor",
"Anor",
56458,
56458,
"paa",
"paa-aia",
"Latn",
"Latn",
}
}
Line 2,104: Line 2,103:
"Anem",
"Anem",
56512,
56512,
"paa",
"qfa-dis", -- Papuan; might be an isolate or in a putative West New Britain family
"Latn",
"Latn",
}
}
Line 2,119: Line 2,118:
"Abom",
"Abom",
3446647,
3446647,
"ngf",
"qfa-dis", -- Papuan; possibly a divergent Tirio language (Anim family), or a top-level TNG node
"Latn",
"Latn",
}
}
Line 2,133: Line 2,132:
"Andarum",
"Andarum",
3507888,
3507888,
"paa",
"paa-ata",
"Latn",
"Latn",
}
}
Line 2,140: Line 2,139:
"Angal Enen",
"Angal Enen",
10951638,
10951638,
"paa-eng",
"ngf-ank",
"Latn",
"Latn",
}
}
Line 2,147: Line 2,146:
"Bragat",
"Bragat",
3507977,
3507977,
"qfa-tor",
"paa-pal",
"Latn",
"Latn",
}
}
Line 2,154: Line 2,153:
"Angoram",
"Angoram",
56366, -- cf 6754745 for merged dialect
56366, -- cf 6754745 for merged dialect
"paa-lsp",
"paa-lse",
"Latn",
"Latn",
}
}
Line 2,168: Line 2,167:
"Mufian",
"Mufian",
3507881,
3507881,
"qfa-tor",
"paa-ara",
"Latn",
"Latn",
}
}
Line 2,180: Line 2,179:


m["aol"] = {
m["aol"] = {
"Alor",
"Alorese",
3332062,
3332062,
"poz",
"poz",
Line 2,189: Line 2,188:
"Ömie",
"Ömie",
8078975,
8078975,
"ngf",
"ngf-koi",
"Latn",
"Latn",
}
}
Line 2,196: Line 2,195:
"Bumbita Arapesh",
"Bumbita Arapesh",
3508044,
3508044,
"qfa-tor",
"paa-ara",
"Latn",
"Latn",
}
}
Line 2,210: Line 2,209:
"Taikat",
"Taikat",
7676018,
7676018,
"paa-brd",
"paa-taa",
"Latn",
"Latn",
}
}
Line 2,254: Line 2,253:
"sem-arb",
"sem-arb",
"Arab",
"Arab",
entry_name = "ar-entryname",
strip_diacritics = "ar-stripdiacritics",
}
}


Line 2,262: Line 2,261:
"sem-arb",
"sem-arb",
"Arab",
"Arab",
entry_name = "ar-entryname",
strip_diacritics = "ar-stripdiacritics",
}
}


Line 2,268: Line 2,267:
"Bukiyip",
"Bukiyip",
3507895,
3507895,
"qfa-tor",
"paa-ara",
"Latn",
"Latn",
}
}
Line 2,415: Line 2,414:
"Safeyoka",
"Safeyoka",
7398693,
7398693,
"ngf",
"ngf-woj",
"Latn",
"Latn",
}
}
Line 2,427: Line 2,426:
override_translit = true,
override_translit = true,
display_text = s["cau-Cyrl-displaytext"],
display_text = s["cau-Cyrl-displaytext"],
entry_name = s["cau-Cyrl-entryname"],
strip_diacritics = s["cau-Cyrl-stripdiacritics"],
sort_key = {
sort_key = {
from = {
from = {
Line 2,461: Line 2,460:
"Atohwaim",
"Atohwaim",
11732297,
11732297,
"ngf",
"paa-kay",
"Latn",
"Latn",
}
}
Line 2,509: Line 2,508:
Palm = "Palm-translit",
Palm = "Palm-translit",
},
},
entry_name = {
strip_diacritics = {
Hebr = {remove_diacritics = u(0x0591) .. "-" .. u(0x05BD) .. u(0x05BF) .. "-" .. u(0x05C5) .. u(0x05C7)},
-- The first three were added by [[User:Wikitiki89]] in 2015 for use with Syriac, which has diacritics that look
Syrc = {remove_diacritics = u(0x0730) .. "-" .. u(0x0748)},
-- like a diaeresis (syāmē) and macrons above and below (mṭalqānā); see Wikipedia [[w:Syriac alphabet]]. But
remove_diacritics = c.macron .. c.diaer .. c.macronbelow}, -- Which script(s)?
-- I don't know if they are actually represented using these diacritics.
Syrc = {remove_diacritics = c.macron .. c.diaer .. c.macronbelow .. u(0x0730) .. "-" .. u(0x0748)},
},
-- Hebr display_text, strip_diacritics, sort_key in [[Module:scripts/data]]
-- Samr strip_diacritics, sort_key in [[Module:scripts/data]]; previously no sort_key for Samr, presumably a mistake
-- Phnx translit in [[Module:scripts/data]] (NOTE: not present before, presumably an accidental omission)
}
}


Line 2,525: Line 2,529:
"Western Arrernte",
"Western Arrernte",
12645549,
12645549,
"aus-pam",
"aus-rnd",
"Latn",
"Latn",
}
}
Line 2,541: Line 2,545:
"cdd",
"cdd",
"Latn",
"Latn",
entry_name = {remove_diacritics = c.acute},
strip_diacritics = {remove_diacritics = c.acute},
}
}


Line 2,591: Line 2,595:
"sem-arb",
"sem-arb",
"Arab",
"Arab",
entry_name = "ar-entryname",
strip_diacritics = "ar-stripdiacritics",
}
}


Line 2,606: Line 2,610:
"sem-arb",
"sem-arb",
"Arab",
"Arab",
entry_name = "ar-entryname",
strip_diacritics = "ar-stripdiacritics",
}
}


Line 2,642: Line 2,646:
"sem-arb",
"sem-arb",
"Arab",
"Arab",
entry_name = "ar-entryname",
strip_diacritics = "ar-stripdiacritics",
sort_key = {
from = {"^%f[" .. u(0x5D0) .. "-" .. u(0x5EA) .. "]"},
to = {u(0xFB21)},
},
}
}


Line 2,654: Line 2,654:
"sem-arb",
"sem-arb",
"Arab",
"Arab",
entry_name = "ar-entryname",
strip_diacritics = "ar-stripdiacritics",
}
}


Line 2,674: Line 2,674:
"Casuarina Coast Asmat",
"Casuarina Coast Asmat",
11732046,
11732046,
"ngf",
"ngf-asm",
"Latn",
"Latn",
}
}
Line 2,702: Line 2,702:
"Abishira",
"Abishira",
2871740,
2871740,
"qfa-iso",
"qfa-dis", -- extinct, poorly documented; isolate or in a proposed Tequiraca-Canichana family by Kaufman (1994)
"Latn",
"Latn",
}
}
Line 2,709: Line 2,709:
"Buruwai",
"Buruwai",
5001031,
5001031,
"ngf",
"ngf-sab",
"Latn",
"Latn",
}
}
Line 2,744: Line 2,744:
"Dano",
"Dano",
5220979,
5220979,
"paa-kag",
"ngf-gah",
"Latn",
"Latn",
}
}
Line 2,778: Line 2,778:
"Asturian",
"Asturian",
29507,
29507,
"roa-ibe",
"roa-asl",
"Latn",
"Latn",
ancestors = "roa-ole",
}
}


Line 2,807: Line 2,806:
"Muratayak",
"Muratayak",
11732766,
11732766,
"ngf-fin",
"ngf-war",
"Latn",
"Latn",
}
}
Line 2,814: Line 2,813:
"Yaosakor Asmat",
"Yaosakor Asmat",
16113158,
16113158,
"ngf",
"ngf-asm",
"Latn",
"Latn",
}
}
Line 2,828: Line 2,827:
"Pele-Ata",
"Pele-Ata",
56511,
56511,
"paa",
"qfa-dis", -- Papuan; possibly in a putative West New Britain family, or an isolate
"Latn",
"Latn",
}
}
Line 2,837: Line 2,836:
"tbq-brm",
"tbq-brm",
"Latn, Lisu", -- also Hani?
"Latn, Lisu", -- also Hani?
translit = {
-- Lisu translit, sort_key in [[Module:scripts/data]]
Lisu = "Lisu-translit"
},
sort_key = {
Lisu = s["Lisu-sortkey"]
},
}
}


Line 2,862: Line 2,856:
"Atemble",
"Atemble",
4813055,
4813055,
"ngf-mad",
"ngf-wso",
"Latn",
"Latn",
}
}
Line 3,053: Line 3,047:
"Heyo",
"Heyo",
3504295,
3504295,
"qfa-tor",
"paa-hya",
"Latn",
"Latn",
}
}
Line 3,074: Line 3,068:
"Molmo One",
"Molmo One",
12637224,
12637224,
"qfa-tor",
"paa-trr",
"Latn",
"Latn",
}
}
Line 3,088: Line 3,082:
"Makayam",
"Makayam",
6738863,
6738863,
"ngf",
"paa-tir",
"Latn",
"Latn",
}
}
Line 3,102: Line 3,096:
"Aruek",
"Aruek",
3504279,
3504279,
"qfa-tor",
"paa-kom",
"Latn",
"Latn",
}
}
Line 3,116: Line 3,110:
"Auye",
"Auye",
4827334,
4827334,
"ngf",
"ngf-pan",
"Latn",
"Latn",
}
}
Line 3,123: Line 3,117:
"Awyi",
"Awyi",
3513326,
3513326,
"paa-brd",
"paa-taa",
"Latn",
"Latn",
}
}
Line 3,137: Line 3,131:
"Auyana",
"Auyana",
2873211,
2873211,
"paa-kag",
"ngf-gau",
"Latn",
"Latn",
}
}
Line 3,146: Line 3,140:
"sem-arb",
"sem-arb",
"Arab",
"Arab",
entry_name = "ar-entryname",
strip_diacritics = "ar-stripdiacritics",
}
}


Line 3,210: Line 3,204:
"Au",
"Au",
3446608,
3446608,
"qfa-tor",
"paa-wap",
"Latn",
"Latn",
}
}
Line 3,242: Line 3,236:
"Awa (New Guinea)",
"Awa (New Guinea)",
2874650,
2874650,
"paa-kag",
"ngf-gau",
"Latn",
"Latn",
}
}
Line 3,270: Line 3,264:
"Awbono",
"Awbono",
3446684,
3446684,
"ngf",
"paa-baa",
"Latn",
"Latn",
}
}
Line 3,277: Line 3,271:
"Aekyom",
"Aekyom",
3399691,
3399691,
"ngf",
"paa-kae",
"Latn",
"Latn",
}
}
Line 3,291: Line 3,285:
"Arawum",
"Arawum",
4784537,
4784537,
"ngf-mad",
"ngf-rai",
"Latn",
"Latn",
}
}
Line 3,312: Line 3,306:
"Awera",
"Awera",
56379,
56379,
"paa-lkp",
"paa-flp",
"Latn",
"Latn",
}
}
Line 3,319: Line 3,313:
"South Awyu",
"South Awyu",
12633986,
12633986,
"ngf",
"ngf-awy",
"Latn",
"Latn",
}
}
Line 3,333: Line 3,327:
"Central Awyu",
"Central Awyu",
12628801,
12628801,
"ngf",
"ngf-awy",
"Latn",
"Latn",
}
}
Line 3,340: Line 3,334:
"Jair Awyu",
"Jair Awyu",
16110177,
16110177,
"ngf",
"ngf-awy",
"Latn",
"Latn",
}
}
Line 3,347: Line 3,341:
"Awun",
"Awun",
56369,
56369,
"paa-spk",
"paa-sep",
"Latn",
"Latn",
}
}
Line 3,354: Line 3,348:
"Awara",
"Awara",
2874670,
2874670,
"ngf-fin",
"ngf-waa",
"Latn",
"Latn",
}
}
Line 3,361: Line 3,355:
"Edera Awyu",
"Edera Awyu",
12630425,
12630425,
"ngf",
"ngf-awy",
"Latn",
"Latn",
}
}
Line 3,380: Line 3,374:


m["axg"] = {
m["axg"] = {
"Mato Grosso Arára",
"Arára (Mato Grosso)",
3446660,
3446660,
nil,
nil,
Line 3,396: Line 3,390:
"Lower Southern Aranda",
"Lower Southern Aranda",
6693295,
6693295,
"aus-pam",
"aus-rnd",
"Latn",
"Latn",
}
}
Line 3,406: Line 3,400:
"Armn",
"Armn",
ancestors = "xcl",
ancestors = "xcl",
translit = "Armn-translit",
-- Armn translit in [[Module:scripts/data]]
override_translit = true,
override_translit = true,
entry_name = {
strip_diacritics = {
remove_diacritics = "՞՜՛՟",
remove_diacritics = "՞՜՛՟",
from = {"եւ", "ՙ", "՚"},
from = {"եւ", "ՙ", "՚"},
Line 3,425: Line 3,419:
"Awar",
"Awar",
56876,
56876,
"paa",
"paa-baw",
"Latn",
"Latn",
}
}
Line 3,476: Line 3,470:
"sem-arb",
"sem-arb",
"Arab",
"Arab",
entry_name = "ar-entryname",
strip_diacritics = "ar-stripdiacritics",
}
}


Line 3,483: Line 3,477:
1686766,
1686766,
"sem-arb",
"sem-arb",
"Arab",
"Arab, Hebr",
entry_name = "ar-entryname",
strip_diacritics = {
Arab = "ar-stripdiacritics",
},
-- Hebr display_text, strip_diacritics, sort_key in [[Module:scripts/data]]
}
}


Line 3,500: Line 3,497:
"Arab",
"Arab",
ancestors = "acm",
ancestors = "acm",
entry_name = "ar-entryname",
strip_diacritics = "ar-stripdiacritics",
}
}


Line 3,506: Line 3,503:
"Ayi",
"Ayi",
56449,
56449,
"paa-spk",
"paa-sep",
"Latn",
"Latn",
}
}
Line 3,531: Line 3,528:
}
}


m["ayy"] = {
-- ayy deleted and removed from ISO; per the removal request, "no linguistic data exists for any [Ayta] language that the
"Tayabas Ayta",
-- ancestors of this group might have once spoken. And thus, there is no evidence that this group ever had a language
7689745,
-- distinct from any other Philippine language." [Lobel]
"phi",
"Latn",
}


m["ayz"] = {
m["ayz"] = {
"Maybrat",
"Maybrat",
4830892,
4830892,
"paa-wpa",
"paa-may",
-- either an isolate; grouped with Abun and the West Bird's Head family; or in the putative West Papuan family
"Latn",
"Latn",
}
}
Retrieved from "https://linguifex.com/wiki/Module:languages/data/3/a"