Module:mr-translit

Hello, you have come here looking for the meaning of the word Module:mr-translit. In DICTIOUS you will not only get to know all the dictionary meanings for the word Module:mr-translit, but we will also tell you about its etymology, its characteristics and you will know how to say Module:mr-translit in singular and plural. Everything you need to know about the word Module:mr-translit you have here. The definition of the word Module:mr-translit will help you to be more precise and correct when speaking or writing your texts. Knowing the definition ofModule:mr-translit, as well as those of other words, enriches your vocabulary and provides you with more and better linguistic resources.

This module will transliterate Marathi language text per WT:MR TR. It is also used to transliterate Ahirani, Konkani, and Varhadi. 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:mr-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.

-- Transliteration for Marathi (in progress)
local export = {}

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

local gmatch = m_str_utils.gmatch
local gsub = m_str_utils.gsub
local match = m_str_utils.match
local reverse = m_str_utils.reverse
local toNFC = mw.ustring.toNFC

local conv = {
	-- consonants
	 = 'k',  = 'kh',  = 'g',  = 'gh',  = 'ṅ', 
	 = 'c',  = 'ch',  = 'j',  = 'jh',  = 'ñ', 
	 = 'ṭ',  = 'ṭh',  = 'ḍ',  = 'ḍh',  = 'ṇ',
	 = 't',  = 'th',  = 'd',  = 'dh',  = 'n',
	 = 'p',  = 'ph',  = 'b',  = 'bh',  = 'm', 
	 = 'y',  = 'r',  = 'l',  = 'v',  = 'ḷ',
	 = 'ś',  = 'ṣ',  = 's',  = 'h',
	 = 'r',
	--  = 'jñ',
	
	-- not for page titles
	 = 'j̈',  = 'j̈h',  = 'ċ',

	-- vowel diacritics
	 = 'i',  = 'u',  = 'e',  = 'o', 
	 = 'ā',  = 'ī',  = 'ū', 
	 = 'ŕ',
	 = 'ai',  = 'au',
	 = 'ŏ',
	 = 'ĕ',

	-- vowel signs
	 = 'a',  = 'i',  = 'u',  = 'e',  = 'o',
	 = 'ā',  = 'ī',  = 'ū', 
	 = 'ŕ', 
	 = 'ai',  = 'au', 
	 = 'ŏ',
	 = 'ĕ',  = 'ĕ',
	
	 = 'om',
	
	-- chandrabindu
	 = '̃',
	
	-- anusvara
	 = 'ṁ',
	
	-- visarga
	 = 'ḥ',
	
	-- virama
	 = '',
	
	-- numerals
	 = '0',  = '1',  = '2',  = '3',  = '4',
	 = '5',  = '6',  = '7',  = '8',  = '9',
	
	-- punctuation
	 = '.', -- danda
	 = '.', -- double danda
	 = '', -- compound separator
	
	-- abbreviation sign
	 = '.',
}

local nasal_assim = {
	 = 'ङ',  = 'ङ',  = 'ङ',  = 'ङ', 
	 = 'न',  = 'न',  = 'न', 
	 = 'ञ',  = 'ञ',  = 'ञ',  = 'ञ',  
	 = 'ण',  = 'ण',  = 'ण',  = 'ण',
	 = 'म',  = 'म',  = 'म',  = 'म',  = 'म',
	 = 'इ',  = 'उ',  = 'ल',  = 'उ',
	 = 'उ',  = 'उ',  = 'उ',  = 'उ',
}

local perm_cl = {
	 = true,  = true,  = true,
	
}

local all_cons, special_cons = 'कखगघङचछजझञटठडढतथदधपफबभशषसयरलवहणनमळ', 'दतयरलवहनम'
local vowel, vowel_sign = '%*aिुृेोाीूैौॉॅ', 'अइउएओआईऊऋऐऔऑऍ'
local syncope_pattern = '()(़?)a(़?)(?)'

function export.tr(text, lang, sc)
	text = gsub(text, 'ाँ', 'ॉ' .. 'ं')
	text = gsub(text, 'ँ', 'ॅ' .. 'ं')
	text = gsub(text, '()ं ', '%1अ ')
	text = gsub(text, '()ं$', '%1अ')
	text = gsub(text, '(़?)(?)', function(c, d)
		return c .. (d == "" and 'a' or d) end)
	for word in gmatch(text, "+") do
		local orig_word = word
		word = reverse(word)
		word = gsub(word, '^a(़?)', '%1')
		while match(word, syncope_pattern) do
			word = gsub(word, syncope_pattern, '%1%2%3%4')
		end
		word = gsub(word, '(.?)ं(.)', function(succ, prev)
			return succ .. (succ..prev == "a" and "्म" or 
				(succ == "" and match(prev, '') and "̃" or nasal_assim or "n")) .. prev end)
		text = gsub(text, orig_word, reverse(word))
	end
	text = gsub(text, '.़?', conv)
	text = gsub(text, 'a()̃', 'a͠%1')
	text = gsub(text, 'aa', 'a')
	return toNFC(text)
end

return export