def test_henry_early(self):
"""Test abydos.phonetic.HenryEarly."""
# Base case
self.assertEqual(self.pa.encode(''), '')
# Examples from Legare 1972 paper
self.assertEqual(self.pa.encode('Descarry'), 'DKR')
self.assertEqual(self.pa.encode('Descaries'), 'DKR')
self.assertEqual(self.pa.encode('Campo'), 'KP')
self.assertEqual(self.pa.encode('Campot'), 'KP')
self.assertEqual(self.pa.encode('Gausselin'), 'GSL')
self.assertEqual(self.pa.encode('Gosselin'), 'GSL')
self.assertEqual(self.pa.encode('Bergeron'), 'BRJ')
self.assertEqual(self.pa.encode('Bergereau'), 'BRJ')
self.assertEqual(self.pa.encode('Bosseron'), 'BSR')
self.assertEqual(self.pa.encode('Cicire'), 'SSR')
self.assertEqual(self.pa.encode('Lechevalier'), 'LCV')
self.assertEqual(self.pa.encode('Chevalier'), 'CVL')
self.assertEqual(self.pa.encode('Peloy'), 'PL')
self.assertEqual(self.pa.encode('Beloy'), 'BL')
self.assertEqual(self.pa.encode('Beret'), 'BR')
self.assertEqual(self.pa.encode('Benet'), 'BN')
self.assertEqual(self.pa.encode('Turcot'), 'TRK')
self.assertEqual(self.pa.encode('Turgot'), 'TRG')
self.assertEqual(self.pa.encode('Vigier'), 'VJ')
self.assertEqual(self.pa.encode('Vigiere'), 'VJR')
self.assertEqual(self.pa.encode('Dodin'), 'DD')
self.assertEqual(self.pa.encode('Dodelin'), 'DDL')
# Tests to complete coverage
self.assertEqual(self.pa.encode('Anil'), 'ANL')
self.assertEqual(self.pa.encode('Emmanuel'), 'AMN')
self.assertEqual(self.pa.encode('Ainu'), 'EN')
self.assertEqual(self.pa.encode('Oeuf'), 'OF')
self.assertEqual(self.pa.encode('Yves'), 'IV')
self.assertEqual(self.pa.encode('Yo'), 'I')
self.assertEqual(self.pa.encode('Umman'), 'EM')
self.assertEqual(self.pa.encode('Omman'), 'OM')
self.assertEqual(self.pa.encode('Zoe'), 'S')
self.assertEqual(self.pa.encode('Beauchamp'), 'BCP')
self.assertEqual(self.pa.encode('Chloe'), 'KL')
self.assertEqual(self.pa.encode('Gerard'), 'JRR')
self.assertEqual(self.pa.encode('Agnes'), 'ANN')
self.assertEqual(self.pa.encode('Pinot'), 'PN')
self.assertEqual(self.pa.encode('Philo'), 'FL')
self.assertEqual(self.pa.encode('Quisling'), 'GL')
self.assertEqual(self.pa.encode('Qualite'), 'KLT')
self.assertEqual(self.pa.encode('Sainte-Marie'), 'XMR')
self.assertEqual(self.pa.encode('Saint-Jean'), 'XJ')
self.assertEqual(self.pa.encode('Ste-Marie'), 'XMR')
self.assertEqual(self.pa.encode('St-Jean'), 'XJ')
self.assertEqual(self.pa.encode('Cloe'), 'KL')
self.assertEqual(self.pa.encode('Ahch-To'), 'AKT')
self.assertEqual(self.pa.encode('Zdavros'), 'SDV')
self.assertEqual(self.pa.encode('Sdavros'), 'DVR')
self.assertEqual(self.pa.encode('Coulomb'), 'KLB')
self.assertEqual(self.pa.encode('Calm'), 'K')
self.assertEqual(self.pa.encode('Omnia'), 'ON')
self.assertEqual(self.pa.encode('Ramps'), 'RPS')
self.assertEqual(self.pa.encode('Renault'), 'RN')
self.assertEqual(self.pa.encode('Czech'), 'CSK')
self.assertEqual(self.pa.encode('Imran'), 'ER')
self.assertEqual(
HenryEarly(max_length=-1).encode('Christopher'), 'KRXF')
'double_metaphone':
lambda _: ', '.join(double_metaphone.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':
lambda _: ', '.join(haase.encode(_)),
'haase_phonetik_primary':
lambda _: haase_primary.encode(_)[0],
'henry_early':
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,
'bmpm_sep_exact': BeiderMorse(name_mode='sep', match_mode='exact').encode, 'caverphone_1': Caverphone(version=1).encode, 'caverphone_2': Caverphone().encode, 'daitch_mokotoff_soundex': DaitchMokotoff().encode, 'davidson': Davidson().encode, 'dolby': Dolby().encode, '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,
) from . import EXTREME_TEST, _corpus_file, _fuzz, _random_char 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()