Module:zm-pron

Revision as of 06:20, 4 May 2022 by Aleisi Galan (talk | contribs)


local sub = mw.ustring.sub
local find = mw.ustring.find
local match = mw.ustring.match
local gmatch = mw.ustring.gmatch
local gsub = mw.ustring.gsub
local u = mw.ustring.char
local split = mw.text.split
local gsplit = mw.text.gsplit

-- To avoid weird annoying cursor behavior
local GRAVE = u(0x0300) -- COMBINING GRAVE ACCENT ̀◌
local ACUTE = u(0x0301) -- COMBINING ACUTE ACCENT
local SYLL = u(0x0329) -- COMBINING VERTICAL LINE BELOW ̩◌
local VL = u(0x0325) -- COMBINING RING BELOW ̥◌
local AFFR = u(0x0361) -- COMBINING DOUBLE INVERTED BREVE ͡

local back_vowel = "aouɔǫō"
local front_vowel = "ieɛɪ"
local vowels = "[" .. back_vowel .. front_vowel .. "]"
local acuted = "[áéíóúýÉÓ]"
local oral = "áéíóúýÉÓaouɔieɛ"
local palatal = "[ʨjʎʃʒʥʤʧʦʣ]"
local sonorant = "[rl]"
local plosives = "[ptkbdɡ]"
local velar = "[ɡkx]"
local consonants = "[mnptkbdɡfvszxrljɲŋʋʎʨjʎʃʒʥʤʧʤʣʦ]"

local dialects = {
	["s"] = s_rules,
	["n"] = n_rules,
	["c"] = c_rules,
}

local export = {}

local rules = {
	{"ai", "ɛ"}, {"aí", "É"}, {"au", "ɔ"}, {"aú", "Ó"}, {"è", "ɛ"}, {"ò", "ɔ"}, {"y", "ɪ"},
	{"dź", "ʥ"}, {"dž", "ʤ"}, {"c", "ʦ"}, {"ć", "ʨ"}, {"nj", "ɲ"}, {"č", "ʧ"}, {"ž", "ʒ"},  {"š", "ʃ"},  {"lj", "ʎ"},
	{"h", "x"}, {"g", "ɡ"}, {"ǫ", "o"}, {"ō", "o"}, {"sč", "ʃt͡ʃ"},
	
	{"(" .. vowels .. ")[lv]$", "%1ʋ"}, {"(" .. acuted .. ")[lv]$", "%1ʋ"},
	
	{plosives .. "(" .. plosives .. ")$", "%1"},
	
	{"[ptk]([ptk])", "%1"},	{"[bdɡ]([bdɡ])", "%1"},
	
	{"(" .. consonants ..")([rŕ])(" .. consonants ..")", "%1(ə)%2" .. SYLL .. "%3"}, {"(" .. consonants ..")r$", "%1ər"},
	{"n(" .. velar .. ")", "ŋ%1"},
	{"([ptk])(" .. vowels .. ")", "%1ʰ%2"}, {"([ptk])(" .. acuted .. ")", "%1ʰ%2"},
	
	{"(" .. palatal .. ")e", "%1ɛ"}, {"(" .. palatal .. ")é", "%1É"},
	{"(" .. palatal .. ")o", "%1ɔ"}, {"(" .. palatal .. ")ó", "%1Ó"},
	
	{"É", "ɛ" .. ACUTE}, {"Ó", "ɔ" .. ACUTE}, {"ý", "ɪ" .. ACUTE},
}

local c_rules = {
	{"ʨ", "ʧ"}, {"ʥ", "ʤ"},
	{"[ae]j", "ɛː"}, {"a", "ɐ"}, {"[ei]", "ɪ"}, {"o", "ɔ"}, {"u", "ʊ"}
}

local s_rules = {
	{"ʨ", "ʦ"}, {"ʥ", "ʣ"},
	{"[ae]j", "ɛː"}, {"a", "ɐ"}, {"e", "ɛ"}, {"i", "e"}, {"o", "ɔ"}, {"u", "o"}, {"ɪ", "i"}, 
	{"([bdg])(" .. vowels .. ")", "%1[βðɣ]"}, {"([bdg])(" .. acuted .. ")", "%1[βðɣ]"},
}

local n_rules = {
	{"[ae]", "ə"}, {"ɪ", "ɨ"}, {"y", "ɪ"}, {"i", "y"}, {"o", "ɔ"}, {"u", "ʊ"}, 
}

local affricates = {
	{"ʥ", "d͡ʑ"}, {"ʤ", "d͡ʒ"}, {"ʦ", "t͡s"}, {"ʨ", "t͡ɕ"}, {"ʧ", "t͡ʃ"}, {"ʣ", "d͡z"},
}


function export.crux(term, d)
	term = mw.ustring.lower(term)
	
	-- General
	for _, rule in ipairs(rules) do
		term = gsub(term, rule[1], rule[2])
	end
	
	-- Dialects
	for _, dia_rule in ipairs(d == "n" and n_rules or d == "c" and c_rules or s_rules) do
		term = gsub(term, dia_rule[1], dia_rule[2])
	end
	
	-- Affricates
	for _, aff in ipairs(affricates) do
		term = gsub(term, aff[1], aff[2])
	end
	
	return term
end


function IPA_span(items)
	local bits = {}
	for _, item in ipairs(items) do
		local bit = "<span style=\"font-size:110%;font-family:'Gentium','DejaVu Sans','Segoe UI',sans-serif>" .. item.pron .. "</span>"
		table.insert(bits, bit)
	end
	return table.concat(bits)
end

function format_IPA(items)
	return "[[w:IPA chart|IPA]]<sup>([[IPA for Zemljask|key]])</sup>:&#32;" .. IPA_span(items)
end

function line_format(pronunciation, dialect)
	local full_pronunciations = {}
	local IPA_args = {{pron = '[' .. pronunciation .. ']'}}
	table.insert(full_pronunciations, format_IPA(IPA_args))
	return "(''" .. table.concat(dialect, ", ") .. "'')" .. ' ' .. table.concat(full_pronunciations, ' or ')
end

function separate_word(term, d)
	local result = {}
	
	for word in gsplit(term, " ") do
		table.insert(result, export.crux(word, d))
	end
	
	return table.concat(result, " ")
end

function export.show(frame)
	local params = {
		[1] = { default = mw.title.getCurrentTitle().nsText == 'Template' and "dźélo" or mw.title.getCurrentTitle().text },	
	}
	local args = require("Module:parameters").process(frame:getParent().args, params)
	local term = args[1]
	
	local ipa = "* "
	ipa = ipa .. line_format(separate_word(term), {'Standard'})
	
	if export.crux(term, "n") ~= export.crux(term) then
		ipa = ipa .. "\n* "
		ipa = ipa .. line_format(separate_word(term, "n"), {'Northern'})
	end
	
	if export.crux(term, "c") ~= export.crux(term) then
		ipa = ipa .. "\n* "
		ipa = ipa .. line_format(separate_word(term, "c"), {'Central'})
	end
		
	if export.crux(term, "s") ~= export.crux(term) then
		ipa = ipa .. "\n* "
		ipa = ipa .. line_format(separate_word(term, "s"), {'Southern'})
	end
	
	return ipa
end

return export