class MetaSoundexTestCases(unittest.TestCase):
"""Test MetaSoundex functions.
test cases for abydos.phonetic.MetaSoundex
"""
pa = MetaSoundex()
def test_metasoundex(self):
"""Test abydos.phonetic.MetaSoundex."""
# Base cases
self.assertEqual(self.pa.encode(''), '0000')
self.assertEqual(self.pa.encode('', lang='en'), '0000')
self.assertEqual(self.pa.encode('', lang='es'), '')
# Top 10 Anglo surnames in US
self.assertEqual(self.pa.encode('Smith', lang='en'), '4500')
self.assertEqual(self.pa.encode('Johnson', lang='en'), '1525')
self.assertEqual(self.pa.encode('Williams', lang='en'), '7452')
self.assertEqual(self.pa.encode('Brown', lang='en'), '7650')
self.assertEqual(self.pa.encode('Jones', lang='en'), '1520')
self.assertEqual(self.pa.encode('Miller', lang='en'), '6460')
self.assertEqual(self.pa.encode('Davis', lang='en'), '3120')
self.assertEqual(self.pa.encode('Wilson', lang='en'), '7425')
self.assertEqual(self.pa.encode('Anderson', lang='en'), '0536')
self.assertEqual(self.pa.encode('Thomas', lang='en'), '6200')
self.assertEqual(self.pa.encode('Smith', lang='es'), '4632')
self.assertEqual(self.pa.encode('Johnson', lang='es'), '82646')
self.assertEqual(self.pa.encode('Williams', lang='es'), '564')
self.assertEqual(self.pa.encode('Brown', lang='es'), '196')
self.assertEqual(self.pa.encode('Jones', lang='es'), '864')
self.assertEqual(self.pa.encode('Miller', lang='es'), '659')
self.assertEqual(self.pa.encode('Davis', lang='es'), '314')
self.assertEqual(self.pa.encode('Wilson', lang='es'), '546')
self.assertEqual(self.pa.encode('Anderson', lang='es'), '63946')
self.assertEqual(self.pa.encode('Thomas', lang='es'), '364')
# Top 10 Mexican surnames
self.assertEqual(self.pa.encode('Hernández', lang='en'), '5653')
self.assertEqual(self.pa.encode('García', lang='en'), '5620')
self.assertEqual(self.pa.encode('Lòpez', lang='en'), '8120')
self.assertEqual(self.pa.encode('Martìnez', lang='en'), '6635')
self.assertEqual(self.pa.encode('Rodrìguez', lang='en'), '9362')
self.assertEqual(self.pa.encode('González', lang='en'), '5524')
self.assertEqual(self.pa.encode('Pérez', lang='en'), '7620')
self.assertEqual(self.pa.encode('Sánchez', lang='en'), '4520')
self.assertEqual(self.pa.encode('Gómez', lang='en'), '5520')
self.assertEqual(self.pa.encode('Flores', lang='en'), '7462')
self.assertEqual(self.pa.encode('Hernández', lang='es'), '96634')
self.assertEqual(self.pa.encode('García', lang='es'), '894')
self.assertEqual(self.pa.encode('Lòpez', lang='es'), '504')
self.assertEqual(self.pa.encode('Martìnez', lang='es'), '69364')
self.assertEqual(self.pa.encode('Rodrìguez', lang='es'), '93984')
self.assertEqual(self.pa.encode('González', lang='es'), '86454')
self.assertEqual(self.pa.encode('Pérez', lang='es'), '094')
self.assertEqual(self.pa.encode('Sánchez', lang='es'), '4644')
self.assertEqual(self.pa.encode('Gómez', lang='es'), '864')
self.assertEqual(self.pa.encode('Flores', lang='es'), '2594')
# Test wrapper
self.assertEqual(metasoundex('Smith', lang='en'), '4500')
self.assertEqual(metasoundex('Hernández', lang='es'), '96634')
HenryEarly().encode,
'henry_early_ml8':
HenryEarly(max_length=8).encode,
'koelner_phonetik':
koelner.encode,
'koelner_phonetik_num_to_alpha': (
lambda _: koelner._to_alpha(koelner.encode(_)) # noqa: SF01
),
'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':
'dolby_ml4': Dolby(max_length=4).encode, 'dolby_vowels': Dolby(keep_vowels=True).encode, 'double_metaphone': DoubleMetaphone().encode, 'eudex': Eudex().encode, 'fonem': FONEM().encode, 'fuzzy_soundex': FuzzySoundex().encode, 'fuzzy_soundex_0pad_ml8': FuzzySoundex(max_length=8, zero_pad=True).encode, 'haase_phonetik': Haase().encode, 'haase_phonetik_primary': Haase(primary_only=True).encode, 'henry_early': HenryEarly().encode, 'henry_early_ml8': HenryEarly(max_length=8).encode, 'koelner_phonetik': Koelner().encode, '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,
alpha_sis = AlphaSIS() bm = BeiderMorse() caverphone = Caverphone() davidson = Davidson() dm = DaitchMokotoff() dolby = Dolby() double_metaphone = DoubleMetaphone() 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()