မဝ်ဂျူ:tru-translit

This is the unit-testing module for Module:tru-translit.

All tests passed. (refresh)

testcases for tr function in Module:tru-translit:

	Text	Expected	Actual	Differs at
	ܐܰܕܡܐ	admo	admo
	ܐܰܒܪܐ	abro	abro
	ܐܰܕ݂ܢܐ	aḏno	aḏno
	ܐܷܫܬܐ	ëšto	ëšto
	ܫܰܘܥܐ	šawco	šawco
	ܬܡܰܢܝܐ	tmanyo	tmanyo
	ܬܷܫܥܐ	tëšco	tëšco
	ܚܰܡܫܐ	ḥamšo	ḥamšo
	ܐܰܪܒܥܐ	arbco	arbco
	ܬܠܳܬ݂ܐ	tloṯo	tloṯo
	ܬܪܶܐ	tre	tre
	ܚܰܐ	ḥa	ḥa
	ܬܡܝܢܳܝܐ	tminoyo	tminoyo
	ܕܰܬ ܬܡܰܢܝܐ	dat tmanyo	dat tmanyo
	ܬܡܳܢܰܥܣܰܪ	tmonacsar	tmonacsar
	ܐܰܕܥܰܨܪܝـܝܶܐ	adcaṣriye	adcaṣriye
	ܐܰܕܠܰܠܝܐ	adlalyo	adlalyo
	ܐܰܕܨܰܦܪܐ	adṣafro	adṣafro
	ܐܰܕܝܰܘܡܰܐ	adyawma	adyawma
	ܐܰܬ݂ܡܷܠ	aṯmël	aṯmël
	ܐܰܬ݂ܝܳܢܐ	aṯyono	aṯyono
	ܐܰܙܙܝ	azzi	azzi
	ܒܰܛܝܠܶܐ ܢܶܐ	baṭile ne	baṭile ne
	ܒܢܳܝܐ	bnoyo	bnoyo
	ܕܰܪܓ݂ܶܐ	darġe	darġe
	ܕܘܥܪܝܢܰܐ	ducrina	ducrina
	ܕܘܪܳܫܶܐ ܓܘܫܡܳܢܳܝܶܐ	duroše gušmonoye	duroše gušmonoye
	ܦܰܠܩܐ	falqo	falqo
	ܠܰܫܰܢ	lašan	lašan
	ܡܶܐ ܙܰܒܢܐ ܠܙܰܒܢܐ	me zabno lzabno	me zabno lzabno
	ܩܷܛܪܐ	qëṭro	qëṭro
	ܣܚܳܝܐ	sḥoyo	sḥoyo
	ܬܰܡܐ	tamo	tamo
	ܘܰܥܕܐ	wacdo	wacdo
	ܙܰܒܢܐ	zabno	zabno
	ܢܚܝܪܐ	nḥiro	nḥiro
	ܢܳܫܐ	nošo	nošo
	ܪܝܫܐ	rišo	rišo
	ܫܰܒܬ݂ܐ	šabṯo	šabṯo
	ܐܘܥܕܐ	ucdo	ucdo
	ܘܳܠܝܬ݂ܐ	woliṯo	woliṯo
	ܙܥܘܪܐ	zcuro	zcuro
	ܙܥܘܪܬܐ	zcurto	zcurto
	ܕܰܫܷܫܬܐ	dašëšto	dašëšto
	ܥܷܢܘܶܐ	cënwe	cënwe
	ܨܷܪܬܐ	ṣërto	ṣërto
	ܘܰܟ݂ܰܡ	waxam	waxam
	ܙܷܒܕܐ	zëbdo	zëbdo
	ܐܰܝ ܝܰܘܡܰܢܝ	ay yawmani	ay yawmani
	ܫ̰ܰܢܛܰܐ	čanṭa	čanṭa
	ܙ̰ܱܒܰܫܶܐ	žäbaše	žäbaše
	ܙܱ̰ܒܰܫܶܐ	žäbaše	žäbaše
	ܦ݁ܠܰܢ	plan	plan
	ܒ݂ܝܠܠܰܐ	villa	villa
	ܐܳܢܳܐ	ono	ono
	ܗܰܬܘ	hatu	hatu
	ܐܝـܝܰܪ	iyar	iyar
	ܐܰܘ	aw	aw
	”ܝܐ.“	“yo.”	“yo.”
	ܒܷܬ݂ܷܪ	bëṯër	bëṯër
	ܒܷܬܷ݂ܪ	bëṯër	bëṯër
	ܐܰܘܪܘܦ݁ܰܐ	awrupa	awrupa
	ܐܰܘܪܘܦܰ݁ܐ	awrupa	awrupa
	(ܣܘܪܝܳܝܐ)	(suryoyo)	(suryoyo)
	ܣܘܪܝܳܝܐ܆	suryoyo;	suryoyo;
	ܡܳܪܝ	mor	mor
	ܕܡܳܪܝ	dmor	dmor
	ܛܒܷܥܥܶܗ	ṭbëceh	ṭbëceh
	ܦܬܷܚܚܶܗ	ftëḥeh	ftëḥeh
	ܘܡܰܠܘܰܫܫܶܗ	umalwašeh	umalwašeh
	ܝܘܠܦܳܢܰܬ݂ܬ݂ܶܗ	yulfonaṯeh	yulfonaṯeh
	ܡܰܠܰܟ݂ܟ݂ܶܗ	malaxeh	malaxeh
	ܡ̈ܶܠܐ	melo	melo

---

local export = {}

local U = mw.ustring.char
local U = mw.ustring.char
local rsub = mw.ustring.gsub

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 = "fbtṭdkgqjsṣzšḥchmnrlvžpvṯḏxġ" .. 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(text, consonants_group .. waw .. consonants_group, "%1u%2")
	text = rsub(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, 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