class PhonemTestCases(unittest.TestCase): """Test Phonem functions. test cases for abydos.phonetic.Phonem """ pa = Phonem() def test_phonem(self): """Test abydos.phonetic.Phonem.""" self.assertEqual(self.pa.encode(''), '') # http://phonetik.phil-fak.uni-koeln.de/fileadmin/home/ritters/Allgemeine_Dateien/Martin_Wilz.pdf self.assertEqual(self.pa.encode('müller'), 'MYLR') self.assertEqual(self.pa.encode('schmidt'), 'CMYD') self.assertEqual(self.pa.encode('schneider'), 'CNAYDR') self.assertEqual(self.pa.encode('fischer'), 'VYCR') self.assertEqual(self.pa.encode('weber'), 'VBR') self.assertEqual(self.pa.encode('meyer'), 'MAYR') self.assertEqual(self.pa.encode('wagner'), 'VACNR') self.assertEqual(self.pa.encode('schulz'), 'CULC') self.assertEqual(self.pa.encode('becker'), 'BCR') self.assertEqual(self.pa.encode('hoffmann'), 'OVMAN') self.assertEqual(self.pa.encode('schäfer'), 'CVR') # http://cpansearch.perl.org/src/MAROS/Text-Phonetic-2.05/t/008_phonem.t self.assertEqual(self.pa.encode('mair'), 'MAYR') self.assertEqual(self.pa.encode('bäker'), 'BCR') self.assertEqual(self.pa.encode('schaeffer'), 'CVR') self.assertEqual(self.pa.encode('computer'), 'COMBUDR') self.assertEqual(self.pa.encode('pfeifer'), 'VAYVR') self.assertEqual(self.pa.encode('pfeiffer'), 'VAYVR') # Test wrapper self.assertEqual(phonem('müller'), 'MYLR')
'koelner_phonetik_alpha': Koelner().encode_alpha, 'lein': LEIN().encode, 'lein_nopad_ml8': LEIN(max_length=8, zero_pad=False).encode, 'metasoundex': MetaSoundex().encode, 'metasoundex_es': MetaSoundex(lang='es').encode, 'metaphone': Metaphone().encode, 'mra': MRA().encode, 'norphone': Norphone().encode, 'nrl': NRL().encode, 'nysiis': NYSIIS().encode, 'nysiis_modified': NYSIIS(modified=True).encode, 'nysiis_ml_inf': NYSIIS(max_length=-1).encode, 'onca': ONCA().encode, 'onca_nopad_ml8': ONCA(max_length=8, zero_pad=False).encode, 'parmar_kumbharana': ParmarKumbharana().encode, 'phonem': Phonem().encode, 'phonet_1': Phonet().encode, 'phonet_2': Phonet(mode=2).encode, 'phonet_1_none': Phonet(lang='none').encode, 'phonet_2_none': Phonet(mode=2, lang='none').encode, 'phonetic_spanish': PhoneticSpanish().encode, 'phonetic_spanish_ml4': PhoneticSpanish(max_length=4).encode, 'phonex': Phonex().encode, 'phonex_0pad_ml6': Phonex(max_length=6, zero_pad=True).encode, 'phonic': PHONIC().encode, 'phonic_0pad_ml6': PHONIC(max_length=6, zero_pad=True).encode, 'phonic_ext': PHONIC(extended=True).encode, 'phonix': Phonix().encode, 'phonix_0pad_ml6': Phonix(max_length=6, zero_pad=True).encode, 'pshp_soundex_first': PSHPSoundexFirst().encode, 'pshp_soundex_first_german': PSHPSoundexFirst(german=True).encode,
'nrl': NRL().encode, 'nysiis': NYSIIS().encode, 'nysiis_modified': NYSIIS(modified=True).encode, 'nysiis_ml_inf': NYSIIS(max_length=-1).encode, 'onca': ONCA().encode, 'onca_nopad_ml8': ONCA(max_length=8, zero_pad=False).encode, 'parmar_kumbharana': ParmarKumbharana().encode, 'phonem': Phonem().encode, 'phonet_1': Phonet().encode, 'phonet_2': Phonet(mode=2).encode, 'phonet_1_none': Phonet(lang='none').encode, 'phonet_2_none': Phonet(mode=2, lang='none').encode, 'phonetic_spanish': PhoneticSpanish().encode, 'phonetic_spanish_ml4': PhoneticSpanish(max_length=4).encode, 'phonex': Phonex().encode, 'phonex_0pad_ml6':
eudex = Eudex() fonem = FONEM() fuzzy_soundex = FuzzySoundex() haase = Haase() henry_early = HenryEarly() koelner = Koelner() lein = Lein() metaphone = Metaphone() metasoundex = MetaSoundex() mra = MRA() norphone = Norphone() nrl = NRL() nysiis = NYSIIS() onca = ONCA() parmar_kumbharana = ParmarKumbharana() phonem = Phonem() phonet = Phonet() phonetic_spanish = PhoneticSpanish() phonex = Phonex() phonix = Phonix() pshp_soundex_first = PSHPSoundexFirst() pshp_soundex_last = PSHPSoundexLast() refined_soundex = RefinedSoundex() reth_schek = RethSchek() roger_root = RogerRoot() russell = RussellIndex() sfinxbis = SfinxBis() sound_d = SoundD() soundex = Soundex() soundex_br = SoundexBR() spanish_metaphone = SpanishMetaphone()