Module:ps-translit

The following documentation is generated by Module:documentation/functions/translit.

Useful links: subpage list • links • transclusions • testcases • sandbox (diff)

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

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 = {
	 = 'â',  = 'b',  = 'p',  = 't',  = 'ṭ',  = 's̱',
	 = 'j',  = 'ź',  = 'č',  = 'ś',  = 'ḥ',  = 'x', 
	 = 'd',  = 'ḍ',  = 'ẕ',  = 'r',  = "ṛ",  = 'z',  = 'ž',  = 'ǵ',
	 = 's',  = 'š',  = 'x̌',  = 'ṣ',  = 'ẓ', 
	 = 't̤',  = 'z̤',  = 'ʻ',  = 'ǧ',  = 'f',  = 'q',
	 = 'k',  = 'g',  = 'ṇ',
	 = 'l',  = 'm',  = 'n',  = 'w',  = 'h',  = 'y',  = 'ṉ', 

	 = "wə",  = "əy",  = 'əy',  = 'e',  = 'ə',  = 'y',  = 'y',
	
	-- diacritics
	 = "a",
	 = "ĭ",
	 = "ŭ",
	 = "ə",
	 = "", -- also sukun - no vowel
	 = "-", -- ZWNJ (zero-width non-joiner)
	
	-- ligatures
	 = "lā",
	 = "allāh",
	
	-- kashida
	 = "-", -- kashida, no sound
	
	-- numerals
	 = "1",  = "2",  = "3",  = "4",  = "5",
	 = "6",  = "7",  = "8",  = "9",  = "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 .. '()', "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, '()' .. tashdid, "%1%1")
	text = gsub(text, '()' .. tashdid .. '()', "%1%1%2")
	text = gsub(text, '()' .. ye .. '()' .. tashdid, "%1yy%2")
	text = gsub(text, '()' .. waw .. '()' .. 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, '()' .. '()' .. tashdid, "%1%1%2")
	
	-- tanween diacritic / no need to mess about
	text = gsub(text, '()' .. 'ً' .. alif, "%1an")
	text = gsub(text, alif .. 'ً', "an")
	text = gsub(text, '()' .. 'ً', "%1an")

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

	-- ‘ain
	text = gsub(text, alif .. ain , "â‘") 
	text = gsub(text, ain .. alif  .. '()', "ʻâ%1") 
	text = gsub(text, '()' .. ain .. he, "%1ʻa")
	text = gsub(text, '()' .. '(?)' .. ain, "%1%2ʻ")
	text = gsub(text, ain .. zer  .. '()', "ʻĭ%1")
	text = gsub(text, ain .. pesh  .. '()', "ʻŭ%1")
	text = gsub(text, ain .. zer .. ye .. '()', "ʻi%1")
    text = gsub(text, ain .. pesh .. waw .. '()', "ʻu%1")
    
    ---  alif
    text = gsub(text, '()' .. zwar .. alif, "%1â")
	text = gsub(text, '()' .. alif, "%1â")
	text = gsub(text, '()' .. 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, '()' .. alif .. ye .. waw, "%1âyo")
  
	-- waw
	text = gsub(text, waw .. '()', "w%1")
    text = gsub(text, 'ُو', "u")
	

	-- medial/final consonants

    --- (e) -- works
	text = gsub(text, '()' .. ye .. jazm .. '()', "%1i%2")
	
    --- he 
	text = gsub(text, '()' .. zwar .. he .. zer .. ye, "%1ahi")
	text = gsub(text, '()' .. zwar .. he .. alif, "%1ahâ")
	text = gsub(text, zwar .. he .. '()', "ah%1")
	text = gsub(text, '()' .. zwar .. he, "%1ah")
	text = gsub(text, '()' .. he .. "#", "%1a")
	text = gsub(text, jazm .. waw .. he, "wa")
	text = gsub(text, jazm .. ye .. he, "ya")
	text = gsub(text, '()' .. '()' .. he .. "#", "%1%2a")
	text = gsub(text, '()' .. waw .. he .. "#", "%1oh")
	text = gsub(text, '()' .. ye .. he .. "#", "%1ih")

    --- waw

	text = gsub(text, '()' .. waw, "%1o")

	text = gsub(text, '()' .. tashdid .. waw, "%1%1o")
	text = gsub(text, zer .. ye .. waw, "io")
	text = gsub(text, '()' .. ye .. waw .. jazm, "%1iw")
	text = gsub(text, '()' .. ye .. waw .. "#", "%1yo")
	text = gsub(text, '()' .. ye .. waw .. '()', "%1yo%2")
	text = gsub(text, '()' .. '()' .. waw, "%1%2o")
	text = gsub(text, ye .. waw, "yo")
	text = gsub(text, "#" .. ye .. waw, "yo")

	text = gsub(text, '()' .. tashdid .. zer .. ye .. jazm .. alif, "%1%1iyâ")
	text = gsub(text, '()' .. zer .. ye .. alif, "%1iâ")
	
	--- ye
	--text = gsub(text, '()' .. ye .. waw .. ye, "%1iwi")
	--text = gsub(text, '()' .. waw .. ye .. jazm, "%1oy")
	
	text = gsub(text, ye .. zwar .. alif, "yâ")
	text = gsub(text, '()' .. ye .. '()', "%1i%2")
	text = gsub(text, '()' .. ye .. "#", "%1i")
	text = gsub(text, '()' .. '()', "%1a%2")
	text = gsub(text, '()' .. '()' .. '()', "%1%2a%3")
	text = gsub(text, "#" .. '()' .. '()', "%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

Module:ps-translit

Functions

Wikious

Boobota

Sagapedia