Module:tru-translit

---

The following documentation is generated by Module:documentation/functions/translit. ^[edit]

Useful links: subpage list • links • transclusions • testcases • sandbox

This module will transliterate Turoyo language text. 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:tru-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 export = {}

local U = require("Module:string/char")
local rsub = mw.ustring.gsub
local unpack = unpack or table.unpack -- Lua 5.2 compatibility
-- 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

local rbasa_below = U(0x737)
local pthaha_below = U(0x731)
local rbasa = U(0x736)
local zqapha = U(0x733)
local pthaha = U(0x730)
local vowel_diacritics_capture = "([" .. rbasa_below .. pthaha_below .. rbasa .. zqapha .. pthaha .. "])"

-- we declare consonants representing vowels (matres lectionis) as constants to mitigate differences in how mixing
-- right-to-left and left-to-right characters in the same line appears in an IDE vs wiktionary.  Since matres is used in
-- concatenation via the .. operator,  "ܘ" .. "ܐ" on wiktionary would render as "ܐ" .. "ܘ" in an IDE
local alaph = U(0x710)
local waw = U(0x718)
local yudh = U(0x71D)

local combining_diaeresis = U(0x308)
local combining_tilde_below = U(0x330)
local qushshaya = U(0x741)
local rukkakha = U(0x742)

local tt_transpose_punc = {
	-- left/right single/double quotes
	["“"] = "”",
	["”"] = "“",
	["‘"] = "’",
	["’"] = "‘",
	["؟"] = "?", -- question mark
	["«"] = '“', -- quotation mark
	["»"] = '”', -- quotation mark
	["،"] = ",", -- comma
	["؛"] = ";", -- semicolon
	-- skewed colons from https://r12a.github.io/scripts/syrc/tru.html#phrase
	["܇"] = ',',
	["܆"] = ';'
}

local tt_transpose_punc_keys = ''
for key, _ in pairs(tt_transpose_punc) do tt_transpose_punc_keys = tt_transpose_punc_keys .. key end

local fix = {
	{ vowel_diacritics_capture .. qushshaya, qushshaya .. "%1" },
	{ vowel_diacritics_capture .. rukkakha, rukkakha .. "%1" },
	{ vowel_diacritics_capture .. combining_tilde_below, combining_tilde_below .. "%1" },
	-- partition punctuation marks so "starts with" and "ends with" substitutions work
	{"([".. tt_transpose_punc_keys .. "()!.:\"'])", "#%1#"},
}

local tt = {
	["ܦ"] = "f", ["ܒ"] = "b", ["ܬ"] = "t", ["ܛ"] = "ṭ", ["ܕ"] = "d", ["ܟ"] = "k",
	["ܓ"] = "g", ["ܩ"] = "q", ["ܔ"] = "j", ["ܣ"] = "s", ["ܨ"] = "ṣ", ["ܙ"] = "z",
	["ܫ"] = "š", ["ܚ"] = "ḥ", ["ܥ"] = "c", ["ܗ"] = "h", ["ܡ"] = "m", ["ܢ"] = "n",
	["ܪ"] = "r", ["ܠ"] = "l",
}

local tt_next = {
	[waw] = "w",
	[yudh] = "y",

	[rbasa_below] = "ë",
	[pthaha_below] = "ä",
	[rbasa] = "e",
	[zqapha] = "o",
	[pthaha] = "a",
}

local consonants = "fbtṭdkgqjsṣzščḥchmnrlvžpvṯḏxġ" .. yudh .. waw
local consonants_group = "([" .. consonants .. "])"

local special_cases = {
	-- { matching_aii_text, latin_substitution }
	--
	-- the # symbol pads the start and end of a word, consider the follow examples for matching_aii_text
	-- #float#    only float matches
	-- #float     words starting with float like float or floats match
	-- float#     words ending with float like float or afloat match
	-- float      words containing float like float, floats, afloat and refloats match
	{"ܡܳܪܝ#", "mor#"},
}

function export.tr(text, lang, sc)

	text = rsub(text, " | ", "# | #")
	text = "##" .. rsub(text, " ", "# #") .. "##"
	text = rsub(text, "ـ", "")
	text = rsub(text, combining_diaeresis, "")
	for _, sub in ipairs(fix) do text = rsub(text, unpack(sub)) end

	-- Special cases
	for _, sub in ipairs(special_cases) do text = rsub(text, unpack(sub)) end

	text = rsub(text, "ܫ" .. combining_tilde_below, "č")
	text = rsub(text, "ܙ" .. combining_tilde_below, "ž")

	text = rsub(text, "ܦ" .. qushshaya, "p")

	text = rsub(text, "ܒ" .. rukkakha, "v")
	text = rsub(text, "ܬ" .. rukkakha, "ṯ")
	text = rsub(text, "ܕ" .. rukkakha, "ḏ")
	text = rsub(text, "ܟ" .. rukkakha, "x")
	text = rsub(text, "ܓ" .. rukkakha, "ġ")

	text = rsub(text, ".", tt_transpose_punc)
	text = rsub(text, ".", tt)

	text = rsub_repeatedly(text, consonants_group .. waw .. consonants_group, "%1u%2")
	text = rsub_repeatedly(text, consonants_group .. yudh .. consonants_group, "%1i%2")
	text = rsub(text, "#" .. waw .. consonants_group, "#u%1")
	text = rsub(text, "#" .. yudh .. consonants_group, "#i%1") -- this needs a test case

	text = rsub(text, alaph .. pthaha ..  waw .. "#", "#aw")
	text = rsub(text, alaph .. pthaha .. yudh .. "#", "#ay")

	text = rsub(text, "#" .. alaph .. waw, "#u")
	text = rsub(text, "#" .. alaph .. yudh, "#i")

	text = rsub(text, pthaha .. waw .. "#", "aw#") --<ܝܳܬܰܘ> = yotaw, not yotau
	text = rsub(text, pthaha .. yudh .. "#", "ay#") --<ܚܙܰܝ> = ḥzay, not ḥzai

	text = rsub(text, waw .. "#", "u#")
	text = rsub(text, yudh .. "#", "i#")

	text = rsub(text, pthaha .. alaph .. "#", "a#")
	text = rsub(text, rbasa .. alaph .. "#", "e#")
	text = rsub(text, zqapha .. alaph .. "#", "o#")
	text = rsub(text, alaph .. "#", "o#")
	text = rsub(text, alaph, "")

	text = rsub(text, ".", tt_next)

	text = rsub(text, "cc", "c")
	text = rsub(text, "ḥḥ", "ḥ")
	text = rsub(text, "šš", "š")
	text = rsub(text, "ṯṯ", "ṯ")
	text = rsub(text, "xx", "x")

	text = rsub(text, "#", "")

	return text
end

return export