Module:it-pronunciation/sandbox/testcases

The following documentation is located at Module:it-pronunciation/sandbox/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 of (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	o	o
English letter sequences
	smoking	ˈzmo.kiŋ	ˈzmo.kiŋ
	gangster	ˈgaŋ.ster	ˈɡan.ɡster
	hòckey	ˈɔ.ke.i	ˈɔ.ke.i
	hockeìstico	o.keˈis.ti.ko	o.keˈis.ti.ko
	crawl	krɔl	krɔl
	shòck	ʃɔk	ˈʃɔk
	Oahu	oˈa.u	oˈa.u
y
	yo-yo	ˈjo.jo	ˈjo.jo
	whisky	ˈwis.ki	ˈwis.ki
x
	Craxi	ˈkrak.si	ˈkrak.si
-izzare
	analizzare	a.na.lidˈd͡za.re	a.na.lidˈd͡za.re
	nazionalizzare	nat.t͡sjo.na.lidˈd͡za.re	nat.t͡sjo.na.lidˈd͡za.re
	zonizzare (all z sequences are voiced)	d͡zo.nidˈd͡za.re	d͡zo.nidˈd͡za.re
	rizzare	ritˈt͡sa.re	ritˈt͡sa.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.ze	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	ˈzɡwar.do
	sregolato	zre.ɡoˈla.to	zre.ɡoˈla.to
	gira-sole	d͡ʒi.raˈso.le	d͡ʒi.raˈso.le
	desìdero	deˈzi.de.ro	deˈzi.de.ro
z, zz
	fòrza	ˈfɔr.t͡sa	ˈfɔr.t͡sa
	ragàzza	raˈɡat.t͡sa	raˈɡat.t͡sa
	mèzzo	ˈmɛt.t͡so	ˈmɛt.t͡so
	mèzzo (z sequence 1 is voiced)	ˈmɛd.d͡zo	ˈmɛd.d͡zo
	zanzara (all z sequences are voiced)	d͡zanˈd͡za.ra	d͡zanˈd͡za.ra
	nazione	natˈt͡sjo.ne	natˈt͡sjo.ne
	spazzi	ˈspat.t͡si	ˈspat.t͡si
	zìo	ˈt͡si.o	ˈt͡si.o
	agenzìa	a.d͡ʒenˈt͡si.a	a.d͡ʒenˈt͡si.a
	grazie	ˈɡrat.t͡sje	ˈɡrat.t͡sje
	azienda (z sequence 1 is voiced)	adˈd͡zjen.da	adˈd͡zjen.da
	romanzière (z sequence 1 is voiced)	ro.manˈd͡zjɛ.re	ro.manˈd͡zjɛ.re
	Anzio	ˈan.t͡sjo	ˈan.t͡sjo
	zàino	ˈd͡zai.no	ˈd͡za.i.no
	zampa	ˈt͡sam.pa	ˈt͡sam.pa
	zòccolo	ˈt͡sɔk.ko.lo	ˈt͡sɔk.ko.lo
	zùfolo	ˈt͡su.fo.lo	ˈt͡su.fo.lo
	zàffiro (z sequence 1 is voiced)	ˈd͡zaf.fi.ro	ˈd͡zaf.fi.ro
	zèbra	ˈd͡zɛ.bra	ˈt͡sɛb.ra
	zuzzurellone	d͡zud.d͡zu.relˈlo.ne	t͡sut.t͡su.relˈlo.ne
	zanna	ˈt͡san.na	ˈt͡san.na
	zigano	t͡siˈɡa.no	t͡siˈɡa.no
	spazî	ˈspat.t͡si	ˈspat.t͡si
	ozòno (all z sequences are voiced)	odˈd͡zɔ.no	odˈd͡zɔ.no
semivowels
	quéllo	ˈkwel.lo	ˈkwel.lo
	grànchio	ˈɡran.kjo	ˈɡran.kjo
	capiènza	kaˈpjɛn.t͡sa	kapˈjɛn.t͡sa
	niènte	ˈnjɛn.te	ˈnjɛn.te
	sùo	ˈsu.o	ˈsu.o
	può	ˈpwɔ	ˈpwɔ
	nuòvo	ˈnwɔ.vo	ˈnwɔ.vo
	devi-are	de.viˈa.re	de.viˈa.re
Handling of words without accents
	sono	ˈso.no	ˈso.no
	cane	ˈka.ne	ˈka.ne
	carta	ˈkar.ta	ˈkar.ta
Syllabification
	sottosvillupo	sot.to.zvilˈlu.po	sot.toz.vilˈlu.po
	manùbrio	maˈnu.brjo	maˈnub.rjo

test_to_phonetic:

	Text	Expected	Actual
	càne	ˈkäː.n̺e̞	ˈkäː.n̺e
	bène	ˈbɛː.n̺e	ˈbɛː.n̺e
	sóno	ˈs̪oː.n̺o	ˈsoː.n̺o
	sòno	ˈs̪ɔː.n̺o	ˈsɔː.n̺o
English letter sequences
y
x
-izzare
c, g, sc
	cèlo	ˈt͡ʃɛː.lo	ˈt͡ʃɛː.lo
	ciaccòna	t͡ʃäkˈkɔː.n̺ä	t͡ʃäkˈkɔː.n̺ä
	fàccio	ˈfät͡ʃ.t͡ʃo	ˈfät.t͡ʃo
	che	k̟e	k̟e
	òcchio	ˈɔk̟.k̟jo	ˈɔk.k̟jo
	òcchi	ˈɔk̟.k̟i	ˈɔk.k̟i
	òggi	ˈɔd͡ʒ.d͡ʒi	ˈɔd.d͡ʒi
	Sciàlpi	ˈʃäl.pi	ˈʃäl.pi
	lasciàre	läʃˈʃäː.r̺e̞	läʃˈʃäː.re
	scleràre	s̪kleˈr̺äː.r̺e̞	skleˈräː.re
	ùscio	ˈuʃ.ʃo	ˈuʃ.ʃo
gn, gl
	ógni	ˈoɲ.ɲi	ˈoɲ.ɲi
	gnòcco	ˈɲɔk.ko	ˈɲɔk.ko
	gnagnà	ɲäɲˈɲä	ɲäɲˈɲä
	vòglio	ˈvɔʎ.ʎo	ˈvɔʎ.ʎo
	gli	ʎi	ʎi
	inglése	iŋˈɡleː.z̪e	iŋˈɡleː.ze
ng, nq, nch
	anche	ˈäŋ.k̟e	ˈäŋ.k̟e
	dúnque	ˈduŋ.kwe	ˈduŋ.kwe
	vóngola	ˈvoŋ.ɡo.lä	ˈvoŋ.ɡo.lä
s
	sguardo	ˈzɡwär.do	ˈzɡwär.do
	sregolato	zre.ɡoˈläː.to	zre.ɡoˈläː.to
z, zz
	fòrza	ˈfɔr̺.t̪͡s̪ä	ˈfɔr.t͡sä
	ragàzza	r̺äˈɡät̪͡s̪.t̪͡s̪ä	räˈɡät.t͡sä
	mèzzo	ˈmɛt̪͡s̪.t̪͡s̪o	ˈmɛt.t͡so
	mèzzo (z sequence 1 is voiced)	ˈmɛd̪͡z̪.d̪͡z̪o	ˈmɛd.d͡zo
	zanzara (all z sequences are voiced)	d̪͡z̪änˈd̪͡z̪äː.r̺ä	d͡zän̺ˈd͡zäː.rä
	nazione	n̺ätˈt͡sjoː.n̺e	n̺ätˈt͡sjoː.n̺e
	spazzi	ˈspät.t͡si	ˈspät.t͡si
	spazî	ˈspät.t͡si	ˈspät.t͡si
semivowels
	quéllo	ˈkwel.lo	ˈkwel.lo
	grànchio	ˈɡräŋ.k̟jo	ˈɡräŋ.k̟jo
	capiènza	käˈpjɛn̺.t͡sä	käpˈjɛn̺.t͡sä
	niènte	ˈnjɛn̪.t̪e	ˈn̺jɛn̺.te
	sùo	ˈsuː.o	ˈsuː.o
	può	ˈpwɔ	ˈpwɔ
	nuòvo	ˈn̺wɔː.vo	ˈn̺wɔː.vo
Handling of words without accents
	sono	ˈsoː.n̺o	ˈsoː.n̺o
	cane	ˈkäː.n̺e̞	ˈkäː.n̺e
	carta	ˈkär̺.t̪ä	ˈkär.tä
Syllabification
	sottosvillupo	sot.to.zvilˈluː.po	sot.toz.vilˈluː.po
	manùbrio	mäˈn̺u.brjo	mäˈn̺ub.rjo

---

local tests = require "Module:UnitTests"

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

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", "o", "" },
	"English letter sequences",
	{ "smoking", "ˈzmo.kiŋ", "" },
	{ "gangster", "ˈgaŋ.ster", "" },
	{ "hòckey", "ˈɔ.ke.i", "" },
	{ "hockeìstico", "o.keˈis.ti.ko", "" },
	{ "crawl", "krɔl", "" },
	{ "shòck", "ʃɔk", "" },
	{"Oahu", "oˈa.u", ""},
	"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.ze", "iŋˈɡleː.z̪e" },
	"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", "deˈzi.de.ro", "" },
	"z, zz",
	{ "fòrza", "ˈfɔr.t͡sa", "ˈfɔr̺.t̪͡s̪ä" },
	{ "ragàzza", "raˈɡat.t͡sa", "r̺äˈɡät̪͡s̪.t̪͡s̪ä" },
	{ "mèzzo", "ˈmɛt.t͡so", "ˈmɛt̪͡s̪.t̪͡s̪o" },
	{ "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 } },
	{ "Anzio", "ˈan.t͡sjo", ""},
	
	-- initial z followed by two vowels is usually voiced
	{ "zàino", "ˈd͡zai.no", "" },
	
	-- initial z followed by syllable beginning in voiceless consonant is usually voiceless
	{ "zampa", "ˈt͡sam.pa", "" },
	{ "zòccolo", "ˈt͡sɔk.ko.lo", "" },
	{ "zùfolo", "ˈt͡su.fo.lo", "" },
	-- exceptions
	{ "zàffiro", "ˈd͡zaf.fi.ro", "", { 1 } },
	
	-- initial z followed by syllable beginning in voiced consonant is usually voiced
	{ "zèbra", "ˈd͡zɛ.bra", "" },
	{ "zuzzurellone", "d͡zud.d͡zu.relˈlo.ne", "" },
	-- exceptions
	{ "zanna", "ˈt͡san.na", "" },
	{ "zigano", "t͡siˈɡa.no", "" },
	
	-- intervocalic "autogeminazione" [[w:it:Autogeminazione]]
	{ "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", "" },
	"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?
	
	--[[
	-- 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, 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

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
				mw.logObject(voiced_z, "voiced_z")
				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