Module:mr-IPA/testcases

local tests = require("Module:UnitTests")
local m_IPA = require("Module:mr-IPA")

local function tag_IPA(IPA)
	return '<span class="IPA">' .. IPA .. '</span>'
end

function tests:check_output(term, expected, comment)
	self:equals(
		m_IPA.link(term),
		tag_IPA(m_IPA.toIPA(term, false)),
		tag_IPA(expected),
		{ comment = comment }
	)
end

function tests:check_output_phonetic(term, expected, comment)
	self:equals(
		m_IPA.link(term),
		tag_IPA(m_IPA.toIPA(term, true)),
		tag_IPA(expected),
		{ comment = comment }
	)
end

function tests:test_all()
	examples = {

-- /Broad transcription/

-- Syllabification

-- ळ Syllabification
-- ळ Syllabification: Word-final, Syllable-final, One Syllable ⟨σ⟩
        { "ओळ", "oɭ̆", ] Syllabification: ⟨σ⟩, Word-final, Syllable-final: Vɭ̆]=] },
        { "वेळ", "ʋeɭ̆", ] Syllabification: ⟨σ⟩, Word-final, Syllable-final: CVɭ̆]=] },

-- ळ Syllabification: Word-final, Syllable-final, Two Syllables ⟨σσ⟩
        { "देऊळ", "d̪e.uɭ̆", ] Syllabification: ⟨σσ⟩, Word-final, Syllable-final: Vɭ̆]=] },
        { "केवळ", "ke.ʋəɭ̆", ] Syllabification: ⟨σσ⟩, Word-final, Syllable-final: CVɭ̆]=] },

--  ळ Syllabification: Word-medial, Syllable-final
        { "आळशी", "aɭ̆.ɕi", ] Syllabification: ⟨σσ⟩, Word-medial, Syllable-final: Vɭ̆]=] },
        { "काळजी", "kaɭ̆.d͡ʑi", ] Syllabification: ⟨σσ⟩, Word-medial, Syllable-final: CVɭ̆]=] },

-- ळ Syllabification: Word-medial, Syllable-initial
        { "मुळे", "mu.ɭ̆e", ] Syllabification: ⟨σσ⟩, Word-medial, Syllable-initial: ɭ̆V]=] },
        { "आळस", "a.ɭ̆əs", ] Syllabification: ⟨σσ⟩, Word-medial, syllable-initial: ɭ̆VC]=] },

-- /t͡s/, /d͡z/ syllabification: Word-medial
		{ "डिवच़णे", "ɖi.ʋət͡s.ɳe", =] },
		{ "खेच़णे", "kʰet͡s.ɳe", =] },
		{ "अंदाज़", "ən.d̪ad͡z", =] },
		{ "अंदाज़े", "ən.d̪a.d͡ze", =] },

        { "अवहेलना", "əʋ.ɦel.na", =] },

-- Consonant clusters and geminates

-- Word-final consonant clusters and geminates
		{ "मार्ग", "maɾ.ɡə", =] },
		{ "खुद्द", "kʰud̪.d̪ə", =] },

-- Aspirated geminates: orthographic CʰCʰ → phonological CCʰ
        { "अख्खे", "ək.kʰe",  =] },
        { "पुठ्ठा", "puʈ.ʈʰa", =] },

-- Fundamental tests

-- Vowels

-- Non-word-final ई, ऊ
		{ "ईशान्य", "i.ɕan.jə", ], ]: ] Independent ]=] },
		{ "ऊर्फ", "uɾ.pʰə", ], ]: ] Independent ]=] },
		{ "श्रीमंत", "ɕɾi.mən.t̪ə", ], ]: ] Diacritic ]=] },
		{ "पूर्ण", "puɾ.ɳə", ], ]: ] Diacritic ]=] },

-- Diphthongs
        { "ऐक", "əik", ] Independent, Stem of ]]=] },
        { "हौस", "ɦəus", ] Diacritic]=] },

-- ऋ
        { "ऋण", "ɾuɳ", ]: Independent]=] },
        { "कृपा", "kɾu.pa", ]: Diacritic]=] },

-- Consonants

-- ल
        { "लाल", "lal", ]: Checks if ] is /l/ or /l̪/]=]},

-- ऱ् (Eyelash र)
        { "ऱ्हास", "ɾʱas", =] },
        { "गोऱ्हा", "ɡo.ɾʱa", =] },
        { "दऱ्या", "d̪ə.ɾja", ]]=] },
        { "दर्या", "d̪əɾ.ja", =] }, 

-- /ŋ/: Velar nasal
        { "सांग", "saŋ.ɡə", ]]=] },
        { "कंगवा", "kəŋ.ɡʋa", =] },
        { "पलंग", "pə.ləŋ.ɡə",  =] },

-- Spelt mumured consonants: न्ह, म्ह, ल्ह, व्ह
        { "न्हावी", "nʱa.ʋi", =] },
        { "तान्हा", "t̪a.nʱa", =] },
        { "म्हण", "mʱəɳ", =] },
        { "आम्ही", "a.mʱi", =] },
        { "जिल्हा", "d͡ʑi.lʱa", =] },
        { "व्हा", "ʋʱa", =] },
        { "नव्हे", "nə.ʋʱe", =] },

-- य 
-- य: Word-final
        { "काय", "kaj", ]: ⟨σ⟩, Word-final, Syllable-final: Vj]=] },
        { "उदय", "u.d̪əj", ]: ⟨σσ⟩, Word-final, Syllable-final: CVj]=] },

-- य: Word-medial
        { "आयते", "aj.t̪e", ]: ⟨σσ⟩, Word-medial, Syllable-final: Vj]=] },
        { "फायदा", "pʰaj.d̪a", ]: ⟨σσ⟩, Word-medial, Syllable-final: CVj]=] },
        { "नायक", "na.jək", ]: ⟨σσ⟩, Word-medial, Syllable-initial: jVC]=] },

-- ज्ञ
		{ "ज्ञान", "d̪njan", ]: Word-initial]=] },
		{ "आज्ञा", "ad̪.nja", ]: Word-medial]=] },

-- ह: Word-final 
		{ "मोह", "moɦ", ]: ⟨σ⟩, Word-final]=] },

-- English borrowings (See ] for details)
        { "ॲप्", "æp", ] Independent, ]]=] },
        { "ऍप्", "æp", ] Independent, ]]=] },
        { "ऑस्ट्रेलिया", "ɔs.ʈɾe.li.ja", ] Independent, ] ]=] },
        { "बॅट", "bæʈ", ] Diacritic, ]]=] },
        { "कॉट", "kɔʈ", ] Diacritic, ]]=] },
        { "बँक्", "bæŋk", ] Diacritic, ]]=] }, 
        { "ऑगस्ट्", "ɔ.ɡəsʈ", ] ]=] },
        { "काँग्रेस", "kɔŋ.ɡɾes", ], Hindi ] ]=] },
        { "हाँग्-काँग्", "ɦɔŋɡ‿kɔŋɡ", ], Hindi ] ]=] }, 
        
}--[[	Copy the following to add more examples:
		{ "", "" },
]]
	
	tests:iterate(examples, "check_output")
end

function tests:test_phonetic()
	examples = {

-- 

-- Final syllable high vowels

-- Open syllables
        { "ऊ", "uː", ] Independent, Open syllables ]=] },
		{ "मी", "miː", ] Diacritic, Open syllables ]=] },
        { "तू", "t̪uː", ] Diacritic, Open syllables ]=] },
        { "आणि", "a.ɳiː", ] Diacritic, Open syllables ]=]  },
        { "परंतु", "pə.ɾən.t̪uː", ] Diacritic, Open syllables ]=]  },

-- Closed syllables
        { "उत", "uːt̪", ] Independent, Closed syllables ]=]  },
        { "तपशील", "t̪əp.ɕiːl", ] Diacritic, Closed syllables ]=]  },
        { "कबूल", "kə.buːl", ] Diacritic, Closed syllables ]=]  },
        { "गणित", "ɡə.ɳiːt̪", ] Diacritic, Closed syllables ]=]  },
        { "खुश", "kʰuːɕ", ] Diacritic, Closed syllables ]=]  },

-- Murmur rule and ɦ-deletion in the environment CV₁_

-- Murmur rule: result has Cʱ
-- C murmur class = /m/, /n/, /l/, /ʋ/, /ɾ/, /d͡ʑ/, d͡z, /d̪/, /b/
-- V₁ = /ə/, /a/

-- V₂ = /i/, /u/
        { "दही", "d̪ʱəiː", =] },
        { "बहीण", "bʱəiːɳ", ] ]=] },
        { "वहिणी", "ʋʱəi.ɳiː", =] },
        { "बहुतेक", "bʱəu.t̪ek", =] },
        { "जाहिरात", "d͡ʑʱai.ɾat̪", =] },
        { "बाहुली", "bʱau.liː", =] },

-- V₁ ≠ /ə/, /a/, V₂ = /ə/
        { "मनोहर", "mə.nʱoɾ", ɦə → Cʱ ]=] },
        { "बेहद्द", "bʱed̪.d̪ə", ɦə → Cʱ ]=] },

--  ≠ /i/, /u/, /o/
        { "ज़हाज़", "d͡zʱad͡z",  → Cʱ, C = /d͡z/, V₂ = /a/ ]=] }, 
        { "दहा", "d̪ʱa",   → Cʱ, C = /d̪/, V₂ = /a/, Konkani ] ]=] },
        { "उदाहरण", "u.d̪ʱa.ɾəɳ",  , C = /d̪/, C₂ = /ɾ/ ]=] },
        { "नाहणे", "nʱa.ɳe", , C = /n/, C₂ = /ɳ/ ]=] },
        { "बाहेर", "bʱa.eɾ", , C = /b/, V₂ = /e/ ]=] },
        { "मेहेरबानी", "mʱeɾ.ba.niː", , C = /m/, V₁ = V₂ = /e/ ]=] },
        { "मोहीम", "mʱo.iːm", , C = /m/, V₁ = /o/, V₂ = /i/ ]=] },
        { "राहणे", "ɾʱa.ɳe", , C = /ɾ/, C₂ = /ɳ/ ]=] },
        { "लिहिणे", "lʱi.ɳe", , C = /l/, V₁ = V₂ = /i/ ]=] },
        { "वाहणे", "ʋʱa.ɳe", , C = /ʋ/, C₂ = /ɳ/ ]=] },
        { "लहान", "lʱan",  → Cʱ, C = /l/, V₂ = /a/, Konkani ] ]=] },

-- ɦ-deletion: ɦ → ∅ 
-- C ≠ C murmur class

-- V₁ = /ə/, /a/, V₂ = /i/, /u/

        { "पहिले", "pəi.le", =] },
        { "सही", "səiː", =] },
 		{ "गहू", "ɡəuː", =] },
        { "काही", "kaiː", =] },
        { "पाहुणा", "pau.ɳa", =] },

-- V₁ = /ə/, /a/, V₂ ≠ /i/, /u/, /o/
        { "तहान", "t̪an", , V₂ = /a/, Konkani ] ]=] },
        { "शहर", "ɕəɾ",  , C = /ɕ/, V₂ = /ə/ ]=] },
        { "सहन", "sən",  , C = /s/, V₂ = /ə/ ]=] },
        { "साहेब", "sa.eb", ɦ ]=] },

-- V₁ ≠ /ə/, /a/, V₂ = /ə/
        { "पेहलवान", "pel.ʋan", _ə, ɦ-deleted spelling: ] ]=] },

--  ≠ /ə/, /i/, /u/, /o/
        { "सहमत", "sə.mət̪", _, V₁ = /ə/, C₂ = /m/ ]=] },
        { "चेहरा", "t͡ɕe.ɾa", _, V₁ = /e/, C₂ = /ɾ/ ]=] },
        { "पाहणे", "pa.ɳe", _, V₁ = /a/, C₂ = /ɳ/ ]=] },

-- /t͡sʰ/: Any sequence of /ts/ → /t͡sʰ/
        { "वत्स", "ʋə.t͡sʰə", =] },
        { "मत्सर", "mə.t͡sʰəɾ", =] },
        { "उत्साह", "u.t͡sʰa", =] },

-- ज्ञ
		{ "ज्ञान", "njan", ]: Word-initial]=] },
}
	
	tests:iterate(examples, "check_output_phonetic")
end

return tests