local data = {}
local U = mw.ustring.char
local macron = U(0x304)
local spacing_macron = U(0xAF)
local modifier_macron = U(0x2C9)
local breve = U(0x306)
local spacing_breve = U(0x2D8)
local rough = U(0x314)
local smooth = U(0x313)
local diaeresis = U(0x308)
local acute = U(0x301)
local grave = U(0x300)
local circum = U(0x342)
local Latin_circum = U(0x302)
local coronis = U(0x343)
local subscript = U(0x345)
local undertie = mw.ustring.char(0x35C) -- actually "combining double breve below"
data = {
= macron,
= spacing_macron,
= modifier_macron,
= breve,
= spacing_breve,
= rough,
= smooth,
= diaeresis,
= acute,
= grave,
= circum,
= Latin_circum,
= coronis,
= subscript,
}
data.diacritics.all = ""
for name, diacritic in pairs(data.diacritics) do
data.diacritics.all = data.diacritics.all .. diacritic
end
data = data
data = ""
data = data
data = {
= "",
= "",
= "",
= subscript,
}
data = data
data = data
data = {
= 1,
= 1,
= 2,
= 2,
= 2,
= 3,
= 3,
= 3,
= 4,
}
data = {
-- Convert spacing to combining diacritics
= macron, -- macron
= macron,
= breve, -- breve
= rough, -- rough breathing, modifier letter reversed comma
= rough,
= smooth, -- smooth breathing, modifier letter apostrophe, coronis, combining coronis
= smooth,
= smooth,
= acute, -- acute
= grave, -- grave
= circum, -- Greek circumflex (perispomeni), circumflex, combining circumflex
= circum,
= circum,
= smooth .. acute, -- smooth and acute
= smooth .. grave, -- smooth and grave
= smooth .. circum, -- smooth and circumflex
= rough .. acute, -- rough and acute
= rough .. grave, -- rough and grave
= rough .. circum, -- rough and circumflex
= diaeresis,
= diaeresis .. acute,
= diaeresis .. grave,
= diaeresis .. circum,
}
data = data
data = "ΒβΓγΔδΖζΘθΚκΛλΜμΝνΞξΠπΡρΣσςΤτΦφΧχΨψ"
data = ""
data = "ΑαΕεΗηΙιΟοΥυΩω"
data = ""
data = table.concat{
macron, breve,
rough, smooth, diaeresis,
acute, grave, circum,
subscript
}
data = ""
-- Basic letters with and without diacritics
local letters_with_diacritics = 'ΆΈ-ώϜϝἀ-ᾼῂ-ῌῐ-' ..
-- capital iota with oxia, normalized to capital iota with tonos if entered
-- literally in a string
U(0x1FDB) ..
'Ὶῠ-Ῥῲ-ῼ'
data.word_characters = letters_with_diacritics .. data.combining_diacritics ..
undertie
data.word_character = ""
return data