Jump to content

Module:ckb-translit

From Wiktionary, the free dictionary
The following documentation is located at Module:ckb-translit/documentation. [edit] Categories were auto-generated by Module:module categorization. [edit]
Useful links: subpage list • links • transclusions • testcases • sandbox

This module will transliterate Central Kurdish language text. It is also used to transliterate Gurani and Northern Kurdish. The module should preferably not be called directly from templates or other modules. To use it from a template, use {{xlit}}. Within a module, use Module:languages#Language:transliterate.

For testcases, see Module:ckb-translit/testcases.

Functions

tr(text, lang, sc)
Transliterates a given piece of text written in the script specified by the code sc, and language specified by the code lang.
When the transliteration fails, returns nil.

-- Authors: JavaScript ئاسۆ; Lua Ghybu, Calak

local export = {}

local m_str_utils = require("Module:string utilities")

local find = m_str_utils.find
local gsub = m_str_utils.gsub
local sub = m_str_utils.sub
local U = m_str_utils.char

local mapping = {
	["ا"] = "a", ["ب"] = "b", ["چ"] = "ç", ["ج"] = "c", ["د"] = "d", ["ە"] = "e", ["ێ"] = "ê", ["ف"] = "f", ["گ"] = "g",
	["ھ"] = "h", ["ه"] = "h", ["ح"] = "ḧ", ["ژ"] = "j", ["ک"] = "k", ["ڵ"] = "ll", ["ل"] = "l", ["م"] = "m", ["ن"] = "n",
	["ۆ"] = "o", ["پ"] = "p", ["ق"] = "q", ["ر"] = "r", ["ڕ"] = "r", ["س"] = "s", ["ش"] = "ş", ["ت"] = "t", ["ڤ"] = "v",
	["خ"] = "x", ["غ"] = "ẍ", ["ز"] = "z", ["ئ"] = "", ["ع"] = "'",
	
	[U(0x200C)] = "", -- ZWNJ (zero-width non-joiner)
	["ـ"] = "", -- kashida, no sound
	
	-- numerals
    ["١"] = "1", ["٢"] = "2", ["٣"] = "3", ["٤"] = "4", ["٥"] = "5",
	["٦"] = "6", ["٧"] = "7", ["٨"] = "8", ["٩"] = "9", ["٠"] = "0",
	-- persian variants to numerals
	["۱"] = "1", ["۲"] = "2", ["۳"] = "3", ["۴"] = "4", ["۵"] = "5",
	["۶"] = "6", ["۷"] = "7", ["۸"] = "8", ["۹"] = "9", ["۰"] = "0",
}

	-- punctuation (leave on separate lines)
local punctuation = {
	["؟"] = "?", -- question mark
	["،"] = ",", -- comma
	["؛"] = ";", -- semicolon
	["«"] = '“', -- quotation mark
	["»"] = '”', -- quotation mark
	["٪"] = "%", -- percent
	["؉"] = "‰", -- per mille
	["٫"] = ".", -- decimals
	["٬"] = ",", -- thousand
}

-- translit
local function tr_word(word)
	
    word = gsub(word, '.', punctuation)
		
	--Remove punctuation at the end of the word.
	local ponct
	if find(word, '[%.%!،؛»«٪؉٫٬%p]$') then
	   ponct =  sub(word, -1)
	   word = gsub(word, '[%.%!،؛»«٪؉٫٬%p]$', '')
	else
	   word = word
	   ponct = ''
	end
	
	word = gsub(word, 'ه‌', "ە") --correct unicode for letter ە
	-- U+0647 (Arabic letter heh) + U+200C (zero-width non-joiner)
	-- ↓
	-- U+06D5 (Arabic letter ae)
	
	-- diacritics
	word = gsub(word, 'ْ', "i") -- U+0652, Arabic sukun
	word = gsub(word, 'ِ', "i") -- U+0650, Arabic kasra
	 
	--managing 'و' and 'ی'
	word = gsub(word, 'و([iاێۆە])', "w%1") --و + vowel => w (e.g. wan)
	word = gsub(word, 'ی([iاێۆە])', "y%1") --ی + vowel => y (e.g. yas)
	word = gsub(word, '([iاێۆە])و', "%1w") --vowel + و => w (e.g. kew)
	word = gsub(word, '([iاێۆە])ی', "%1y") --vowel + ی => y (e.g. bey)
	word = gsub(word, '^و$', "û") --non-letter + 'و' + non-letter => û (=and)
	word = gsub(word, '([^ء-يٱ-ەiwy])و', "%1w") --non-letter + 'و' => w (e.g. wtar)

	word = gsub(word, '^و', "w") --first 'و' => w (e.g. wtar)
	word = gsub(word, 'یو', "îw") --'ی' + 'و' => îw (e.g. nîw)
	word = gsub(word, '([^و])یی', "%1îy") --'ی' + 'ی' => îy (e.g. kanîy)
	word = gsub(word, 'وی', "uy") --'و' + 'ی' => uy (e.g. buyn)
	word = gsub(word, 'وو', "û") --'و' + 'و' => û (e.g. bû)
	word = gsub(word, 'ی', "î")
	word = gsub(word, 'و', "u")
	word = gsub(word, 'uu', "û") --'و' + 'و' => û (e.g. bû)
	word = gsub(word, '([ء-يٱ-ەiîuûwy])ڕ', "%1rr") --when 'ڕ' not at the beginning of a word => rr
	word = gsub(word, '([ء-يٱ-ەiîuûwy])ئ', "%1'") --when 'ئ' not at the beginning of a word => '
	
	word = gsub(word, '.', mapping)
	
	--insert i where applicable
	word = gsub(word, 'll', "Ľ") -- temporary conversion to avoid seeing ll as 2 letters
	word = gsub(word, 'rr', "Ŕ") -- temporary conversion to avoid seeing rr as 2 letters
	
	word = gsub(word, '([bcçdfghḧjklĽmnpqrŔsştvwxẍz])([fjlĽmnrŔsşvwxẍyz])([fjlĽmnrŔsşvwxẍyz])([^aeêiîouûy])', "%1%2i%3%4") --e.g. grft -> grift
	word = gsub(word, '([aeêiîouû])([bcçdfghḧjklĽmnpqrŔsştvwxẍz])([bcçdfghḧjklĽmnpqrŔsştvwxẍz])([bcçdfghḧjklĽmnpqrŔsştvwxẍz])$', "%1%2%3i%4") --e.g. cejnt -> cejnit
	word = gsub(word, '([fjlĽrŔsşwyz])([fjlĽmnrŔsşvwxẍyz])([bcçdfghḧjklĽmnpqrŔsştvwxẍz])', "%1i%2%3") --e.g. wrd -> wird
	
	word = gsub(word, '([bcçdghḧkmnpqtvxẍ])([fjlĽmnrŔsşvwxẍyz])([^aeêiîouû])', "%1i%2%3") --e.g. prd -> pird
	word = gsub(word, '([bcçdghḧkmnpqtvxẍ])([fjlĽmnrŔsşvwxẍyz])$', "%1i%2") --like above
	
	word = gsub(word, '([^aeêiîouû])([bcçdghḧkmnpqtvxẍ])([fjlĽmnrŔsşvwxẍyz])([^aeêiîouû])', "%1%2i%3%4") --repeat the latter expression, in case skipped
	word = gsub(word, '([^aeêiîouû])([bcçdghḧkmnpqtvxẍ])([fjlĽmnrŔsşvwxẍyz])$', "%1%2i%3") --repeat the latter expression, in case skipped

	word = gsub(word, '^([bcçdfghḧjklĽmnpqrŔsştvwxẍz])([bcçdfghḧjklĽmnpqrŔsştvwxẍz])([^aeêiîouû])', "%1i%2%3") --e.g. ktk -> kitk
	word = gsub(word, '^([bcçdfghḧjklĽmnpqrŔsştvwxẍz])([bcçdfghḧjklĽmnpqrŔsştvwxẍz])$', "%1i%2") --e.g. ktk -> kitk
	word = gsub(word, '([^aeêiîouy])([bcçdfghḧjklĽmnpqrŔsştvwxẍz])([bcçdfghḧjklĽmnpqrŔsştvwxẍz])([^aeêiîouû])', "%1%2i%3%4") --e.g. ktk -> kitk
	word = gsub(word, '([^aeêiîouy])([bcçdfghḧjklĽmnpqrŔsştvwxẍz])([bcçdfghḧjklĽmnpqrŔsştvwxẍz])$', "%1%2i%3") --e.g. ktk -> kitk

	word = gsub(word, '([^a-zçşêîûĽŔ])([bcçdfghḧjklĽmnpqrŔsştvwxẍz])$', "%1%2i") --e.g. j -> ji
	word = gsub(word, '^([bcçdfghḧjklĽmnpqrŔsştvwxẍz])$', "%1i") --e.g. j -> ji	


	--word = gsub(word, '([^a-zêîûçş0-9\'’])([bcçdfghḧjklĽmnpqrŔsştvwxẍz])([bcçdfghḧjklĽmnpqrŔsştvxẍz])', "%1%2i%3") --e.g. bra -> bira
	--word = gsub(word, '^([bcçdfghḧjklĽmnpqrŔsştvwxẍz])([bcçdfghḧjklĽmnpqrŔsştvxẍz])', "%1i%2") --e.g. bra -> bira

	--word = gsub(word, '([bcçdfghḧjklmnpqrsştvwxẍz][bcçdfghḧjklĽmnpqrŔsştvwxẍz])([bcçdfghḧjklĽmnpqrŔsştvwxẍz])', "%1i%2") --e.g. aşkra -> aşkira
	
	--word = gsub(word, 'si([tp][aeêiîouû])', "s%1") -- sp, st cluster
	
	word = gsub(word, 'Ľ', "ll") --revert the temporary conversion
	word = gsub(word, 'Ŕ', "rr") --revert the temporary conversion

    -- Add the punctuation who had previously deleted.
    word = word .. ponct
    
	return word
end

function export.tr(text, lang, sc)
    local textTab = {}
    
    -- Create a word table separated by a space (%s).
	for _, word in ipairs(mw.text.split(text, '%s+')) do
		table.insert(textTab, word)
	end
	
	-- Tablo of translit.
	for key, word in ipairs(textTab) do
		textTab[key] = tr_word(word)
	end

	return table.concat(textTab, ' ')
end

return export
Retrieved from "https://en.wiktionary.org/w/index.php?title=Module:ckb-translit&oldid=79061689"