Linguifex

Module:scripts/data: Difference between revisions

← Older edit
Vrianne (talk | contribs)
2,581 edits
No edit summary
No edit summary
 
(17 intermediate revisions by 3 users not shown)
Line 1: Line 1:
--[=[
--[=[
    This is imported from Wiktionary - it'll be updated for this wiki - the data is left currently as examples.
When adding new scripts to this file, please don't forget to add
When adding new scripts to this file, please don't forget to add
style definitons for the script in [[MediaWiki:Common.css]].
style definitons for the script in [[MediaWiki:Gadget-LanguagesAndScripts.css]].
]=]
]=]
local concat = table.concat
local concat = table.concat
local insert = table.insert
local insert = table.insert
Line 13: Line 10:
local select = select
local select = select
local sort = table.sort
local sort = table.sort
local u = require("Module:string utilities").char
 
-- Loaded on demand, as it may not be needed (depending on the data).
local function u(...)
u = require("Module:string/char")
return u(...)
end
 
-- We can't use mw.loadData() on [[Module:languages/chars]] because [[Module:languages/data]] itself is sometimes loaded
-- using mw.loadData(), and calling mw.loadData() on [[Module:languages/chars]] will insert metatables into the
-- character tables, which the second mw.loadData() will choke on.
local m_chars = require("Module:languages/chars")
 
local c = m_chars.chars
local p = m_chars.puaChars
local cs = m_chars.chars_substitutions


------------------------------------------------------------------------------------
------------------------------------------------------------------------------------
Line 92: Line 103:
local m = {}
local m = {}


--Constructed languages
m["Adlm"] = process_ranges{
m["Ayer"] = {
"Adlam",
"Tahano Hikamu",
19606346,
"abugida",
"alphabet",
ranges = {
ranges = {
0x0041, 0x005A,
0x061F, 0x061F,
0x0061, 0x007A,
0x0640, 0x0640,
0x002A, 0x002A,
0x1E900, 0x1E94B,
0x00F1, 0x00F1,
0x1E950, 0x1E959,
0x00D1, 0x00D1,
0x1E95E, 0x1E95F,
0x0294, 0x0294,
0x0259, 0x0259,
0x018F, 0x018F,
0xA736, 0xA737,
0x0026, 0x0026,
0x002B, 0x002D,
0x005B, 0x005B,
0x005D, 0x005D,
0x00A8, 0x00A8,
0x00AF, 0x00AF,
0x00B2, 0x00B2,
0x00B9, 0x00B9,
0x02B0, 0x2B2,
0x02C0, 0x02C0,
0x02D0, 0x02D0,
},
},
character_category = false,
capitalized = true,
direction = "rtl",
}
}


m["Roka"] = {
m["Afak"] = {
"Rokadong Curakjang",
"Afaka",
"abugida",
382019,
ranges = {
"syllabary",
0x0041, 0x005A,
-- Not in Unicode
0x0061, 0x007A,
0x0022, 0x0022,
0x0027, 0x0027,
0x002A, 0x002A,
0x002D, 0x002D,
0x005B, 0x005D,
0x007B, 0x007B,
0x007D, 0x007D
},
character_category = false,
}
}


m["Rsnold"] = {
m["Aghb"] = process_ranges{
"Old Raysian",
"Caucasian Albanian",
2495716,
"alphabet",
"alphabet",
ranges = {
ranges = {
0x0041, 0x007A
0x10530, 0x10563,
0x1056F, 0x1056F,
},
},
character_category = false,
}
}


--Natural languages
m["Ahom"] = process_ranges{
 
"Ahom",
m["Adlm"] = process_ranges{
2839633,
"Adlam",
"abugida",
"alphabet",
ranges = {
ranges = {
0x061F, 0x061F,
0x11700, 0x1171A,
0x0640, 0x0640,
0x1171D, 0x1172B,
0x1E900, 0x1E94B,
0x1E950, 0x1E959,
0x1E95E, 0x1E95F,
},
capitalized = true,
direction = "rtl",
}
 
m["Afak"] = {
"Afaka",
"syllabary",
-- Not in Unicode
}
 
m["Aghb"] = process_ranges{
"Caucasian Albanian",
"alphabet",
ranges = {
0x10530, 0x10563,
0x1056F, 0x1056F,
},
}
 
m["Ahom"] = process_ranges{
"Ahom",
"abugida",
ranges = {
0x11700, 0x1171A,
0x1171D, 0x1172B,
0x11730, 0x11746,
0x11730, 0x11746,
},
},
Line 190: Line 148:
m["Arab"] = process_ranges{
m["Arab"] = process_ranges{
"Arabic",
"Arabic",
"abjad", -- more precisely, impure abjad
1828555,
"abjad", -- more precisely, impure abjad
varieties = {"Jawi", {"Nastaliq", "Nastaleeq"}},
varieties = {"Jawi", {"Nastaliq", "Nastaleeq"}},
ranges = {
ranges = {
Line 197: Line 156:
0x0870, 0x088E,
0x0870, 0x088E,
0x0890, 0x0891,
0x0890, 0x0891,
0x0898, 0x08E1,
0x0897, 0x08E1,
0x08E3, 0x08FF,
0x08E3, 0x08FF,
0xFB50, 0xFBC2,
0xFB50, 0xFBC2,
Line 208: Line 167:
0x102E0, 0x102FB,
0x102E0, 0x102FB,
0x10E60, 0x10E7E,
0x10E60, 0x10E7E,
0x10EFD, 0x10EFF,
0x10EC2, 0x10EC4,
0x10EFC, 0x10EFF,
0x1EE00, 0x1EE03,
0x1EE00, 0x1EE03,
0x1EE05, 0x1EE1F,
0x1EE05, 0x1EE1F,
Line 253: Line 213:
m["fa-Arab"] = {
m["fa-Arab"] = {
"Arabic",
"Arabic",
m["Arab"][2],
744068,
m["Arab"][3],
ranges = m["Arab"].ranges,
ranges = m["Arab"].ranges,
characters = m["Arab"].characters,
characters = m["Arab"].characters,
otherNames = {"Perso-Arabic"},
other_names = {"Perso-Arabic"},
direction = "rtl",
direction = "rtl",
parent = "Arab",
parent = "Arab",
Line 264: Line 225:
m["kk-Arab"] = {
m["kk-Arab"] = {
"Arabic",
"Arabic",
m["Arab"][2],
90681452,
m["Arab"][3],
ranges = m["Arab"].ranges,
ranges = m["Arab"].ranges,
characters = m["Arab"].characters,
characters = m["Arab"].characters,
Line 280: Line 242:
m["pa-Arab"] = {
m["pa-Arab"] = {
"Shahmukhi",
"Shahmukhi",
m["Arab"][2],
133800,
m["Arab"][3],
ranges = m["Arab"].ranges,
ranges = m["Arab"].ranges,
characters = m["Arab"].characters,
characters = m["Arab"].characters,
otherNames = {"Arabic"},
other_names = {"Arabic"},
direction = "rtl",
direction = "rtl",
parent = "Arab",
parent = "Arab",
Line 299: Line 262:
m["Armi"] = process_ranges{
m["Armi"] = process_ranges{
"Imperial Aramaic",
"Imperial Aramaic",
26978,
"abjad",
"abjad",
ranges = {
ranges = {
Line 309: Line 273:
m["Armn"] = process_ranges{
m["Armn"] = process_ranges{
"Armenian",
"Armenian",
11932,
"alphabet",
"alphabet",
ranges = {
ranges = {
Line 317: Line 282:
},
},
capitalized = true,
capitalized = true,
translit = "Armn-translit",
}
}


m["Avst"] = process_ranges{
m["Avst"] = process_ranges{
"Avestan",
"Avestan",
790681,
"alphabet",
"alphabet",
ranges = {
ranges = {
Line 331: Line 298:
m["pal-Avst"] = {
m["pal-Avst"] = {
"Pazend",
"Pazend",
m["Avst"][2],
4925073,
m["Avst"][3],
ranges = m["Avst"].ranges,
ranges = m["Avst"].ranges,
characters = m["Avst"].characters,
characters = m["Avst"].characters,
Line 340: Line 308:
m["Bali"] = process_ranges{
m["Bali"] = process_ranges{
"Balinese",
"Balinese",
804984,
"abugida",
"abugida",
ranges = {
ranges = {
0x1B00, 0x1B4C,
0x1B00, 0x1B4C,
0x1B50, 0x1B7E,
0x1B4E, 0x1B7F,
},
},
}
}
Line 349: Line 318:
m["Bamu"] = process_ranges{
m["Bamu"] = process_ranges{
"Bamum",
"Bamum",
806024,
"syllabary",
"syllabary",
ranges = {
ranges = {
Line 358: Line 328:
m["Bass"] = process_ranges{
m["Bass"] = process_ranges{
"Bassa",
"Bassa",
810458,
"alphabet",
"alphabet",
aliases = {"Bassa Vah", "Vah"},
aliases = {"Bassa Vah", "Vah"},
Line 368: Line 339:
m["Batk"] = process_ranges{
m["Batk"] = process_ranges{
"Batak",
"Batak",
51592,
"abugida",
"abugida",
ranges = {
ranges = {
Line 377: Line 349:
m["Beng"] = process_ranges{
m["Beng"] = process_ranges{
"Bengali",
"Bengali",
756802,
"abugida",
"abugida",
ranges = {
ranges = {
Line 415: Line 388:
m["as-Beng"] = process_ranges{
m["as-Beng"] = process_ranges{
"Assamese",
"Assamese",
m["Beng"][2],
191272,
otherNames = {"Bengali-Assamese", "Eastern Nagari"},
m["Beng"][3],
other_names = {"Eastern Nagari"},
ranges = {
ranges = {
0x0951, 0x0952,
0x0951, 0x0952,
Line 450: Line 424:
m["Bhks"] = process_ranges{
m["Bhks"] = process_ranges{
"Bhaiksuki",
"Bhaiksuki",
17017839,
"abugida",
"abugida",
ranges = {
ranges = {
Line 460: Line 435:


m["Blis"] = {
m["Blis"] = {
"Blissymbols",
"Blissymbolic",
609817,
"logography",
"logography",
aliases = {"Blissymbolics"},
aliases = {"Blissymbols"},
-- Not in Unicode
-- Not in Unicode
}
}
Line 468: Line 444:
m["Bopo"] = process_ranges{
m["Bopo"] = process_ranges{
"Zhuyin",
"Zhuyin",
198269,
"semisyllabary",
"semisyllabary",
aliases = {"Zhuyin Fuhao", "Bopomofo"},
aliases = {"Zhuyin Fuhao", "Bopomofo"},
Line 488: Line 465:
m["Brah"] = process_ranges{
m["Brah"] = process_ranges{
"Brahmi",
"Brahmi",
185083,
"abugida",
"abugida",
ranges = {
ranges = {
Line 498: Line 476:
to = {"𑀆", "𑀌", "𑀐"}
to = {"𑀆", "𑀌", "𑀐"}
},
},
translit = "Brah-translit",
}
}


m["Brai"] = process_ranges{
m["Brai"] = process_ranges{
"Braille",
"Braille",
79894,
"alphabet",
"alphabet",
ranges = {
ranges = {
Line 510: Line 490:
m["Bugi"] = process_ranges{
m["Bugi"] = process_ranges{
"Lontara",
"Lontara",
1074947,
"abugida",
"abugida",
aliases = {"Buginese"},
aliases = {"Buginese"},
Line 521: Line 502:
m["Buhd"] = process_ranges{
m["Buhd"] = process_ranges{
"Buhid",
"Buhid",
1002969,
"abugida",
"abugida",
ranges = {
ranges = {
Line 531: Line 513:
m["Cakm"] = process_ranges{
m["Cakm"] = process_ranges{
"Chakma",
"Chakma",
1059328,
"abugida",
"abugida",
ranges = {
ranges = {
Line 541: Line 524:


m["Cans"] = process_ranges{
m["Cans"] = process_ranges{
"Canadian syllabics",
"Canadian syllabic",
2479183,
"abugida",
"abugida",
ranges = {
ranges = {
Line 552: Line 536:
m["Cari"] = process_ranges{
m["Cari"] = process_ranges{
"Carian",
"Carian",
1094567,
"alphabet",
"alphabet",
ranges = {
ranges = {
Line 560: Line 545:
m["Cham"] = process_ranges{
m["Cham"] = process_ranges{
"Cham",
"Cham",
1060381,
"abugida",
"abugida",
ranges = {
ranges = {
Line 571: Line 557:
m["Cher"] = process_ranges{
m["Cher"] = process_ranges{
"Cherokee",
"Cherokee",
26549,
"syllabary",
"syllabary",
ranges = {
ranges = {
Line 581: Line 568:
m["Chis"] = {
m["Chis"] = {
"Chisoi",
"Chisoi",
123173777,
"abugida",
"abugida",
-- Not in Unicode
-- Not in Unicode
Line 586: Line 574:


m["Chrs"] = process_ranges{
m["Chrs"] = process_ranges{
"Chorasmian",
"Khwarezmian",
72386710,
"abjad",
"abjad",
aliases = {"Chorasmian"},
ranges = {
ranges = {
0x10FB0, 0x10FCB,
0x10FB0, 0x10FCB,
Line 596: Line 586:
m["Copt"] = process_ranges{
m["Copt"] = process_ranges{
"Coptic",
"Coptic",
321083,
"alphabet",
"alphabet",
ranges = {
ranges = {
Line 608: Line 599:
m["Cpmn"] = process_ranges{
m["Cpmn"] = process_ranges{
"Cypro-Minoan",
"Cypro-Minoan",
1751985,
"syllabary",
"syllabary",
aliases = {"Cypro Minoan"},
aliases = {"Cypro Minoan"},
Line 618: Line 610:
m["Cprt"] = process_ranges{
m["Cprt"] = process_ranges{
"Cypriot",
"Cypriot",
1757689,
"syllabary",
"syllabary",
ranges = {
ranges = {
Line 635: Line 628:
m["Cyrl"] = process_ranges{
m["Cyrl"] = process_ranges{
"Cyrillic",
"Cyrillic",
8209,
"alphabet",
"alphabet",
ranges = {
ranges = {
0x0400, 0x052F,
0x0400, 0x052F,
0x1C80, 0x1C88,
0x1C80, 0x1C8A,
0x1D2B, 0x1D2B,
0x1D2B, 0x1D2B,
0x1D78, 0x1D78,
0x1D78, 0x1D78,
Line 654: Line 648:
m["Cyrs"] = {
m["Cyrs"] = {
"Old Cyrillic",
"Old Cyrillic",
m["Cyrl"][2],
442244,
m["Cyrl"][3],
aliases = {"Early Cyrillic"},
aliases = {"Early Cyrillic"},
ranges = m["Cyrl"].ranges,
ranges = m["Cyrl"].ranges,
Line 664: Line 659:
to = {"Ꙋ", "ꙋ"}
to = {"Ꙋ", "ꙋ"}
},
},
strip_diacritics = {remove_diacritics = cs.Cyrs_remove_diacritics},
sort_key = {
remove_diacritics = cs.Cyrs_remove_diacritics,
from = {
"ї", "оу", -- 2 chars
"[ґꙣєѕꙃꙅꙁіꙇђꙉѻꙩꙫꙭꙮꚙꚛꙋѡѿꙍѽꙑѣꙗѥꙕѧꙙѩꙝꙛѫѭѯѱѳѵҁ]"
},
to = {
"и" .. p[1], "у", {
["ґ"] = "г" .. p[1], ["ꙣ"] = "д" .. p[1], ["є"] = "е", ["ѕ"] = "ж" .. p[1], ["ꙃ"] = "ж" .. p[1],
["ꙅ"] = "ж" .. p[1], ["ꙁ"] = "з", ["і"] = "и" .. p[1], ["ꙇ"] = "и" .. p[1], ["ђ"] = "и" .. p[2],
["ꙉ"] = "и" .. p[2], ["ѻ"] = "о", ["ꙩ"] = "о", ["ꙫ"] = "о", ["ꙭ"] = "о",
["ꙮ"] = "о", ["ꚙ"] = "о", ["ꚛ"] = "о", ["ꙋ"] = "у", ["ѡ"] = "х" .. p[1],
["ѿ"] = "х" .. p[1], ["ꙍ"] = "х" .. p[1], ["ѽ"] = "х" .. p[1], ["ꙑ"] = "ы", ["ѣ"] = "ь" .. p[1],
["ꙗ"] = "ь" .. p[2], ["ѥ"] = "ь" .. p[3], ["ꙕ"] = "ю", ["ѧ"] = "я", ["ꙙ"] = "я",
["ѩ"] = "я" .. p[1], ["ꙝ"] = "я" .. p[1], ["ꙛ"] = "я" .. p[2], ["ѫ"] = "я" .. p[3], ["ѭ"] = "я" .. p[4],
["ѯ"] = "я" .. p[5], ["ѱ"] = "я" .. p[6], ["ѳ"] = "я" .. p[7], ["ѵ"] = "я" .. p[8], ["ҁ"] = "я" .. p[9],
}
},
}
}
}


m["Deva"] = process_ranges{
m["Deva"] = process_ranges{
"Devanagari",
"Devanagari",
38592,
"abugida",
"abugida",
ranges = {
ranges = {
Line 686: Line 702:
m["Diak"] = process_ranges{
m["Diak"] = process_ranges{
"Dhives Akuru",
"Dhives Akuru",
3307073,
"abugida",
"abugida",
aliases = {"Dhivehi Akuru", "Dives Akuru", "Divehi Akuru"},
aliases = {"Dhivehi Akuru", "Dives Akuru", "Divehi Akuru"},
Line 702: Line 719:
m["Dogr"] = process_ranges{
m["Dogr"] = process_ranges{
"Dogra",
"Dogra",
72402987,
"abugida",
"abugida",
ranges = {
ranges = {
Line 712: Line 730:
m["Dsrt"] = process_ranges{
m["Dsrt"] = process_ranges{
"Deseret",
"Deseret",
1200582,
"alphabet",
"alphabet",
ranges = {
ranges = {
Line 721: Line 740:
m["Dupl"] = process_ranges{
m["Dupl"] = process_ranges{
"Duployan",
"Duployan",
5316025,
"alphabet",
"alphabet",
ranges = {
ranges = {
Line 733: Line 753:
m["Egyd"] = {
m["Egyd"] = {
"Demotic",
"Demotic",
188519,
"abjad, logography",
"abjad, logography",
-- Not in Unicode
-- Not in Unicode
Line 739: Line 760:
m["Egyh"] = {
m["Egyh"] = {
"Hieratic",
"Hieratic",
208111,
"abjad, logography",
"abjad, logography",
-- Unified with Egyptian hieroglyphic in Unicode
-- Unified with Egyptian hieroglyphic in Unicode
Line 745: Line 767:
m["Egyp"] = process_ranges{
m["Egyp"] = process_ranges{
"Egyptian hieroglyphic",
"Egyptian hieroglyphic",
132659,
"abjad, logography",
"abjad, logography",
ranges = {
ranges = {
0x13000, 0x13455,
0x13000, 0x13455,
0x13460, 0x143FA,
},
},
varieties = {"Hieratic"},
varieties = {"Hieratic"},
Line 759: Line 783:
m["Elba"] = process_ranges{
m["Elba"] = process_ranges{
"Elbasan",
"Elbasan",
1036714,
"alphabet",
"alphabet",
ranges = {
ranges = {
Line 767: Line 792:
m["Elym"] = process_ranges{
m["Elym"] = process_ranges{
"Elymaic",
"Elymaic",
60744423,
"abjad",
"abjad",
ranges = {
ranges = {
Line 776: Line 802:
m["Ethi"] = process_ranges{
m["Ethi"] = process_ranges{
"Ethiopic",
"Ethiopic",
257634,
"abugida",
"abugida",
aliases = {"Ge'ez"},
aliases = {"Ge'ez", "Geʽez"},
ranges = {
ranges = {
0x1200, 0x1248,
0x1200, 0x1248,
Line 816: Line 843:
0x1E7F0, 0x1E7FE,
0x1E7F0, 0x1E7FE,
},
},
sort_key = "Ethi-sortkey",
strip_diacritics = {remove_diacritics = u(0x135D) .. u(0x135E) .. u(0x135F)}
}
}


m["Gara"] = {
m["Gara"] = process_ranges{
"Garay",
"Garay",
3095302,
"alphabet",
"alphabet",
capitalized = true,
capitalized = true,
direction = "rtl",
direction = "rtl",
-- Not in Unicode
ranges = {
0x060C, 0x060C,
0x061B, 0x061B,
0x061F, 0x061F,
0x10D40, 0x10D65,
0x10D69, 0x10D85,
0x10D8E, 0x10D8F,
},
}
}


m["Geok"] = process_ranges{
m["Geok"] = process_ranges{
"Khutsuri",
"Khutsuri",
1090055,
"alphabet",
"alphabet",
ranges = { -- Ⴀ-Ⴭ is Asomtavruli, ⴀ-ⴭ is Nuskhuri
ranges = { -- Ⴀ-Ⴭ is Asomtavruli, ⴀ-ⴭ is Nuskhuri
Line 840: Line 878:
varieties = {"Nuskhuri", "Asomtavruli"},
varieties = {"Nuskhuri", "Asomtavruli"},
capitalized = true,
capitalized = true,
translit = "Geok-translit",
}
}


m["Geor"] = process_ranges{
m["Geor"] = process_ranges{
"Georgian",
"Georgian",
3317411,
"alphabet",
"alphabet",
ranges = { -- ა-ჿ is lowercase Mkhedruli; Ა-Ჿ is uppercase Mkhedruli (Mtavruli)
ranges = { -- ა-ჿ is lowercase Mkhedruli; Ა-Ჿ is uppercase Mkhedruli (Mtavruli)
0x0589, 0x0589,
0x10D0, 0x10FF,
0x10D0, 0x10FF,
0x1C90, 0x1CBA,
0x1C90, 0x1CBA,
Line 852: Line 893:
varieties = {"Mkhedruli", "Mtavruli"},
varieties = {"Mkhedruli", "Mtavruli"},
capitalized = true,
capitalized = true,
translit = "Geor-translit",
}
}


m["Glag"] = process_ranges{
m["Glag"] = process_ranges{
"Glagolitic",
"Glagolitic",
145625,
"alphabet",
"alphabet",
ranges = {
ranges = {
0x0484, 0x0484,
0x0484, 0x0484,
0x0487, 0x0487,
0x0487, 0x0487,
0x0589, 0x0589,
0x10FB, 0x10FB,
0x2C00, 0x2C5F,
0x2C00, 0x2C5F,
0x2E43, 0x2E43,
0x2E43, 0x2E43,
Line 874: Line 919:
m["Gong"] = process_ranges{
m["Gong"] = process_ranges{
"Gunjala Gondi",
"Gunjala Gondi",
18125340,
"abugida",
"abugida",
ranges = {
ranges = {
Line 888: Line 934:
m["Gonm"] = process_ranges{
m["Gonm"] = process_ranges{
"Masaram Gondi",
"Masaram Gondi",
16977603,
"abugida",
"abugida",
ranges = {
ranges = {
Line 903: Line 950:
m["Goth"] = process_ranges{
m["Goth"] = process_ranges{
"Gothic",
"Gothic",
467784,
"alphabet",
"alphabet",
ranges = {
ranges = {
Line 912: Line 960:
m["Gran"] = process_ranges{
m["Gran"] = process_ranges{
"Grantha",
"Grantha",
1119274,
"abugida",
"abugida",
ranges = {
ranges = {
Line 944: Line 993:
m["Grek"] = process_ranges{
m["Grek"] = process_ranges{
"Greek",
"Greek",
8216,
"alphabet",
"alphabet",
ranges = {
ranges = {
0x0342, 0x0342,
0x0341, 0x0341,
0x0345, 0x0345,
0x0374, 0x0375,
0x0370, 0x0377,
0x037E, 0x037E,
0x037A, 0x037F,
0x0384, 0x038A,
0x0384, 0x038A,
0x038C, 0x038C,
0x038C, 0x038C,
0x038E, 0x03A1,
0x038E, 0x03A1,
0x03A3, 0x03E1,
0x03A3, 0x03D7,
0x03F0, 0x03FF,
0x03DA, 0x03DB,
0x03DE, 0x03E1,
0x03F0, 0x03F1,
0x03F4, 0x03F4,
0x03FC, 0x03FC,
0x1D26, 0x1D2A,
0x1D26, 0x1D2A,
0x1D5D, 0x1D61,
0x1D5D, 0x1D61,
Line 968: Line 1,021:
},
},
capitalized = true,
capitalized = true,
display_text = cs["Grek-displaytext"],
strip_diacritics = cs["Grek-stripdiacritics"],
sort_key = {
remove_diacritics = "'ʼ;·`¨´῀" .. c.grave .. c.acute .. c.diaer .. c.caron .. c.turnedcommaabove .. c.commaabove .. c.revcommaabove .. c.macron .. c.breve .. c.diaerbelow .. c.brevebelow .. c.perispomeni .. c.ypogegrammeni .. c.RSQuo .. c.prime .. c.keraia .. c.lowerkeraia .. c.tonos .. c.coronis .. c.psili .. c.dasia,
from = {"ϝ", "ͷ", "ϛ", "ͱ", "ͺ", "ϳ", "ϻ", "[ϟϙ]", "[ςϲ]", "ͳ"},
to = {"ε" .. p[1], "ε" .. p[2], "ε" .. p[3], "ζ" .. p[1], "ι", "ι" .. p[1], "π" .. p[1], "π" .. p[2], "σ", "ϡ"},
},
}
}


m["Polyt"] = process_ranges{
m["Polyt"] = process_ranges{
"Greek",
"Greek",
m["Grek"][2],
1475332,
m["Grek"][3],
ranges = union(m["Grek"].ranges, {
ranges = union(m["Grek"].ranges, {
0x0340, 0x0340,
0x0342, 0x0345,
0x0370, 0x0373,
0x0376, 0x0377,
0x037A, 0x037D,
0x037F, 0x037F,
0x03D8, 0x03D9,
0x03DC, 0x03DD,
0x03F2, 0x03F3,
0x03F5, 0x03FB,
0x03FD, 0x03FF,
0x1F00, 0x1F15,
0x1F00, 0x1F15,
0x1F18, 0x1F1D,
0x1F18, 0x1F1D,
Line 994: Line 1,066:
capitalized = m["Grek"].capitalized,
capitalized = m["Grek"].capitalized,
parent = "Grek",
parent = "Grek",
display_text = m["Grek"].display_text,
strip_diacritics = "Polyt-stripdiacritics",
sort_key = m["Grek"].sort_key,
translit = "grc-translit",
}
}


m["Gujr"] = process_ranges{
m["Gujr"] = process_ranges{
"Gujarati",
"Gujarati",
733944,
"abugida",
"abugida",
ranges = {
ranges = {
Line 1,024: Line 1,101:
}
}


m["Gukh"] = {
m["Gukh"] = process_ranges{
"Khema",
"Khema",
110064239,
"abugida",
"abugida",
aliases = {"Gurung Khema", "Khema Phri", "Khema Lipi"},
aliases = {"Gurung Khema", "Khema Phri", "Khema Lipi"},
-- Not in Unicode
ranges = {
0x0965, 0x0965,
0x16100, 0x16139,
},
}
}


m["Guru"] = process_ranges{
m["Guru"] = process_ranges{
"Gurmukhi",
"Gurmukhi",
689894,
"abugida",
"abugida",
ranges = {
ranges = {
Line 1,063: Line 1,145:
m["Hang"] = process_ranges{
m["Hang"] = process_ranges{
"Hangul",
"Hangul",
8222,
"syllabary",
"syllabary",
aliases = {"Hangeul"},
aliases = {"Hangeul"},
Line 1,092: Line 1,175:
m["Hani"] = process_ranges{
m["Hani"] = process_ranges{
"Han",
"Han",
8201,
"logography",
"logography",
ranges = {
ranges = {
Line 1,105: Line 1,189:
0x3037, 0x303F,
0x3037, 0x303F,
0x3190, 0x319F,
0x3190, 0x319F,
0x31C0, 0x31E3,
0x31C0, 0x31E5,
0x31EF, 0x31EF,
0x31EF, 0x31EF,
0x3220, 0x3247,
0x3220, 0x3247,
Line 1,142: Line 1,226:
m["Hans"] = {
m["Hans"] = {
"Simplified Han",
"Simplified Han",
m["Hani"][2],
185614,
m["Hani"][3],
ranges = m["Hani"].ranges,
ranges = m["Hani"].ranges,
characters = m["Hani"].characters,
characters = m["Hani"].characters,
Line 1,151: Line 1,236:
m["Hant"] = {
m["Hant"] = {
"Traditional Han",
"Traditional Han",
m["Hani"][2],
178528,
m["Hani"][3],
ranges = m["Hani"].ranges,
ranges = m["Hani"].ranges,
characters = m["Hani"].characters,
characters = m["Hani"].characters,
Line 1,160: Line 1,246:
m["Hano"] = process_ranges{
m["Hano"] = process_ranges{
"Hanunoo",
"Hanunoo",
1584045,
"abugida",
"abugida",
aliases = {"Hanunó'o", "Hanuno'o"},
ranges = {
ranges = {
0x1720, 0x1736,
0x1720, 0x1736,
Line 1,168: Line 1,256:
m["Hatr"] = process_ranges{
m["Hatr"] = process_ranges{
"Hatran",
"Hatran",
20813038,
"abjad",
"abjad",
ranges = {
ranges = {
Line 1,179: Line 1,268:
m["Hebr"] = process_ranges{
m["Hebr"] = process_ranges{
"Hebrew",
"Hebrew",
"abjad", -- more precisely, impure abjad
33513,
"abjad", -- more precisely, impure abjad
ranges = {
ranges = {
0x0591, 0x05C7,
0x0591, 0x05C7,
Line 1,193: Line 1,283:
},
},
direction = "rtl",
direction = "rtl",
display_text = "Hebr-common",
sort_key = "Hebr-common",
strip_diacritics = "Hebr-common",
}
}


m["Hira"] = process_ranges{
m["Hira"] = process_ranges{
"Hiragana",
"Hiragana",
48332,
"syllabary",
"syllabary",
ranges = {
ranges = {
Line 1,222: Line 1,316:


m["Hluw"] = process_ranges{
m["Hluw"] = process_ranges{
"Anatolian Hieroglyphs",
"Anatolian hieroglyphic",
521323,
"logography, syllabary",
"logography, syllabary",
ranges = {
ranges = {
Line 1,232: Line 1,327:
m["Hmng"] = process_ranges{
m["Hmng"] = process_ranges{
"Pahawh Hmong",
"Pahawh Hmong",
365954,
"semisyllabary",
"semisyllabary",
aliases = {"Hmong"},
aliases = {"Hmong"},
Line 1,245: Line 1,341:
m["Hmnp"] = process_ranges{
m["Hmnp"] = process_ranges{
"Nyiakeng Puachue Hmong",
"Nyiakeng Puachue Hmong",
33712499,
"alphabet",
"alphabet",
ranges = {
ranges = {
Line 1,256: Line 1,353:
m["Hung"] = process_ranges{
m["Hung"] = process_ranges{
"Old Hungarian",
"Old Hungarian",
446224,
"alphabet",
"alphabet",
aliases = {"Hungarian runic"},
aliases = {"Hungarian runic"},
Line 1,269: Line 1,367:
m["Ibrnn"] = {
m["Ibrnn"] = {
"Northeastern Iberian",
"Northeastern Iberian",
1113155,
"semisyllabary",
"semisyllabary",
ietf_subtag = "Zzzz",
ietf_subtag = "Zzzz",
Line 1,276: Line 1,375:
m["Ibrns"] = {
m["Ibrns"] = {
"Southeastern Iberian",
"Southeastern Iberian",
2305351,
"semisyllabary",
"semisyllabary",
ietf_subtag = "Zzzz",
ietf_subtag = "Zzzz",
Line 1,284: Line 1,384:
-- To be used to avoid any formatting or link processing
-- To be used to avoid any formatting or link processing
"Image-rendered",
"Image-rendered",
478798,
-- This should not have any characters listed
-- This should not have any characters listed
ietf_subtag = "Zyyy",
ietf_subtag = "Zyyy",
translit = false,
translit = false,
character_category = false,
character_category = false, -- none
}
}


m["Inds"] = {
m["Inds"] = {
"Indus",
"Indus",
601388,
aliases = {"Harappan", "Indus Valley"},
aliases = {"Harappan", "Indus Valley"},
}
}
Line 1,297: Line 1,399:
m["Ipach"] = {
m["Ipach"] = {
"International Phonetic Alphabet",
"International Phonetic Alphabet",
21204,
aliases = {"IPA"},
aliases = {"IPA"},
ietf_subtag = "Latn",
ietf_subtag = "Latn",
Line 1,303: Line 1,406:
m["Ital"] = process_ranges{
m["Ital"] = process_ranges{
"Old Italic",
"Old Italic",
4891256,
"alphabet",
"alphabet",
ranges = {
ranges = {
Line 1,308: Line 1,412:
0x1032D, 0x1032F,
0x1032D, 0x1032F,
},
},
translit = "Ital-translit",
}
}


m["Java"] = process_ranges{
m["Java"] = process_ranges{
"Javanese",
"Javanese",
879704,
"abugida",
"abugida",
ranges = {
ranges = {
Line 1,322: Line 1,428:
m["Jurc"] = {
m["Jurc"] = {
"Jurchen",
"Jurchen",
912240,
"logography",
"logography",
spaces = false,
spaces = false,
Line 1,328: Line 1,435:
m["Kali"] = process_ranges{
m["Kali"] = process_ranges{
"Kayah Li",
"Kayah Li",
4919239,
"abugida",
"abugida",
ranges = {
ranges = {
Line 1,336: Line 1,444:
m["Kana"] = process_ranges{
m["Kana"] = process_ranges{
"Katakana",
"Katakana",
82946,
"syllabary",
"syllabary",
ranges = {
ranges = {
Line 1,364: Line 1,473:
m["Kawi"] = process_ranges{
m["Kawi"] = process_ranges{
"Kawi",
"Kawi",
975802,
"abugida",
"abugida",
ranges = {
ranges = {
0x11F00, 0x11F10,
0x11F00, 0x11F10,
0x11F12, 0x11F3A,
0x11F12, 0x11F3A,
0x11F3E, 0x11F59,
0x11F3E, 0x11F5A,
},
},
}
}
Line 1,374: Line 1,484:
m["Khar"] = process_ranges{
m["Khar"] = process_ranges{
"Kharoshthi",
"Kharoshthi",
1161266,
"abugida",
"abugida",
ranges = {
ranges = {
Line 1,390: Line 1,501:
m["Khmr"] = process_ranges{
m["Khmr"] = process_ranges{
"Khmer",
"Khmer",
1054190,
"abugida",
"abugida",
ranges = {
ranges = {
Line 1,406: Line 1,518:
m["Khoj"] = process_ranges{
m["Khoj"] = process_ranges{
"Khojki",
"Khojki",
1740656,
"abugida",
"abugida",
ranges = {
ranges = {
Line 1,417: Line 1,530:
to = {"𑈇", "𑈁", "𑈅", "𑈇", "𑈇", "𑈃", "𑈲", "𑈳", "𑈂"}
to = {"𑈇", "𑈁", "𑈅", "𑈇", "𑈇", "𑈃", "𑈲", "𑈳", "𑈂"}
},
},
}
m["Khomt"] = {
"Khom Thai",
13023788,
"abugida",
-- Not in Unicode
}
}


m["Kitl"] = {
m["Kitl"] = {
"Khitan Large",
"Khitan large",
6401797,
"logography",
"logography",
spaces = false,
spaces = false,
Line 1,426: Line 1,547:


m["Kits"] = process_ranges{
m["Kits"] = process_ranges{
"Khitan Small",
"Khitan small",
6401800,
"logography, syllabary",
"logography, syllabary",
ranges = {
ranges = {
0x16FE4, 0x16FE4,
0x16FE4, 0x16FE4,
0x18B00, 0x18CD5,
0x18B00, 0x18CD5,
0x18CFF, 0x18CFF,
},
},
spaces = false,
spaces = false,
Line 1,437: Line 1,560:
m["Knda"] = process_ranges{
m["Knda"] = process_ranges{
"Kannada",
"Kannada",
839666,
"abugida",
"abugida",
ranges = {
ranges = {
Line 1,455: Line 1,579:
0x0CF1, 0x0CF3,
0x0CF1, 0x0CF3,
0x1CD0, 0x1CD0,
0x1CD0, 0x1CD0,
0x1CD2, 0x1CD2,
0x1CD2, 0x1CD3,
0x1CDA, 0x1CDA,
0x1CDA, 0x1CDA,
0x1CF2, 0x1CF2,
0x1CF2, 0x1CF2,
Line 1,465: Line 1,589:
to = {"ಊ", "ೠ", "ಔ"}
to = {"ಊ", "ೠ", "ಔ"}
},
},
translit = "kn-translit",
}
}


m["Kpel"] = {
m["Kpel"] = {
"Kpelle",
"Kpelle",
1586299,
"syllabary",
"syllabary",
-- Not in Unicode
-- Not in Unicode
}
}


m["Krai"] = {
m["Krai"] = process_ranges{
"Kirat Rai",
"Kirat Rai",
123173834,
"abugida",
"abugida",
aliases = {"Rai", "Khambu Rai", "Rai Barṇamālā", "Kirat Khambu Rai"},
aliases = {"Rai", "Khambu Rai", "Rai Barṇamālā", "Kirat Khambu Rai"},
-- Not in Unicode
ranges = {
0x16D40, 0x16D79,
},
}
}


m["Kthi"] = process_ranges{
m["Kthi"] = process_ranges{
"Kaithi",
"Kaithi",
1253814,
"abugida",
"abugida",
ranges = {
ranges = {
Line 1,489: Line 1,619:
0x110CD, 0x110CD,
0x110CD, 0x110CD,
},
},
}
m["Kulit"] = {
"Kulitan",
6443044,
"abugida",
-- Not in Unicode
}
}


m["Lana"] = process_ranges{
m["Lana"] = process_ranges{
"Tai Tham",
"Tai Tham",
1314503,
"abugida",
"abugida",
aliases = {"Tham", "Tua Mueang", "Lanna"},
aliases = {"Tham", "Tua Mueang", "Lanna"},
Line 1,507: Line 1,645:
m["Laoo"] = process_ranges{
m["Laoo"] = process_ranges{
"Lao",
"Lao",
1815229,
"abugida",
"abugida",
ranges = {
ranges = {
Line 1,526: Line 1,665:
m["Latn"] = process_ranges{
m["Latn"] = process_ranges{
"Latin",
"Latin",
8229,
"alphabet",
"alphabet",
aliases = {"Roman"},
aliases = {"Roman"},
Line 1,547: Line 1,687:
0x1D6B, 0x1D77,
0x1D6B, 0x1D77,
0x1D79, 0x1DBE,
0x1D79, 0x1DBE,
0x1DF8, 0x1DF8,
0x1E00, 0x1EFF,
0x1E00, 0x1EFF,
0x202F, 0x202F,
0x202F, 0x202F,
Line 1,562: Line 1,703:
0xA700, 0xA707,
0xA700, 0xA707,
0xA722, 0xA787,
0xA722, 0xA787,
0xA78B, 0xA7CA,
0xA78B, 0xA7CD,
0xA7D0, 0xA7D1,
0xA7D0, 0xA7D1,
0xA7D3, 0xA7D3,
0xA7D3, 0xA7D3,
0xA7D5, 0xA7D9,
0xA7D5, 0xA7DC,
0xA7F2, 0xA7FF,
0xA7F2, 0xA7FF,
0xA92E, 0xA92E,
0xA92E, 0xA92E,
Line 1,587: Line 1,728:
m["Latf"] = {
m["Latf"] = {
"Fraktur",
"Fraktur",
m["Latn"][2],
148443,
m["Latn"][3],
ranges = m["Latn"].ranges,
ranges = m["Latn"].ranges,
characters = m["Latn"].characters,
characters = m["Latn"].characters,
otherNames = {"Blackletter"}, -- Blackletter is actually the parent "script"
other_names = {"Blackletter"}, -- Blackletter is actually the parent "script"
capitalized = m["Latn"].capitalized,
capitalized = m["Latn"].capitalized,
translit = m["Latn"].translit,
translit = m["Latn"].translit,
Line 1,598: Line 1,740:
m["Latg"] = {
m["Latg"] = {
"Gaelic",
"Gaelic",
m["Latn"][2],
1432616,
m["Latn"][3],
ranges = m["Latn"].ranges,
ranges = m["Latn"].ranges,
characters = m["Latn"].characters,
characters = m["Latn"].characters,
otherNames = {"Irish"},
other_names = {"Irish"},
capitalized = m["Latn"].capitalized,
capitalized = m["Latn"].capitalized,
translit = m["Latn"].translit,
translit = m["Latn"].translit,
Line 1,609: Line 1,752:
m["pjt-Latn"] = {
m["pjt-Latn"] = {
"Latin",
"Latin",
m["Latn"][2],
nil,
m["Latn"][3],
ranges = m["Latn"].ranges,
ranges = m["Latn"].ranges,
characters = m["Latn"].characters,
characters = m["Latn"].characters,
Line 1,619: Line 1,763:
m["Leke"] = {
m["Leke"] = {
"Leke",
"Leke",
19572613,
"abugida",
"abugida",
-- Not in Unicode
-- Not in Unicode
Line 1,625: Line 1,770:
m["Lepc"] = process_ranges{
m["Lepc"] = process_ranges{
"Lepcha",
"Lepcha",
1481626,
"abugida",
"abugida",
aliases = {"Róng"},
ranges = {
ranges = {
0x1C00, 0x1C37,
0x1C00, 0x1C37,
Line 1,635: Line 1,782:
m["Limb"] = process_ranges{
m["Limb"] = process_ranges{
"Limbu",
"Limbu",
933796,
"abugida",
"abugida",
ranges = {
ranges = {
Line 1,648: Line 1,796:
m["Lina"] = process_ranges{
m["Lina"] = process_ranges{
"Linear A",
"Linear A",
30972,
ranges = {
ranges = {
0x10107, 0x10133,
0x10107, 0x10133,
Line 1,658: Line 1,807:
m["Linb"] = process_ranges{
m["Linb"] = process_ranges{
"Linear B",
"Linear B",
190102,
ranges = {
ranges = {
0x10000, 0x1000B,
0x10000, 0x1000B,
Line 1,674: Line 1,824:
m["Lisu"] = process_ranges{
m["Lisu"] = process_ranges{
"Fraser",
"Fraser",
1194621,
"alphabet",
"alphabet",
aliases = {"Old Lisu", "Lisu"},
aliases = {"Old Lisu", "Lisu"},
ranges = {
ranges = {
0x300A, 0x300B,
0xA4D0, 0xA4FF,
0xA4D0, 0xA4FF,
0x11FB0, 0x11FB0,
0x11FB0, 0x11FB0,
Line 1,683: Line 1,835:
from = {"['’]", "[.ꓸ][.ꓸ]", "[.ꓸ][,ꓹ]"},
from = {"['’]", "[.ꓸ][.ꓸ]", "[.ꓸ][,ꓹ]"},
to = {"ʼ", "ꓺ", "ꓻ"}
to = {"ʼ", "ꓺ", "ꓻ"}
},
translit = "Lisu-translit",
sort_key = {
from = {"𑾰"},
to = {"ꓬ" .. p[1]}
},
},
}
}
Line 1,688: Line 1,845:
m["Loma"] = {
m["Loma"] = {
"Loma",
"Loma",
13023816,
"syllabary",
"syllabary",
-- Not in Unicode
-- Not in Unicode
Line 1,694: Line 1,852:
m["Lyci"] = process_ranges{
m["Lyci"] = process_ranges{
"Lycian",
"Lycian",
913587,
"alphabet",
"alphabet",
ranges = {
ranges = {
Line 1,702: Line 1,861:
m["Lydi"] = process_ranges{
m["Lydi"] = process_ranges{
"Lydian",
"Lydian",
4261300,
"alphabet",
"alphabet",
ranges = {
ranges = {
Line 1,712: Line 1,872:
m["Mahj"] = process_ranges{
m["Mahj"] = process_ranges{
"Mahajani",
"Mahajani",
6732850,
"abugida",
"abugida",
ranges = {
ranges = {
Line 1,722: Line 1,883:
m["Maka"] = process_ranges{
m["Maka"] = process_ranges{
"Makasar",
"Makasar",
72947229,
"abugida",
"abugida",
aliases = {"Old Makasar"},
aliases = {"Old Makasar"},
Line 1,731: Line 1,893:
m["Mand"] = process_ranges{
m["Mand"] = process_ranges{
"Mandaic",
"Mandaic",
1812130,
aliases = {"Mandaean"},
aliases = {"Mandaean"},
ranges = {
ranges = {
Line 1,742: Line 1,905:
m["Mani"] = process_ranges{
m["Mani"] = process_ranges{
"Manichaean",
"Manichaean",
3544702,
"abjad",
"abjad",
ranges = {
ranges = {
Line 1,749: Line 1,913:
},
},
direction = "rtl",
direction = "rtl",
translit = "Mani-translit",
}
}


m["Marc"] = process_ranges{
m["Marc"] = process_ranges{
"Marchen",
"Marchen",
72403709,
"abugida",
"abugida",
ranges = {
ranges = {
Line 1,763: Line 1,929:
m["Maya"] = process_ranges{
m["Maya"] = process_ranges{
"Maya",
"Maya",
211248,
aliases = {"Maya hieroglyphic", "Mayan", "Mayan hieroglyphic"},
aliases = {"Maya hieroglyphic", "Mayan", "Mayan hieroglyphic"},
ranges = {
ranges = {
Line 1,771: Line 1,938:
m["Medf"] = process_ranges{
m["Medf"] = process_ranges{
"Medefaidrin",
"Medefaidrin",
1519764,
aliases = {"Oberi Okaime", "Oberi Ɔkaimɛ"},
aliases = {"Oberi Okaime", "Oberi Ɔkaimɛ"},
ranges = {
ranges = {
Line 1,780: Line 1,948:
m["Mend"] = process_ranges{
m["Mend"] = process_ranges{
"Mende",
"Mende",
951069,
aliases = {"Mende Kikakui"},
aliases = {"Mende Kikakui"},
ranges = {
ranges = {
Line 1,790: Line 1,959:
m["Merc"] = process_ranges{
m["Merc"] = process_ranges{
"Meroitic cursive",
"Meroitic cursive",
73028124,
"abugida",
"abugida",
ranges = {
ranges = {
Line 1,801: Line 1,971:
m["Mero"] = process_ranges{
m["Mero"] = process_ranges{
"Meroitic hieroglyphic",
"Meroitic hieroglyphic",
73028623,
"abugida",
"abugida",
ranges = {
ranges = {
Line 1,806: Line 1,977:
},
},
direction = "rtl",
direction = "rtl",
wikipedia_article = "Meroitic hieroglyphs",
}
}


m["Mlym"] = process_ranges{
m["Mlym"] = process_ranges{
"Malayalam",
"Malayalam",
1164129,
"abugida",
"abugida",
ranges = {
ranges = {
Line 1,829: Line 2,002:
to = {"ഈ", "ഊ", "ഐ", "ഓ", "ഔ", "ൿ", "ൺ", "ൻറ", "ൻ", "ൔ", "ൕ", "ർ", "ൽ", "ൾ", "ൖ", "ൈ", "ന്റ"}
to = {"ഈ", "ഊ", "ഐ", "ഓ", "ഔ", "ൿ", "ൺ", "ൻറ", "ൻ", "ൔ", "ൕ", "ർ", "ൽ", "ൾ", "ൖ", "ൈ", "ന്റ"}
},
},
translit = "ml-translit",
}
}


m["Modi"] = process_ranges{
m["Modi"] = process_ranges{
"Modi",
"Modi",
1703713,
"abugida",
"abugida",
ranges = {
ranges = {
Line 1,845: Line 2,020:
}
}


m["Mong"] = process_ranges{
do
"Mongolian",
local Mong_displaytext = {
"alphabet",
from = {"([ᠨ-ᡂᡸ])ᠶ([ᠨ-ᡂᡸ])", "([ᠠ-ᡂᡸ])ᠸ([^᠋ᠠ-ᠧ])", "([ᠠ-ᡂᡸ])ᠸ$"},
aliases = {"Mongol bichig", "Hudum Mongol bichig"},
to = {"%1ᠢ%2", "%1ᠧ%2", "%1ᠧ"}
ranges = {
}
0x1800, 0x1805,
0x180A, 0x1819,
m["Mong"] = process_ranges{
0x1820, 0x1842,
"Mongolian",
0x1878, 0x1878,
1055705,
0x1880, 0x1897,
"alphabet",
0x18A6, 0x18A6,
aliases = {"Mongol bichig", "Hudum Mongol bichig"},
0x18A9, 0x18A9,
0x200C, 0x200D,
0x202F, 0x202F,
0x11660, 0x11668,
},
direction = "vertical-ltr",
}
 
m["mnc-Mong"] = process_ranges{
"Manchu",
m["Mong"][2],
ranges = {
ranges = {
0x1801, 0x1801,
0x1800, 0x1805,
0x1804, 0x1804,
0x180A, 0x1819,
0x1808, 0x180F,
0x1820, 0x1842,
0x1820, 0x1820,
0x1878, 0x1878,
0x1823, 0x1823,
0x1880, 0x1897,
0x1828, 0x182A,
0x18A6, 0x18A6,
0x182E, 0x1830,
0x18A9, 0x18A9,
0x1834, 0x1838,
0x183A, 0x183A,
0x185D, 0x185D,
0x185F, 0x1861,
0x1864, 0x1869,
0x186C, 0x1871,
0x1873, 0x1877,
0x1880, 0x1888,
0x188F, 0x188F,
0x189A, 0x18A5,
0x18A8, 0x18A8,
0x18AA, 0x18AA,
0x200C, 0x200D,
0x200C, 0x200D,
0x202F, 0x202F,
0x202F, 0x202F,
0x3001, 0x3002,
0x3008, 0x300B,
0x11660, 0x11668,
},
},
direction = "vertical-ltr",
direction = "vertical-ltr",
parent = "Mong",
display_text = Mong_displaytext,
}
strip_diacritics = Mong_displaytext,
translit = "Mong-translit",
m["sjo-Mong"] = process_ranges{
"Xibe",
m["Mong"][2],
aliases = {"Sibe"},
ranges = {
0x1804, 0x1804,
0x1807, 0x1807,
0x180A, 0x180F,
0x1820, 0x1820,
0x1823, 0x1823,
0x1828, 0x1828,
0x182A, 0x182A,
0x182E, 0x1830,
0x1834, 0x1838,
0x183A, 0x183A,
0x185D, 0x1872,
0x200C, 0x200D,
0x202F, 0x202F,
},
direction = "vertical-ltr",
parent = "mnc-Mong",
}
m["xwo-Mong"] = process_ranges{
"Clear Script",
m["Mong"][2],
aliases = {"Todo", "Todo bichig"},
ranges = {
0x1800, 0x1801,
0x1804, 0x1806,
0x180A, 0x1820,
0x1828, 0x1828,
0x182F, 0x1831,
0x1834, 0x1834,
0x1837, 0x1838,
0x183A, 0x183B,
0x1840, 0x1840,
0x1843, 0x185C,
0x1880, 0x1887,
0x1889, 0x188F,
0x1894, 0x1894,
0x1896, 0x1899,
0x18A7, 0x18A7,
0x200C, 0x200D,
0x202F, 0x202F,
0x11669, 0x1166C,
},
direction = "vertical-ltr",
parent = "Mong",
}
}
m["mnc-Mong"] = process_ranges{
"Manchu",
122888,
m["Mong"][3],
ranges = {
0x1801, 0x1801,
0x1804, 0x1804,
0x1808, 0x180F,
0x1820, 0x1820,
0x1823, 0x1823,
0x1828, 0x182A,
0x182E, 0x1830,
0x1834, 0x1838,
0x183A, 0x183A,
0x185D, 0x185D,
0x185F, 0x1861,
0x1864, 0x1869,
0x186C, 0x1871,
0x1873, 0x1877,
0x1880, 0x1888,
0x188F, 0x188F,
0x189A, 0x18A5,
0x18A8, 0x18A8,
0x18AA, 0x18AA,
0x200C, 0x200D,
0x202F, 0x202F,
},
direction = "vertical-ltr",
parent = "Mong",
translit = "mnc-translit",
}
m["sjo-Mong"] = process_ranges{
"Xibe",
113624153,
m["Mong"][3],
aliases = {"Sibe"},
ranges = {
0x1804, 0x1804,
0x1807, 0x1807,
0x180A, 0x180F,
0x1820, 0x1820,
0x1823, 0x1823,
0x1828, 0x1828,
0x182A, 0x182A,
0x182E, 0x1830,
0x1834, 0x1838,
0x183A, 0x183A,
0x185D, 0x1872,
0x200C, 0x200D,
0x202F, 0x202F,
},
direction = "vertical-ltr",
parent = "mnc-Mong",
}
m["xwo-Mong"] = process_ranges{
"Clear Script",
529085,
m["Mong"][3],
aliases = {"Todo", "Todo bichig"},
ranges = {
0x1800, 0x1801,
0x1804, 0x1806,
0x180A, 0x1820,
0x1828, 0x1828,
0x182F, 0x1831,
0x1834, 0x1834,
0x1837, 0x1838,
0x183A, 0x183B,
0x1840, 0x1840,
0x1843, 0x185C,
0x1880, 0x1887,
0x1889, 0x188F,
0x1894, 0x1894,
0x1896, 0x1899,
0x18A7, 0x18A7,
0x200C, 0x200D,
0x202F, 0x202F,
0x11669, 0x1166C,
},
direction = "vertical-ltr",
parent = "Mong",
translit = "xwo-translit",
}
end


m["Moon"] = {
m["Moon"] = {
"Moon",
"Moon",
918391,
"alphabet",
"alphabet",
aliases = {"Moon System of Embossed Reading", "Moon type", "Moon writing", "Moon alphabet", "Moon code"},
aliases = {"Moon System of Embossed Reading", "Moon type", "Moon writing", "Moon alphabet", "Moon code"},
Line 1,954: Line 2,148:
m["Morse"] = {
m["Morse"] = {
"Morse code",
"Morse code",
79897,
ietf_subtag = "Zsym",
ietf_subtag = "Zsym",
}
}


m["Mroo"] = process_ranges{
m["Mroo"] = process_ranges{
"Mro",
"Mru",
75919253,
aliases = {"Mro", "Mrung"},
ranges = {
ranges = {
0x16A40, 0x16A5E,
0x16A40, 0x16A5E,
Line 1,968: Line 2,165:
m["Mtei"] = process_ranges{
m["Mtei"] = process_ranges{
"Meitei Mayek",
"Meitei Mayek",
2981413,
"abugida",
"abugida",
aliases = {"Meetei Mayek", "Manipuri"},
aliases = {"Meetei Mayek", "Manipuri"},
Line 1,979: Line 2,177:
m["Mult"] = process_ranges{
m["Mult"] = process_ranges{
"Multani",
"Multani",
17047906,
"abugida",
"abugida",
ranges = {
ranges = {
Line 1,991: Line 2,190:


m["Music"] = process_ranges{
m["Music"] = process_ranges{
"Musical notation",
"musical notation",
233861,
"pictography",
"pictography",
ranges = {
ranges = {
Line 2,004: Line 2,204:
m["Mymr"] = process_ranges{
m["Mymr"] = process_ranges{
"Burmese",
"Burmese",
43887939,
"abugida",
"abugida",
aliases = {"Myanmar"},
aliases = {"Myanmar"},
Line 2,011: Line 2,212:
0xA9E0, 0xA9FE,
0xA9E0, 0xA9FE,
0xAA60, 0xAA7F,
0xAA60, 0xAA7F,
0x116D0, 0x116E3,
},
},
spaces = false,
spaces = false,
Line 2,016: Line 2,218:


m["Nagm"] = process_ranges{
m["Nagm"] = process_ranges{
"Nag Mundari",
"Mundari Bani",
106917274,
"alphabet",
"alphabet",
aliases = {"Nag Mundari"},
ranges = {
ranges = {
0x1E4D0, 0x1E4F9,
0x1E4D0, 0x1E4F9,
Line 2,025: Line 2,229:
m["Nand"] = process_ranges{
m["Nand"] = process_ranges{
"Nandinagari",
"Nandinagari",
6963324,
"abugida",
"abugida",
ranges = {
ranges = {
Line 2,040: Line 2,245:


m["Narb"] = process_ranges{
m["Narb"] = process_ranges{
"Old North Arabian",
"Ancient North Arabian",
1472213,
"abjad",
"abjad",
aliases = {"Old North Arabian"},
ranges = {
ranges = {
0x10A80, 0x10A9F,
0x10A80, 0x10A9F,
},
},
direction = "rtl",
direction = "rtl",
translit = "Narb-translit",
}
}


m["Nbat"] = process_ranges{
m["Nbat"] = process_ranges{
"Nabataean",
"Nabataean",
855624,
"abjad",
"abjad",
aliases = {"Nabatean"},
aliases = {"Nabatean"},
Line 2,061: Line 2,270:
m["Newa"] = process_ranges{
m["Newa"] = process_ranges{
"Newa",
"Newa",
7237292,
"abugida",
"abugida",
aliases = {"Newar", "Newari", "Prachalit Nepal"},
aliases = {"Newar", "Newari", "Prachalit Nepal"},
Line 2,071: Line 2,281:
m["Nkdb"] = {
m["Nkdb"] = {
"Dongba",
"Dongba",
1190953,
"pictography",
"pictography",
aliases = {"Naxi Dongba", "Nakhi Dongba", "Tomba", "Tompa", "Mo-so"},
aliases = {"Naxi Dongba", "Nakhi Dongba", "Tomba", "Tompa", "Mo-so"},
Line 2,079: Line 2,290:
m["Nkgb"] = {
m["Nkgb"] = {
"Geba",
"Geba",
731189,
"syllabary",
"syllabary",
aliases = {"Nakhi Geba", "Naxi Geba"},
aliases = {"Nakhi Geba", "Naxi Geba"},
Line 2,087: Line 2,299:
m["Nkoo"] = process_ranges{
m["Nkoo"] = process_ranges{
"N'Ko",
"N'Ko",
1062587,
"alphabet",
"alphabet",
ranges = {
ranges = {
Line 2,100: Line 2,313:


m["None"] = {
m["None"] = {
"Unspecified", -- renders as 'unspecified script'
"unspecified",
nil,
-- This should not have any characters listed
-- This should not have any characters listed
ietf_subtag = "Zyyy",
ietf_subtag = "Zyyy",
translit = false,
translit = false,
character_category = false,
character_category = false, -- none
}
}


m["Nshu"] = process_ranges{
m["Nshu"] = process_ranges{
"Nüshu",
"Nüshu",
56436,
"syllabary",
"syllabary",
aliases = {"Nushu"},
aliases = {"Nushu"},
Line 2,120: Line 2,335:
m["Ogam"] = process_ranges{
m["Ogam"] = process_ranges{
"Ogham",
"Ogham",
184661,
ranges = {
ranges = {
0x1680, 0x169C,
0x1680, 0x169C,
Line 2,127: Line 2,343:
m["Olck"] = process_ranges{
m["Olck"] = process_ranges{
"Ol Chiki",
"Ol Chiki",
201688,
aliases = {"Ol Chemetʼ", "Ol", "Santali"},
aliases = {"Ol Chemetʼ", "Ol", "Santali"},
ranges = {
ranges = {
Line 2,133: Line 2,350:
}
}


m["Onao"] = {
m["Onao"] = process_ranges{
"Ol Onal",
"Ol Onal",
108607084,
"alphabet",
"alphabet",
-- Not in Unicode
ranges = {
0x0964, 0x0965,
0x1E5D0, 0x1E5FA,
0x1E5FF, 0x1E5FF,
},
}
}


m["Orkh"] = process_ranges{
m["Orkh"] = process_ranges{
"Orkhon runes",
"Old Turkic",
aliases = {"Old Turkic"},
5058305,
aliases = {"Orkhon runic"},
ranges = {
ranges = {
0x10C00, 0x10C48,
0x10C00, 0x10C48,
},
},
direction = "rtl",
direction = "rtl",
translit = "Orkh-translit",
}
}


m["Orya"] = process_ranges{
m["Orya"] = process_ranges{
"Odia",
"Odia",
1760127,
"abugida",
"abugida",
aliases = {"Oriya"},
aliases = {"Oriya"},
Line 2,180: Line 2,405:
m["Osge"] = process_ranges{
m["Osge"] = process_ranges{
"Osage",
"Osage",
7105529,
ranges = {
ranges = {
0x104B0, 0x104D3,
0x104B0, 0x104D3,
Line 2,189: Line 2,415:
m["Osma"] = process_ranges{
m["Osma"] = process_ranges{
"Osmanya",
"Osmanya",
1377866,
ranges = {
ranges = {
0x10480, 0x1049D,
0x10480, 0x1049D,
Line 2,197: Line 2,424:
m["Ougr"] = process_ranges{
m["Ougr"] = process_ranges{
"Old Uyghur",
"Old Uyghur",
1998938,
"abjad, alphabet",
"abjad, alphabet",
ranges = {
ranges = {
Line 2,209: Line 2,437:
m["Palm"] = process_ranges{
m["Palm"] = process_ranges{
"Palmyrene",
"Palmyrene",
17538100,
ranges = {
ranges = {
0x10860, 0x1087F,
0x10860, 0x1087F,
Line 2,217: Line 2,446:
m["Pauc"] = process_ranges{
m["Pauc"] = process_ranges{
"Pau Cin Hau",
"Pau Cin Hau",
25339852,
ranges = {
ranges = {
0x11AC0, 0x11AF8,
0x11AC0, 0x11AF8,
},
},
}
m["Pcun"] = {
"Proto-Cuneiform",
1650699,
"pictography",
-- Not in Unicode
}
m["Pelm"] = {
"Proto-Elamite",
56305763,
"pictography",
-- Not in Unicode
}
}


m["Perm"] = process_ranges{
m["Perm"] = process_ranges{
"Old Permic",
"Old Permic",
147899,
ranges = {
ranges = {
0x0483, 0x0483,
0x0483, 0x0483,
Line 2,232: Line 2,477:
m["Phag"] = process_ranges{
m["Phag"] = process_ranges{
"Phags-pa",
"Phags-pa",
822836,
"abugida",
"abugida",
ranges = {
ranges = {
Line 2,246: Line 2,492:
m["Phli"] = process_ranges{
m["Phli"] = process_ranges{
"Inscriptional Pahlavi",
"Inscriptional Pahlavi",
24089793,
"abjad",
"abjad",
ranges = {
ranges = {
Line 2,256: Line 2,503:
m["Phlp"] = process_ranges{
m["Phlp"] = process_ranges{
"Psalter Pahlavi",
"Psalter Pahlavi",
7253954,
"abjad",
"abjad",
ranges = {
ranges = {
Line 2,268: Line 2,516:
m["Phlv"] = {
m["Phlv"] = {
"Book Pahlavi",
"Book Pahlavi",
72403118,
"abjad",
"abjad",
direction = "rtl",
direction = "rtl",
wikipedia_article = "Pahlavi scripts#Book Pahlavi",
-- Not in Unicode
-- Not in Unicode
}
}
Line 2,275: Line 2,525:
m["Phnx"] = process_ranges{
m["Phnx"] = process_ranges{
"Phoenician",
"Phoenician",
26752,
"abjad",
"abjad",
ranges = {
ranges = {
Line 2,281: Line 2,532:
},
},
direction = "rtl",
direction = "rtl",
translit = "Phnx-translit",
}
}


m["Plrd"] = process_ranges{
m["Plrd"] = process_ranges{
"Pollard",
"Pollard",
601734,
"abugida",
"abugida",
aliases = {"Miao"},
aliases = {"Miao"},
Line 2,296: Line 2,549:
m["Prti"] = process_ranges{
m["Prti"] = process_ranges{
"Inscriptional Parthian",
"Inscriptional Parthian",
13023804,
ranges = {
ranges = {
0x10B40, 0x10B55,
0x10B40, 0x10B55,
Line 2,301: Line 2,555:
},
},
direction = "rtl",
direction = "rtl",
}
m["Psin"] = {
"Proto-Sinaitic",
1065250,
"abjad",
direction = "rtl",
-- Not in Unicode
}
}


m["Ranj"] = {
m["Ranj"] = {
"Ranjana",
"Ranjana",
2385276,
"abugida",
"abugida",
-- Not in Unicode
-- Not in Unicode
Line 2,311: Line 2,574:
m["Rjng"] = process_ranges{
m["Rjng"] = process_ranges{
"Rejang",
"Rejang",
2007960,
"abugida",
"abugida",
ranges = {
ranges = {
Line 2,320: Line 2,584:
m["Rohg"] = process_ranges{
m["Rohg"] = process_ranges{
"Hanifi Rohingya",
"Hanifi Rohingya",
21028705,
"alphabet",
"alphabet",
ranges = {
ranges = {
Line 2,335: Line 2,600:
m["Roro"] = {
m["Roro"] = {
"Rongorongo",
"Rongorongo",
209764,
-- Not in Unicode
-- Not in Unicode
}
}
Line 2,340: Line 2,606:
m["Rumin"] = process_ranges{
m["Rumin"] = process_ranges{
"Rumi numerals",
"Rumi numerals",
nil,
ranges = {
ranges = {
0x10E60, 0x10E7E,
0x10E60, 0x10E7E,
},
},
ietf_subtag = "Arab",
ietf_subtag = "Arab",
character_category = "Rumi numerals",
}
}


m["Runr"] = process_ranges{
m["Runr"] = process_ranges{
"Runic",
"Runic",
82996,
"alphabet",
"alphabet",
ranges = {
ranges = {
Line 2,356: Line 2,623:
}
}


m["Samr"] = process_ranges{
do
"Samaritan",
local Samr_stripdiacritics = {
"abjad",
remove_diacritics = c.CGJ .. u(0x0816) .. "-" .. u(0x082D),
ranges = {
}
0x0800, 0x082D,
0x0830, 0x083E,
m["Samr"] = process_ranges{
},
"Samaritan",
direction = "rtl",
1550930,
}
"abjad",
ranges = {
0x0800, 0x082D,
0x0830, 0x083E,
},
direction = "rtl",
strip_diacritics = Samr_stripdiacritics,
sort_key = Samr_stripdiacritics,
}
end


m["Sarb"] = process_ranges{
m["Sarb"] = process_ranges{
"Old South Arabian",
"Ancient South Arabian",
446074,
"abjad",
"abjad",
aliases = {"Old South Arabian"},
ranges = {
ranges = {
0x10A60, 0x10A7F,
0x10A60, 0x10A7F,
},
},
direction = "rtl",
direction = "rtl",
translit = "Sarb-translit",
}
}


m["Saur"] = process_ranges{
m["Saur"] = process_ranges{
"Saurashtra",
"Saurashtra",
3535165,
"abugida",
"abugida",
ranges = {
ranges = {
Line 2,386: Line 2,666:
m["Semap"] = {
m["Semap"] = {
"flag semaphore",
"flag semaphore",
250796,
"pictography",
"pictography",
ietf_subtag = "Zsym",
ietf_subtag = "Zsym",
Line 2,392: Line 2,673:
m["Sgnw"] = process_ranges{
m["Sgnw"] = process_ranges{
"SignWriting",
"SignWriting",
1497335,
"pictography",
"pictography",
aliases = {"Sutton SignWriting"},
aliases = {"Sutton SignWriting"},
Line 2,404: Line 2,686:
m["Shaw"] = process_ranges{
m["Shaw"] = process_ranges{
"Shavian",
"Shavian",
1970098,
aliases = {"Shaw"},
aliases = {"Shaw"},
ranges = {
ranges = {
Line 2,412: Line 2,695:
m["Shrd"] = process_ranges{
m["Shrd"] = process_ranges{
"Sharada",
"Sharada",
2047117,
"abugida",
"abugida",
ranges = {
ranges = {
Line 2,423: Line 2,707:
0x11180, 0x111DF,
0x11180, 0x111DF,
},
},
translit = "Shrd-translit",
}
}


m["Shui"] = {
m["Shui"] = {
"Sui",
"Sui",
752854,
"logography",
"logography",
spaces = false,
spaces = false,
Line 2,434: Line 2,720:
m["Sidd"] = process_ranges{
m["Sidd"] = process_ranges{
"Siddham",
"Siddham",
250379,
"abugida",
"abugida",
ranges = {
ranges = {
Line 2,439: Line 2,726:
0x115B8, 0x115DD,
0x115B8, 0x115DD,
},
},
translit = "Sidd-translit",
}
}


m["Sidt"] = {
m["Sidt"] = {
"Sidetic",
"Sidetic",
36659,
"alphabet",
"alphabet",
direction = "rtl",
direction = "rtl",
Line 2,449: Line 2,738:


m["Sind"] = process_ranges{
m["Sind"] = process_ranges{
"Khudawadi",
"Khudabadi",
6402810,
"abugida",
"abugida",
aliases = {"Khudabadi"},
aliases = {"Khudawadi"},
ranges = {
ranges = {
0x0964, 0x0965,
0x0964, 0x0965,
Line 2,466: Line 2,756:
m["Sinh"] = process_ranges{
m["Sinh"] = process_ranges{
"Sinhalese",
"Sinhalese",
1574992,
"abugida",
"abugida",
aliases = {"Sinhala"},
aliases = {"Sinhala"},
Line 2,493: Line 2,784:
m["Sogd"] = process_ranges{
m["Sogd"] = process_ranges{
"Sogdian",
"Sogdian",
578359,
"abjad",
"abjad",
ranges = {
ranges = {
Line 2,503: Line 2,795:
m["Sogo"] = process_ranges{
m["Sogo"] = process_ranges{
"Old Sogdian",
"Old Sogdian",
72403254,
"abjad",
"abjad",
ranges = {
ranges = {
Line 2,512: Line 2,805:
m["Sora"] = process_ranges{
m["Sora"] = process_ranges{
"Sorang Sompeng",
"Sorang Sompeng",
7563292,
aliases = {"Sora Sompeng"},
aliases = {"Sora Sompeng"},
ranges = {
ranges = {
Line 2,521: Line 2,815:
m["Soyo"] = process_ranges{
m["Soyo"] = process_ranges{
"Soyombo",
"Soyombo",
8009382,
"abugida",
"abugida",
ranges = {
ranges = {
Line 2,529: Line 2,824:
m["Sund"] = process_ranges{
m["Sund"] = process_ranges{
"Sundanese",
"Sundanese",
51589,
"abugida",
"abugida",
ranges = {
ranges = {
Line 2,536: Line 2,832:
}
}


m["Sunu"] = {
m["Sunu"] = process_ranges{
"Sunuwar",
"Sunuwar",
109984965,
"alphabet",
"alphabet",
-- Not in Unicode
ranges = {
0x11BC0, 0x11BE1,
0x11BF0, 0x11BF9,
},
}
}


m["Sylo"] = process_ranges{
m["Sylo"] = process_ranges{
"Syloti Nagri",
"Sylheti Nagri",
144128,
"abugida",
"abugida",
aliases = {"Sylheti Nagari"},
aliases = {"Sylheti Nāgarī", "Syloti Nagri"},
ranges = {
ranges = {
0x0964, 0x0965,
0x0964, 0x0965,
Line 2,555: Line 2,856:
m["Syrc"] = process_ranges{
m["Syrc"] = process_ranges{
"Syriac",
"Syriac",
"abjad", -- more precisely, impure abjad
26567,
"abjad", -- more precisely, impure abjad
ranges = {
ranges = {
0x060C, 0x060C,
0x060C, 0x060C,
Line 2,577: Line 2,879:
m["Tagb"] = process_ranges{
m["Tagb"] = process_ranges{
"Tagbanwa",
"Tagbanwa",
977444,
"abugida",
"abugida",
ranges = {
ranges = {
Line 2,588: Line 2,891:
m["Takr"] = process_ranges{
m["Takr"] = process_ranges{
"Takri",
"Takri",
759202,
"abugida",
"abugida",
ranges = {
ranges = {
Line 2,603: Line 2,907:
m["Tale"] = process_ranges{
m["Tale"] = process_ranges{
"Tai Nüa",
"Tai Nüa",
2566326,
"abugida",
"abugida",
aliases = {"Tai Nuea", "New Tai Nüa", "New Tai Nuea", "Dehong Dai", "Tai Dehong", "Tai Le"},
aliases = {"Tai Nuea", "New Tai Nüa", "New Tai Nuea", "Dehong Dai", "Tai Dehong", "Tai Le"},
Line 2,615: Line 2,920:
m["Talu"] = process_ranges{
m["Talu"] = process_ranges{
"New Tai Lue",
"New Tai Lue",
3498863,
"abugida",
"abugida",
ranges = {
ranges = {
Line 2,627: Line 2,933:
m["Taml"] = process_ranges{
m["Taml"] = process_ranges{
"Tamil",
"Tamil",
26803,
"abugida",
"abugida",
ranges = {
ranges = {
Line 2,663: Line 2,970:
m["Tang"] = process_ranges{
m["Tang"] = process_ranges{
"Tangut",
"Tangut",
1373610,
"logography, syllabary",
"logography, syllabary",
ranges = {
ranges = {
0x31EF, 0x31EF,
0x16FE0, 0x16FE0,
0x16FE0, 0x16FE0,
0x17000, 0x187F7,
0x17000, 0x187F7,
Line 2,671: Line 2,980:
},
},
spaces = false,
spaces = false,
translit = "txg-translit",
}
}


m["Tavt"] = process_ranges{
m["Tavt"] = process_ranges{
"Tai Viet",
"Tai Viet",
11818517,
"abugida",
"abugida",
ranges = {
ranges = {
Line 2,683: Line 2,994:
}
}


m["Tayo"] = {
m["Tayo"] = process_ranges{
"Lai Tay",
"Lai Tay",
16306701,
"abugida",
"abugida",
aliases = {"Tai Yo"},
aliases = {"Tai Yo"},
direction = "vertical-rtl",
direction = "vertical-rtl",
-- Not in Unicode
ranges = {
0x1E6C0, 0x1E6DE,
0x1E6E0, 0x1E6F5,
0x1E6FE, 0x1E6FF,
},
spaces = false,
}
}


m["Telu"] = process_ranges{
m["Telu"] = process_ranges{
"Telugu",
"Telugu",
570450,
"abugida",
"abugida",
ranges = {
ranges = {
Line 2,721: Line 3,039:
m["Teng"] = {
m["Teng"] = {
"Tengwar",
"Tengwar",
473725,
}
}


m["Tfng"] = process_ranges{
m["Tfng"] = process_ranges{
"Tifinagh",
"Tifinagh",
208503,
"abjad, alphabet",
"abjad, alphabet",
ranges = {
ranges = {
Line 2,731: Line 3,051:
0x2D7F, 0x2D7F,
0x2D7F, 0x2D7F,
},
},
otherNames = {"Libyco-Berber", "Berber"}, -- per Wikipedia, Libyco-Berber is the parent
other_names = {"Libyco-Berber", "Berber"}, -- per Wikipedia, Libyco-Berber is the parent
}
}


m["Tglg"] = process_ranges{
m["Tglg"] = process_ranges{
"Baybayin",
"Baybayin",
812124,
"abugida",
"abugida",
aliases = {"Tagalog"},
aliases = {"Tagalog"},
varieties = {"Kur-itan"},
ranges = {
ranges = {
0x1700, 0x1715,
0x1700, 0x1715,
Line 2,747: Line 3,069:
m["Thaa"] = process_ranges{
m["Thaa"] = process_ranges{
"Thaana",
"Thaana",
877906,
"abugida",
"abugida",
ranges = {
ranges = {
Line 2,762: Line 3,085:
m["Thai"] = process_ranges{
m["Thai"] = process_ranges{
"Thai",
"Thai",
236376,
"abugida",
"abugida",
ranges = {
ranges = {
Line 2,770: Line 3,094:
}
}


m["Tibt"] = process_ranges{
do
"Tibetan",
local Tibt_displaytext = {
"abugida",
from = {"ༀ", "༌", "།།", "༚༚", "༚༝", "༝༚", "༝༝", "ཷ", "ཹ", "ེེ", "ོོ"},
ranges = {
to = {"ཨོཾ", "་", "༎", "༛", "༟", "࿎", "༞", "ྲཱྀ", "ླཱྀ", "ཻ", "ཽ"}
0x0F00, 0x0F47,
}
0x0F49, 0x0F6C,
0x0F71, 0x0F97,
0x0F99, 0x0FBC,
0x0FBE, 0x0FCC,
0x0FCE, 0x0FD4,
0x0FD9, 0x0FDA,
},
normalizationFixes = handle_normalization_fixes{
combiningClasses = {["༹"] = 1},
from = {"ཷ", "ཹ"},
to = {"ྲཱྀ", "ླཱྀ"}
},
}


m["sit-tam-Tibt"] = {
m["Tibt"] = process_ranges{
"Tamyig",
"Tibetan",
m["Tibt"][2],
46861,
ranges = m["Tibt"].ranges,
"abugida",
characters = m["Tibt"].characters,
ranges = {
parent = "Tibt",
0x0F00, 0x0F47,
normalizationFixes = m["Tibt"].normalizationFixes,
0x0F49, 0x0F6C,
0x0F71, 0x0F97,
0x0F99, 0x0FBC,
0x0FBE, 0x0FCC,
0x0FCE, 0x0FD4,
0x0FD9, 0x0FDA,
0x3008, 0x300B,
},
normalizationFixes = handle_normalization_fixes{
combiningClasses = {["༹"] = 1},
from = {"ཷ", "ཹ"},
to = {"ྲཱྀ", "ླཱྀ"}
},
display_text = Tibt_displaytext,
strip_diacritics = Tibt_displaytext,
sort_key = "Tibt-sortkey",
translit = "Tibt-translit",
}
}
m["sit-tam-Tibt"] = {
"Tamyig",
109875213,
m["Tibt"][3],
-- There is no inheritance of properties currently implemented for scripts. Per [[User:Theknightwho]], this
-- is because it's tricky to do since there are several types of child scripts: those that are mere display
-- variants (like fa-Arab, kk-Arab), which should be eliminated in favor of CSS language selectors to
-- handle the font differences; those that are genuinely different scripts that happen to share the same
-- Unicode codepoints but have mostly different properties (e.g. Manchu vs. Mongolian); and those that are
-- somewhere in between (like Tamyig vs. Tibetan). As a result, we currently have to manually specify
-- which properties we want inherited as follows.
ranges = m["Tibt"].ranges,
characters = m["Tibt"].characters,
parent = "Tibt",
normalizationFixes = m["Tibt"].normalizationFixes,
display_text = m["Tibt"].display_text,
strip_diacritics = m["Tibt"].strip_diacritics,
sort_key = m["Tibt"].sort_key,
translit = m["Tibt"].translit,
}
end


m["Tirh"] = process_ranges{
m["Tirh"] = process_ranges{
"Tirhuta",
"Tirhuta",
1765752,
"abugida",
"abugida",
ranges = {
ranges = {
Line 2,817: Line 3,167:
m["Tnsa"] = process_ranges{
m["Tnsa"] = process_ranges{
"Tangsa",
"Tangsa",
105576311,
"alphabet",
"alphabet",
ranges = {
ranges = {
Line 2,824: Line 3,175:
}
}


m["Todr"] = {
m["Todr"] = process_ranges{
"Todhri",
"Todhri",
10274731,
"alphabet",
"alphabet",
direction = "rtl",
direction = "rtl",
-- Not in Unicode
ranges = {
0x105C0, 0x105F3,
},
}
}


m["Tols"] = {
m["Tols"] = {
"Tolong Siki",
"Tolong Siki",
4459822,
"alphabet",
"alphabet",
-- Not in Unicode
-- Not in Unicode
Line 2,839: Line 3,194:
m["Toto"] = process_ranges{
m["Toto"] = process_ranges{
"Toto",
"Toto",
104837516,
"abugida",
"abugida",
ranges = {
ranges = {
Line 2,845: Line 3,201:
}
}


m["Tutg"] = {
m["Tutg"] = process_ranges{
"Tigalari",
"Tigalari",
2604990,
"abugida",
"abugida",
aliases = {"Tulu"},
aliases = {"Tulu"},
-- Not in Unicode
ranges = {
}
0x1CF2, 0x1CF2,
0x1CF4, 0x1CF4,
0xA8F1, 0xA8F1,
0x11380, 0x11389,
0x1138B, 0x1138B,
0x1138E, 0x1138E,
0x11390, 0x113B5,
0x113B7, 0x113C0,
0x113C2, 0x113C2,
0x113C5, 0x113C5,
0x113C7, 0x113CA,
0x113CC, 0x113D5,
0x113D7, 0x113D8,
0x113E1, 0x113E2,
},
}


m["Ugar"] = process_ranges{
m["Ugar"] = process_ranges{
"Ugaritic",
"Ugaritic",
332652,
"abjad",
"abjad",
ranges = {
ranges = {
Line 2,863: Line 3,236:
m["Vaii"] = process_ranges{
m["Vaii"] = process_ranges{
"Vai",
"Vai",
523078,
"syllabary",
"syllabary",
ranges = {
ranges = {
Line 2,871: Line 3,245:
m["Visp"] = {
m["Visp"] = {
"Visible Speech",
"Visible Speech",
1303365,
"alphabet",
"alphabet",
-- Not in Unicode
-- Not in Unicode
Line 2,877: Line 3,252:
m["Vith"] = process_ranges{
m["Vith"] = process_ranges{
"Vithkuqi",
"Vithkuqi",
3301993,
"alphabet",
"alphabet",
ranges = {
ranges = {
Line 2,893: Line 3,269:
m["Wara"] = process_ranges{
m["Wara"] = process_ranges{
"Varang Kshiti",
"Varang Kshiti",
79199,
aliases = {"Warang Citi"},
aliases = {"Warang Citi"},
ranges = {
ranges = {
Line 2,903: Line 3,280:
m["Wcho"] = process_ranges{
m["Wcho"] = process_ranges{
"Wancho",
"Wancho",
33713728,
"alphabet",
"alphabet",
ranges = {
ranges = {
Line 2,912: Line 3,290:
m["Wole"] = {
m["Wole"] = {
"Woleai",
"Woleai",
6643710,
"syllabary",
"syllabary",
-- Not in Unicode
-- Not in Unicode
Line 2,918: Line 3,297:
m["Xpeo"] = process_ranges{
m["Xpeo"] = process_ranges{
"Old Persian",
"Old Persian",
1471822,
ranges = {
ranges = {
0x103A0, 0x103C3,
0x103A0, 0x103C3,
Line 2,926: Line 3,306:
m["Xsux"] = process_ranges{
m["Xsux"] = process_ranges{
"Cuneiform",
"Cuneiform",
401,
aliases = {"Sumero-Akkadian Cuneiform"},
aliases = {"Sumero-Akkadian Cuneiform"},
ranges = {
ranges = {
Line 2,937: Line 3,318:
m["Yezi"] = process_ranges{
m["Yezi"] = process_ranges{
"Yezidi",
"Yezidi",
13175481,
"alphabet",
"alphabet",
ranges = {
ranges = {
Line 2,952: Line 3,334:
m["Yiii"] = process_ranges{
m["Yiii"] = process_ranges{
"Yi",
"Yi",
1197646,
"syllabary",
"syllabary",
ranges = {
ranges = {
Line 2,966: Line 3,349:
m["Zanb"] = process_ranges{
m["Zanb"] = process_ranges{
"Zanabazar Square",
"Zanabazar Square",
50809208,
"abugida",
ranges = {
ranges = {
0x11A00, 0x11A47,
0x11A00, 0x11A47,
Line 2,973: Line 3,358:
m["Zmth"] = process_ranges{
m["Zmth"] = process_ranges{
"mathematical notation",
"mathematical notation",
1140046,
ranges = {
ranges = {
0x00AC, 0x00AC,
0x00AC, 0x00AC,
Line 3,110: Line 3,496:
},
},
translit = false,
translit = false,
character_category = "Mathematical notation symbols", -- ?
}
 
m["Zname"] = process_ranges{
"Znamenny musical notation",
965834,
"pictography",
ranges = {
0x1CF00, 0x1CF2D,
0x1CF30, 0x1CF46,
0x1CF50, 0x1CFC3,
},
ietf_subtag = "Zsym",
translit = false,
}
}


m["Zsym"] = process_ranges{
m["Zsym"] = process_ranges{
"symbol",
"symbolic",
80071,
"pictography",
"pictography",
ranges = {
ranges = {
Line 3,209: Line 3,608:
m["Zyyy"] = {
m["Zyyy"] = {
"undetermined",
"undetermined",
104839687,
-- This should not have any characters listed, probably
-- This should not have any characters listed, probably
translit = false,
translit = false,
Line 3,216: Line 3,616:
m["Zzzz"] = {
m["Zzzz"] = {
"uncoded",
"uncoded",
104839675,
-- This should not have any characters listed
-- This should not have any characters listed
translit = false,
translit = false,
Line 3,225: Line 3,626:
m["Hrkt"] = process_ranges{
m["Hrkt"] = process_ranges{
"Kana",
"Kana",
187659,
"syllabary",
"syllabary",
aliases = {"Japanese syllabaries"},
aliases = {"Japanese syllabaries"},
Line 3,236: Line 3,638:
m["Jpan"] = process_ranges{
m["Jpan"] = process_ranges{
"Japanese",
"Japanese",
190502,
"logography, syllabary",
"logography, syllabary",
ranges = union(
ranges = union(
Line 3,248: Line 3,651:
m["Kore"] = process_ranges{
m["Kore"] = process_ranges{
"Korean",
"Korean",
711797,
"logography, syllabary",
"logography, syllabary",
ranges = union(
ranges = union(
Line 3,254: Line 3,658:
m["Latn"].ranges
m["Latn"].ranges
),
),
-- `漢字(한자)`→`漢字`
-- `가-나-다`→`가나다`, `가--나--다`→`가-나-다`
-- `온돌(溫突/溫堗)`→`온돌` ([[ondol]])
strip_diacritics = {
remove_diacritics = u(0x302E) .. u(0x302F),
from = {"([" .. m["Hani"].characters .. "])%(.-%)", "^%-", "%-$", "%-(%-?)", "\1", "%([" .. m["Hani"].characters .. "/]+%)"},
to = {"%1", "\1", "\1", "%1", "-"}
}
}
}


return m
--Constructed languages
m["Ayer"] = process_ranges{
"Tahano Hikamu",
nil,
"abugida",
ranges = {
0x0041, 0x005A,
0x0061, 0x007A,
0x002A, 0x002A,
0x00F1, 0x00F1,
0x00D1, 0x00D1,
0x0294, 0x0294,
0x0259, 0x0259,
0x018F, 0x018F,
0xA736, 0xA737,
0x0026, 0x0026,
0x002B, 0x002D,
0x005B, 0x005B,
0x005D, 0x005D,
0x00A8, 0x00A8,
0x00AF, 0x00AF,
0x00B2, 0x00B2,
0x00B9, 0x00B9,
0x02B0, 0x2B2,
0x02C0, 0x02C0,
0x02D0, 0x02D0,
},
character_category = false,
}
 
m["Jovl"] = process_ranges{
"Jovlish",
nil,
"alphabet",
ranges = {
0x0041, 0x005A,
0x0061, 0x007A,
0x00AA, 0x00AA,
0x00BA, 0x00BA,
0x00C0, 0x00D6,
0x00D8, 0x00F6,
0x00F8, 0x02B8,
0x022B, 0x022B,
0x02C0, 0x02C1,
0x02E0, 0x02E4,
0x0363, 0x036F,
0x039E, 0x039E,
0x03A8, 0x03A8,
0x03BE, 0x03BE,
0x03C8, 0x03C8,
0x0485, 0x0486,
0x0951, 0x0952,
0x10FB, 0x10FB,
0x1D00, 0x1D25,
0x1D2C, 0x1D5C,
0x1D62, 0x1D65,
0x1D6B, 0x1D77,
0x1D79, 0x1DBE,
0x1DF8, 0x1DF8,
0x1E00, 0x1EFF,
0x202F, 0x202F,
0x2071, 0x2071,
0x207F, 0x207F,
0x2090, 0x209C,
0x20F0, 0x20F0,
0x2100, 0x2125,
0x2128, 0x2128,
0x212A, 0x2134,
0x2139, 0x213B,
0x2141, 0x214E,
0x2160, 0x2188,
0x2C60, 0x2C7F,
0xA700, 0xA707,
0xA722, 0xA787,
0xA78B, 0xA7CD,
0xA7D0, 0xA7D1,
0xA7D3, 0xA7D3,
0xA7D5, 0xA7DC,
0xA7F2, 0xA7FF,
0xA92E, 0xA92E,
0xAB30, 0xAB5A,
0xAB5C, 0xAB64,
0xAB66, 0xAB69,
0xFB00, 0xFB06,
0xFF21, 0xFF3A,
0xFF41, 0xFF5A,
0x10780, 0x10785,
0x10787, 0x107B0,
0x107B2, 0x107BA,
0x1DF00, 0x1DF1E,
0x1DF25, 0x1DF2A,
},
character_category = false,
}
 
m["Gthv"] = process_ranges{
"Gothevian",
nil,
"alphabet",
ranges = {
    0x0041, 0x005A,
    0x0061, 0x007A,
    0x00C1, 0x00C4,
    0x00C8, 0x00CB,
    0x00CD, 0x00CD,
    0x00CF, 0x00CF,
    0x00D2, 0x00D4,
    0x00D6, 0x00D6,
    0x00DA, 0x00DC,
    0x00DD, 0x00DD,
    0x00E1, 0x00E4,
    0x00E8, 0x00EB,
    0x00ED, 0x00ED,
    0x00EF, 0x00EF,
    0x00F2, 0x00F4,
    0x00F6, 0x00F6,
    0x00FA, 0x00FC,
    0x00FD, 0x00FD,
    0x00FF, 0x00FF,
    0x0110, 0x0111,
    0x0160, 0x0161,
    0x0178, 0x0178,
    0x017D, 0x017E,
    0x0186, 0x0186,
    0x0190, 0x0190,
    0x0195, 0x0195,
    0x01F6, 0x01F6,
    0x0254, 0x0254,
    0x025B, 0x025B,
    0x0398, 0x0398,
    0x039E, 0x039E,
    0x03A8, 0x03A8,
    0x03B8, 0x03B8,
    0x03BE, 0x03BE,
    0x03C8, 0x03C8,
},
character_category = false,
}
 
m["Roka"] = process_ranges{
"Rokadong Curakjang",
nil,
"abugida",
ranges = {
0x0041, 0x005A,
0x0061, 0x007A,
0x0022, 0x0022,
0x0027, 0x0027,
0x002A, 0x002A,
0x002D, 0x002D,
0x005B, 0x005D,
0x007B, 0x007B,
0x007D, 0x007D
},
character_category = false,
}
m["Rsnold"] = process_ranges{
"Old Raysian",
nil,
"alphabet",
ranges = {
0x0041, 0x007A
},
character_category = false,
}
m["Pann"] = process_ranges{
"Pannonian",
nil,
"alphabet",
ranges = {
0x0041, 0x005A,
0x0061, 0x007A,
0x1D9C, 0x1D9D,
0x1D47, 0x1D4B,
0x02E1, 0x02E3,
0x0410, 0x044F,
0x0404, 0x0454,
0x04AE, 0x04B1,
0x0250, 0x0254,
0x0265, 0x0278,
0x028C, 0x028D,
0x0224, 0x0225,
0x01BA, 0x01BE,
0x019A, 0x01A3,
0x012D, 0x0131,
0xA793, 0xA794
},
character_category = false,
}
 
m["Teul"] = process_ranges{
"Teulgi",
nil,
"alphabet",
ranges = m["Latn"].ranges,
characters = m["Latn"].characters,
character_category = false,
}
 
m["Tugv"] = process_ranges{
"Tuġvut",
nil,
"alphabet",
ranges = m["Latn"].ranges,
characters = m["Latn"].characters,
character_category = false,
}
 
m["Ucrn"] = process_ranges{
"Draconian",
nil,
"alphabet",
ranges = {
    0x0020, 0x0021,
    0x0023, 0x0023,
    0x0027, 0x0027,
    0x0030, 0x0034,
    0x0040, 0x0040,
    0x0047, 0x0048,
    0x004B, 0x004B,
    0x0050, 0x0050,
    0x0058, 0x0058,
    0x0066, 0x0067,
    0x0069, 0x006A,
    0x006F, 0x0072,
    0x0079, 0x0079,
    0x010D, 0x010D,
    0x014B, 0x014B,
    0x01A9, 0x01A9,
    0x01E7, 0x01E7,
    0x0238, 0x0238,
    0x024F, 0x024F,
    0x1EFA, 0x1EFB,
};
character_category = false,
}
 
 
return require("Module:languages").finalizeData(m, "script")
Retrieved from "https://linguifex.com/wiki/Module:scripts/data"