Module:ps-translit

From Wiktionary, the free dictionary
Jump to navigation Jump to search

This module will transliterate Pashto language text per WT:PS TR. 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:ps-translit/testcases.

Functions

[edit]
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.

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

local U = m_str_utils.char
local gsub = m_str_utils.gsub

local export = {}

local zwar = U(0x64E)
local zer = U(0x650)
local pesh = U(0x64F)
local tashdid = U(0x651) -- also called shadda
local zwarakay = U(0x659) -- Pashto /ə/
local jazm = "ْ"
local he = "ه"

local ain = 'ع'
local alif = 'ا'
local ye = 'ي'
local ye2 = "ےی"
local ye3 = 'ې'
local waw = "و"
local nasal = 'ں'

local consonants = "بپتټثجځچڅحخدډذرړزژږسشښصضطظعغفقکګلمنڼوه"
local consonantS = "بپتټثجځچڅحخدډذرړزژږسشښصضطظعغفقکګلمنڼه"
local consonantS2 = "بپتټثجځچڅحخدډذرړزژږسشښصضطظعغفقکګلمنڼوهي" 
local vowels = "اآیېيۍئےو"
local vowels2 = "آیېيۍئےو"
local semivowels = "وي"
local hes = "هح"
local diacritics = "َُِّْٰٙ"
local ZZPZ = "َُِٙ"

local mapping = {
	["آ"] = 'â', ["ب"] = 'b', ["پ"] = 'p', ["ت"] = 't', ["ټ"] = 'ṭ', ["ث"] = 's̱',
	["ج"] = 'j', ["ځ"] = 'ź', ["چ"] = 'č', ["څ"] = 'ś', ["ح"] = 'ḥ', ["خ"] = 'x', 
	["د"] = 'd', ["ډ"] = 'ḍ', ["ذ"] = 'ẕ', ["ر"] = 'r', ['ړ'] = "ṛ", ["ز"] = 'z', ["ژ"] = 'ž', ["ږ"] = 'ǵ',
	["س"] = 's', ["ش"] = 'š', ["ښ"] = 'x̌', ["ص"] = 'ṣ', ["ض"] = 'ẓ', 
	["ط"] = 't̤', ["ظ"] = 'z̤', ["ع"] = 'ʻ', ["غ"] = 'ǧ', ["ف"] = 'f', ["ق"] = 'q',
	["ک"] = 'k', ["ګ"] = 'g', ["ڼ"] = 'ṇ',
	["ل"] = 'l', ["م"] = 'm', ["ن"] = 'n', ["و"] = 'w', ["ه"] = 'h', ["ي"] = 'y', ["ں"] = 'ṉ', 

	["ؤ"] = "wë", ["ۍ"] = "ëy", ["ئ"] = 'ëy', ["ې"] = 'e', ["ۀ"] = 'ë', ["ی"] = 'y', ["ے"] = 'y',
	
	-- diacritics
	[zwar] = "a",
	[zer] = "ĭ",
	[pesh] = "ŭ",
	[zwarakay] = "ë",
	[jazm] = "", -- also sukun - no vowel
	[U(0x200C)] = "-", -- ZWNJ (zero-width non-joiner)
	
	-- ligatures
	["ﻻ"] = "lā",
	["ﷲ"] = "allāh",
	
	-- kashida
	["ـ"] = "-", -- kashida, no sound
	
	-- 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)
	["؟"] = "?", -- question mark
	["،"] = ",", -- comma
	["؛"] = ";", -- semicolon
	["«"] = '“', -- quotation mark
	["»"] = '”', -- quotation mark
	["٪"] = "%", -- percent
	["؉"] = "‰", -- per mille
	["٫"] = ".", -- decimals
	["٬"] = ",", -- thousand
}

function export.tr(text, lang, sc)
	
	--define the "end" of a word
	text = gsub(text, "#", "HASHTAG")
	text = gsub(text, " | ", "# | #")
	text = gsub(text, "\n" , "#".."\n" .. "#")
	text = "##" .. gsub(text, " ", "# #") .. "##"
	-- hastags now mark the beginning and end of a word
	
	-- EXCEPTIONS - leave as they are, unless they have been sorted out elsewhere

    text = gsub(text, "ن٘", "ṉ")
    text = gsub(text, "الله", "allâh")
    
  	-- diacritics
	text = gsub(text, pesh .. waw .. jazm .. "", "u")
    text = gsub(text, jazm .. alif, "â")
    
	-- Initial alif
	text = gsub(text, alif .. zwar .. '([' .. consonantS .. '])', "a%1")
	text = gsub(text, alif .. zer .. ye .. jazm .. "", "i")

	text = gsub(text, alif .. zer, "ĭ")
	text = gsub(text, alif .. waw .. jazm .. "", "o")

	text = gsub(text, alif .. pesh .. waw, "u")
	text = gsub(text, alif .. pesh .. waw .. jazm .. "", "u")	
	text = gsub(text, alif .. pesh, "ŭ")

	-- Tashdeed
	text = gsub(text, '([' .. consonantS2 .. '])' .. tashdid, "%1%1")
	text = gsub(text, '([' .. consonantS2 .. '])' .. tashdid .. '([' .. ZZPZ .. '])', "%1%1%2")
	text = gsub(text, '([' .. ZZPZ .. '])' .. ye .. '([' .. ZZPZ .. '])' .. tashdid, "%1yy%2")
	text = gsub(text, '([' .. ZZPZ .. '])' .. waw .. '([' .. ZZPZ .. '])' .. tashdid, "%1ww%2")
	-- For some reason the tashdeed gets pushed after the other diacritics, so this line is necessary for tashdeed to work with other diacritics
	text = gsub(text, '([' .. consonants .. '])' .. '([' .. ZZPZ .. '])' .. tashdid, "%1%1%2")
	
	-- tanween diacritic / no need to mess about
	text = gsub(text, '([' .. consonants .. '])' .. 'ً' .. alif, "%1an")
	text = gsub(text, alif .. 'ً', "an")
	text = gsub(text, '([' .. consonants .. '])' .. 'ً', "%1an")

	-- tall zwar -- / no need to mess about
	text = gsub(text, '([' .. vowels .. '])' .. 'ٰ', "á")
	text = gsub(text, '([' .. consonants .. '])' .. 'ٰ' .. '([' .. vowels .. '])', "%1á")

	-- ‘ain
	text = gsub(text, alif .. ain , "â‘") 
	text = gsub(text, ain .. alif  .. '([' .. consonants .. '])', "ʻâ%1") 
	text = gsub(text, '([' .. consonants .. '])' .. ain .. he, "%1ʻa")
	text = gsub(text, '([' .. consonants .. '])' .. '([' .. zer .. pesh .. ']?)' .. ain, "%1%2ʻ")
	text = gsub(text, ain .. zer  .. '([' .. consonants .. '])', "ʻĭ%1")
	text = gsub(text, ain .. pesh  .. '([' .. consonants .. '])', "ʻŭ%1")
	text = gsub(text, ain .. zer .. ye .. '([' .. consonants .. '])', "ʻi%1")
    text = gsub(text, ain .. pesh .. waw .. '([' .. consonantS .. '])', "ʻu%1")
    
    ---  alif
    text = gsub(text, '([' .. consonants .. '])' .. zwar .. alif, "%1â")
	text = gsub(text, '([' .. consonantS2 .. '])' .. alif, "%1â")
	text = gsub(text, '([' .. consonants .. '])' .. tashdid .. alif, "%1%1â")
	text = gsub(text, "#" .. alif .. ye, "i")
	text = gsub(text, "#" .. alif .. waw, "o")
	text = gsub(text, "#" .. alif .. ye3, "e")
	text = gsub(text, '([' .. consonantS2 .. '])' .. alif .. ye .. waw, "%1âyo")
  
	-- waw
	text = gsub(text, waw .. '([' .. ZZPZ .. '])', "w%1")
    text = gsub(text, 'ُو', "u")
	

	-- medial/final consonants

    --- (e) -- works
	text = gsub(text, '([' .. consonants .. '])' .. ye .. jazm .. '([' .. consonants .. '])', "%1i%2")
	
    --- he 
	text = gsub(text, '([' .. consonantS2 .. '])' .. zwar .. he .. zer .. ye, "%1ahi")
	text = gsub(text, '([' .. consonantS2 .. '])' .. zwar .. he .. alif, "%1ahâ")
	text = gsub(text, zwar .. he .. '([' .. consonants .. vowels .. '])', "ah%1")
	text = gsub(text, '([' .. consonantS2 .. '])' .. zwar .. he, "%1ah")
	text = gsub(text, '([' .. consonantS .. '])' .. he .. "#", "%1a")
	text = gsub(text, jazm .. waw .. he, "wa")
	text = gsub(text, jazm .. ye .. he, "ya")
	text = gsub(text, '([' .. vowels2 .. diacritics .. '])' .. '([' .. semivowels .. '])' .. he .. "#", "%1%2a")
	text = gsub(text, '([' .. consonantS .. '])' .. waw .. he .. "#", "%1oh")
	text = gsub(text, '([' .. consonantS .. '])' .. ye .. he .. "#", "%1ih")

    --- waw

	text = gsub(text, '([' .. consonants .. '])' .. waw, "%1o")
	text = gsub(text, ye .. waw, "yo")
	text = gsub(text, '([' .. consonantS2 .. '])' .. tashdid .. waw, "%1%1o")
	text = gsub(text, zer .. ye .. waw, "io")
	text = gsub(text, '([' .. consonantS2 .. '])' .. ye .. waw .. "#", "%1yo")
	text = gsub(text, '([' .. consonantS2 .. '])' .. ye .. waw .. '([' .. consonantS .. '])', "%1yo%2")
	text = gsub(text, '([' .. consonantS2 .. '])' .. ye .. waw .. jazm, "%1iw")
	text = gsub(text, '([' .. diacritics .. '])' .. '([' .. semivowels .. '])' .. waw, "%1%2o")
	text = gsub(text, "#" .. ye .. waw, "yo")

	text = gsub(text, '([' .. consonants .. '])' .. tashdid .. zer .. ye .. jazm .. alif, "%1%1iyâ")
	text = gsub(text, '([' .. consonants .. '])' .. zer .. ye .. alif, "%1iâ")
	
	--- ye
	text = gsub(text, ye .. zwar .. alif, "yâ")
	text = gsub(text, '([' .. consonants .. zer .. '])' .. ye .. '([' .. consonantS .. '])', "%1i%2")
	text = gsub(text, '([' .. consonants .. zer .. '])' .. ye .. "#", "%1i")
	text = gsub(text, '([' .. consonantS .. '])' .. '([' .. ye2 .. '])', "%1a%2")
	text = gsub(text, '([' .. diacritics .. '])' .. '([' .. semivowels .. '])' .. '([' .. ye2 .. '])', "%1%2a%3")
	text = gsub(text, "#" .. '([' .. semivowels .. '])' .. '([' .. ye2 .. '])', "%1a%2")

    -- get rid of hashtags (not needed)
    text = gsub(text, "#", "")
    text = gsub(text, "HASHTAG", "#")

	text = gsub(text, '.', mapping)

	
	text = gsub(text, 'ĭy', "i")
	text = gsub(text, 'ŭw', "u")
	text = gsub(text, 'ĭi', "i")
	text = gsub(text, 'ŭu', "u")
	text = gsub(text, "اa", "a")
	text = gsub(text, 'aa', "â")
	--

	return text
end
return export