Module:it-pronunciation/testcases

The following documentation is located at Module:it-pronunciation/testcases/documentation. ^[edit] Categories were auto-generated by Module:module categorization. ^[edit]

Useful links: root page • root page’s subpages • links • transclusions • tested module • sandbox (diff)

(refresh)

test_to_phonemic:

	Text	Expected	Actual
	càne	ˈka.ne	ˈka.ne
	bène	ˈbɛ.ne	ˈbɛ.ne
	sóno	ˈso.no	ˈso.no
	sòno	ˈsɔ.no	ˈsɔ.no
	ho	ɔ	o
	all'	all	ˈall‿
English letter sequences
	smoking	ˈzmo.kiŋ	Error: Module:it-pronunciation:350: When stressed vowel is e or o, it must be marked é/è or ó/ò to indicate quality: smoking
	gangster	ˈgaŋ.ster	ˈɡanɡ.ster
	hòckey	ˈɔ.ke.i	ˈɔ.kej
	hockeìstico	o.keˈis.ti.ko	o.keˈi.sti.ko
	crawl	krɔl	ˈkrawl
y
	yo-yo	ˈjo.jo	ˈi.o ˈi.o
	whisky	ˈwis.ki	ˈwi.ski
x
	Craxi	ˈkrak.si	ˈkrak.si
-izzare
	analizzare	a.na.lidˈd͡za.re	a.na.lidˈd͡za.re
	nazionalizzare	nat.t͡sjo.na.lidˈd͡za.re	Error: Module:it-pronunciation:535: z must be respelled (d)dz or (t)ts: nazionaliddzàre
	zonizzare	d͡zo.nidˈd͡za.re	Error: Module:it-pronunciation:535: z must be respelled (d)dz or (t)ts: zoniddzàre
	rizzare	ritˈt͡sa.re	ridˈd͡za.re
c, g, sc
	cèlo	ˈt͡ʃɛ.lo	ˈt͡ʃɛ.lo
	ciaccòna	t͡ʃakˈkɔ.na	t͡ʃakˈkɔ.na
	fàccio	ˈfat.t͡ʃo	ˈfat.t͡ʃo
	che	ke	ke
	òcchio	ˈɔk.kjo	ˈɔk.kjo
	òcchi	ˈɔk.ki	ˈɔk.ki
	òggi	ˈɔd.d͡ʒi	ˈɔd.d͡ʒi
	Sciàlpi	ˈʃal.pi	ˈʃal.pi
	lasciàre	laʃˈʃa.re	laʃˈʃa.re
	scleràre	skleˈra.re	skleˈra.re
	ùscio	ˈuʃ.ʃo	ˈuʃ.ʃo
gn, gl
	ógni	ˈoɲ.ɲi	ˈoɲ.ɲi
	gnòcco	ˈɲɔk.ko	ˈɲɔk.ko
	gnagnà	ɲaɲˈɲa	ɲaɲˈɲa
	vòglio	ˈvɔʎ.ʎo	ˈvɔʎ.ʎo
	gli	ʎi	ʎi
	inglése	inˈɡle.se	inˈɡle.ze
ng, nq, nch
	anche	ˈan.ke	ˈan.ke
	dúnque	ˈdun.kwe	ˈdun.kwe
	vóngola	ˈvon.ɡo.la	ˈvon.ɡo.la
s
	sguardo	ˈzɡwar.do	Error: Module:it-pronunciation:350: With more than two vowels and an unrecognized suffix, stress must be explicitly given: sguardo
	sregolato	zre.ɡoˈla.to	zre.ɡoˈla.to
	gira-sole	d͡ʒi.raˈso.le	Error: Module:it-pronunciation:350: When stressed vowel is e or o, it must be marked é/è or ó/ò to indicate quality: sole
	desìdero	deˈsi.de.ro	deˈzi.de.ro
	ròsa	ˈrɔ.za	ˈrɔ.za
z, zz
	fòrza	ˈfɔr.t͡sa	Error: Module:it-pronunciation:535: z must be respelled (d)dz or (t)ts: fòrza
	ragàzza	raˈɡat.t͡sa	Error: Module:it-pronunciation:535: z must be respelled (d)dz or (t)ts: ragàzza
	mèzzo	ˈmɛd.d͡zo	Error: Module:it-pronunciation:535: z must be respelled (d)dz or (t)ts: mèzzo
	mèzzo	ˈmɛd.d͡zo	Error: Module:it-pronunciation:535: z must be respelled (d)dz or (t)ts: mèzzo
	zanzara	d͡zanˈd͡za.ra	Error: Module:it-pronunciation:350: With more than two vowels and an unrecognized suffix, stress must be explicitly given: zanzara
	nazione	natˈt͡sjo.ne	natˈt͡sjo.ne
	spazzi	ˈspat.t͡si	Error: Module:it-pronunciation:535: z must be respelled (d)dz or (t)ts: spàzzi
	zìo	ˈt͡si.o	Error: Module:it-pronunciation:535: z must be respelled (d)dz or (t)ts: zìo
	agenzìa	a.d͡ʒenˈt͡si.a	Error: Module:it-pronunciation:535: z must be respelled (d)dz or (t)ts: agenzìa
	grazie	ˈɡrat.t͡sje	Error: Module:it-pronunciation:350: With more than two vowels and an unrecognized suffix, stress must be explicitly given: grazie
	azienda	adˈd͡zjen.da	Error: Module:it-pronunciation:350: With more than two vowels and an unrecognized suffix, stress must be explicitly given: azienda
	romanzière	ro.manˈd͡zjɛ.re	Error: Module:it-pronunciation:535: z must be respelled (d)dz or (t)ts: romanzière
	spazi	ˈspat.t͡si	Error: Module:it-pronunciation:535: z must be respelled (d)dz or (t)ts: spàzi
	spazî	ˈspat.t͡si	Error: Module:it-pronunciation:535: z must be respelled (d)dz or (t)ts: spàzî
	ozòno	odˈd͡zɔ.no	Error: Module:it-pronunciation:535: z must be respelled (d)dz or (t)ts: ozòno
semivowels
	quéllo	ˈkwel.lo	ˈkwel.lo
	grànchio	ˈɡran.kjo	ˈɡran.kjo
	capiènza	kaˈpjɛn.t͡sa	Error: Module:it-pronunciation:535: z must be respelled (d)dz or (t)ts: capiènza
	niènte	ˈnjɛn.te	ˈnjɛn.te
	sùo	ˈsu.o	ˈsu.o
	può	ˈpwɔ	ˈpwɔ
	nuòvo	ˈnwɔ.vo	ˈnwɔ.vo
	devi-are	de.viˈa.re	Error: Module:it-pronunciation:350: When stressed vowel is e or o, it must be marked é/è or ó/ò to indicate quality: devi
	televisione	te.le.viˈzjo.ne	te.le.viˈzjo.ne
Handling of words without accents
	sono	ˈso.no	Error: Module:it-pronunciation:350: When stressed vowel is e or o, it must be marked é/è or ó/ò to indicate quality: sono
	cane	ˈka.ne	ˈka.ne
	carta	ˈkar.ta	ˈkar.ta
Syllabification
	sottosvillupo	sot.to.zvilˈlu.po	Error: Module:it-pronunciation:350: With more than two vowels and an unrecognized suffix, stress must be explicitly given: sottosvillupo
	manùbrio	maˈnu.brjo	maˈnu.brjo
	àulico	ˈau.li.ko	ˈaw.li.ko

---

local tests = require "Module:UnitTests"

setmetatable(_G, { __index = require "Module:it-pronunciation" })

local function tag_IPA(transcription)
	if transcription:find "^Error" then
		return transcription
	else
		return '<span class="IPA">' .. transcription .. '</span>'
	end
end

local examples = {
	{ "càne", "ˈka.ne", "ˈkäː.n̺e̞" },
	{ "bène", "ˈbɛ.ne", "ˈbɛː.n̺e" },
	{ "sóno", "ˈso.no", "ˈs̪oː.n̺o" },
	{ "sòno", "ˈsɔ.no", "ˈs̪ɔː.n̺o" },
	{ "ho", "ɔ", "" },
	{"all'", "all", ""},
	"English letter sequences",
	{ "smoking", "ˈzmo.kiŋ", "" },
	{ "gangster", "ˈgaŋ.ster", "" },
	{ "hòckey", "ˈɔ.ke.i", "" },
	{ "hockeìstico", "o.keˈis.ti.ko", "" },
	{ "crawl", "krɔl", "" },
	"y",
	{ "yo-yo", "ˈjo.jo", "" },
	{ "whisky", "ˈwis.ki", "" },
	"x",
	{ "Craxi", "ˈkrak.si", "" },
	"-izzare",
	{ "analizzare", "a.na.lidˈd͡za.re", ""},
	{ "nazionalizzare", "nat.t͡sjo.na.lidˈd͡za.re", "" },
	{ "zonizzare", "d͡zo.nidˈd͡za.re", "", true },
	{ "rizzare", "ritˈt͡sa.re", ""},
	"c, g, sc",
	{ "cèlo", "ˈt͡ʃɛ.lo", "ˈt͡ʃɛː.lo" },
	{ "ciaccòna", "t͡ʃakˈkɔ.na", "t͡ʃäkˈkɔː.n̺ä" },
	{ "fàccio", "ˈfat.t͡ʃo", "ˈfät͡ʃ.t͡ʃo" }, -- ˈfat.t͡ʃo is too phonetic; other alternative, ˈfa.t͡ʃːo
	{ "che", "ke", "k̟e" },
	{ "òcchio", "ˈɔk.kjo", "ˈɔk̟.k̟jo" }, -- Good test for syllabification.
	{ "òcchi", "ˈɔk.ki", "ˈɔk̟.k̟i" },
	{ "òggi", "ˈɔd.d͡ʒi", "ˈɔd͡ʒ.d͡ʒi" }, -- ˈɔd.d͡ʒi is too phonetic; other alternative, ˈɔ.d͡ʒːi 
	{ "Sciàlpi", "ˈʃal.pi", "ˈʃäl.pi" },
	{ "lasciàre", "laʃˈʃa.re", "läʃˈʃäː.r̺e̞" },
	{ "scleràre", "skleˈra.re", "s̪kleˈr̺äː.r̺e̞" },
	{ "ùscio", "ˈuʃ.ʃo", "ˈuʃ.ʃo" },
	"gn, gl",
	{ "ógni", "ˈoɲ.ɲi", "ˈoɲ.ɲi" },
	{ "gnòcco", "ˈɲɔk.ko", "ˈɲɔk.ko" },
	{ "gnagnà", "ɲaɲˈɲa", "ɲäɲˈɲä" }, -- probably not a real word
	{ "vòglio", "ˈvɔʎ.ʎo", "ˈvɔʎ.ʎo" },
	{ "gli", "ʎi", "ʎi" },
	{ "inglése", "inˈɡle.se", "iŋˈɡleː.s̪e" },
	"ng, nq, nch",
	{ "anche", "ˈan.ke", "ˈäŋ.k̟e" },
	{ "dúnque", "ˈdun.kwe", "ˈduŋ.kwe"  },
	{ "vóngola", "ˈvon.ɡo.la", "ˈvoŋ.ɡo.lä" }, 
	"s",
	{ "sguardo", "ˈzɡwar.do", "ˈzɡwär.do" },
	{ "sregolato", "zre.ɡoˈla.to", "zre.ɡoˈläː.to" },
	{ "gira-sole", "d͡ʒi.raˈso.le", "" },
    { "desìdero", "deˈsi.de.ro", "" },
    { "ròsa", "ˈrɔ.za", "" },
	"z, zz",
	{ "fòrza", "ˈfɔr.t͡sa", "ˈfɔr̺.t̪͡s̪ä" },
	{ "ragàzza", "raˈɡat.t͡sa", "r̺äˈɡät̪͡s̪.t̪͡s̪ä" },
	{ "mèzzo", "ˈmɛd.d͡zo", "ˈmɛd̪͡z̪.d̪͡z̪o" },
	{ "mèzzo", "ˈmɛd.d͡zo", "ˈmɛd̪͡z̪.d̪͡z̪o", { 1 } },
	{ "zanzara", "d͡zanˈd͡za.ra", "d̪͡z̪änˈd̪͡z̪äː.r̺ä", true },
	-- [[w:Italian orthography]] says the z is geminate, while the English
	-- and Italian Wiktionaries say it isn't. It sounds geminate in the soundfile.
	{ "nazione", "natˈt͡sjo.ne" , "n̺ätˈt͡sjoː.n̺e" },
	{ "spazzi", "ˈspat.t͡si", "ˈspät.t͡si" },
	{ "zìo", "ˈt͡si.o", "" },
	{ "agenzìa", "a.d͡ʒenˈt͡si.a", "" },
	{ "grazie", "ˈɡrat.t͡sje", "" },
	{ "azienda", "adˈd͡zjen.da", "", { 1 } },
	{ "romanzière", "ro.manˈd͡zjɛ.re", "",  { 1 } },
	-- intervocalic "autogeminazione" [[w:it:Autogeminazione]]
	{ "spazi", "ˈspat.t͡si", "ˈspät.t͡si" },
	{ "spazî", "ˈspat.t͡si", "ˈspät.t͡si" },
	{ "ozòno", "odˈd͡zɔ.no", "", true },
	"semivowels",
	{ "quéllo", "ˈkwel.lo", "ˈkwel.lo" },
	{ "grànchio", "ˈɡran.kjo", "ˈɡräŋ.k̟jo" },
	{ "capiènza", "kaˈpjɛn.t͡sa", "käˈpjɛn̺.t͡sä" },
	{ "niènte", "ˈnjɛn.te", "ˈnjɛn̪.t̪e" }, -- or [n̺ʲ-]?
	{ "sùo", "ˈsu.o", "ˈsuː.o" },
	{ "può", "ˈpwɔ", "ˈpwɔ" },
	{ "nuòvo", "ˈnwɔ.vo", "ˈn̺wɔː.vo" },
	{ "devi-are", "de.viˈa.re", "" },
	{ "televisione", "te.le.viˈzjo.ne", "" },
	"Handling of words without accents",
	{ "sono", "ˈso.no", "ˈsoː.n̺o" },
	{ "cane", "ˈka.ne", "ˈkäː.n̺e̞" },
	{ "carta", "ˈkar.ta", "ˈkär̺.t̪ä" },
	"Syllabification",
	{ "sottosvillupo", "sot.to.zvilˈlu.po", "sot.to.zvilˈluː.po" },
	{ "manùbrio", "maˈnu.brjo", "mäˈn̺u.brjo" }, -- Is u long here?
	{ "àulico", "ˈau.li.ko", "" }
	
	--[[
	-- For new examples:
	{ "", "", "" },
	-- respelling, phonemic, phonetic
	]]
}

function tests:test_to_phonemic()
	self:iterate(examples,
		function (self, example, expected, _, voiced_z)
			local success, result = pcall(to_phonemic,example,example)
			if not success then
				result = ("Error: %s"):format(result)
			else
				result = result.phonemic
			end
			
			--[[local voiced_text
			if not voiced_z then
				voiced_text = ""
			elseif type(voiced_z) == "boolean" then
				if voiced_z then
					voiced_text = " (all z sequences are voiced)"
				else
					voiced_text = " (no z sequences are voiced)"
				end
			else
				voiced_text = (" (z sequence%s %s %s voiced)"):format(
					voiced_z[2] and "s" or "",
					table.concat(voiced_z, ", "),
					voiced_z[2] and "are" or "is")
			end]]
			
			self:equals(example, result, expected, { display = tag_IPA })
		end)
end

--[[function tests:test_to_phonetic()
	self:iterate(examples,
		function (self, example, _, expected, voiced_z)
			if expected == "" then
				return
			end
			
			local success, result = pcall(to_phonetic, example, voiced_z)
			if not success then
				result = ("Error: %s"):format(result)
			end
			
			local voiced_text
			if not voiced_z then
				voiced_text = ""
			elseif type(voiced_z) == "boolean" then
				if voiced_z then
					voiced_text = " (all z sequences are voiced)"
				else
					voiced_text = " (no z sequences are voiced)"
				end
			else
				voiced_text = (" (z sequence%s %s %s voiced)"):format(
					voiced_z[2] and "s" or "",
					table.concat(voiced_z, ", "),
					voiced_z[2] and "are" or "is")
			end
			
			self:equals(example .. voiced_text, result, expected, { display = tag_IPA })
		end)
end]]

return tests