Modul:scripts/data
This module contains definitions and metadata for all script codes on Wiktionary. See Wiktionary:Scripts for more information.
This module must not be imported using require
. Instead, it is imported like this:
local m_scripts = mw.loadData("Module:scripts")
This ensures that the data is only loaded once per page, rather than once for every module invocation like normal.
To access this data from templates, use Module:script utilities.
See Module:data consistency check to check for errors in this data module.
Required values
szerkesztésEvery entry in the table must contain the following properties:
canonicalName
- The "canonical" name of the script. This is the name that is used in Wiktionary entries and category names.
Optional values
szerkesztésotherNames
- A table of all the names that this script is known by, other than the canonical name.
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 (for 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 (for example,"A-Za-z"
). This character set is used for automatic script recognition (seefindBestScript
in Module:scripts) if a language has this script's code in itsscripts
table. character_category
- Used by Module:character info. If
false
, prevents{{character info}}
from adding acharacters
category, such as Category:Latin script characters. direction
- Describes the direction of writing. Most scripts are "ltr" (left-to-right) so they can be omitted. Some scripts are "rtl" (right-to-left) anyway. Very few scripts are "down" such as Mongolian and Phags-pa.
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/script cat. The system will only be displayed if there is only one category. See Category:Latin script for an example.
--[=[
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",
characters = "𞤀-𞥟",
direction = "rtl",
}
m["Afak"] = {
canonicalName = "afaka",
}
m["Aghb"] = {
canonicalName = "kaukázusi albán",
characters = "𐔰-𐕣𐕯",
}
m["Ahom"] = {
canonicalName = "ahom",
characters = "𑜀-𑜿",
systems = {"abugida"},
}
m["Arab"] = {
canonicalName = "arab",
varieties = {"Jawi", "Nastaliq", "Nastaleeq"},
characters = "-ۿݐ-ݿࢠ-ࣿﭐ-﷽ﹰ-ﻼ",
direction = "rtl",
systems = {"abjad"}, -- more precisely, impure abjad
}
m["fa-Arab"] = {
canonicalName = "arab",
otherNames = {"Perso-Arabic"},
characters = m["Arab"].characters,
direction = "rtl",
parent = "Arab",
}
m["kk-Arab"] = {
canonicalName = "arab",
characters = m["Arab"].characters,
direction = "rtl",
parent = "Arab",
}
m["ks-Arab"] = {
canonicalName = "arab",
characters = m["Arab"].characters,
direction = "rtl",
parent = "Arab",
}
m["ku-Arab"] = {
canonicalName = "arab",
characters = m["Arab"].characters,
direction = "rtl",
parent = "Arab",
}
m["ms-Arab"] = {
canonicalName = "arab",
characters = m["Arab"].characters,
direction = "rtl",
parent = "Arab",
}
m["mzn-Arab"] = {
canonicalName = "arab",
characters = m["Arab"].characters,
direction = "rtl",
parent = "Arab",
}
m["ota-Arab"] = {
canonicalName = "arab",
characters = m["Arab"].characters,
direction = "rtl",
parent = "Arab",
}
m["pa-Arab"] = {
canonicalName = "shahmukhi",
otherNames = {"Arabic"},
characters = m["Arab"].characters,
direction = "rtl",
parent = "Arab",
}
m["ps-Arab"] = {
canonicalName = "arab",
characters = m["Arab"].characters,
direction = "rtl",
parent = "Arab",
}
m["sd-Arab"] = {
canonicalName = "arab",
characters = m["Arab"].characters,
direction = "rtl",
parent = "Arab",
}
m["tt-Arab"] = {
canonicalName = "arab",
characters = m["Arab"].characters,
direction = "rtl",
parent = "Arab",
}
m["ug-Arab"] = {
canonicalName = "arab",
characters = m["Arab"].characters,
direction = "rtl",
parent = "Arab",
}
m["ur-Arab"] = {
canonicalName = "arab",
characters = m["Arab"].characters,
direction = "rtl",
parent = "Arab",
}
-- Aran (Nastaliq) is subsumed into Arab
m["Armi"] = {
canonicalName = "imperial aramaic",
characters = "𐡀-𐡟",
direction = "rtl",
systems = {"abjad"},
}
m["Armn"] = {
canonicalName = "örmény",
characters = "Ա-֏ﬓ-ﬗ",
}
m["Avst"] = {
canonicalName = "avestan",
characters = "𐬀-𐬿",
direction = "rtl",
}
m["pal-Avst"] = {
canonicalName = "pazend",
characters = m["Avst"].characters,
direction = "rtl",
parent = "Avst",
}
m["Bali"] = {
canonicalName = "balinese",
characters = "ᬀ-᭼",
systems = {"abugida"},
}
m["Bamu"] = {
canonicalName = "bamum",
characters = "ꚠ-꛷𖠀-𖨸",
}
m["Bass"] = {
canonicalName = "bassa",
aliases = {"Bassa Vah", "Vah"},
characters = "𖫐-𖫵",
}
m["Batk"] = {
canonicalName = "batak",
characters = "ᯀ-᯿",
systems = {"abugida"},
}
m["Beng"] = {
canonicalName = "bengáli",
characters = "ঀ-ঃঅ-ঌএঐও-নপ-রললশ-হ়-ৄেৈো-ৎৗড়ঢ়য়়ৠ-ৣ০-৯",
systems = {"abugida"},
}
m["as-Beng"] = {
canonicalName = "bengáli",
otherNames = {"Bengali-Assamese", "Assamese", "Eastern Nagari"},
characters = "ঁ-ঃঅ-ঌএঐও-নপ-যশ-হ়-ৄেৈো-ৎৗড়ঢ়য়়ৠ-ৣ০-ৱ",
systems = {"abugida"},
}
m["Bhks"] = {
canonicalName = "bhaiksuki",
characters = "𑰀-𑱬",
systems = {"abugida"},
}
m["Bopo"] = {
canonicalName = "zhuyin",
aliases = {"Zhuyin Fuhao", "Bopomofo"},
characters = "ㄅ-ㄯㆠ-ㆺ",
}
m["Brah"] = {
canonicalName = "brahmi",
characters = "𑀀-𑁿",
systems = {"abugida"},
}
m["Brai"] = {
canonicalName = "braille",
characters = "⠀-⣿",
}
m["Bugi"] = {
canonicalName = "buginese",
aliases = {"Lontara"},
characters = "ᨀ-᨟",
systems = {"abugida"},
}
m["Buhd"] = {
canonicalName = "buhid",
characters = "ᝀ-ᝓ",
systems = {"abugida"},
}
m["Cakm"] = {
canonicalName = "chakma",
characters = "𑄀-𑅆",
systems = {"abugida"},
}
m["Cans"] = {
canonicalName = "kanadai szótagírás",
characters = "᐀-ᙿ",
systems = {"abugida"},
}
m["Cari"] = {
canonicalName = "carian",
characters = "𐊠-𐋐",
systems = {"alphabet"},
}
m["Cham"] = {
canonicalName = "cham",
characters = "ꨀ-꩟",
systems = {"abugida"},
}
m["Chrs"] = {
canonicalName = "chorasmian",
characters = "𐾰-𐿋",
systems = {"abjad"},
}
m["Cher"] = {
canonicalName = "cherokee",
characters = "Ꭰ-Ᏼꭰ-ꮿ",
systems = {"syllabary"},
}
m["Copt"] = {
canonicalName = "kopt",
characters = "Ϣ-ϯⲀ-⳿𐋡-𐋻", -- this is mostly "Coptic", not unified "Greek and Coptic"
systems = {"alphabet"},
}
m["Cprt"] = {
canonicalName = "ciprusi",
characters = "𐠀-𐠿",
direction = "rtl",
systems = {"syllabary"},
}
m["Cyrl"] = {
canonicalName = "cirill",
characters = "Ѐ-џѢѣѪѫѬѭѲѳѴѵҊ-ԧꚀ-ꚗ",
systems = {"alphabet"},
}
m["Cyrs"] = {
canonicalName = "ócirill",
aliases = { "Early Cyrillic" },
characters = "Ѐ-ԧꙀ-ꚗ",
wikipedia_article = "Early Cyrillic alphabet",
systems = {"alphabet"},
}
m["Deva"] = {
canonicalName = "dévanágari",
characters = "ऀ-ॿ꣠-ꣿ",
systems = {"abugida"},
}
m["Dogr"] = {
canonicalName = "dogra",
characters = "𑠀-𑠻",
systems = {"abugida"},
}
m["Dsrt"] = {
canonicalName = "deseret",
characters = "𐐀-𐑏",
systems = {"alphabet"},
}
m["Dupl"] = {
canonicalName = "duployan",
characters = "𛰀-𛲟",
}
m["Egyd"] = {
canonicalName = "démotikus",
systems = {"abjad", "logography"},
}
m["Egyp"] = {
canonicalName = "egyiptomi hieroglif",
varieties = {"Hieratic"},
characters = "𓀀-𓐮",
wikipedia_article = "Egyptian hieroglyphs",
systems = {"abjad", "logography"},
}
m["Elba"] = {
canonicalName = "elbasan",
characters = "𐔀-𐔧",
systems = {"alphabet"},
}
m["Ethi"] = {
canonicalName = "etióp",
aliases = {"Ge'ez"},
characters = "ሀ-᎙ⶀ-ⷞꬁ-ꬮ",
systems = {"abugida"},
}
m["Geok"] = {
canonicalName = "khutsuri",
varieties = {"Nuskhuri", "Asomtavruli"},
characters = "Ⴀ-Ⴭⴀ-ⴭ", -- Ⴀ-Ⴭ is Asomtavruli, ⴀ-ⴭ is Nuskhuri
systems = {"alphabet"},
}
m["Geor"] = {
canonicalName = "grúz",
varieties = {"Mkhedruli", "Mtavruli"},
characters = "ა-ჿᲐ-Ჿ", -- ა-ჿ is lowercase Mkhedruli; Ა-Ჿ is uppercase Mkhedruli (Mtavruli)
systems = {"alphabet"},
}
m["Glag"] = {
canonicalName = "glagolita",
characters = "Ⰰ-ⱞ𞀀-𞀪",
systems = {"alphabet"},
}
m["Gong"] = {
canonicalName = "gunjala gondi",
characters = "𑵠-𑶩",
systems = {"abugida"},
}
m["Gonm"] = {
canonicalName = "masaram gondi",
characters = "𑴀-𑵙",
systems = {"abugida"},
}
m["Goth"] = {
canonicalName = "gothic",
characters = "𐌰-𐍊",
systems = {"alphabet"},
}
m["Gran"] = {
canonicalName = "grantha",
characters = "𑌁-𑍴",
systems = {"abugida"},
}
m["Grek"] = {
canonicalName = "görög",
characters = "Ͱ-ϡϰ-Ͽ",
systems = {"alphabet"},
}
m["polytonic"] = {
canonicalName = "görög",
characters = "ἀ-῾" .. m["Grek"].characters,
parent = "Grek",
systems = {"alphabet"},
}
m["Gujr"] = {
canonicalName = "gudzsaráti",
characters = "ઁ-૱",
systems = {"abugida"},
}
m["Guru"] = {
canonicalName = "gurmukhi",
characters = "ਁ-੶",
systems = {"abugida"},
}
m["Hang"] = {
canonicalName = "hangul",
aliases = {"Hangeul"},
characters = "ᄀ-ᇿ가-힣ㄱ-ㆎ",
systems = {"syllabary"},
}
m["Hani"] = {
canonicalName = "kínai",
varieties = {"Hanzi", "Chu Nom"},
characters = "一-鿿㐀-䶵𠀀-"..u(0x2EBE0).."﨎﨏﨑﨓﨔﨟﨡﨣﨤﨧﨨﨩⺀-㇀-㇣ -〿㍻-㍿㋿",
systems = {"logography"},
}
m["Hans"] = {
canonicalName = "egyszerűsített kínai",
characters = m["Hani"].characters,
systems = {"logography"},
}
m["Hant"] = {
canonicalName = "hagyományos kínai",
characters = m["Hani"].characters,
systems = {"logography"},
}
m["Hatr"] = {
canonicalName = "hatran",
characters = "𐣠-𐣿",
systems = {"abjad"},
}
m["Hira"] = {
canonicalName = "hiragana",
varieties = {"Hentaigana"},
characters = "ぁ-ゟ𛀁-𛄞𛅐𛅑𛅒🈀",
systems = {"syllabary"},
}
m["Hluw"] = {
canonicalName = "anatóliai hieroglifák",
characters = "𔐀-𔙆",
wikipedia_article = "Anatolian hieroglyphs",
}
m["Hung"] = {
canonicalName = "ómagyar",
aliases = {"Hungarian runic"},
characters = "𐲀-𐲲",
}
m["Kana"] = {
canonicalName = "katakana",
characters = "゠-ヿㇰ-ㇿ㌀-㍗𛀀𛅤𛅥𛅦𛅧",
systems = {"syllabary"},
}
-- These should be defined after the scripts they are composed of
m["Kore"] = {
canonicalName = "koreai",
characters = m["Hang"].characters .. m["Hani"].characters .. "!-○",
systems = {"syllabary", "logography"},
}
m["Hano"] = {
canonicalName = "hanunoo",
characters = "ᜠ-᜴",
systems = {"abugida"},
}
m["Hebr"] = {
canonicalName = "héber",
characters = u(0x0590) .. "-" .. u(0x05FF) .. u(0xFB1D) .. "-" .. u(0xFB4F),
direction = "rtl",
systems = {"abjad"}, -- more precisely, impure abjad
}
m["Hmng"] = {
canonicalName = "hmong",
aliases = {"Pahawh Hmong"},
characters = "𖬀-𖮏",
}
m["Ibrn"] = {
canonicalName = "iberian",
}
m["Imag"] = {
-- To be used to avoid any formatting or link processing
canonicalName = "image-rendered",
-- This should not have any characters listed
character_category = false,
}
m["Inds"] = {
canonicalName = "indus",
aliases = {"Harappan", "Indus Valley"},
}
m["IPAchar"] = {
canonicalName = "international phonetic alphabet",
}
m["Ital"] = {
canonicalName = "old italic",
characters = "𐌀-𐌣",
systems = {"alphabet"},
}
m["Java"] = {
canonicalName = "jávai",
characters = "ꦀ-꧟",
systems = {"abugida"},
}
m["Jurc"] = {
canonicalName = "jurchen",
}
m["Kali"] = {
canonicalName = "kayah li",
characters = "꤀-꤯",
}
m["Khar"] = {
canonicalName = "kharoshthi",
characters = "𐨀-𐩘",
systems = {"abugida"},
direction = "rtl",
}
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 = "ಀ-ೲ",
systems = {"abugida"},
}
m["Kthi"] = {
canonicalName = "kaithi",
characters = "𑂀-",
systems = {"abugida"},
}
m["Lana"] = {
canonicalName = "tai tham",
aliases = {"Tham", "Tua Mueang", "Lanna"},
characters = "ᨠ-᪭",
systems = {"abugida"},
}
m["Laoo"] = {
canonicalName = "lao",
characters = "ກ-ໟ",
systems = {"abugida"},
}
m["Latn"] = {
canonicalName = "latin",
aliases = {"Roman"},
varieties = {"Rumi", {"Romaji", "Rōmaji"}},
characters = "A-Za-zÀ-ÖØ-öø-ɏḀ-ỿ",
systems = {"alphabet"},
}
m["Latf"] = {
canonicalName = "fraktur",
otherNames = {"Blackletter"}, -- Blackletter is actually the parent "script"
characters = m["Latn"].characters,
}
m["Latinx"] = {
canonicalName = "latin",
characters = m["Latn"].characters .. "Ⱡ-Ɀ꜠-ꟿꬰ-ꭥ",
parent = "Latn",
}
m["nv-Latn"] = {
canonicalName = "latin",
characters = m["Latn"].characters,
parent = "Latn",
}
m["pjt-Latn"] = {
canonicalName = "latin",
characters = m["Latn"].characters,
parent = "Latn",
}
m["Jpan"] = {
canonicalName = "japán",
characters = m["Hira"].characters .. m["Kana"].characters .. m["Hani"].characters .. m["Latn"].characters,
systems = {"syllabary", "logography"},
}
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 = "lineáris A",
characters = "𐘀-𐝧",
}
m["Linb"] = {
canonicalName = "lineáris B",
characters = "𐀀-𐃺",
}
m["Lisu"] = {
canonicalName = "lisu",
aliases = {"Fraser"},
characters = "ꓐ-꓿",
systems = {"alphabet"},
}
m["Lyci"] = {
canonicalName = "lycian",
characters = "𐊀-𐊜",
systems = {"alphabet"},
}
m["Lydi"] = {
canonicalName = "lüd",
characters = "𐤠-𐤿",
systems = {"alphabet"},
}
m["Mahj"] = {
canonicalName = "mahajani",
characters = "𑅐-𑅶",
systems = {"abugida"},
}
m["Maka"] = {
canonicalName = "makasar",
characters = "𑻠-𑻸",
systems = {"abugida"},
}
m["Mand"] = {
canonicalName = "mandaic",
aliases = {"Mandaean"},
characters = "ࡀ-࡞",
direction = "rtl",
}
m["Mani"] = {
canonicalName = "manichaean",
characters = "𐫀-𐫶",
direction = "rtl",
systems = {"abjad"},
}
m["Maya"] = {
canonicalName = "maja",
aliases = {"Maya hieroglyphic", "Mayan", "Mayan hieroglyphic"},
characters = "𝋠-𝋳",
}
m["Medf"] = {
canonicalName = "medefaidrin",
aliases = {"Oberi Okaime", "Oberi Ɔkaimɛ"},
characters = "𖹀-𖺚",
}
m["Mend"] = {
canonicalName = "mende",
aliases = {"Mende Kikakui"},
characters = "𞠀-𞣖",
direction = "rtl",
}
m["Merc"] = {
canonicalName = "meroitic cursive",
characters = "𐦠-𐦿",
systems = {"abugida"},
}
m["Mero"] = {
canonicalName = "meroitic hieroglyphic",
characters = "𐦀-𐦟",
systems = {"abugida"},
}
m["Mlym"] = {
canonicalName = "malajálam",
characters = "ം-ൿ",
systems = {"abugida"},
}
m["Modi"] = {
canonicalName = "modi",
characters = "𑘀-𑙙",
systems = {"abugida"},
}
m["Mong"] = {
canonicalName = "mongolian",
characters = "᠀-ᢪ",
direction = "down",
}
m["Morse"] = {
canonicalName = "morse code",
}
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 = "zenei jelölés",
characters = "𝄀-𝇝",
systems = {"pictography"},
}
m["Mymr"] = {
canonicalName = "burmai",
aliases = {"Myanmar"},
characters = "က-႟ꩠ-ꩿꧠ-ꧾ",
systems = {"abugida"},
}
m["Narb"] = {
canonicalName = "óészakarab",
characters = "𐪀-𐪟",
direction = "rtl",
systems = {"abjad"},
}
m["Nbat"] = {
canonicalName = "nabataean",
aliases = {"Nabatean"},
characters = "𐢀-𐢯",
direction = "rtl",
systems = {"abjad"},
}
m["Newa"] = {
canonicalName = "newa",
aliases = {"Newar", "Newari", "Prachalit Nepal"}, -- and Ranjana?
characters = "𑐀-𑑞",
systems = {"abugida"},
}
m["Nkoo"] = {
canonicalName = "n'Ko",
characters = "߀-߿",
direction = "rtl",
}
m["None"] = {
canonicalName = "unspecified", -- renders as 'unspecified script'
-- This should not have any characters listed
character_category = false, -- none
}
m["Nshu"] = {
canonicalName = "nushu",
aliases = {"Nüshu"},
characters = "𖿡𛅰-𛋻",
systems = {"syllabary"},
}
m["Ogam"] = {
canonicalName = "ogham",
characters = " -᚜",
}
m["Olck"] = {
canonicalName = "ol chiki",
characters = "᱐-᱿",
}
m["Orkh"] = {
canonicalName = "orkhon runes",
characters = "𐰀-𐱈",
direction = "rtl",
}
m["Orya"] = {
canonicalName = "oriya",
aliases = {"Odia"},
characters = "ଁ-୷",
}
m["Osge"] = {
canonicalName = "osage",
characters = "𐒰-𐓻",
}
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 = "ópermi",
characters = "𐍐-𐍺",
}
m["Phag"] = {
canonicalName = "phags-pa",
characters = "ꡀ-꡷",
systems = {"abugida"},
}
m["Marc"] = {
canonicalName = "marchen",
characters = "𑱰-𑲶",
systems = {"abugida"},
}
m["Phli"] = {
canonicalName = "inscriptional pahlavi",
characters = "𐭠-𐭿",
direction = "rtl",
systems = {"abjad"},
}
m["Phlp"] = {
canonicalName = "psalter pahlavi",
characters = "𐮀-𐮯",
direction = "rtl",
systems = {"abjad"},
}
m["Phlv"] = {
canonicalName = "book pahlavi",
direction = "rtl",
systems = {"abjad"},
-- Not in Unicode
}
m["Phnx"] = {
canonicalName = "főníciai",
characters = "𐤀-𐤟",
direction = "rtl",
systems = {"abjad"},
}
m["Plrd"] = {
canonicalName = "pollard",
characters = "𖼀-𖾟",
systems = {"abugida"},
}
m["Prti"] = {
canonicalName = "inscriptional parthian",
characters = "𐭀-𐭟",
direction = "rtl",
}
m["Rjng"] = {
canonicalName = "rejang",
characters = "ꤰ-꥟",
systems = {"abugida"},
}
m["Rohg"] = {
canonicalName = "hanifi rohingya",
characters = "𐴀-𐴹",
direction = "rtl",
systems = {"alphabet"},
}
m["Ruminumerals"] = {
canonicalName = "rumi numerals",
characters = "𐹠-𐹾",
character_category = "Rumi numerals",
}
m["Runr"] = {
canonicalName = "rúna",
characters = "ᚠ-ᛰ",
systems = {"alphabet"},
}
m["Samr"] = {
canonicalName = "samaritan",
characters = "ࠀ-࠾",
direction = "rtl",
systems = {"abjad"},
}
m["Sarb"] = {
canonicalName = "ódélarab",
characters = "𐩠-𐩿",
direction = "rtl",
systems = {"abjad"},
}
m["Saur"] = {
canonicalName = "saurashtra",
characters = "ꢀ-꣙",
systems = {"abugida"},
}
m["Semap"] = {
canonicalName = "flag semaphore",
systems = {"pictography"},
}
m["Sgnw"] = {
canonicalName = "signWriting",
characters = "𝠀-𝪯",
systems = {"pictography"},
}
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 = "szingaléz",
characters = "ං-෴",
systems = {"abugida"},
}
m["Sogd"] = {
canonicalName = "sogdian",
characters = "𐼰-𐽙",
direction = "rtl",
systems = {"abjad"},
}
m["Sogo"] = {
canonicalName = "old sogdian",
characters = "𐼀-𐼧",
direction = "rtl",
systems = {"abjad"},
}
m["Sora"] = {
canonicalName = "sorang sompeng",
aliases = {"Sora Sompeng"},
characters = "𑃐-𑃹",
}
m["Soyo"] = {
canonicalName = "soyombo",
characters = "𑩐-𑪢",
systems = {"abugida"},
}
m["Sund"] = {
canonicalName = "szundanéz",
characters = "ᮀ-ᮿ",
systems = {"abugida"},
}
m["Sylo"] = {
canonicalName = "syloti nagri",
aliases = {"Sylheti Nagari"},
characters = "ꠀ-꠫",
systems = {"abugida"},
}
m["Syrc"] = {
canonicalName = "szír",
characters = "܀-ݏ"..u(0x0860).."-"..u(0x086A),
direction = "rtl",
systems = {"abjad"}, -- more precisely, impure abjad
}
-- Syre, Syrj, Syrn are apparently subsumed into Syrc; discuss if this causes issues
m["Tagb"] = {
canonicalName = "tagbanwa",
characters = "ᝠ-ᝳ",
systems = {"abugida"},
}
m["Takr"] = {
canonicalName = "takri",
characters = "𑚀-𑛉",
systems = {"abugida"},
}
m["Tale"] = {
canonicalName = "tai nüa",
aliases = {"Tai Nuea", "New Tai Nüa", "New Tai Nuea", "Dehong Dai", "Tai Dehong", "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",
characters = "𖿠𗀀-𘫲",
systems = {"logography", "syllabary"},
}
m["Tavt"] = {
canonicalName = "tai viet",
characters = "ꪀ-꫟",
systems = {"abugida"},
}
m["Telu"] = {
canonicalName = "telugu",
characters = "ఀ-౿",
systems = {"abugida"},
}
m["Teng"] = {
canonicalName = "tengwar",
}
m["Tfng"] = {
canonicalName = "tifinagh",
otherNames = {"Libyco-Berber", "Berber"}, -- per Wikipedia, Libyco-Berber is the parent
characters = "ⴰ-⵿",
systems = {"abjad", "alphabet"},
}
m["Tglg"] = {
canonicalName = "baybayin",
aliases = {"Tagalog"},
characters = "ᜀ-᜔",
systems = {"abugida"},
}
m["Thaa"] = {
canonicalName = "thaana",
characters = "ހ-ޱ",
systems = {"abugida"},
direction = "rtl",
}
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-𐎟",
systems = {"abjad"},
}
m["Vaii"] = {
canonicalName = "vai",
characters = "ꔀ-ꘫ",
systems = {"syllabary"},
}
m["Wara"] = {
canonicalName = "varang kshiti",
characters = "𑢠-𑣿",
}
m["Xpeo"] = {
canonicalName = "óperzsa",
characters = "𐎠-𐏕",
}
m["Xsux"] = {
canonicalName = "ékírás",
aliases = {"Sumero-Akkadian Cuneiform"},
characters = "𒀀-𒍮𒐀-𒑳",
}
m["Yiii"] = {
canonicalName = "yi",
characters = "ꀀ-꓆",
systems = {"syllabary"},
}
m["Zanb"] = {
canonicalName = "zanabazar square",
characters = u(0x11A00).."-"..u(0x11A47),
}
m["Zmth"] = {
canonicalName = "matematikai jelölés",
characters = "ℵ∀-⋿⟀-⟯⦀-⫿𝐀-𝟿",
character_category = "Mathematical notation symbols", -- ?
}
m["Zsym"] = {
canonicalName = "symbol",
characters = "─-➿←-⇿⌀-⏿⬀-⯾🀀-🃵🌀-🩭",
character_category = false, -- none
systems = {"pictography"},
}
m["Zyyy"] = {
canonicalName = "meghatározatlan",
-- This should not have any characters listed, probably
character_category = false, -- none
characters = m["Latn"].characters,
}
m["Zzzz"] = {
canonicalName = "uncoded",
-- This should not have any characters listed
character_category = false, -- none
}
return m