మాడ్యూల్:scripts/data
Appearance
Documentation for this module may be created at మాడ్యూల్:scripts/data/doc
-- When adding new scripts to this file, please don't forget to add
-- style definitons for the script in [[MediaWiki:Common.css]].
local u = mw.ustring.char
local m = {}
m["Adlm"] = {
canonicalName = "Adlam",
}
m["Afak"] = {
canonicalName = "Afaka",
}
m["Aghb"] = {
canonicalName = "Caucasian Albanian",
characters = "𐔰-𐕣𐕯",
}
m["Ahom"] = {
canonicalName = "Ahom",
characters = "𑜀-𑜿",
systems = {"abugida"},
}
m["Arab"] = {
canonicalName = "Arabic",
otherNames = {"Jawi"},
characters = "-ۿݐ-ݿࢠ-ࣿﭐ-﷽ﹰ-ﻼ",
}
m["fa-Arab"] = {
canonicalName = "Arabic",
otherNames = {"Perso-Arabic"},
characters = m["Arab"].characters,
}
m["kk-Arab"] = {
canonicalName = "Arabic",
characters = m["Arab"].characters,
}
m["ks-Arab"] = {
canonicalName = "Arabic",
characters = m["Arab"].characters,
}
m["ku-Arab"] = {
canonicalName = "Arabic",
characters = m["Arab"].characters,
}
m["mzn-Arab"] = {
canonicalName = "Arabic",
characters = m["Arab"].characters,
}
m["ota-Arab"] = {
canonicalName = "Arabic",
characters = m["Arab"].characters,
}
m["pa-Arab"] = {
canonicalName = "Arabic",
otherNames = {"Shahmukhi"},
characters = m["Arab"].characters,
}
m["ps-Arab"] = {
canonicalName = "Arabic",
characters = m["Arab"].characters,
}
m["sd-Arab"] = {
canonicalName = "Arabic",
characters = m["Arab"].characters,
}
m["tt-Arab"] = {
canonicalName = "Arabic",
characters = m["Arab"].characters,
}
m["ug-Arab"] = {
canonicalName = "Arabic",
characters = m["Arab"].characters,
}
m["ur-Arab"] = {
canonicalName = "Arabic",
characters = m["Arab"].characters,
}
m["Aran"] = {
canonicalName = "Nastaleeq",
characters = m["Arab"].characters,
}
m["Armi"] = {
canonicalName = "Imperial Aramaic",
characters = "𐡀-𐡟",
}
m["Armn"] = {
canonicalName = "Armenian",
characters = "Ա-֏ﬓ-ﬗ",
}
m["Avst"] = {
canonicalName = "Avestan",
characters = "𐬀-𐬿",
}
m["Bali"] = {
canonicalName = "Balinese",
characters = "ᬀ-᭼",
systems = {"abugida"},
}
m["Bamu"] = {
canonicalName = "Bamum",
characters = "ꚠ-꛷𖠀-𖨸",
}
m["Bass"] = {
canonicalName = "Bassa",
otherNames = {"Bassa Vah", "Vah"},
characters = "𖫐-𖫵",
}
m["Batk"] = {
canonicalName = "Batak",
characters = "ᯀ-᯿",
systems = {"abugida"},
}
m["Beng"] = {
canonicalName = "Bengali",
characters = "ঁ-৺",
systems = {"abugida"},
}
m["Bhks"] = {
canonicalName = "Bhaiksuki",
systems = {"abugida"},
}
m["Bopo"] = {
canonicalName = "Zhuyin",
otherNames = {"Zhuyin Fuhao", "Bopomofo"},
characters = "ㄅ-ㄭㆠ-ㆺ",
}
m["Brah"] = {
canonicalName = "Brahmi",
characters = "𑀀-𑁯",
systems = {"abugida"},
}
m["Brai"] = {
canonicalName = "Braille",
characters = "⠀-⣿",
}
m["Bugi"] = {
canonicalName = "Buginese",
characters = "ᨀ-᨟",
}
m["Buhd"] = {
canonicalName = "Buhid",
characters = "ᝀ-ᝓ",
}
m["Cakm"] = {
canonicalName = "Chakma",
characters = "𑄀-𑅃",
systems = {"abugida"},
}
m["Cans"] = {
canonicalName = "Canadian syllabics",
characters = "᐀-ᙿ",
systems = {"abugida"},
}
m["Cari"] = {
canonicalName = "Carian",
characters = "𐊠-𐋐",
}
m["Cham"] = {
canonicalName = "Cham",
characters = "ꨀ-꩟",
systems = {"abugida"},
}
m["Cher"] = {
canonicalName = "Cherokee",
characters = "Ꭰ-Ᏼꭰ-ꮿ",
}
m["Copt"] = {
canonicalName = "Coptic",
characters = "Ⲁ-⳿", -- This is the separate "Coptic" block, not the unified "Greek and Coptic"
}
m["Cprt"] = {
canonicalName = "Cypriot",
characters = "𐠀-𐠿",
}
m["Cyrl"] = {
canonicalName = "Cyrillic",
characters = "Ѐ-џҊ-ԧꚀ-ꚗ",
}
m["Cyrs"] = {
canonicalName = "Old Cyrillic",
characters = "Ѐ-ԧꙀ-ꚗ",
}
m["Deva"] = {
canonicalName = "Devanagari",
characters = "ऀ-ॿ꣠-ꣻ",
systems = {"abugida"},
}
m["Dsrt"] = {
canonicalName = "Deseret",
characters = "𐐀-𐑏",
}
m["Dupl"] = {
canonicalName = "Duployan",
characters = "𛰀-𛲟",
}
m["Egyd"] = {
canonicalName = "Demotic",
}
m["Egyp"] = {
canonicalName = "Egyptian hieroglyphic",
characters = "𓀀-𓐮",
}
m["Elba"] = {
canonicalName = "Elbasan",
characters = "𐔀-𐔧",
}
m["Ethi"] = {
canonicalName = "Ethiopic",
otherNames = {"Ge'ez"},
characters = "ሀ-᎙ⶀ-ⷞꬁ-ꬮ",
systems = {"abugida"},
}
m["Geok"] = {
canonicalName = "Khutsuri",
otherNames = {"Nuskhuri", "Asomtavruli"},
characters = "Ⴀ-Ⴭⴀ-ⴭ", -- Ⴀ-Ⴭ is Asomtavruli, ⴀ-ⴭ is Nuskhuri
}
m["Geor"] = {
canonicalName = "Georgian",
otherNames = {"Mkhedruli"},
characters = "Ⴀ-ჼ", -- technically only the range [ა-ჿ] is Mkhedruli
}
m["Glag"] = {
canonicalName = "Glagolitic",
characters = "Ⰰ-ⱞ",
}
m["Goth"] = {
canonicalName = "Gothic",
characters = "𐌰-𐍊",
}
m["Gran"] = {
canonicalName = "Grantha",
characters = "𑌁-𑍴",
systems = {"abugida"},
}
m["Grek"] = {
canonicalName = "Greek",
characters = "Ͱ-Ͽ",
}
m["polytonic"] = {
canonicalName = "Greek",
characters = "ἀ-῾" .. m["Grek"].characters,
}
m["Gujr"] = {
canonicalName = "Gujarati",
characters = "ઁ-૱",
systems = {"abugida"},
}
m["Guru"] = {
canonicalName = "Gurmukhi",
characters = "ਁ-ੵ",
systems = {"abugida"},
}
m["Hang"] = {
canonicalName = "Hangul",
characters = "ᄀ-ᇿ가-힣ㄱ-ㆎ",
}
m["Hani"] = {
canonicalName = "Han",
otherNames = {"Hanzi", "Chu Nom"},
characters = "一-鿌㐀-䶵 -〿𠀀-!-○",
}
m["Hans"] = {
canonicalName = "Simplified Han",
characters = m["Hani"].characters,
}
m["Hant"] = {
canonicalName = "Traditional Han",
characters = m["Hani"].characters,
}
m["Hatr"] = {
canonicalName = "Hatran",
characters = "𐣠-𐣿",
}
m["Hira"] = {
canonicalName = "Hiragana",
characters = "ぁ-ゟ",
}
m["Hluw"] = {
canonicalName = "Anatolian Hieroglyphs",
characters = "𔐀-𔙆",
}
m["Hung"] = {
canonicalName = "Hungarian Runes",
characters = "𐲀-𐲲",
}
m["Kana"] = {
canonicalName = "Katakana",
characters = "゠-ヿㇰ-ㇿ",
}
-- These should be defined after the scripts they are composed of
m["Jpan"] = {
canonicalName = "Japanese",
characters = m["Hira"].characters .. m["Kana"].characters .. m["Hani"].characters,
}
m["Kore"] = {
canonicalName = "Korean",
characters = m["Hang"].characters .. m["Hani"].characters .. "!-○",
}
m["CGK"] = {
canonicalName = "Korean",
}
m["Hano"] = {
canonicalName = "Hanunoo",
characters = "ᜠ-᜴",
systems = {"abugida"},
}
m["Hebr"] = {
canonicalName = "Hebrew",
characters = u(0x0590) .. "-" .. u(0x05FF) .. u(0xFB1D) .. "-" .. u(0xFB4F),
}
m["Hmng"] = {
canonicalName = "Hmong",
otherNames = {"Pahawh Hmong"},
characters = "𖬀-𖮏",
}
m["Ibrn"] = {
canonicalName = "Iberian",
}
m["Inds"] = {
canonicalName = "Indus",
otherNames = {"Harappan", "Indus Valley"},
}
m["IPAchar"] = {
canonicalName = "International Phonetic Alphabet",
}
m["Ital"] = {
canonicalName = "Old Italic",
characters = "𐌀-𐌣",
}
m["Java"] = {
canonicalName = "Javanese",
characters = "ꦀ-꧟",
systems = {"abugida"},
}
m["Jurc"] = {
canonicalName = "Jurchen",
}
m["Kali"] = {
canonicalName = "Kayah Li",
characters = "꤀-꤯",
}
m["Khar"] = {
canonicalName = "Kharoshthi",
characters = "𐨀-𐩘",
systems = {"abugida"},
}
m["Khmr"] = {
canonicalName = "Khmer",
characters = "ក-៹",
systems = {"abugida"},
}
m["Khoj"] = {
canonicalName = "Khojki",
characters = "𑈀-𑈽",
systems = {"abugida"},
}
m["Kitl"] = {
canonicalName = "Khitan Large",
}
m["Kits"] = {
canonicalName = "Khitan Small",
}
m["Knda"] = {
canonicalName = "Kannada",
characters = "ಂ-ೲ",
systems = {"abugida"},
}
m["Kthi"] = {
canonicalName = "Kaithi",
characters = "𑂀-𑃁",
systems = {"abugida"},
}
m["Lana"] = {
canonicalName = "Lanna",
characters = "ᨠ-᪭",
}
m["Laoo"] = {
canonicalName = "Lao",
characters = "ກ-ໟ",
systems = {"abugida"},
}
m["Latn"] = {
canonicalName = "Latin",
otherNames = {"Roman", "Rumi", "Romaji", "Rōmaji"},
characters = "0-9A-Za-z¡-\205\175Ḁ-ỿ",
}
m["Latf"] = {
canonicalName = "Fraktur",
otherNames = {"Blackletter"},
characters = m["Latn"].characters,
}
m["Latinx"] = {
canonicalName = "Latin",
characters = m["Latn"].characters .. "Ⱡ-Ɀ꜠-ꟿꬰ-ꭥ",
}
m["nv-Latn"] = {
canonicalName = "Latin",
characters = m["Latn"].characters,
}
m["pjt-Latn"] = {
canonicalName = "Latin",
characters = m["Latn"].characters,
}
m["Leke"] = {
canonicalName = "Leke",
systems = {"abugida"},
}
m["Lepc"] = {
canonicalName = "Lepcha",
characters = "ᰀ-ᱏ",
systems = {"abugida"},
}
m["Limb"] = {
canonicalName = "Limbu",
characters = "ᤀ-᥏",
systems = {"abugida"},
}
m["Lina"] = {
canonicalName = "Linear A",
characters = "𐘀-𐝧",
}
m["Linb"] = {
canonicalName = "Linear B",
characters = "𐀀-𐃺",
}
m["Lisu"] = {
canonicalName = "Lisu",
otherNames = {"Fraser"},
characters = "ꓐ-꓿",
}
m["Lyci"] = {
canonicalName = "Lycian",
characters = "𐊀-𐊜",
}
m["Lydi"] = {
canonicalName = "Lydian",
characters = "𐤠-𐤿",
}
m["Mahj"] = {
canonicalName = "Mahajani",
characters = "𑅶-𑅐",
systems = {"abugida"},
}
m["Mand"] = {
canonicalName = "Mandaic",
characters = "ࡀ-࡞",
}
m["Mani"] = {
canonicalName = "Manichaean",
characters = "𐫀-𐫶",
}
m["Maya"] = {
canonicalName = "Maya",
otherNames = {"Maya hieroglyphic", "Mayan", "Mayan hieroglyphic"},
}
m["Mend"] = {
canonicalName = "Mende",
otherNames = {"Mende Kikakui"},
characters = "𞠀-𞣖",
}
m["Merc"] = {
canonicalName = "Meroitic cursive",
characters = "𐦠-𐦿",
systems = {"abugida"},
}
m["Mero"] = {
canonicalName = "Meroitic hieroglyphic",
characters = "𐦀-𐦟",
systems = {"abugida"},
}
m["Mlym"] = {
canonicalName = "Malayalam",
characters = "ം-ൿ",
systems = {"abugida"},
}
m["Modi"] = {
canonicalName = "Modi",
characters = "𑘀-𑙙",
systems = {"abugida"},
}
m["Mong"] = {
canonicalName = "Mongolian",
characters = "᠀-ᢪ",
}
m["Mroo"] = {
canonicalName = "Mro",
characters = "𖩀-𖩯",
}
m["Mtei"] = {
canonicalName = "Meitei Mayek",
characters = "ꯀ-ꫠ-",
}
m["Mult"] = {
canonicalName = "Multani",
characters = "𑊀-𑊩",
systems = {"abugida"},
}
m["musical"] = {
canonicalName = "Musical notation",
characters = "𝄀-𝇝",
}
m["Mymr"] = {
canonicalName = "Burmese",
otherNames = {"Myanmar"},
characters = "က-႟ꩠ-ꩿꧠ-ꧾ",
systems = {"abugida"},
}
m["Narb"] = {
canonicalName = "Old North Arabian",
characters = "𐪀-𐪟",
}
m["Nbat"] = {
canonicalName = "Nabataean",
otherNames = {"Nabatean"},
characters = "𐢀-𐢯",
}
m["Nkoo"] = {
canonicalName = "N'Ko",
characters = "߀-ߺ",
}
m["None"] = {
canonicalName = "No script specified",
-- This should not have any characters listed
character_category = false, -- none
}
m["Ogam"] = {
canonicalName = "Ogham",
characters = " -᚜",
}
m["Olck"] = {
canonicalName = "Ol Chiki",
characters = "᱐-᱿",
}
m["Orkh"] = {
canonicalName = "Orkhon runes",
characters = "𐰀-𐱈",
}
m["Orya"] = {
canonicalName = "Oriya",
characters = "ଁ-୷",
}
m["Osge"] = {
canonicalName = "Osage",
}
m["Osma"] = {
canonicalName = "Osmanya",
characters = "𐒀-𐒩",
}
m["Palm"] = {
canonicalName = "Palmyrene",
characters = "𐡠-𐡿",
}
m["Pauc"] = {
canonicalName = "Pau Cin Hau",
characters = "𑫀-𑫸",
}
m["Perm"] = {
canonicalName = "Old Permic",
characters = "𐍐-𐍺",
}
m["Phag"] = {
canonicalName = "Phags-pa",
characters = "ꡀ-꡷",
systems = {"abugida"},
}
m["Marc"] = {
canonicalName = "Marchen",
characters = m["Phag"].characters,
systems = {"abugida"},
}
m["Phli"] = {
canonicalName = "Inscriptional Pahlavi",
characters = "𐭠-𐭿",
}
m["Phlp"] = {
canonicalName = "Psalter Pahlavi",
characters = "𐮀-𐮯",
}
m["Phlv"] = {
canonicalName = "Book Pahlavi",
-- Not in Unicode
}
m["Phnx"] = {
canonicalName = "Phoenician",
characters = "𐤀-𐤟",
}
m["Plrd"] = {
canonicalName = "Pollard",
characters = "𖼀-𖾟",
systems = {"abugida"},
}
m["Prti"] = {
canonicalName = "Parthian",
characters = "𐭀-𐭟",
}
m["Rjng"] = {
canonicalName = "Rejang",
characters = "ꤰ-꥟",
systems = {"abugida"},
}
m["Ruminumerals"] = {
canonicalName = "Rumi numerals",
characters = "𐹠-𐹾",
character_category = "Rumi numerals",
}
m["Runr"] = {
canonicalName = "Runic",
characters = "ᚠ-ᛰ",
}
m["Samr"] = {
canonicalName = "Samaritan",
characters = "ࠀ-࠾",
}
m["Sarb"] = {
canonicalName = "Old South Arabian",
characters = "𐩠-𐩿",
}
m["Saur"] = {
canonicalName = "Saurashtra",
characters = "ꢀ-꣙",
}
m["Sgnw"] = {
canonicalName = "SignWriting",
characters = "𝠀-𝪯",
}
m["Shaw"] = {
canonicalName = "Shavian",
characters = "𐑐-𐑿",
}
m["Shrd"] = {
canonicalName = "Sharada",
characters = "𑆀-𑇙",
systems = {"abugida"},
}
m["Sidd"] = {
canonicalName = "Siddham",
characters = "𑖀-𑗝",
systems = {"abugida"},
}
m["Sind"] = {
canonicalName = "Khudawadi",
characters = "𑊰-𑋹",
systems = {"abugida"},
}
m["Sinh"] = {
canonicalName = "Sinhalese",
characters = "ං-෴",
systems = {"abugida"},
}
m["Sora"] = {
canonicalName = "Sorang Sompeng",
otherNames = {"Sora Sompeng"},
characters = "𑃐-𑃹"
}
m["Sund"] = {
canonicalName = "Sundanese",
characters = "ᮀ-ᮿ",
systems = {"abugida"},
}
m["Sylo"] = {
canonicalName = "Syloti Nagri",
otherNames = {"Sylheti Nagari"},
systems = {"abugida"},
}
m["Syrc"] = {
canonicalName = "Syriac",
characters = "܀-ݏ",
}
m["Tagb"] = {
canonicalName = "Tagbanwa",
characters = "ᝠ-ᝳ",
systems = {"abugida"},
}
m["Takr"] = {
canonicalName = "Takri",
characters = "𑚀-𑛉",
systems = {"abugida"},
}
m["Tale"] = {
canonicalName = "Tai Le",
characters = "ᥐ-ᥴ",
systems = {"abugida"},
}
m["Talu"] = {
canonicalName = "New Tai Lue",
characters = "ᦀ-᧟",
systems = {"abugida"},
}
m["Taml"] = {
canonicalName = "Tamil",
characters = "ஂ-௺",
systems = {"abugida"},
}
m["Tang"] = {
canonicalName = "Tangut",
}
m["Tavt"] = {
canonicalName = "Tai Viet",
characters = "ꪀ-꫟",
}
m["Telu"] = {
canonicalName = "Telugu",
characters = "ఁ-౿",
systems = {"abugida"},
}
m["Teng"] = {
canonicalName = "Tengwar",
}
m["Tfng"] = {
canonicalName = "Tifinagh",
otherNames = {"Libyco-Berber", "Berber"},
characters = "ⴰ-⵿",
}
m["Tglg"] = {
canonicalName = "Tagalog",
characters = "ᜀ-᜔",
}
m["Thaa"] = {
canonicalName = "Thaana",
characters = "ހ-ޱ",
systems = {"abugida"},
}
m["Thai"] = {
canonicalName = "Thai",
characters = "ก-๛",
systems = {"abugida"},
}
m["Tibt"] = {
canonicalName = "Tibetan",
characters = "ༀ-࿚",
systems = {"abugida"},
}
m["Tirh"] = {
canonicalName = "Tirhuta",
characters = "𑒀-𑓙",
systems = {"abugida"},
}
m["xzh-Tibt"] = {
canonicalName = "Zhang-Zhung",
systems = {"abugida"},
}
m["Ugar"] = {
canonicalName = "Ugaritic",
characters = "𐎀-𐎟",
}
m["Vaii"] = {
canonicalName = "Vai",
characters = "ꔀ-ꘫ",
}
m["Wara"] = {
canonicalName = "Varang Kshiti",
characters = "𑢠-𑣿",
}
m["Xpeo"] = {
canonicalName = "Old Persian",
characters = "𐎠-𐏕",
}
m["Xsux"] = {
canonicalName = "Cuneiform",
otherNames = {"Sumero-Akkadian Cuneiform"},
characters = "𒀀-𒍮𒐀-𒑳",
}
m["Yiii"] = {
canonicalName = "Yi",
characters = "ꀀ-꓆",
}
m["Zmth"] = {
canonicalName = "mathematical notation",
characters = "ℵ∀-⋿⟀-⟯⦀-⧿⨀-⫿𝐀-𝟿",
character_category = "Mathematical notation symbols" -- ?
}
m["Zsym"] = {
canonicalName = "symbol",
characters = "─-➿←⇿⌀-⏳🌀-🛅",
character_category = false, -- none
}
m["Zyyy"] = {
canonicalName = "undetermined",
-- This should not have any characters listed, probably
character_category = false, -- none
}
m["Zzzz"] = {
canonicalName = "uncoded",
-- This should not have any characters listed
character_category = false, -- none
}
return m