模組:Scripts/data
該模塊包含Wiktionary上所有文字代碼的定義和元數據。有關更多信息，請參見en:Wiktionary:Scripts。
此模塊不得使用require導入。正確的導入方式如下：
local m_scripts = mw.loadData("Module:scripts")
這樣可以確保每個頁面僅加載一次數據，而不是像通常那樣為每個模塊調用加載一次。
要從模板訪問此數據，請使用Module:script utilities。
必需值
表中的每個段落（entry）必須包含以下屬性：
canonicalName- 文字的“規範”（canonical）名稱，即維基詞典條目和類分類名稱中所使用的名稱。
可選值
otherNames- 此文字除了規範名稱以外的其他名稱。
characters- A Lua character class that matches on any character that belongs to this script. The character classes are the same as those in Lua search/replace patterns, but without the surrounding
[ ](these are implicitly added). They also resemble those found in regular expressions. - In its simplest form, the character class can just be a list of all the characters in the script (Example:
"ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz"). But it's easier to describe using character ranges, especially when the script contains many dozens or even hundreds of different characters. Character ranges are given with only the first and last character, and separated by a hyphen-. The set then implicitly includes all characters whose Unicode codepoints are in between the two given characters (Example:"A-Za-z"). character_category- Used by Module:character info. If
false, prevents{{character info/new}}from adding acharacterscategory, such as Category:Latin script characters. systems- The categories of writing system to which the script belongs. See Module:writing_systems/data for a list of supported values. At the moment, this is only used by Module:category tree/scriptcatboiler. The system will only be displayed if there is only one category. See Category:拉丁文字 for an example.
--[=[
When adding new scripts to this file, please don't forget to add
style definitons for the script in [[MediaWiki:Gadget-LanguagesAndScripts.css]].
]=]
local concat = table.concat
local insert = table.insert
local ipairs = ipairs
local next = next
local remove = table.remove
local select = select
local sort = table.sort
-- 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
------------------------------------------------------------------------------------
--
-- Helper functions
--
------------------------------------------------------------------------------------
-- Note: a[2] > b[2] means opens are sorted before closes if otherwise equal.
local function sort_ranges(a, b)
return a[1] < b[1] or a[1] == b[1] and a[2] > b[2]
end
-- Returns the union of two or more range tables.
local function union(...)
local ranges = {}
for i = 1, select("#", ...) do
local argt = select(i, ...)
for j, v in ipairs(argt) do
insert(ranges, {v, j % 2 == 1 and 1 or -1})
end
end
sort(ranges, sort_ranges)
local ret, i = {}, 0
for _, range in ipairs(ranges) do
i = i + range[2]
if i == 0 and range[2] == -1 then -- close
insert(ret, range[1])
elseif i == 1 and range[2] == 1 then -- open
if ret[#ret] and range[1] <= ret[#ret] + 1 then
remove(ret) -- merge adjacent ranges
else
insert(ret, range[1])
end
end
end
return ret
end
-- Adds the `characters` key, which is determined by a script's `ranges` table.
local function process_ranges(sc)
local ranges, chars = sc.ranges, {}
for i = 2, #ranges, 2 do
if ranges[i] == ranges[i - 1] then
insert(chars, u(ranges[i]))
else
insert(chars, u(ranges[i - 1]))
if ranges[i] > ranges[i - 1] + 1 then
insert(chars, "-")
end
insert(chars, u(ranges[i]))
end
end
sc.characters = concat(chars)
ranges.n = #ranges
return sc
end
local function handle_normalization_fixes(fixes)
local combiningClasses = fixes.combiningClasses
if combiningClasses then
local chars, i = {}, 0
for char in next, combiningClasses do
i = i + 1
chars[i] = char
end
fixes.combiningClassCharacters = concat(chars)
end
return fixes
end
------------------------------------------------------------------------------------
--
-- Data
--
------------------------------------------------------------------------------------
local m = {}
m["Adlm"] = process_ranges{
"阿德拉姆文",
19606346,
"全音素文字",
aliases = {"Adlam"},
ranges = {
0x061F, 0x061F,
0x0640, 0x0640,
0x1E900, 0x1E94B,
0x1E950, 0x1E959,
0x1E95E, 0x1E95F,
},
capitalized = true,
direction = "rtl",
}
m["Afak"] = {
"阿法卡文",
382019,
"音節文字",
aliases = {"Afaka"},
-- Not in Unicode
}
m["Aghb"] = process_ranges{
"高加索阿爾巴尼亞文",
2495716,
"全音素文字",
aliases = {"Caucasian Albanian"},
ranges = {
0x10530, 0x10563,
0x1056F, 0x1056F,
},
}
m["Ahom"] = process_ranges{
"阿洪姆文",
2839633,
"元音附標文字",
aliases = {"Ahom"},
ranges = {
0x11700, 0x1171A,
0x1171D, 0x1172B,
0x11730, 0x11746,
},
}
m["Arab"] = process_ranges{
"阿拉伯文",
1828555,
"輔音音素文字", -- more precisely, impure abjad
aliases = {"Arabic"},
varieties = {"Jawi", "Perso-Arabic", "Sulat Sūg"},
ranges = {
0x0600, 0x06FF,
0x0750, 0x077F,
0x0870, 0x088E,
0x0890, 0x0891,
0x0897, 0x08E1,
0x08E3, 0x08FF,
0xFB50, 0xFBC2,
0xFBD3, 0xFD8F,
0xFD92, 0xFDC7,
0xFDCF, 0xFDCF,
0xFDF0, 0xFDFF,
0xFE70, 0xFE74,
0xFE76, 0xFEFC,
0x102E0, 0x102FB,
0x10E60, 0x10E7E,
0x10EC2, 0x10EC4,
0x10EFC, 0x10EFF,
0x1EE00, 0x1EE03,
0x1EE05, 0x1EE1F,
0x1EE21, 0x1EE22,
0x1EE24, 0x1EE24,
0x1EE27, 0x1EE27,
0x1EE29, 0x1EE32,
0x1EE34, 0x1EE37,
0x1EE39, 0x1EE39,
0x1EE3B, 0x1EE3B,
0x1EE42, 0x1EE42,
0x1EE47, 0x1EE47,
0x1EE49, 0x1EE49,
0x1EE4B, 0x1EE4B,
0x1EE4D, 0x1EE4F,
0x1EE51, 0x1EE52,
0x1EE54, 0x1EE54,
0x1EE57, 0x1EE57,
0x1EE59, 0x1EE59,
0x1EE5B, 0x1EE5B,
0x1EE5D, 0x1EE5D,
0x1EE5F, 0x1EE5F,
0x1EE61, 0x1EE62,
0x1EE64, 0x1EE64,
0x1EE67, 0x1EE6A,
0x1EE6C, 0x1EE72,
0x1EE74, 0x1EE77,
0x1EE79, 0x1EE7C,
0x1EE7E, 0x1EE7E,
0x1EE80, 0x1EE89,
0x1EE8B, 0x1EE9B,
0x1EEA1, 0x1EEA3,
0x1EEA5, 0x1EEA9,
0x1EEAB, 0x1EEBB,
0x1EEF0, 0x1EEF1,
},
direction = "rtl",
normalizationFixes = handle_normalization_fixes{
from = {"ٳ"},
to = {"اٟ"}
},
}
m["Aran"] = {
{
hnd = "沙穆基文", -- Southern Hindko
hno = "沙穆基文", -- Northern Hindko
["inc-opa"] = "沙穆基文", -- Old Punjabi
lah = "沙穆基文", -- Lahnda
pa = "沙穆基文", -- Punjabi
phr = "沙穆基文", -- Pahari-Potwari
skr = "沙穆基文", -- Saraiki
default = "阿拉伯文",
},
1133121, -- FIXME: 133800 for Shahmukhi
m["Arab"][3],
ranges = m["Arab"].ranges,
characters = m["Arab"].characters,
aliases = {"Arabic", "Shahmukhi", "Nastaliq", "Nastaleeq"},
direction = "rtl",
parent = "Arab",
normalizationFixes = m["Arab"].normalizationFixes,
}
m["Armi"] = process_ranges{
"帝國亞拉姆文字",
26978,
"輔音音素文字",
aliases = {"Imperial Aramaic"},
ranges = {
0x10840, 0x10855,
0x10857, 0x1085F,
},
direction = "rtl",
}
m["Armn"] = process_ranges{
"亞美尼亞文",
11932,
"全音素文字",
aliases = {"Armenian"},
ranges = {
0x0531, 0x0556,
0x0559, 0x058A,
0x058D, 0x058F,
0xFB13, 0xFB17,
},
capitalized = true,
translit = "Armn-translit",
}
m["Avst"] = process_ranges{
"阿維斯陀文",
790681,
"全音素文字",
aliases = {"Avestan"},
ranges = {
0x10B00, 0x10B35,
0x10B39, 0x10B3F,
},
direction = "rtl",
}
m["pal-Avst"] = {
"帕贊德文",
4925073,
m["Avst"][3],
aliases = {"Pazend"},
ranges = m["Avst"].ranges,
characters = m["Avst"].characters,
direction = "rtl",
parent = "Avst",
}
m["Bali"] = process_ranges{
"峇里文字",
804984,
"元音附標文字",
aliases = {"Balinese"},
ranges = {
0x1B00, 0x1B4C,
0x1B4E, 0x1B7F,
},
}
m["Bamu"] = process_ranges{
"巴姆穆文字",
806024,
"音節文字",
aliases = {"Bamum"},
ranges = {
0xA6A0, 0xA6F7,
0x16800, 0x16A38,
},
}
m["Bass"] = process_ranges{
"巴薩文",
810458,
"全音素文字",
aliases = {"Bassa", "Bassa Vah", "Vah"},
ranges = {
0x16AD0, 0x16AED,
0x16AF0, 0x16AF5,
},
}
m["Batk"] = process_ranges{
"巴塔克文",
51592,
"元音附標文字",
aliases = {"Batak"},
ranges = {
0x1BC0, 0x1BF3,
0x1BFC, 0x1BFF,
},
}
m["Beng"] = process_ranges{
"孟加拉文",
756802,
"元音附標文字",
aliases = {"Bengali"},
ranges = {
0x0951, 0x0952,
0x0964, 0x0965,
0x0980, 0x0983,
0x0985, 0x098C,
0x098F, 0x0990,
0x0993, 0x09A8,
0x09AA, 0x09B0,
0x09B2, 0x09B2,
0x09B6, 0x09B9,
0x09BC, 0x09C4,
0x09C7, 0x09C8,
0x09CB, 0x09CE,
0x09D7, 0x09D7,
0x09DC, 0x09DD,
0x09DF, 0x09E3,
0x09E6, 0x09EF,
0x09F2, 0x09FE,
0x1CD0, 0x1CD0,
0x1CD2, 0x1CD2,
0x1CD5, 0x1CD6,
0x1CD8, 0x1CD8,
0x1CE1, 0x1CE1,
0x1CEA, 0x1CEA,
0x1CED, 0x1CED,
0x1CF2, 0x1CF2,
0x1CF5, 0x1CF7,
0xA8F1, 0xA8F1,
},
normalizationFixes = handle_normalization_fixes{
from = {"অা", "ঋৃ", "ঌৢ"},
to = {"আ", "ৠ", "ৡ"}
},
}
m["as-Beng"] = process_ranges{
"阿薩姆文",
191272,
m["Beng"][3],
aliases = {"Assamese"},
other_names = {"Eastern Nagari"},
ranges = {
0x0951, 0x0952,
0x0964, 0x0965,
0x0980, 0x0983,
0x0985, 0x098C,
0x098F, 0x0990,
0x0993, 0x09A8,
0x09AA, 0x09AF,
0x09B2, 0x09B2,
0x09B6, 0x09B9,
0x09BC, 0x09C4,
0x09C7, 0x09C8,
0x09CB, 0x09CE,
0x09D7, 0x09D7,
0x09DC, 0x09DD,
0x09DF, 0x09E3,
0x09E6, 0x09FE,
0x1CD0, 0x1CD0,
0x1CD2, 0x1CD2,
0x1CD5, 0x1CD6,
0x1CD8, 0x1CD8,
0x1CE1, 0x1CE1,
0x1CEA, 0x1CEA,
0x1CED, 0x1CED,
0x1CF2, 0x1CF2,
0x1CF5, 0x1CF7,
0xA8F1, 0xA8F1,
},
normalizationFixes = m["Beng"].normalizationFixes,
}
m["Bhks"] = process_ranges{
"拜克舒基文",
17017839,
"元音附標文字",
aliases = {"Bhaiksuki"},
ranges = {
0x11C00, 0x11C08,
0x11C0A, 0x11C36,
0x11C38, 0x11C45,
0x11C50, 0x11C6C,
},
}
m["Blis"] = {
"布列斯符號",
609817,
"語素文字",
aliases = {"Blissymbolic", "Blissymbols"},
-- Not in Unicode
}
m["Bopo"] = process_ranges{
"注音符號",
198269,
"半音節文字",
aliases = {"Zhuyin", "Zhuyin Fuhao", "Bopomofo"},
ranges = {
0x02EA, 0x02EB,
0x3001, 0x3003,
0x3008, 0x3011,
0x3013, 0x301F,
0x302A, 0x302D,
0x3030, 0x3030,
0x3037, 0x3037,
0x30FB, 0x30FB,
0x3105, 0x312F,
0x31A0, 0x31BF,
0xFE45, 0xFE46,
0xFF61, 0xFF65,
},
}
m["Brah"] = process_ranges{
"婆羅米文",
185083,
"元音附標文字",
aliases = {"Brahmi"},
ranges = {
0x11000, 0x1104D,
0x11052, 0x11075,
0x1107F, 0x1107F,
},
normalizationFixes = handle_normalization_fixes{
from = {"𑀅𑀸", "𑀋𑀾", "𑀏𑁂"},
to = {"𑀆", "𑀌", "𑀐"}
},
translit = "Brah-translit",
}
m["Brai"] = process_ranges{
"盲文",
79894,
"全音素文字",
aliases = {"Braille"},
ranges = {
0x2800, 0x28FF,
},
}
m["Bugi"] = process_ranges{
"隆塔拉文",
1074947,
"元音附標文字",
aliases = {"Lontara", "Buginese"},
ranges = {
0x1A00, 0x1A1B,
0x1A1E, 0x1A1F,
0xA9CF, 0xA9CF,
},
}
m["Buhd"] = process_ranges{
"布希德文",
1002969,
"元音附標文字",
aliases = {"Buhid"},
ranges = {
0x1735, 0x1736,
0x1740, 0x1751,
0x1752, 0x1753,
},
}
m["Cakm"] = process_ranges{
"查克馬文",
1059328,
"元音附標文字",
aliases = {"Chakma"},
ranges = {
0x09E6, 0x09EF,
0x1040, 0x1049,
0x11100, 0x11134,
0x11136, 0x11147,
},
}
m["Cans"] = process_ranges{
"加拿大原住民音節文字",
2479183,
"元音附標文字",
aliases = {"Canadian syllabic"},
ranges = {
0x1400, 0x167F,
0x18B0, 0x18F5,
0x11AB0, 0x11ABF,
},
}
m["Cari"] = process_ranges{
"卡利亞字母",
1094567,
"全音素文字",
aliases = {"Carian"},
ranges = {
0x102A0, 0x102D0,
},
}
m["Cham"] = process_ranges{
"占語字母",
1060381,
"元音附標文字",
aliases = {"Cham"},
ranges = {
0xAA00, 0xAA36,
0xAA40, 0xAA4D,
0xAA50, 0xAA59,
0xAA5C, 0xAA5F,
},
}
m["Cher"] = process_ranges{
"切羅基文",
26549,
"音節文字",
aliases = {"Cherokee"},
ranges = {
0x13A0, 0x13F5,
0x13F8, 0x13FD,
0xAB70, 0xABBF,
},
}
m["Chis"] = {
"Chisoi",
123173777,
"元音附標文字",
-- Not in Unicode
}
m["Chrs"] = process_ranges{
"花剌子模文",
72386710,
"輔音音素文字",
aliases = {"Khwarezmian", "Chorasmian"},
ranges = {
0x10FB0, 0x10FCB,
},
direction = "rtl",
}
m["Copt"] = process_ranges{
"科普特文",
321083,
"全音素文字",
aliases = {"Coptic"},
ranges = {
0x03E2, 0x03EF,
0x2C80, 0x2CF3,
0x2CF9, 0x2CFF,
0x102E0, 0x102FB,
},
capitalized = true,
}
m["Cpmn"] = process_ranges{
"塞普勒斯-米諾斯文字",
1751985,
"音節文字",
aliases = {"Cypro-Minoan", "Cypro Minoan"},
ranges = {
0x10100, 0x10101,
0x12F90, 0x12FF2,
},
}
m["Cprt"] = process_ranges{
"賽普勒斯音節文字",
1757689,
"音節文字",
aliases = {"Cypriot"},
ranges = {
0x10100, 0x10102,
0x10107, 0x10133,
0x10137, 0x1013F,
0x10800, 0x10805,
0x10808, 0x10808,
0x1080A, 0x10835,
0x10837, 0x10838,
0x1083C, 0x1083C,
0x1083F, 0x1083F,
},
direction = "rtl",
}
m["Cyrl"] = process_ranges{
"西里爾字母",
8209,
"全音素文字",
aliases = {"Cyrillic"},
ranges = {
0x0400, 0x052F,
0x1C80, 0x1C8A,
0x1D2B, 0x1D2B,
0x1D78, 0x1D78,
0x1DF8, 0x1DF8,
0x2DE0, 0x2DFF,
0x2E43, 0x2E43,
0xA640, 0xA69F,
0xFE2E, 0xFE2F,
0x1E030, 0x1E06D,
0x1E08F, 0x1E08F,
},
capitalized = true,
}
m["Cyrs"] = {
"早期西里爾字母",
442244,
m["Cyrl"][3],
aliases = {"Old Cyrillic", "Early Cyrillic"},
ranges = m["Cyrl"].ranges,
characters = m["Cyrl"].characters,
capitalized = m["Cyrl"].capitalized,
wikipedia_article = "Early Cyrillic alphabet",
normalizationFixes = handle_normalization_fixes{
from = {"Ѹ", "ѹ"},
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{
{
ahr = "Balbodh", -- Ahirani
kfq = "Balbodh", -- Korku
kok = "Balbodh", -- Konkani
mr = "Balbodh", -- Marathi
omr = "Balbodh", -- Old Marathi
vah = "Balbodh", -- Varhadi
default = "天城文",
},
38592, -- FIXME: 16948817 for Balbodh
"元音附標文字",
aliases = {"Devanagari"},
ranges = {
0x0900, 0x097F,
0x1CD0, 0x1CF6,
0x1CF8, 0x1CF9,
0x20F0, 0x20F0,
0xA830, 0xA839,
0xA8E0, 0xA8FF,
0x11B00, 0x11B09,
},
normalizationFixes = handle_normalization_fixes{
from = {"ॆॆ", "ेे", "ाॅ", "ाॆ", "ाꣿ", "ॊॆ", "ाे", "ाै", "ोे", "ाऺ", "ॖॖ", "अॅ", "अॆ", "अा", "एॅ", "एॆ", "एे", "एꣿ", "ऎॆ", "अॉ", "आॅ", "अॊ", "आॆ", "अो", "आे", "अौ", "आै", "ओे", "अऺ", "अऻ", "आऺ", "अाꣿ", "आꣿ", "ऒॆ", "अॖ", "अॗ", "ॶॖ", "्?ा"},
to = {"ꣿ", "ै", "ॉ", "ॊ", "ॏ", "ॏ", "ो", "ौ", "ौ", "ऻ", "ॗ", "ॲ", "ऄ", "आ", "ऍ", "ऎ", "ऐ", "ꣾ", "ꣾ", "ऑ", "ऑ", "ऒ", "ऒ", "ओ", "ओ", "औ", "औ", "औ", "ॳ", "ॴ", "ॴ", "ॵ", "ॵ", "ॵ", "ॶ", "ॷ", "ॷ"}
},
}
m["Diak"] = process_ranges{
"迪維西阿庫魯文",
3307073,
"元音附標文字",
aliases = {"Dhives Akuru", "Dhivehi Akuru", "Dives Akuru", "Divehi Akuru"},
ranges = {
0x11900, 0x11906,
0x11909, 0x11909,
0x1190C, 0x11913,
0x11915, 0x11916,
0x11918, 0x11935,
0x11937, 0x11938,
0x1193B, 0x11946,
0x11950, 0x11959,
},
}
m["Dogr"] = process_ranges{
"多格拉文",
72402987,
"元音附標文字",
aliases = {"Dogra"},
ranges = {
0x0964, 0x096F,
0xA830, 0xA839,
0x11800, 0x1183B,
},
}
m["Dsrt"] = process_ranges{
"德瑟雷特字母",
1200582,
"全音素文字",
aliases = {"Deseret"},
ranges = {
0x10400, 0x1044F,
},
capitalized = true,
}
m["Dupl"] = process_ranges{
"杜普雷速記",
5316025,
"全音素文字",
aliases = {"Duployan"},
ranges = {
0x1BC00, 0x1BC6A,
0x1BC70, 0x1BC7C,
0x1BC80, 0x1BC88,
0x1BC90, 0x1BC99,
0x1BC9C, 0x1BCA3,
},
}
m["Egyd"] = {
"世俗體",
188519,
"輔音音素文字, 語素文字",
aliases = {"Demotic"},
-- Not in Unicode
}
m["Egyh"] = {
"僧侶體",
208111,
"輔音音素文字, 語素文字",
aliases = {"Hieratic"},
-- Unified with Egyptian hieroglyphic in Unicode
}
m["Egyp"] = process_ranges{
"聖書體",
132659,
"輔音音素文字, 語素文字",
aliases = {"Egyptian hieroglyphic"},
ranges = {
0x13000, 0x13455,
0x13460, 0x143FA,
},
varieties = {"Hieratic"},
wikipedia_article = "Egyptian hieroglyphs",
normalizationFixes = handle_normalization_fixes{
from = {"𓃁", "𓆖"},
to = {"𓃀𓂝", "𓆓𓏏𓇿"}
},
}
m["Elba"] = process_ranges{
"艾爾巴桑字母",
1036714,
"全音素文字",
aliases = {"Elbasan"},
ranges = {
0x10500, 0x10527,
},
}
m["Elym"] = process_ranges{
"埃利邁文",
60744423,
"輔音音素文字",
aliases = {"Elymaic"},
ranges = {
0x10FE0, 0x10FF6,
},
direction = "rtl",
}
m["Ethi"] = process_ranges{
"吉茲字母",
257634,
"元音附標文字",
aliases = {"Ethiopic", "Ge'ez", "Geʽez"},
ranges = {
0x1200, 0x1248,
0x124A, 0x124D,
0x1250, 0x1256,
0x1258, 0x1258,
0x125A, 0x125D,
0x1260, 0x1288,
0x128A, 0x128D,
0x1290, 0x12B0,
0x12B2, 0x12B5,
0x12B8, 0x12BE,
0x12C0, 0x12C0,
0x12C2, 0x12C5,
0x12C8, 0x12D6,
0x12D8, 0x1310,
0x1312, 0x1315,
0x1318, 0x135A,
0x135D, 0x137C,
0x1380, 0x1399,
0x2D80, 0x2D96,
0x2DA0, 0x2DA6,
0x2DA8, 0x2DAE,
0x2DB0, 0x2DB6,
0x2DB8, 0x2DBE,
0x2DC0, 0x2DC6,
0x2DC8, 0x2DCE,
0x2DD0, 0x2DD6,
0x2DD8, 0x2DDE,
0xAB01, 0xAB06,
0xAB09, 0xAB0E,
0xAB11, 0xAB16,
0xAB20, 0xAB26,
0xAB28, 0xAB2E,
0x1E7E0, 0x1E7E6,
0x1E7E8, 0x1E7EB,
0x1E7ED, 0x1E7EE,
0x1E7F0, 0x1E7FE,
},
sort_key = "Ethi-sortkey",
strip_diacritics = {remove_diacritics = u(0x135D) .. u(0x135E) .. u(0x135F)}
}
m["Gara"] = process_ranges{
"加萊文",
3095302,
"全音素文字",
aliases = {"Garay"},
capitalized = true,
direction = "rtl",
ranges = {
0x060C, 0x060C,
0x061B, 0x061B,
0x061F, 0x061F,
0x10D40, 0x10D65,
0x10D69, 0x10D85,
0x10D8E, 0x10D8F,
},
}
m["Geok"] = process_ranges{
"教士體",
1090055,
"全音素文字",
aliases = {"Khutsuri"},
ranges = { -- Ⴀ-Ⴭ is Asomtavruli, ⴀ-ⴭ is Nuskhuri
0x10A0, 0x10C5,
0x10C7, 0x10C7,
0x10CD, 0x10CD,
0x10FB, 0x10FB,
0x2D00, 0x2D25,
0x2D27, 0x2D27,
0x2D2D, 0x2D2D,
},
varieties = {"Nuskhuri", "Asomtavruli"},
capitalized = true,
translit = "Geok-translit",
}
m["Geor"] = process_ranges{
"格魯吉亞文",
3317411,
"全音素文字",
aliases = {"Georgian"},
ranges = { -- ა-ჿ is lowercase Mkhedruli; Ა-Ჿ is uppercase Mkhedruli (Mtavruli)
0x0589, 0x0589,
0x10D0, 0x10FF,
0x1C90, 0x1CBA,
0x1CBD, 0x1CBF,
},
varieties = {"Mkhedruli", "Mtavruli"},
capitalized = true,
translit = "Geor-translit",
}
m["Glag"] = process_ranges{
"格拉哥里字母",
145625,
"全音素文字",
aliases = {"Glagolitic"},
ranges = {
0x0484, 0x0484,
0x0487, 0x0487,
0x0589, 0x0589,
0x10FB, 0x10FB,
0x2C00, 0x2C5F,
0x2E43, 0x2E43,
0xA66F, 0xA66F,
0x1E000, 0x1E006,
0x1E008, 0x1E018,
0x1E01B, 0x1E021,
0x1E023, 0x1E024,
0x1E026, 0x1E02A,
},
capitalized = true,
}
m["Gong"] = process_ranges{
"貢賈拉貢德文字",
18125340,
"元音附標文字",
aliases = {"Gunjala Gondi"},
ranges = {
0x0964, 0x0965,
0x11D60, 0x11D65,
0x11D67, 0x11D68,
0x11D6A, 0x11D8E,
0x11D90, 0x11D91,
0x11D93, 0x11D98,
0x11DA0, 0x11DA9,
},
}
m["Gonm"] = process_ranges{
"馬薩拉姆貢德文字",
16977603,
"元音附標文字",
aliases = {"Masaram Gondi"},
ranges = {
0x0964, 0x0965,
0x11D00, 0x11D06,
0x11D08, 0x11D09,
0x11D0B, 0x11D36,
0x11D3A, 0x11D3A,
0x11D3C, 0x11D3D,
0x11D3F, 0x11D47,
0x11D50, 0x11D59,
},
}
m["Goth"] = process_ranges{
"哥特字母",
467784,
"全音素文字",
aliases = {"Gothic"},
ranges = {
0x10330, 0x1034A,
},
wikipedia_article = "Gothic alphabet",
}
m["Gran"] = process_ranges{
"古蘭塔文",
1119274,
"元音附標文字",
aliases = {"Grantha"},
ranges = {
0x0951, 0x0952,
0x0964, 0x0965,
0x0BE6, 0x0BF3,
0x1CD0, 0x1CD0,
0x1CD2, 0x1CD3,
0x1CF2, 0x1CF4,
0x1CF8, 0x1CF9,
0x20F0, 0x20F0,
0x11300, 0x11303,
0x11305, 0x1130C,
0x1130F, 0x11310,
0x11313, 0x11328,
0x1132A, 0x11330,
0x11332, 0x11333,
0x11335, 0x11339,
0x1133B, 0x11344,
0x11347, 0x11348,
0x1134B, 0x1134D,
0x11350, 0x11350,
0x11357, 0x11357,
0x1135D, 0x11363,
0x11366, 0x1136C,
0x11370, 0x11374,
0x11FD0, 0x11FD1,
0x11FD3, 0x11FD3,
},
}
m["Grek"] = process_ranges{
"希臘文",
8216,
"全音素文字",
aliases = {"Greek"},
ranges = {
0x0341, 0x0341,
0x0374, 0x0375,
0x037E, 0x037E,
0x0384, 0x038A,
0x038C, 0x038C,
0x038E, 0x03A1,
0x03A3, 0x03D7,
0x03DA, 0x03DB,
0x03DE, 0x03E1,
0x03F0, 0x03F1,
0x03F4, 0x03F4,
0x03FC, 0x03FC,
0x1D26, 0x1D2A,
0x1D5D, 0x1D61,
0x1D66, 0x1D6A,
0x1DBF, 0x1DBF,
0x2126, 0x2127,
0x2129, 0x2129,
0x213C, 0x2140,
0xAB65, 0xAB65,
0x10140, 0x1018E,
0x101A0, 0x101A0,
0x1D200, 0x1D245,
},
capitalized = true,
display_text = "Grek-common",
strip_diacritics = "Grek-common",
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{
"希臘文",
1475332,
m["Grek"][3],
aliases = {"Greek"},
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,
0x1F18, 0x1F1D,
0x1F20, 0x1F45,
0x1F48, 0x1F4D,
0x1F50, 0x1F57,
0x1F59, 0x1F59,
0x1F5B, 0x1F5B,
0x1F5D, 0x1F5D,
0x1F5F, 0x1F7D,
0x1F80, 0x1FB4,
0x1FB6, 0x1FC4,
0x1FC6, 0x1FD3,
0x1FD6, 0x1FDB,
0x1FDD, 0x1FEF,
0x1FF2, 0x1FF4,
0x1FF6, 0x1FFE,
}),
ietf_subtag = "Grek",
capitalized = m["Grek"].capitalized,
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{
"古吉拉特文",
733944,
"元音附標文字",
aliases = {"Gujarati"},
ranges = {
0x0951, 0x0952,
0x0964, 0x0965,
0x0A81, 0x0A83,
0x0A85, 0x0A8D,
0x0A8F, 0x0A91,
0x0A93, 0x0AA8,
0x0AAA, 0x0AB0,
0x0AB2, 0x0AB3,
0x0AB5, 0x0AB9,
0x0ABC, 0x0AC5,
0x0AC7, 0x0AC9,
0x0ACB, 0x0ACD,
0x0AD0, 0x0AD0,
0x0AE0, 0x0AE3,
0x0AE6, 0x0AF1,
0x0AF9, 0x0AFF,
0xA830, 0xA839,
},
normalizationFixes = handle_normalization_fixes{
from = {"ઓ", "અાૈ", "અા", "અૅ", "અે", "અૈ", "અૉ", "અો", "અૌ", "આૅ", "આૈ", "ૅા"},
to = {"અાૅ", "ઔ", "આ", "ઍ", "એ", "ઐ", "ઑ", "ઓ", "ઔ", "ઓ", "ઔ", "ૉ"}
},
}
m["Gukh"] = process_ranges{
"凱瑪文",
110064239,
"元音附標文字",
aliases = {"Khema", "Gurung Khema", "Khema Phri", "Khema Lipi"},
ranges = {
0x0965, 0x0965,
0x16100, 0x16139,
},
}
m["Guru"] = process_ranges{
"古木基文",
689894,
"元音附標文字",
aliases = {"Gurmukhi"},
ranges = {
0x0951, 0x0952,
0x0964, 0x0965,
0x0A01, 0x0A03,
0x0A05, 0x0A0A,
0x0A0F, 0x0A10,
0x0A13, 0x0A28,
0x0A2A, 0x0A30,
0x0A32, 0x0A33,
0x0A35, 0x0A36,
0x0A38, 0x0A39,
0x0A3C, 0x0A3C,
0x0A3E, 0x0A42,
0x0A47, 0x0A48,
0x0A4B, 0x0A4D,
0x0A51, 0x0A51,
0x0A59, 0x0A5C,
0x0A5E, 0x0A5E,
0x0A66, 0x0A76,
0xA830, 0xA839,
},
normalizationFixes = handle_normalization_fixes{
from = {"ਅਾ", "ਅੈ", "ਅੌ", "ੲਿ", "ੲੀ", "ੲੇ", "ੳੁ", "ੳੂ", "ੳੋ"},
to = {"ਆ", "ਐ", "ਔ", "ਇ", "ਈ", "ਏ", "ਉ", "ਊ", "ਓ"}
},
}
m["Hang"] = process_ranges{
"諺文",
8222,
"音節文字",
aliases = {"Hangul", "Hangeul"},
ranges = {
0x1100, 0x11FF,
0x3001, 0x3003,
0x3008, 0x3011,
0x3013, 0x301F,
0x302E, 0x3030,
0x3037, 0x3037,
0x30FB, 0x30FB,
0x3131, 0x318E,
0x3200, 0x321E,
0x3260, 0x327E,
0xA960, 0xA97C,
0xAC00, 0xD7A3,
0xD7B0, 0xD7C6,
0xD7CB, 0xD7FB,
0xFE45, 0xFE46,
0xFF61, 0xFF65,
0xFFA0, 0xFFBE,
0xFFC2, 0xFFC7,
0xFFCA, 0xFFCF,
0xFFD2, 0xFFD7,
0xFFDA, 0xFFDC,
},
}
m["Hani"] = process_ranges{
"漢字",
8201,
"語素文字",
aliases = {"Han"},
ranges = {
0x2E80, 0x2E99,
0x2E9B, 0x2EF3,
0x2F00, 0x2FD5,
0x2FF0, 0x2FFF,
0x3001, 0x3003,
0x3005, 0x3011,
0x3013, 0x301F,
0x3021, 0x302D,
0x3030, 0x3030,
0x3037, 0x303F,
0x3190, 0x319F,
0x31C0, 0x31E5,
0x31EF, 0x31EF,
0x3220, 0x3247,
0x3280, 0x32B0,
0x32C0, 0x32CB,
0x30FB, 0x30FB,
0x32FF, 0x32FF,
0x3358, 0x3370,
0x337B, 0x337F,
0x33E0, 0x33FE,
0x3400, 0x4DBF,
0x4E00, 0x9FFF,
0xA700, 0xA707,
0xF900, 0xFA6D,
0xFA70, 0xFAD9,
0xFE45, 0xFE46,
0xFF61, 0xFF65,
0x16FE2, 0x16FE3,
0x16FF0, 0x16FF1,
0x1D360, 0x1D371,
0x1F250, 0x1F251,
0x20000, 0x2A6DF,
0x2A700, 0x2B739,
0x2B740, 0x2B81D,
0x2B820, 0x2CEA1,
0x2CEB0, 0x2EBE0,
0x2EBF0, 0x2EE5D,
0x2F800, 0x2FA1D,
0x30000, 0x3134A,
0x31350, 0x3347F,
},
varieties = {"Hanzi", "Kanji", "Hanja", "Chu Nom"},
spaces = false,
}
m["Hans"] = {
"簡體字",
185614,
m["Hani"][3],
aliases = {"Simplified Han"},
ranges = m["Hani"].ranges,
characters = m["Hani"].characters,
spaces = m["Hani"].spaces,
parent = "Hani",
}
m["Hant"] = {
"繁體字",
178528,
m["Hani"][3],
aliases = {"Traditional Han"},
ranges = m["Hani"].ranges,
characters = m["Hani"].characters,
spaces = m["Hani"].spaces,
parent = "Hani",
}
m["Hano"] = process_ranges{
"哈努諾文",
1584045,
"元音附標文字",
aliases = {"Hanunoo", "Hanunó'o", "Hanuno'o"},
ranges = {
0x1720, 0x1736,
},
}
m["Hatr"] = process_ranges{
"哈特拉文",
20813038,
"輔音音素文字",
aliases = {"Hatran"},
ranges = {
0x108E0, 0x108F2,
0x108F4, 0x108F5,
0x108FB, 0x108FF,
},
direction = "rtl",
}
m["Hebr"] = process_ranges{
"希伯來文",
33513,
"輔音音素文字", -- more precisely, impure abjad
aliases = {"Hebrew"},
ranges = {
0x0591, 0x05C7,
0x05D0, 0x05EA,
0x05EF, 0x05F4,
0x2135, 0x2138,
0xFB1D, 0xFB36,
0xFB38, 0xFB3C,
0xFB3E, 0xFB3E,
0xFB40, 0xFB41,
0xFB43, 0xFB44,
0xFB46, 0xFB4F,
},
direction = "rtl",
display_text = "Hebr-common",
sort_key = "Hebr-common",
strip_diacritics = "Hebr-common",
}
m["Hira"] = process_ranges{
"平假名",
48332,
"音節文字",
aliases = {"Hiragana"},
ranges = {
0x3001, 0x3003,
0x3008, 0x3011,
0x3013, 0x301F,
0x3030, 0x3035,
0x3037, 0x3037,
0x303C, 0x303D,
0x3041, 0x3096,
0x3099, 0x30A0,
0x30FB, 0x30FC,
0xFE45, 0xFE46,
0xFF61, 0xFF65,
0xFF70, 0xFF70,
0xFF9E, 0xFF9F,
0x1B001, 0x1B11F,
0x1B132, 0x1B132,
0x1B150, 0x1B152,
0x1F200, 0x1F200,
},
varieties = {"Hentaigana"},
spaces = false,
}
m["Hluw"] = process_ranges{
"安納托利亞象形文字",
521323,
"語素文字, 音節文字",
aliases = {"Anatolian hieroglyphic"},
ranges = {
0x14400, 0x14646,
},
wikipedia_article = "Anatolian hieroglyphs",
}
m["Hmng"] = process_ranges{
"帕哈苗文",
365954,
"半音節文字",
aliases = {"Pahawh Hmong", "Hmong"},
ranges = {
0x16B00, 0x16B45,
0x16B50, 0x16B59,
0x16B5B, 0x16B61,
0x16B63, 0x16B77,
0x16B7D, 0x16B8F,
},
}
m["Hmnp"] = process_ranges{
"創世紀苗文",
33712499,
"全音素文字",
aliases = {"Nyiakeng Puachue Hmong"},
ranges = {
0x1E100, 0x1E12C,
0x1E130, 0x1E13D,
0x1E140, 0x1E149,
0x1E14E, 0x1E14F,
},
}
m["Hung"] = process_ranges{
"古匈牙利字母",
446224,
"全音素文字",
aliases = {"Old Hungarian", "Hungarian runic"},
ranges = {
0x10C80, 0x10CB2,
0x10CC0, 0x10CF2,
0x10CFA, 0x10CFF,
},
capitalized = true,
direction = "rtl",
}
m["Ibrnn"] = {
"東北伊比利亞文字",
1113155,
"半音節文字",
aliases = {"Northeastern Iberian"},
ietf_subtag = "Zzzz",
-- Not in Unicode
}
m["Ibrns"] = {
"東南伊比利亞文字",
2305351,
"半音節文字",
aliases = {"Southeastern Iberian"},
ietf_subtag = "Zzzz",
-- Not in Unicode
}
m["Image"] = {
-- To be used to avoid any formatting or link processing
"圖像渲染",
478798,
aliases = {"Image-rendered"},
-- This should not have any characters listed
ietf_subtag = "Zyyy",
translit = false,
character_category = false, -- none
}
m["Inds"] = {
"印度河文字",
601388,
aliases = {"Indus", "Harappan", "Indus Valley"},
}
m["Ipach"] = {
"國際音標",
21204,
aliases = {"International Phonetic Alphabet", "IPA"},
ietf_subtag = "Latn",
}
m["Ital"] = process_ranges{
"古意大利字母",
4891256,
"全音素文字",
aliases = {"Old Italic"},
ranges = {
0x10300, 0x10323,
0x1032D, 0x1032F,
},
translit = "Ital-translit",
}
m["Java"] = process_ranges{
"爪哇字母",
879704,
"元音附標文字",
aliases = {"Javanese"},
ranges = {
0xA980, 0xA9CD,
0xA9CF, 0xA9D9,
0xA9DE, 0xA9DF,
},
}
m["Jurc"] = {
"女真文",
912240,
"語素文字",
aliases = {"Jurchen"},
spaces = false,
}
m["Kali"] = process_ranges{
"克耶里字母",
4919239,
"元音附標文字",
aliases = {"Kayah Li"},
ranges = {
0xA900, 0xA92F,
},
}
m["Kana"] = process_ranges{
"片假名",
82946,
"音節文字",
aliases = {"Katakana"},
ranges = {
0x3001, 0x3003,
0x3008, 0x3011,
0x3013, 0x301F,
0x3030, 0x3035,
0x3037, 0x3037,
0x303C, 0x303D,
0x3099, 0x309C,
0x30A0, 0x30FF,
0x31F0, 0x31FF,
0x32D0, 0x32FE,
0x3300, 0x3357,
0xFE45, 0xFE46,
0xFF61, 0xFF9F,
0x1AFF0, 0x1AFF3,
0x1AFF5, 0x1AFFB,
0x1AFFD, 0x1AFFE,
0x1B000, 0x1B000,
0x1B120, 0x1B122,
0x1B155, 0x1B155,
0x1B164, 0x1B167,
},
spaces = false,
}
m["Kawi"] = process_ranges{
"卡維文",
975802,
"元音附標文字",
aliases = {"Kawi"},
ranges = {
0x11F00, 0x11F10,
0x11F12, 0x11F3A,
0x11F3E, 0x11F5A,
},
}
m["Khar"] = process_ranges{
"佉盧文",
1161266,
"元音附標文字",
aliases = {"Kharoshthi"},
ranges = {
0x10A00, 0x10A03,
0x10A05, 0x10A06,
0x10A0C, 0x10A13,
0x10A15, 0x10A17,
0x10A19, 0x10A35,
0x10A38, 0x10A3A,
0x10A3F, 0x10A48,
0x10A50, 0x10A58,
},
direction = "rtl",
}
m["Khmr"] = process_ranges{
"高棉文",
1054190,
"元音附標文字",
aliases = {"Khmer"},
ranges = {
0x1780, 0x17DD,
0x17E0, 0x17E9,
0x17F0, 0x17F9,
0x19E0, 0x19FF,
},
spaces = false,
normalizationFixes = handle_normalization_fixes{
from = {"ឣ", "ឤ"},
to = {"អ", "អា"}
},
}
m["Khoj"] = process_ranges{
"可吉文",
1740656,
"元音附標文字",
aliases = {"Khojki"},
ranges = {
0x0AE6, 0x0AEF,
0xA830, 0xA839,
0x11200, 0x11211,
0x11213, 0x11241,
},
normalizationFixes = handle_normalization_fixes{
from = {"𑈀𑈬𑈱", "𑈀𑈬", "𑈀𑈱", "𑈀𑈳", "𑈁𑈱", "𑈆𑈬", "𑈬𑈰", "𑈬𑈱", "𑉀𑈮"},
to = {"𑈇", "𑈁", "𑈅", "𑈇", "𑈇", "𑈃", "𑈲", "𑈳", "𑈂"}
},
}
m["Khomt"] = {
"泰國高棉文",
13023788,
"元音附標文字",
aliases = {"Khom Thai"},
-- Not in Unicode
}
m["Kitl"] = {
"契丹大字",
6401797,
"語素文字",
aliases = {"Khitan large"},
spaces = false,
}
m["Kits"] = process_ranges{
"契丹小字",
6401800,
"語素文字, 音節文字",
aliases = {"Khitan small"},
ranges = {
0x16FE4, 0x16FE4,
0x18B00, 0x18CD5,
0x18CFF, 0x18CFF,
},
spaces = false,
}
m["Knda"] = process_ranges{
"卡納達文",
839666,
"元音附標文字",
aliases = {"Kannada"},
ranges = {
0x0951, 0x0952,
0x0964, 0x0965,
0x0C80, 0x0C8C,
0x0C8E, 0x0C90,
0x0C92, 0x0CA8,
0x0CAA, 0x0CB3,
0x0CB5, 0x0CB9,
0x0CBC, 0x0CC4,
0x0CC6, 0x0CC8,
0x0CCA, 0x0CCD,
0x0CD5, 0x0CD6,
0x0CDD, 0x0CDE,
0x0CE0, 0x0CE3,
0x0CE6, 0x0CEF,
0x0CF1, 0x0CF3,
0x1CD0, 0x1CD0,
0x1CD2, 0x1CD3,
0x1CDA, 0x1CDA,
0x1CF2, 0x1CF2,
0x1CF4, 0x1CF4,
0xA830, 0xA835,
},
normalizationFixes = handle_normalization_fixes{
from = {"ಉಾ", "ಋಾ", "ಒೌ"},
to = {"ಊ", "ೠ", "ಔ"}
},
translit = "kn-translit",
}
m["Kpel"] = {
"克培列文",
1586299,
"音節文字",
aliases = {"Kpelle"},
-- Not in Unicode
}
m["Krai"] = process_ranges{
"基拉特拉伊文",
123173834,
"元音附標文字",
aliases = {"Kirat Rai", "Rai", "Khambu Rai", "Rai Barṇamālā", "Kirat Khambu Rai"},
ranges = {
0x16D40, 0x16D79,
},
}
m["Kthi"] = process_ranges{
"凱提文",
1253814,
"元音附標文字",
aliases = {"Kaithi"},
ranges = {
0x0966, 0x096F,
0xA830, 0xA839,
0x11080, 0x110C2,
0x110CD, 0x110CD,
},
}
m["Kulit"] = {
"庫利坦字母",
6443044,
"元音附標文字",
aliases = {"Kulitan"},
-- Not in Unicode
}
m["Lana"] = process_ranges{
"老傣文",
1314503,
"元音附標文字",
aliases = {"Tai Tham", "Tham", "Tua Mueang", "Lanna"},
ranges = {
0x1A20, 0x1A5E,
0x1A60, 0x1A7C,
0x1A7F, 0x1A89,
0x1A90, 0x1A99,
0x1AA0, 0x1AAD,
},
spaces = false,
}
m["Laoo"] = process_ranges{
"寮文",
1815229,
"元音附標文字",
aliases = {"Lao"},
ranges = {
0x0E81, 0x0E82,
0x0E84, 0x0E84,
0x0E86, 0x0E8A,
0x0E8C, 0x0EA3,
0x0EA5, 0x0EA5,
0x0EA7, 0x0EBD,
0x0EC0, 0x0EC4,
0x0EC6, 0x0EC6,
0x0EC8, 0x0ECE,
0x0ED0, 0x0ED9,
0x0EDC, 0x0EDF,
},
spaces = false,
}
m["Latn"] = process_ranges{
"拉丁字母",
8229,
"全音素文字",
aliases = {"Latin", "Roman"},
ranges = {
0x0041, 0x005A,
0x0061, 0x007A,
0x00AA, 0x00AA,
0x00BA, 0x00BA,
0x00C0, 0x00D6,
0x00D8, 0x00F6,
0x00F8, 0x02B8,
0x02C0, 0x02C1,
0x02E0, 0x02E4,
0x0363, 0x036F,
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,
},
varieties = {"Rumi", "Romaji", "Rōmaji", "Romaja"},
capitalized = true,
translit = false,
}
m["Latf"] = {
"德文尖角體",
148443,
m["Latn"][3],
aliases = {"Fraktur"},
ranges = m["Latn"].ranges,
characters = m["Latn"].characters,
other_names = {"Blackletter"}, -- Blackletter is actually the parent "script"
capitalized = m["Latn"].capitalized,
translit = m["Latn"].translit,
parent = "Latn",
}
m["Latg"] = {
"蓋爾文",
1432616,
m["Latn"][3],
aliases = {"Gaelic"},
ranges = m["Latn"].ranges,
characters = m["Latn"].characters,
other_names = {"Irish"},
capitalized = m["Latn"].capitalized,
translit = m["Latn"].translit,
parent = "Latn",
}
m["pjt-Latn"] = {
"拉丁字母",
nil,
m["Latn"][3],
aliases = {"Latin"},
ranges = m["Latn"].ranges,
characters = m["Latn"].characters,
capitalized = m["Latn"].capitalized,
translit = m["Latn"].translit,
parent = "Latn",
}
m["Leke"] = {
"萊克文",
19572613,
"元音附標文字",
aliases = {"Leke"},
-- Not in Unicode
}
m["Lepc"] = process_ranges{
"絨巴文",
1481626,
"元音附標文字",
aliases = {"Lepcha", "Róng"},
ranges = {
0x1C00, 0x1C37,
0x1C3B, 0x1C49,
0x1C4D, 0x1C4F,
},
}
m["Limb"] = process_ranges{
"林布文",
933796,
"元音附標文字",
aliases = {"Limbu"},
ranges = {
0x0965, 0x0965,
0x1900, 0x191E,
0x1920, 0x192B,
0x1930, 0x193B,
0x1940, 0x1940,
0x1944, 0x194F,
},
}
m["Lina"] = process_ranges{
"線形文字A",
30972,
aliases = {"Linear A"},
ranges = {
0x10107, 0x10133,
0x10600, 0x10736,
0x10740, 0x10755,
0x10760, 0x10767,
},
}
m["Linb"] = process_ranges{
"線形文字B",
190102,
aliases = {"Linear B"},
ranges = {
0x10000, 0x1000B,
0x1000D, 0x10026,
0x10028, 0x1003A,
0x1003C, 0x1003D,
0x1003F, 0x1004D,
0x10050, 0x1005D,
0x10080, 0x100FA,
0x10100, 0x10102,
0x10107, 0x10133,
0x10137, 0x1013F,
},
}
m["Lisu"] = process_ranges{
"老傈僳文",
1194621,
"全音素文字",
aliases = {"Fraser", "Old Lisu", "Lisu"},
ranges = {
0x300A, 0x300B,
0xA4D0, 0xA4FF,
0x11FB0, 0x11FB0,
},
normalizationFixes = handle_normalization_fixes{
from = {"['’]", "[.ꓸ][.ꓸ]", "[.ꓸ][,ꓹ]"},
to = {"ʼ", "ꓺ", "ꓻ"}
},
translit = "Lisu-translit",
sort_key = {
from = {"𑾰"},
to = {"ꓬ" .. p[1]}
},
}
m["Loma"] = {
"Loma",
13023816,
"音節文字",
-- Not in Unicode
}
m["Lyci"] = process_ranges{
"呂基亞字母",
913587,
"全音素文字",
aliases = {"Lycian"},
ranges = {
0x10280, 0x1029C,
},
}
m["Lydi"] = process_ranges{
"呂底亞字母",
4261300,
"全音素文字",
aliases = {"Lydian"},
ranges = {
0x10920, 0x10939,
0x1093F, 0x1093F,
},
direction = "rtl",
}
m["Mahj"] = process_ranges{
"馬哈佳尼文",
6732850,
"元音附標文字",
aliases = {"Mahajani"},
ranges = {
0x0964, 0x096F,
0xA830, 0xA839,
0x11150, 0x11176,
},
}
m["Maka"] = process_ranges{
"望加錫文",
72947229,
"元音附標文字",
aliases = {"Makasar", "Old Makasar"},
ranges = {
0x11EE0, 0x11EF8,
},
}
m["Mand"] = process_ranges{
"曼達安字母",
1812130,
aliases = {"Mandaic", "Mandaean"},
ranges = {
0x0640, 0x0640,
0x0840, 0x085B,
0x085E, 0x085E,
},
direction = "rtl",
}
m["Mani"] = process_ranges{
"摩尼字母",
3544702,
"輔音音素文字",
aliases = {"Manichaean"},
ranges = {
0x0640, 0x0640,
0x10AC0, 0x10AE6,
0x10AEB, 0x10AF6,
},
direction = "rtl",
translit = "Mani-translit",
}
m["Marc"] = process_ranges{
"瑪欽文",
72403709,
"元音附標文字",
aliases = {"Marchen"},
ranges = {
0x11C70, 0x11C8F,
0x11C92, 0x11CA7,
0x11CA9, 0x11CB6,
},
}
m["Maya"] = process_ranges{
"馬雅文字",
211248,
aliases = {"Maya", "Maya hieroglyphic", "Mayan", "Mayan hieroglyphic"},
ranges = {
0x1D2E0, 0x1D2F3,
},
}
m["Medf"] = process_ranges{
"梅德法伊德林文",
1519764,
aliases = {"Medefaidrin", "Oberi Okaime", "Oberi Ɔkaimɛ"},
ranges = {
0x16E40, 0x16E9A,
},
capitalized = true,
}
m["Mend"] = process_ranges{
"門德基卡庫文",
951069,
aliases = {"Mende", "Mende Kikakui"},
ranges = {
0x1E800, 0x1E8C4,
0x1E8C7, 0x1E8D6,
},
direction = "rtl",
}
m["Merc"] = process_ranges{
"麥羅埃文草書體",
73028124,
"元音附標文字",
aliases = {"Meroitic cursive"},
ranges = {
0x109A0, 0x109B7,
0x109BC, 0x109CF,
0x109D2, 0x109FF,
},
direction = "rtl",
}
m["Mero"] = process_ranges{
"麥羅埃文聖書體",
73028623,
"元音附標文字",
aliases = {"Meroitic hieroglyphic"},
ranges = {
0x10980, 0x1099F,
},
direction = "rtl",
wikipedia_article = "麥羅埃字母",
}
m["Mlym"] = process_ranges{
"馬拉雅拉姆文",
1164129,
"元音附標文字",
aliases = {"Malayalam"},
ranges = {
0x0951, 0x0952,
0x0964, 0x0965,
0x0D00, 0x0D0C,
0x0D0E, 0x0D10,
0x0D12, 0x0D44,
0x0D46, 0x0D48,
0x0D4A, 0x0D4F,
0x0D54, 0x0D63,
0x0D66, 0x0D7F,
0x1CDA, 0x1CDA,
0x1CF2, 0x1CF2,
0xA830, 0xA832,
},
normalizationFixes = handle_normalization_fixes{
from = {"ഇൗ", "ഉൗ", "എെ", "ഒാ", "ഒൗ", "ക്", "ണ്", "ന്റ", "ന്", "മ്", "യ്", "ര്", "ല്", "ള്", "ഴ്", "െെ", "ൻ്റ"},
to = {"ഈ", "ഊ", "ഐ", "ഓ", "ഔ", "ൿ", "ൺ", "ൻറ", "ൻ", "ൔ", "ൕ", "ർ", "ൽ", "ൾ", "ൖ", "ൈ", "ന്റ"}
},
translit = "ml-translit",
}
m["Modi"] = process_ranges{
"莫迪文",
1703713,
"元音附標文字",
aliases = {"Modi"},
ranges = {
0xA830, 0xA839,
0x11600, 0x11644,
0x11650, 0x11659,
},
normalizationFixes = handle_normalization_fixes{
from = {"𑘀𑘹", "𑘀𑘺", "𑘁𑘹", "𑘁𑘺"},
to = {"𑘊", "𑘋", "𑘌", "𑘍"}
},
}
do
local Mong_displaytext = {
from = {"([ᠨ-ᡂᡸ])ᠶ([ᠨ-ᡂᡸ])", "([ᠠ-ᡂᡸ])ᠸ([^᠋ᠠ-ᠧ])", "([ᠠ-ᡂᡸ])ᠸ$"},
to = {"%1ᠢ%2", "%1ᠧ%2", "%1ᠧ"}
}
m["Mong"] = process_ranges{
"蒙古文",
1055705,
"全音素文字",
aliases = {"Mongolian", "Mongol bichig", "Hudum Mongol bichig"},
ranges = {
0x1800, 0x1805,
0x180A, 0x1819,
0x1820, 0x1842,
0x1878, 0x1878,
0x1880, 0x1897,
0x18A6, 0x18A6,
0x18A9, 0x18A9,
0x200C, 0x200D,
0x202F, 0x202F,
0x3001, 0x3002,
0x3008, 0x300B,
0x11660, 0x11668,
},
direction = "vertical-ltr",
display_text = Mong_displaytext,
strip_diacritics = Mong_displaytext,
translit = "Mong-translit",
}
m["mnc-Mong"] = process_ranges{
"滿文",
122888,
m["Mong"][3],
aliases = {"Manchu"},
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{
"錫伯文",
113624153,
m["Mong"][3],
aliases = {"Xibe", "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{
"托忒文",
529085,
m["Mong"][3],
aliases = {"Clear Script", "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"] = {
"Moon",
918391,
"全音素文字",
aliases = {"Moon System of Embossed Reading", "Moon type", "Moon writing", "Moon alphabet", "Moon code"},
-- Not in Unicode
}
m["Morse"] = {
"摩爾斯電碼",
79897,
aliases = {"Morse code"},
ietf_subtag = "Zsym",
}
m["Mroo"] = process_ranges{
"默祿文",
75919253,
aliases = {"Mru", "Mro", "Mrung"},
ranges = {
0x16A40, 0x16A5E,
0x16A60, 0x16A69,
0x16A6E, 0x16A6F,
},
}
m["Mtei"] = process_ranges{
"曼尼普爾文",
2981413,
"元音附標文字",
aliases = {"Meitei Mayek", "Meetei Mayek", "Manipuri"},
ranges = {
0xAAE0, 0xAAF6,
0xABC0, 0xABED,
0xABF0, 0xABF9,
},
}
m["Mult"] = process_ranges{
"穆爾塔尼文",
17047906,
"元音附標文字",
aliases = {"Multani"},
ranges = {
0x0A66, 0x0A6F,
0x11280, 0x11286,
0x11288, 0x11288,
0x1128A, 0x1128D,
0x1128F, 0x1129D,
0x1129F, 0x112A9,
},
}
m["Music"] = process_ranges{
"音樂記號",
233861,
"象形文字",
aliases = {"musical notation"},
ranges = {
0x2669, 0x266F,
0x1D100, 0x1D126,
0x1D129, 0x1D1EA,
},
ietf_subtag = "Zsym",
translit = false,
}
m["Mymr"] = process_ranges{
"緬甸文",
43887939,
"元音附標文字",
aliases = {"Burmese", "Myanmar"},
ranges = {
0x1000, 0x109F,
0xA92E, 0xA92E,
0xA9E0, 0xA9FE,
0xAA60, 0xAA7F,
0x116D0, 0x116E3,
},
spaces = false,
}
m["Nagm"] = process_ranges{
"Mundari Bani",
106917274,
"全音素文字",
aliases = {"Nag Mundari"},
ranges = {
0x1E4D0, 0x1E4F9,
},
}
m["Nand"] = process_ranges{
"南迪城文",
6963324,
"元音附標文字",
aliases = {"Nandinagari"},
ranges = {
0x0964, 0x0965,
0x0CE6, 0x0CEF,
0x1CE9, 0x1CE9,
0x1CF2, 0x1CF2,
0x1CFA, 0x1CFA,
0xA830, 0xA835,
0x119A0, 0x119A7,
0x119AA, 0x119D7,
0x119DA, 0x119E4,
},
}
m["Narb"] = process_ranges{
"古北阿拉伯字母",
1472213,
"輔音音素文字",
aliases = {"Ancient North Arabian", "Old North Arabian"},
ranges = {
0x10A80, 0x10A9F,
},
direction = "rtl",
translit = "Narb-translit",
}
m["Nbat"] = process_ranges{
"納巴泰字母",
855624,
"輔音音素文字",
aliases = {"Nabataean", "Nabatean"},
ranges = {
0x10880, 0x1089E,
0x108A7, 0x108AF,
},
direction = "rtl",
}
m["Newa"] = process_ranges{
"尼瓦爾文",
7237292,
"元音附標文字",
aliases = {"Newa", "Newar", "Newari", "Prachalit Nepal"},
ranges = {
0x11400, 0x1145B,
0x1145D, 0x11461,
},
}
m["Nkdb"] = {
"東巴文",
1190953,
"象形文字",
aliases = {"Dongba", "Naxi Dongba", "Nakhi Dongba", "Tomba", "Tompa", "Mo-so"},
spaces = false,
-- Not in Unicode
}
m["Nkgb"] = {
"哥巴文",
731189,
"音節文字",
aliases = {"Geba", "Nakhi Geba", "Naxi Geba"},
spaces = false,
-- Not in Unicode
}
m["Nkoo"] = process_ranges{
"西非書面文字",
1062587,
"全音素文字",
aliases = {"N'Ko"},
ranges = {
0x060C, 0x060C,
0x061B, 0x061B,
0x061F, 0x061F,
0x07C0, 0x07FA,
0x07FD, 0x07FF,
0xFD3E, 0xFD3F,
},
direction = "rtl",
}
m["None"] = {
"未指定文字",
nil,
aliases = {"unspecified"},
-- This should not have any characters listed
ietf_subtag = "Zyyy",
translit = false,
character_category = false, -- none
}
m["Nshu"] = process_ranges{
"女書",
56436,
"音節文字",
aliases = {"Nüshu", "Nushu"},
ranges = {
0x16FE1, 0x16FE1,
0x1B170, 0x1B2FB,
},
spaces = false,
}
m["Ogam"] = process_ranges{
"歐甘字母",
184661,
aliases = {"Ogham"},
ranges = {
0x1680, 0x169C,
},
}
m["Olck"] = process_ranges{
"桑塔利文",
201688,
aliases = {"Ol Chiki", "Ol Chemetʼ", "Ol", "Santali"},
ranges = {
0x1C50, 0x1C7F,
},
}
m["Onao"] = process_ranges{
"普密吉文",
108607084,
"全音素文字",
aliases = {"Ol Onal"},
ranges = {
0x0964, 0x0965,
0x1E5D0, 0x1E5FA,
0x1E5FF, 0x1E5FF,
},
}
m["Orkh"] = process_ranges{
"突厥字母",
5058305,
aliases = {"Old Turkic", "Orkhon runic"},
ranges = {
0x10C00, 0x10C48,
},
direction = "rtl",
translit = "Orkh-translit",
}
m["Orya"] = process_ranges{
"奧里亞文",
1760127,
"元音附標文字",
aliases = {"Odia", "Oriya"},
ranges = {
0x0951, 0x0952,
0x0964, 0x0965,
0x0B01, 0x0B03,
0x0B05, 0x0B0C,
0x0B0F, 0x0B10,
0x0B13, 0x0B28,
0x0B2A, 0x0B30,
0x0B32, 0x0B33,
0x0B35, 0x0B39,
0x0B3C, 0x0B44,
0x0B47, 0x0B48,
0x0B4B, 0x0B4D,
0x0B55, 0x0B57,
0x0B5C, 0x0B5D,
0x0B5F, 0x0B63,
0x0B66, 0x0B77,
0x1CDA, 0x1CDA,
0x1CF2, 0x1CF2,
},
normalizationFixes = handle_normalization_fixes{
from = {"ଅା", "ଏୗ", "ଓୗ"},
to = {"ଆ", "ଐ", "ଔ"}
},
}
m["Osge"] = process_ranges{
"奧塞奇文",
7105529,
aliases = {"Osage"},
ranges = {
0x104B0, 0x104D3,
0x104D8, 0x104FB,
},
capitalized = true,
translit = "Osge-translit",
}
m["Osma"] = process_ranges{
"奧斯曼亞字母",
1377866,
aliases = {"Osmanya"},
ranges = {
0x10480, 0x1049D,
0x104A0, 0x104A9,
},
}
m["Ougr"] = process_ranges{
"回鶻字母",
1998938,
"輔音音素文字, 全音素文字",
aliases = {"Old Uyghur"},
ranges = {
0x0640, 0x0640,
0x10AF2, 0x10AF2,
0x10F70, 0x10F89,
},
-- This should ideally be "vertical-ltr", but getting the CSS right is tricky because it's right-to-left horizontally, but left-to-right vertically. Currently, displaying it vertically causes it to display bottom-to-top.
direction = "rtl",
}
m["Palm"] = process_ranges{
"帕爾邁拉字母",
17538100,
aliases = {"Palmyrene"},
ranges = {
0x10860, 0x1087F,
},
direction = "rtl",
}
m["Pauc"] = process_ranges{
"包欽豪文",
25339852,
aliases = {"Pau Cin Hau"},
ranges = {
0x11AC0, 0x11AF8,
},
}
m["Pcun"] = {
"原始楔形文字",
1650699,
"象形文字",
aliases = {"Proto-Cuneiform"},
-- Not in Unicode
}
m["Pelm"] = {
"原始埃蘭文",
56305763,
"象形文字",
aliases = {"Proto-Elamite"},
-- Not in Unicode
}
m["Perm"] = process_ranges{
"古彼爾姆文",
147899,
aliases = {"Old Permic"},
ranges = {
0x0483, 0x0483,
0x10350, 0x1037A,
},
}
m["Phag"] = process_ranges{
"八思巴字",
822836,
"元音附標文字",
aliases = {"Phags-pa"},
ranges = {
0x1802, 0x1803,
0x1805, 0x1805,
0x200C, 0x200D,
0x202F, 0x202F,
0x3002, 0x3002,
0xA840, 0xA877,
},
direction = "vertical-ltr",
}
m["Phli"] = process_ranges{
"碑刻巴列維文",
24089793,
"輔音音素文字",
aliases = {"Inscriptional Pahlavi"},
ranges = {
0x10B60, 0x10B72,
0x10B78, 0x10B7F,
},
direction = "rtl",
}
m["Phlp"] = process_ranges{
"詩篇巴列維文",
7253954,
"輔音音素文字",
aliases = {"Psalter Pahlavi"},
ranges = {
0x0640, 0x0640,
0x10B80, 0x10B91,
0x10B99, 0x10B9C,
0x10BA9, 0x10BAF,
},
direction = "rtl",
}
m["Phlv"] = {
"書冊巴列維文",
72403118,
"輔音音素文字",
aliases = {"Book Pahlavi"},
direction = "rtl",
wikipedia_article = "en:Pahlavi scripts#Book Pahlavi",
-- Not in Unicode
}
m["Phnx"] = process_ranges{
"腓尼基字母",
26752,
"輔音音素文字",
aliases = {"Phoenician"},
ranges = {
0x10900, 0x1091B,
0x1091F, 0x1091F,
},
direction = "rtl",
translit = "Phnx-translit",
}
m["Plrd"] = process_ranges{
"柏格理苗文",
601734,
"元音附標文字",
aliases = {"Pollard", "Miao"},
ranges = {
0x16F00, 0x16F4A,
0x16F4F, 0x16F87,
0x16F8F, 0x16F9F,
},
}
m["Prti"] = process_ranges{
"碑刻帕提亞文",
13023804,
aliases = {"Inscriptional Parthian"},
ranges = {
0x10B40, 0x10B55,
0x10B58, 0x10B5F,
},
direction = "rtl",
}
m["Psin"] = {
"原始西奈字母",
1065250,
"輔音音素文字",
aliases = {"Proto-Sinaitic"},
direction = "rtl",
-- Not in Unicode
}
m["Ranj"] = {
"Ranjana",
2385276,
"元音附標文字",
-- Not in Unicode
}
m["Rjng"] = process_ranges{
"勒姜字母",
2007960,
"元音附標文字",
aliases = {"Rejang"},
ranges = {
0xA930, 0xA953,
0xA95F, 0xA95F,
},
}
m["Rohg"] = process_ranges{
"哈乃斐羅興亞文字",
21028705,
"全音素文字",
aliases = {"Hanifi Rohingya"},
ranges = {
0x060C, 0x060C,
0x061B, 0x061B,
0x061F, 0x061F,
0x0640, 0x0640,
0x06D4, 0x06D4,
0x10D00, 0x10D27,
0x10D30, 0x10D39,
},
direction = "rtl",
}
m["Roro"] = {
"朗格朗格",
209764,
aliases = {"Rongorongo"},
-- Not in Unicode
}
m["Rumin"] = process_ranges{
"盧米文數字",
nil,
aliases = {"Rumi numerals"},
ranges = {
0x10E60, 0x10E7E,
},
ietf_subtag = "Arab",
}
m["Runr"] = process_ranges{
"盧恩字母",
82996,
"全音素文字",
aliases = {"Runic"},
ranges = {
0x16A0, 0x16EA,
0x16EE, 0x16F8,
},
}
do
local Samr_stripdiacritics = {
remove_diacritics = c.CGJ .. u(0x0816) .. "-" .. u(0x082D),
}
m["Samr"] = process_ranges{
"撒瑪利亞字母",
1550930,
"輔音音素文字",
aliases = {"Samaritan"},
ranges = {
0x0800, 0x082D,
0x0830, 0x083E,
},
direction = "rtl",
strip_diacritics = Samr_stripdiacritics,
sort_key = Samr_stripdiacritics,
}
end
m["Sarb"] = process_ranges{
"古南阿拉伯文",
446074,
"輔音音素文字",
aliases = {"Ancient South Arabian", "Old South Arabian"},
ranges = {
0x10A60, 0x10A7F,
},
direction = "rtl",
translit = "Sarb-translit",
}
m["Saur"] = process_ranges{
"索拉什特拉文",
3535165,
"元音附標文字",
aliases = {"Saurashtra"},
ranges = {
0xA880, 0xA8C5,
0xA8CE, 0xA8D9,
},
}
m["Semap"] = {
"旗語",
250796,
"象形文字",
aliases = {"flag semaphore"},
ietf_subtag = "Zsym",
}
m["Sgnw"] = process_ranges{
"手語符號",
1497335,
"象形文字",
aliases = {"SignWriting", "Sutton SignWriting"},
ranges = {
0x1D800, 0x1DA8B,
0x1DA9B, 0x1DA9F,
0x1DAA1, 0x1DAAF,
},
translit = false,
}
m["Shaw"] = process_ranges{
"蕭伯納字母",
1970098,
aliases = {"Shavian", "Shaw"},
ranges = {
0x10450, 0x1047F,
},
}
m["Shrd"] = process_ranges{
"夏拉達文",
2047117,
"元音附標文字",
aliases = {"Sharada"},
ranges = {
0x0951, 0x0951,
0x1CD7, 0x1CD7,
0x1CD9, 0x1CD9,
0x1CDC, 0x1CDD,
0x1CE0, 0x1CE0,
0xA830, 0xA835,
0xA838, 0xA838,
0x11180, 0x111DF,
},
translit = "Shrd-translit",
}
m["Shui"] = {
"水書",
752854,
"語素文字",
aliases = {"Sui"},
spaces = false,
-- Not in Unicode
}
m["Sidd"] = process_ranges{
"悉曇文字",
250379,
"元音附標文字",
aliases = {"Siddham"},
ranges = {
0x11580, 0x115B5,
0x115B8, 0x115DD,
},
translit = "Sidd-translit",
}
m["Sidt"] = {
"錫德文",
36659,
"全音素文字",
aliases = {"Sidetic"},
direction = "rtl",
-- Not in Unicode
}
m["Sind"] = process_ranges{
"庫達瓦迪文",
6402810,
"元音附標文字",
aliases = {"Khudabadi", "Khudawadi"},
ranges = {
0x0964, 0x0965,
0xA830, 0xA839,
0x112B0, 0x112EA,
0x112F0, 0x112F9,
},
normalizationFixes = handle_normalization_fixes{
from = {"𑊰𑋠", "𑊰𑋥", "𑊰𑋦", "𑊰𑋧", "𑊰𑋨"},
to = {"𑊱", "𑊶", "𑊷", "𑊸", "𑊹"}
},
}
m["Sinh"] = process_ranges{
"僧伽羅文",
1574992,
"元音附標文字",
aliases = {"Sinhalese", "Sinhala"},
ranges = {
0x0964, 0x0965,
0x0D81, 0x0D83,
0x0D85, 0x0D96,
0x0D9A, 0x0DB1,
0x0DB3, 0x0DBB,
0x0DBD, 0x0DBD,
0x0DC0, 0x0DC6,
0x0DCA, 0x0DCA,
0x0DCF, 0x0DD4,
0x0DD6, 0x0DD6,
0x0DD8, 0x0DDF,
0x0DE6, 0x0DEF,
0x0DF2, 0x0DF4,
0x1CF2, 0x1CF2,
0x111E1, 0x111F4,
},
normalizationFixes = handle_normalization_fixes{
from = {"අා", "අැ", "අෑ", "උෟ", "ඍෘ", "ඏෟ", "එ්", "එෙ", "ඔෟ", "ෘෘ"},
to = {"ආ", "ඇ", "ඈ", "ඌ", "ඎ", "ඐ", "ඒ", "ඓ", "ඖ", "ෲ"}
},
}
m["Sogd"] = process_ranges{
"粟特字母",
578359,
"輔音音素文字",
aliases = {"Sogdian"},
ranges = {
0x0640, 0x0640,
0x10F30, 0x10F59,
},
direction = "rtl",
}
m["Sogo"] = process_ranges{
"古粟特字母",
72403254,
"輔音音素文字",
aliases = {"Old Sogdian"},
ranges = {
0x10F00, 0x10F27,
},
direction = "rtl",
}
m["Sora"] = process_ranges{
"索拉僧平文字",
7563292,
aliases = {"Sorang Sompeng", "Sora Sompeng"},
ranges = {
0x110D0, 0x110E8,
0x110F0, 0x110F9,
},
}
m["Soyo"] = process_ranges{
"索永布文字",
8009382,
"元音附標文字",
aliases = {"Soyombo"},
ranges = {
0x11A50, 0x11AA2,
},
}
m["Sund"] = process_ranges{
"巽他字母",
51589,
"元音附標文字",
aliases = {"Sundanese"},
ranges = {
0x1B80, 0x1BBF,
0x1CC0, 0x1CC7,
},
}
m["Sunu"] = process_ranges{
"蘇努瓦爾文",
109984965,
"全音素文字",
aliases = {"Sunuwar"},
ranges = {
0x11BC0, 0x11BE1,
0x11BF0, 0x11BF9,
},
}
m["Sylo"] = process_ranges{
"錫爾赫特文",
144128,
"元音附標文字",
aliases = {"Sylheti Nagri", "Sylheti Nāgarī", "Syloti Nagri"},
ranges = {
0x0964, 0x0965,
0x09E6, 0x09EF,
0xA800, 0xA82C,
},
}
m["Syrc"] = process_ranges{
"敘利亞字母",
26567,
"輔音音素文字", -- more precisely, impure abjad
aliases = {"Syriac"},
ranges = {
0x060C, 0x060C,
0x061B, 0x061C,
0x061F, 0x061F,
0x0640, 0x0640,
0x064B, 0x0655,
0x0670, 0x0670,
0x0700, 0x070D,
0x070F, 0x074A,
0x074D, 0x074F,
0x0860, 0x086A,
0x1DF8, 0x1DF8,
0x1DFA, 0x1DFA,
},
direction = "rtl",
}
-- Syre, Syrj, Syrn are apparently subsumed into Syrc; discuss if this causes issues
m["Tagb"] = process_ranges{
"塔格巴努瓦字母",
977444,
"元音附標文字",
aliases = {"Tagbanwa"},
ranges = {
0x1735, 0x1736,
0x1760, 0x176C,
0x176E, 0x1770,
0x1772, 0x1773,
},
}
m["Takr"] = process_ranges{
"Takri",
759202,
"元音附標文字",
ranges = {
0x0964, 0x0965,
0xA830, 0xA839,
0x11680, 0x116B9,
0x116C0, 0x116C9,
},
normalizationFixes = handle_normalization_fixes{
from = {"𑚀𑚭", "𑚀𑚴", "𑚀𑚵", "𑚆𑚲"},
to = {"𑚁", "𑚈", "𑚉", "𑚇"}
},
}
m["Tale"] = process_ranges{
"德宏傣文",
2566326,
"元音附標文字",
aliases = {"Tai Nüa", "Tai Nuea", "New Tai Nüa", "New Tai Nuea", "Dehong Dai", "Tai Dehong", "Tai Le"},
ranges = {
0x1040, 0x1049,
0x1950, 0x196D,
0x1970, 0x1974,
},
spaces = false,
}
m["Talu"] = process_ranges{
"新傣文",
3498863,
"元音附標文字",
aliases = {"New Tai Lue"},
ranges = {
0x1980, 0x19AB,
0x19B0, 0x19C9,
0x19D0, 0x19DA,
0x19DE, 0x19DF,
},
spaces = false,
}
m["Taml"] = process_ranges{
"泰米爾文",
26803,
"元音附標文字",
aliases = {"Tamil"},
ranges = {
0x0951, 0x0952,
0x0964, 0x0965,
0x0B82, 0x0B83,
0x0B85, 0x0B8A,
0x0B8E, 0x0B90,
0x0B92, 0x0B95,
0x0B99, 0x0B9A,
0x0B9C, 0x0B9C,
0x0B9E, 0x0B9F,
0x0BA3, 0x0BA4,
0x0BA8, 0x0BAA,
0x0BAE, 0x0BB9,
0x0BBE, 0x0BC2,
0x0BC6, 0x0BC8,
0x0BCA, 0x0BCD,
0x0BD0, 0x0BD0,
0x0BD7, 0x0BD7,
0x0BE6, 0x0BFA,
0x1CDA, 0x1CDA,
0xA8F3, 0xA8F3,
0x11301, 0x11301,
0x11303, 0x11303,
0x1133B, 0x1133C,
0x11FC0, 0x11FF1,
0x11FFF, 0x11FFF,
},
normalizationFixes = handle_normalization_fixes{
from = {"அூ", "ஸ்ரீ"},
to = {"ஆ", "ஶ்ரீ"}
},
}
m["Tang"] = process_ranges{
"西夏文",
1373610,
"語素文字, 音節文字",
aliases = {"Tangut"},
ranges = {
0x31EF, 0x31EF,
0x16FE0, 0x16FE0,
0x17000, 0x187F7,
0x18800, 0x18AFF,
0x18D00, 0x18D08,
},
spaces = false,
translit = "txg-translit",
}
m["Tavt"] = process_ranges{
"越南傣文",
11818517,
"元音附標文字",
aliases = {"Tai Viet"},
ranges = {
0xAA80, 0xAAC2,
0xAADB, 0xAADF,
},
spaces = false,
}
m["Tayo"] = process_ranges{
"Lai Tay",
16306701,
"元音附標文字",
aliases = {"Tai Yo"},
direction = "vertical-rtl",
ranges = {
0x1E6C0, 0x1E6DE,
0x1E6E0, 0x1E6F5,
0x1E6FE, 0x1E6FF,
},
spaces = false,
}
m["Telu"] = process_ranges{
"泰盧固文",
570450,
"元音附標文字",
aliases = {"Telugu"},
ranges = {
0x0951, 0x0952,
0x0964, 0x0965,
0x0C00, 0x0C0C,
0x0C0E, 0x0C10,
0x0C12, 0x0C28,
0x0C2A, 0x0C39,
0x0C3C, 0x0C44,
0x0C46, 0x0C48,
0x0C4A, 0x0C4D,
0x0C55, 0x0C56,
0x0C58, 0x0C5A,
0x0C5D, 0x0C5D,
0x0C60, 0x0C63,
0x0C66, 0x0C6F,
0x0C77, 0x0C7F,
0x1CDA, 0x1CDA,
0x1CF2, 0x1CF2,
},
normalizationFixes = handle_normalization_fixes{
from = {"ఒౌ", "ఒౕ", "ిౕ", "ెౕ", "ొౕ"},
to = {"ఔ", "ఓ", "ీ", "ే", "ో"}
},
}
m["Teng"] = {
"談格瓦文字",
473725,
aliases = {"Tengwar"},
}
m["Tfng"] = process_ranges{
"提非納文",
208503,
"輔音音素文字, 全音素文字",
aliases = {"Tifinagh"},
ranges = {
0x2D30, 0x2D67,
0x2D6F, 0x2D70,
0x2D7F, 0x2D7F,
},
other_names = {"Libyco-Berber", "Berber"}, -- per Wikipedia, Libyco-Berber is the parent
}
m["Tglg"] = process_ranges{
"他加祿字母",
812124,
"元音附標文字",
aliases = {"Baybayin", "Tagalog"},
varieties = {"Badlit", "Basahan", "Kur-itan"},
ranges = {
0x1700, 0x1715,
0x171F, 0x171F,
0x1735, 0x1736,
},
}
m["Thaa"] = process_ranges{
"它拿字母",
877906,
"元音附標文字",
aliases = {"Thaana"},
ranges = {
0x060C, 0x060C,
0x061B, 0x061C,
0x061F, 0x061F,
0x0660, 0x0669,
0x0780, 0x07B1,
0xFDF2, 0xFDF2,
0xFDFD, 0xFDFD,
},
direction = "rtl",
}
m["Thai"] = process_ranges{
"泰文",
236376,
"元音附標文字",
aliases = {"Thai"},
ranges = {
0x0E01, 0x0E3A,
0x0E40, 0x0E5B,
},
spaces = false,
}
do
local Tibt_displaytext = {
from = {"ༀ", "༌", "།།", "༚༚", "༚༝", "༝༚", "༝༝", "ཷ", "ཹ", "ེེ", "ོོ"},
to = {"ཨོཾ", "་", "༎", "༛", "༟", "࿎", "༞", "ྲཱྀ", "ླཱྀ", "ཻ", "ཽ"}
}
m["Tibt"] = process_ranges{
"藏文",
46861,
"元音附標文字",
aliases = {"Tibetan"},
ranges = {
0x0F00, 0x0F47,
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"] = {
"達芒文",
109875213,
m["Tibt"][3],
aliases = {"Tamyig"},
-- 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), 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{
"提爾胡塔文",
1765752,
"元音附標文字",
aliases = {"Tirhuta"},
ranges = {
0x0951, 0x0952,
0x0964, 0x0965,
0x1CF2, 0x1CF2,
0xA830, 0xA839,
0x11480, 0x114C7,
0x114D0, 0x114D9,
},
normalizationFixes = handle_normalization_fixes{
from = {"𑒁𑒰", "𑒋𑒺", "𑒍𑒺", "𑒪𑒵", "𑒪𑒶"},
to = {"𑒂", "𑒌", "𑒎", "𑒉", "𑒊"}
},
}
m["Tnsa"] = process_ranges{
"唐薩文",
105576311,
"全音素文字",
aliases = {"Tangsa"},
ranges = {
0x16A70, 0x16ABE,
0x16AC0, 0x16AC9,
},
}
m["Todr"] = process_ranges{
"托特里文",
10274731,
"全音素文字",
aliases = {"Todhri"},
direction = "rtl",
ranges = {
0x105C0, 0x105F3,
},
}
m["Tols"] = {
"Tolong Siki",
4459822,
"全音素文字",
-- Not in Unicode
}
m["Toto"] = process_ranges{
"托托文",
104837516,
"元音附標文字",
aliases = {"Toto"},
ranges = {
0x1E290, 0x1E2AE,
},
}
m["Tutg"] = process_ranges{
"提加拉里文",
2604990,
"元音附標文字",
aliases = {"Tigalari", "Tulu"},
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{
"烏加里特字母",
332652,
"輔音音素文字",
aliases = {"Ugaritic"},
ranges = {
0x10380, 0x1039D,
0x1039F, 0x1039F,
},
}
m["Vaii"] = process_ranges{
"瓦伊文",
523078,
"音節文字",
aliases = {"Vai"},
ranges = {
0xA500, 0xA62B,
},
}
m["Visp"] = {
"Visible Speech",
1303365,
"全音素文字",
-- Not in Unicode
}
m["Vith"] = process_ranges{
"維斯庫奇字母",
3301993,
"全音素文字",
aliases = {"Vithkuqi"},
ranges = {
0x10570, 0x1057A,
0x1057C, 0x1058A,
0x1058C, 0x10592,
0x10594, 0x10595,
0x10597, 0x105A1,
0x105A3, 0x105B1,
0x105B3, 0x105B9,
0x105BB, 0x105BC,
},
capitalized = true,
}
m["Wara"] = process_ranges{
"瓦蘭齊地文",
79199,
aliases = {"Varang Kshiti", "Warang Citi"},
ranges = {
0x118A0, 0x118F2,
0x118FF, 0x118FF,
},
capitalized = true,
}
m["Wcho"] = process_ranges{
"Wancho",
33713728,
"全音素文字",
ranges = {
0x1E2C0, 0x1E2F9,
0x1E2FF, 0x1E2FF,
},
}
m["Wole"] = {
"Woleai",
6643710,
"音節文字",
-- Not in Unicode
}
m["Xpeo"] = process_ranges{
"古波斯文",
1471822,
aliases = {"Old Persian"},
ranges = {
0x103A0, 0x103C3,
0x103C8, 0x103D5,
},
}
m["Xsux"] = process_ranges{
"楔形文字",
401,
aliases = {"Cuneiform", "Sumero-Akkadian Cuneiform"},
ranges = {
0x12000, 0x12399,
0x12400, 0x1246E,
0x12470, 0x12474,
0x12480, 0x12543,
},
}
m["Yezi"] = process_ranges{
"雅茲迪文",
13175481,
"全音素文字",
aliases = {"Yezidi"},
ranges = {
0x060C, 0x060C,
0x061B, 0x061B,
0x061F, 0x061F,
0x0660, 0x0669,
0x10E80, 0x10EA9,
0x10EAB, 0x10EAD,
0x10EB0, 0x10EB1,
},
direction = "rtl",
}
m["Yiii"] = process_ranges{
"彝文",
1197646,
"音節文字",
aliases = {"Yi"},
ranges = {
0x3001, 0x3002,
0x3008, 0x3011,
0x3014, 0x301B,
0x30FB, 0x30FB,
0xA000, 0xA48C,
0xA490, 0xA4C6,
0xFF61, 0xFF65,
},
}
m["Zanb"] = process_ranges{
"札那巴札爾方形字母",
50809208,
"元音附標文字",
aliases = {"Zanabazar Square"},
ranges = {
0x11A00, 0x11A47,
},
}
m["Zmth"] = process_ranges{
"數學記號",
1140046,
aliases = {"mathematical notation"},
ranges = {
0x00AC, 0x00AC,
0x00B1, 0x00B1,
0x00D7, 0x00D7,
0x00F7, 0x00F7,
0x03D0, 0x03D2,
0x03D5, 0x03D5,
0x03F0, 0x03F1,
0x03F4, 0x03F6,
0x0606, 0x0608,
0x2016, 0x2016,
0x2032, 0x2034,
0x2040, 0x2040,
0x2044, 0x2044,
0x2052, 0x2052,
0x205F, 0x205F,
0x2061, 0x2064,
0x207A, 0x207E,
0x208A, 0x208E,
0x20D0, 0x20DC,
0x20E1, 0x20E1,
0x20E5, 0x20E6,
0x20EB, 0x20EF,
0x2102, 0x2102,
0x2107, 0x2107,
0x210A, 0x2113,
0x2115, 0x2115,
0x2118, 0x211D,
0x2124, 0x2124,
0x2128, 0x2129,
0x212C, 0x212D,
0x212F, 0x2131,
0x2133, 0x2138,
0x213C, 0x2149,
0x214B, 0x214B,
0x2190, 0x21A7,
0x21A9, 0x21AE,
0x21B0, 0x21B1,
0x21B6, 0x21B7,
0x21BC, 0x21DB,
0x21DD, 0x21DD,
0x21E4, 0x21E5,
0x21F4, 0x22FF,
0x2308, 0x230B,
0x2320, 0x2321,
0x237C, 0x237C,
0x239B, 0x23B5,
0x23B7, 0x23B7,
0x23D0, 0x23D0,
0x23DC, 0x23E2,
0x25A0, 0x25A1,
0x25AE, 0x25B7,
0x25BC, 0x25C1,
0x25C6, 0x25C7,
0x25CA, 0x25CB,
0x25CF, 0x25D3,
0x25E2, 0x25E2,
0x25E4, 0x25E4,
0x25E7, 0x25EC,
0x25F8, 0x25FF,
0x2605, 0x2606,
0x2640, 0x2640,
0x2642, 0x2642,
0x2660, 0x2663,
0x266D, 0x266F,
0x27C0, 0x27FF,
0x2900, 0x2AFF,
0x2B30, 0x2B44,
0x2B47, 0x2B4C,
0xFB29, 0xFB29,
0xFE61, 0xFE66,
0xFE68, 0xFE68,
0xFF0B, 0xFF0B,
0xFF1C, 0xFF1E,
0xFF3C, 0xFF3C,
0xFF3E, 0xFF3E,
0xFF5C, 0xFF5C,
0xFF5E, 0xFF5E,
0xFFE2, 0xFFE2,
0xFFE9, 0xFFEC,
0x1D400, 0x1D454,
0x1D456, 0x1D49C,
0x1D49E, 0x1D49F,
0x1D4A2, 0x1D4A2,
0x1D4A5, 0x1D4A6,
0x1D4A9, 0x1D4AC,
0x1D4AE, 0x1D4B9,
0x1D4BB, 0x1D4BB,
0x1D4BD, 0x1D4C3,
0x1D4C5, 0x1D505,
0x1D507, 0x1D50A,
0x1D50D, 0x1D514,
0x1D516, 0x1D51C,
0x1D51E, 0x1D539,
0x1D53B, 0x1D53E,
0x1D540, 0x1D544,
0x1D546, 0x1D546,
0x1D54A, 0x1D550,
0x1D552, 0x1D6A5,
0x1D6A8, 0x1D7CB,
0x1D7CE, 0x1D7FF,
0x1EE00, 0x1EE03,
0x1EE05, 0x1EE1F,
0x1EE21, 0x1EE22,
0x1EE24, 0x1EE24,
0x1EE27, 0x1EE27,
0x1EE29, 0x1EE32,
0x1EE34, 0x1EE37,
0x1EE39, 0x1EE39,
0x1EE3B, 0x1EE3B,
0x1EE42, 0x1EE42,
0x1EE47, 0x1EE47,
0x1EE49, 0x1EE49,
0x1EE4B, 0x1EE4B,
0x1EE4D, 0x1EE4F,
0x1EE51, 0x1EE52,
0x1EE54, 0x1EE54,
0x1EE57, 0x1EE57,
0x1EE59, 0x1EE59,
0x1EE5B, 0x1EE5B,
0x1EE5D, 0x1EE5D,
0x1EE5F, 0x1EE5F,
0x1EE61, 0x1EE62,
0x1EE64, 0x1EE64,
0x1EE67, 0x1EE6A,
0x1EE6C, 0x1EE72,
0x1EE74, 0x1EE77,
0x1EE79, 0x1EE7C,
0x1EE7E, 0x1EE7E,
0x1EE80, 0x1EE89,
0x1EE8B, 0x1EE9B,
0x1EEA1, 0x1EEA3,
0x1EEA5, 0x1EEA9,
0x1EEAB, 0x1EEBB,
0x1EEF0, 0x1EEF1,
},
translit = false,
}
m["Zname"] = process_ranges{
"茲納緬尼記譜法",
965834,
"象形文字",
aliases = {"Znamenny musical notation"},
ranges = {
0x1CF00, 0x1CF2D,
0x1CF30, 0x1CF46,
0x1CF50, 0x1CFC3,
},
ietf_subtag = "Zsym",
translit = false,
}
m["Zsym"] = process_ranges{
"符號",
80071,
"象形文字",
aliases = {"symbolic"},
ranges = {
0x20DD, 0x20E0,
0x20E2, 0x20E4,
0x20E7, 0x20EA,
0x20F0, 0x20F0,
0x2100, 0x2101,
0x2103, 0x2106,
0x2108, 0x2109,
0x2114, 0x2114,
0x2116, 0x2117,
0x211E, 0x2123,
0x2125, 0x2127,
0x212A, 0x212B,
0x212E, 0x212E,
0x2132, 0x2132,
0x2139, 0x213B,
0x214A, 0x214A,
0x214C, 0x214F,
0x21A8, 0x21A8,
0x21AF, 0x21AF,
0x21B2, 0x21B5,
0x21B8, 0x21BB,
0x21DC, 0x21DC,
0x21DE, 0x21E3,
0x21E6, 0x21F3,
0x2300, 0x2307,
0x230C, 0x231F,
0x2322, 0x237B,
0x237D, 0x239A,
0x23B6, 0x23B6,
0x23B8, 0x23CF,
0x23D1, 0x23DB,
0x23E3, 0x23FF,
0x2500, 0x259F,
0x25A2, 0x25AD,
0x25B8, 0x25BB,
0x25C2, 0x25C5,
0x25C8, 0x25C9,
0x25CC, 0x25CE,
0x25D4, 0x25E1,
0x25E3, 0x25E3,
0x25E5, 0x25E6,
0x25ED, 0x25F7,
0x2600, 0x2604,
0x2607, 0x263F,
0x2641, 0x2641,
0x2643, 0x265F,
0x2664, 0x266C,
0x2670, 0x27BF,
0x2B00, 0x2B2F,
0x2B45, 0x2B46,
0x2B4D, 0x2B73,
0x2B76, 0x2B95,
0x2B97, 0x2BFF,
0x4DC0, 0x4DFF,
0x1F000, 0x1F02B,
0x1F030, 0x1F093,
0x1F0A0, 0x1F0AE,
0x1F0B1, 0x1F0BF,
0x1F0C1, 0x1F0CF,
0x1F0D1, 0x1F0F5,
0x1F300, 0x1F6D7,
0x1F6DC, 0x1F6EC,
0x1F6F0, 0x1F6FC,
0x1F700, 0x1F776,
0x1F77B, 0x1F7D9,
0x1F7E0, 0x1F7EB,
0x1F7F0, 0x1F7F0,
0x1F800, 0x1F80B,
0x1F810, 0x1F847,
0x1F850, 0x1F859,
0x1F860, 0x1F887,
0x1F890, 0x1F8AD,
0x1F8B0, 0x1F8B1,
0x1F900, 0x1FA53,
0x1FA60, 0x1FA6D,
0x1FA70, 0x1FA7C,
0x1FA80, 0x1FA88,
0x1FA90, 0x1FABD,
0x1FABF, 0x1FAC5,
0x1FACE, 0x1FADB,
0x1FAE0, 0x1FAE8,
0x1FAF0, 0x1FAF8,
0x1FB00, 0x1FB92,
0x1FB94, 0x1FBCA,
0x1FBF0, 0x1FBF9,
},
translit = false,
character_category = false, -- none
}
m["Zxxx"] = {
"無文字",
104839715,
aliases = {"unwritten"},
-- This should not have any characters listed
translit = false,
character_category = false, -- none
}
m["Zyyy"] = {
"未定文字",
104839687,
aliases = {"undetermined"},
-- This should not have any characters listed, probably
translit = false,
character_category = false, -- none
}
m["Zzzz"] = {
"未編碼文字",
104839675,
aliases = {"uncoded"},
-- This should not have any characters listed
translit = false,
character_category = false, -- none
}
-- These should be defined after the scripts they are composed of.
m["Hrkt"] = process_ranges{
"假名",
187659,
"音節文字",
aliases = {"Kana", "Japanese syllabaries"},
ranges = union(
m["Hira"].ranges,
m["Kana"].ranges
),
spaces = false,
}
m["Jpan"] = process_ranges{
"日文",
190502,
"語素文字, 音節文字",
ranges = union(
m["Hrkt"].ranges,
m["Hani"].ranges,
m["Latn"].ranges
),
aliases = {"Japanese"},
spaces = false,
sort_by_scraping = true,
}
m["Kore"] = process_ranges{
"韓文",
711797,
"語素文字, 音節文字",
ranges = union(
m["Hang"].ranges,
m["Hani"].ranges,
m["Latn"].ranges
),
aliases = {"Korean"},
-- `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 require("Module:languages").finalizeData(m, "script")