Module:tl-bay sc

Hello, you have come here looking for the meaning of the word Module:tl-bay sc. In DICTIOUS you will not only get to know all the dictionary meanings for the word Module:tl-bay sc, but we will also tell you about its etymology, its characteristics and you will know how to say Module:tl-bay sc in singular and plural. Everything you need to know about the word Module:tl-bay sc you have here. The definition of the word Module:tl-bay sc will help you to be more precise and correct when speaking or writing your texts. Knowing the definition ofModule:tl-bay sc, as well as those of other words, enriches your vocabulary and provides you with more and better linguistic resources.
The following documentation is located at Module:tl-bay sc/documentation.
Useful links: subpage list • links • transclusions • testcases • sandbox

This module powers {{tl-bay sc}}, which is used to automatically generate Baybayin forms of Tagalog words. 


-- Based on ] by ]. 
-- Adaptation by ].

local export = {}

local lang = require("Module:languages").getByCode("tl")
local sc_Tglg = require("Module:scripts").getByCode("Tglg")
local m_str_utils = require("Module:string utilities")
local tl_utils = require("Module:tl-utilities")

local u = m_str_utils.char
local rmatch = m_str_utils.match
local ugmatch = m_str_utils.gmatch
local rsubn = m_str_utils.gsub
local rsplit = m_str_utils.split
local ulower = m_str_utils.lower
local ulen = m_str_utils.len

local AC = u(0x0301) -- acute =  ́
local GR = u(0x0300) -- grave =  ̀
local CFLEX = u(0x0302) -- circumflex =  ̂
local MACRON = u(0x0304) -- macron 

local vowel = "aeəiou" -- vowel
local V = ""
local accent = AC .. GR .. CFLEX .. MACRON
local separator = accent ..  "# ./"
local C = "" -- consonant
local supported_chars = "a-zA-Záéíóúâêîôûàèìòùë%-.ñŋ#'/,"

local baybayin_chars = { 
	 = "ᜀ", 
	 = "ᜁ", 
	 = "ᜂ",
	 = "ᜊ", 
	 = "ᜃ", 
	 = "ᜇ", 
	 = "ᜄ", 
	 = "ᜑ", 
	 = "ᜎ",
	 = "ᜋ",
	 = "ᜈ",
	 = "ᜅ",
	 = "ᜉ",
	 = "ᜍ",
	 = "ᜐ",
	 = "ᜆ",
	 = "ᜏ",
	 = "ᜌ"
}

local baybayin_marks = {
	 = "",
	 = "ᜒ",
	 = "ᜓ",
	 = "᜔",
	 = "᜕"
}

local special_words = {
	 = "nang",
	 = "manga"
}

-- version of rsubn() that discards all but the first return value
local function rsub(term, foo, bar)
	local retval = rsubn(term, foo, bar)
	return retval
end

-- apply rsub() repeatedly until no change
local function rsub_repeatedly(term, foo, bar)
	while true do
		local new_term = rsub(term, foo, bar)
		if new_term == term then
			return term
		end
		term = new_term
	end
end

-- canonicalize multiple spaces and remove leading and trailing spaces
local function canon_spaces(text)
	text = rsub(text, "%s+", " ")
	text = rsub(text, "^ ", "")
	text = rsub(text, " $", "")
	return text
end

local function get_pronunciation(text, diph)
	-- Convert hyphens to dot
	text = rsub(text, "%-", ".")
	-- canonicalize multiple spaces again, which may have been introduced by hyphens
	text = canon_spaces(text)
	-- now eliminate punctuation
	text = rsub(text, "", "")
	-- put # at word beginning and end and double ## at text/foot boundary beginning/end
	text = rsub(text, " | ", "# | #")
	text = "##" .. rsub(text, " ", "# #") .. "##"
	
	-- Move this early for now
	--c, gü/gu+e or i, q
	text = rsub(text, "c()", "s%1")
	text = rsub(text, "()gü()", "%1ɡw%2")
	text = rsub(text, "gü()", "ɡuw%1")
	text = rsub(text, "gu()", "ɡ%1") -- Only e, so words like "biguin" will not be read as "bigin"
	text = rsub(text, "qu()", "k%1")
	text = rsub(text, "ü", "u") 
	
	--ll
	text = rsub(text, "ll(?)()", "ly%2")
	
	-- Correction for vowels with in-between glottal stop, now default
	text = rsub_repeatedly(text, "(" .. V .. ")(" .. V .. ")", "%1.%2")
	
	-- Reenable "j" sound be equivalent to "dy"
	-- Ex. gaja = ga(r)ya not gariya
	text = rsub(text, "(?)j(".. V .. ")"  , "dy%2")

	-- handle certain combinations; ch ng and sh handling needs to go first
	text = rsub(text, "(?)ch", "ts") --not the real sound
	text = rsub(text, "(?)g̃", "ŋ") -- Spanish spelling support
	text = rsub(text, "ng", "ŋ")
	text = rsub(text, "sh", "ʃ")
	
	--ck
	text = rsub(text, "ck", "k") -- foreign sound in case

	--x
	text = rsub(text, "()x()", "%1s%2")
	text = rsub(text, "x", "ks")

	--alphabet-to-phoneme
	text = rsub(text, "",
	--="ɡ":  U+0067 LATIN SMALL LETTER G → U+0261 LATIN SMALL LETTER SCRIPT G
		{  = "k",  = "ɡ",  = "ĵ",  = "ɲ",  = "k",  = "b",  = "s"})

	text = rsub(text, "ɲ", "ny") -- ñ
	text = rsub(text, "rr", "r") -- r
	
	--determining whether "y" is a consonant or a vowel
	--Baybayin treats as consonant regardless
	text = rsub(text, "y(" .. V .. ")", "ɟ%1") -- not the real sound
	text = rsub(text,"()y(?)()","%1i%2%3")
	text = rsub(text, "()y#", "%1i#")
	text = rsub(text, "w(" .. V .. ")","w%1")
	-- text = rsub(text,"w(?)()","u%1%2")
	-- text = rsub(text, "(" .. C .. ")w#","%1u")

	text = rsub(text, "ŋ", "Ŋ")
	text = rsub(text, "ë", "e") -- mark as e for now
	text = tl_utils.syllabify_from_spelling(text, text)
    text = rsub(text, "Ŋ", "ŋ")
	
	-- Remove accent marks
	text = tl_utils.remove_accents(text)
	
	text = rsub(text, "sh", "ʃ")
	text = rsub(text, "ts", "ĉ") -- ts-not the real sound
	text = rsub(text, "j", "ĵ")

	if (not diph) then
    	--Corrections for diphthongs
	    text = rsub(text,"()i","%1j") --y
	    text = rsub(text,"()u","%1w") --w
    end
    
    text = rsub(text,"dĵ",".ĵ") --/d/ before /j/ 
    text = rsub_repeatedly(text,"(n)(?)()","ŋ%2%3") -- /n/ before /k/ (some proper nouns)
    
    -- After processing pronunciation, Baybayin Start Translate
    text = rsub(text, "", "i")
    text = rsub(text, "", "u")

	return text
end

-- ĵ, ɟ and ć are used internally to represent ,  and 
function export.transcribe(text, trad, diph, force_r)
	text = ulower(text)
    text = canon_spaces(text)
    
    -- Convert punctuation to kulit
    text = rsub(text, "%s*", "/")
    text = rsub(text, "()%s*", "%1 //")
	
	local words = rsplit(text, " ")
	
	for i, word in ipairs(words) do
		if special_words then
			words = special_words
		end
		words = rsub(words, "^%-(" .. V .. ")", "◌%1") -- suffix/infix if vowel, remove glottal stop at start
	end

	text = table.concat(words, " ")
	
	-- Convert slashes to bantasan, kulit divider
	text = rsub(text, "//", " ᜶ ")
	text = rsub(text, "/", trad and ' ᜶ ' or " ᜵ ")

	text = get_pronunciation(text, diph)
     
    -- Check if there are errors with vowels again
    text = rsub(text,"()(?)()","%1.%2%3")
    
    local function baybay_syllable(syll, post, last_vowel)
    	local syll2 = ""
    	
		local bay_double = {
			 = "t",  = "d",
			 = "n",  = "s",
			 = "g"
		}
			
    	local function baybay(character)
    		local bay_soundpre = ''
			character = rsub(character, "", "g")
			
			if rmatch(character, '') then
    			bay_soundpre = bay_double
    			bay_soundpre = baybayin_chars .. baybayin_marks
    			
    			if character == 'ĉ' then
    				if trad then bay_soundpre = '' end
    				character = rsub(character, "", "s")
    			else
    				character = rsub(character, "", "y")
    			end
			end

			if not force_r or trad then
				character = rsub(character, "", "d")
			end
			
    		character = rsub(character, "", "p")
    		character = rsub(character, "", "y")

    		return bay_soundpre .. baybayin_chars
    	end
  
		if not trad then
			-- Remove /h/ as it is not pronounced in between
			syll = rsub(syll, "(+)(h+)", "%1")
			post = rsub(post, "(h+)", "")
			
			post = rsub(post, "ɲ", bay_double)
			post = rsub(post, "ɡ", bay_double)
			post = rsub(post, "ʃ", bay_double)
			post = rsub(post, "ĵ", bay_double .. 's')
			post = rsub(post, "ĉ", bay_double .. 's')
			
			for c in ugmatch(post, '.') do
				syll2 = syll2 .. baybay(c) .. baybayin_marks
			end
		end
		
    	syll = rsub(syll, "(" .. C .. "*)(" .. V .. "+)",
			function(consonant, vowel)
				local bay_char = ''
				
				if ulen(consonant) == 0 then
					bay_char = baybay(vowel)
				elseif ulen(consonant) == 1 and consonant ~= "◌" then
					bay_char = baybay(consonant) .. baybayin_marks
				elseif rmatch(consonant, "^(.*)ll$") then
					for c in ugmatch(consonant, '^(.)ll$') do
						bay_char = bay_char .. baybay(c) .. baybayin_marks
					end
					
					bay_char = bay_char .. baybay("l") .. baybayin_marks
					bay_char = bay_char .. baybay("y") .. baybayin_marks
				else
					-- Two character unicode problems
					consonant = rsub(consonant, "()", function(char)
						return bay_double
					end)
					consonant = rsub(consonant, "ĉ", bay_double .. (trad and 'y' or 's'))
					consonant = rsub(consonant, "ɟ", "y")

					if consonant == "◌" then
						bay_char = bay_char .. (vowel == "a" and "◌" or "") .. baybayin_marks
						last_vowel = nil
					else
						for c in ugmatch(consonant, '.') do
							bay_char = bay_char .. baybay(c) .. baybayin_marks
							last_vowel = nil
						end
					end
					
					bay_char = rsub(bay_char, baybayin_marks .. "$", baybayin_marks)
				end
				return bay_char
			end
		)
		
    	return syll .. syll2
    end
   
    local words = rsplit(text, " ")
	for i, word in ipairs(words) do
		
		-- (C)/y/ and --(C)w fixes
		-- /h/ being pronounced like fahm, paham
		if trad then
			word = rsub(word, "()(w)(" .. V .. ")(" .. C .. "*)(+)", "%1u.%2%3%4%5")
			word = rsub(word, "()(ɟ)(" .. V .. ")(" .. C .. "*)(+)", "%1i.%2%3%4%5")
			word = rsub(word, "(" .. C .. "*)(" .. V .. ")(h)(" .. C .. "+)(+)", "%1%2.%3%2%4%5")
		end
		
		local syllables = rsplit(word, "")
		local last_vowel = nil
		
		for j = 1, #syllables do
			if rmatch(syllables, V) then
				syllables = rsub(syllables, "^(*)(" .. C .. "*)(" .. V .. "+)(" .. C .. "*)(*)$",
					function(temp1 ,pre, vowel, post, temp2)
						retval = temp1 .. baybay_syllable(pre .. vowel, post, last_vowel) .. temp2
						last_vowel = rmatch(post, "") and vowel or nil
						return retval
					end
				)
			elseif not rmatch(syllables, "") then
				-- This is only a fallback when no vowel is entered
				syllables = rsub(syllables, "^(*)(" .. C .. "+)(*)$",
					function(temp1 , consonant , temp2)
						return temp1 .. (trad and baybay_syllable(consonant .. "a", "") or baybay_syllable("", consonant)) .. temp2 
					end
				)
			end
		end
		words = table.concat(syllables, "")
	end
    
    text = table.concat(words, " ")

	-- remove # symbols at word and text boundaries
	text = rsub(text, "#", "")
	
	text = canon_spaces(text)

	return mw.ustring.toNFC(text)
end

function export.show(frame)
	local params = {
		 = {},
		 = {type = "boolean", default = false},
		 = {type = "boolean", default = false},
		 = {type = "boolean", default = false},
		 = {type = "boolean", default = false},
		 = {type = "number", default = 0},
	}

	local parargs = frame:getParent().args
	local args = require("Module:parameters").process(parargs, params)
	local results = ""
	local text = args or mw.title.getCurrentTitle().text
	
	for supported, unsupported in text:gmatch("(*)(*)") do
		results = results .. export.transcribe(supported, args.trad, args.diph, args.r) .. unsupported
	end
	
	local tr = ""
	-- Baybayin to Latin
	if args.tr == 1 then
		tr = rsub(lang:transliterate(results, sc_Tglg), "%s()", "%1")
	elseif args.tr == 2 then
		tr = text
		tr = rsub(tr, "", "")
		tr = rsub(tr, "//", ".")
		tr = rsub(tr, "/", ",")
	else
		tr = ''
	end
	
	if tr ~= "" then
		tr = " " .. table.concat({
				'<span class="mention-gloss-paren annotation-paren">(</span>',
				'<span lang="tl-Latn" class="tr Latn">',
				tr,
				'</span>',
				'<span class="mention-gloss-paren annotation-paren">)</span>'
			})
	end
	
	if args.trad then
		results =  rsub_repeatedly(results, "() ()", "%1%2")
	end
	
	if args.disp then
		results = '<span class="' .. sc_Tglg:getCode()  ..  '" lang="'  .. lang:getCode()  .. '">' .. results ..  "</span>"
	end
	
	return results ..  tr
end

return export
Wikious
Boobota
Sagapedia