'bmpm_french': BeiderMorse(language_arg='french').encode, 'bmpm_gen_exact': BeiderMorse(match_mode='exact').encode, 'bmpm_ash_approx': BeiderMorse(name_mode='ash').encode, 'bmpm_ash_exact': BeiderMorse(name_mode='ash', match_mode='exact').encode, 'bmpm_sep_approx': BeiderMorse(name_mode='sep').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,
class FONEMTestCases(unittest.TestCase):
"""Test FONEM functions.
test cases for abydos.phonetic.FONEM
"""
pa = FONEM()
def test_fonem(self):
"""Test abydos.phonetic.FONEM."""
# Base cases
self.assertEqual(self.pa.encode(''), '')
# Test cases, mostly from the FONEM specification,
# but copied from Talisman:
# https://github.com/Yomguithereal/talisman/blob/master/test/phonetics/french/fonem.js
test_cases = (
('BEAULAC', 'BOLAK'),
('BAULAC', 'BOLAK'),
('IMBEAULT', 'INBO'),
('DUFAUT', 'DUFO'),
('THIBOUTOT', 'TIBOUTOT'),
('DEVAUX', 'DEVO'),
('RONDEAUX', 'RONDO'),
('BOURGAULX', 'BOURGO'),
('PINCHAUD', 'PINCHO'),
('PEDNAULD', 'PEDNO'),
('MAZENOD', 'MASENOD'),
('ARNOLD', 'ARNOL'),
('BERTOLD', 'BERTOL'),
('BELLAY', 'BELE'),
('SANDAY', 'SENDE'),
('GAY', 'GAI'),
('FAYARD', 'FAYAR'),
('LEMIEUX', 'LEMIEU'),
('LHEUREUX', 'LEUREU'),
('BELLEY', 'BELE'),
('WELLEY', 'WELE'),
('MEYER', 'MEYER'),
('BOILY', 'BOILI'),
('LOYSEAU', 'LOISO'),
('MAYRAND', 'MAIREN'),
('GUYON', 'GUYON'),
('FAILLARD', 'FAYAR'),
('FAIARD', 'FAYAR'),
('MEIER', 'MEYER'),
('MEILLER', 'MEYER'),
('GUILLON', 'GUYON'),
('LAVILLE', 'LAVILLE'),
('COUET', 'CWET'),
('EDOUARD', 'EDWAR'),
('GIROUARD', 'JIRWAR'),
('OZOUADE', 'OSWADE'), # differs from test set
('BOUILLE', 'BOUYE'),
('POUYEZ', 'POUYES'), # differs from test set
('LEMEE', 'LEME'),
('ABRAAM', 'ABRAM'),
('ARCHEMBAULT', 'ARCHENBO'),
('AMTHIME', 'ENTIME'),
('ROMPRE', 'RONPRE'),
('BOMSECOURS', 'BONSECOURS'),
('BOULANGER', 'BOULENJER'),
('TANCREDE', 'TENKREDE'),
('BLAIN', 'BLIN'),
('BLAINVILLE', 'BLINVILLE'),
('MAINARD', 'MAINAR'),
('RAIMOND', 'RAIMON'),
('BLACKBORN', 'BLAKBURN'),
('SEABOURNE', 'SEABURN'),
('IMBO', 'INBO'),
('RIMFRET', 'RINFRET'),
('LEFEBVRE', 'LEFEVRE'),
('MACE', 'MASSE'),
('MACON', 'MACON'),
('MARCELIN', 'MARSELIN'),
('MARCEAU', 'MARSO'),
('VINCELETTE', 'VINSELETE'),
('FORCADE', 'FORCADE'),
('CELINE', 'SELINE'),
('CERAPHIN', 'SERAFIN'),
('CAMILLE', 'KAMILLE'),
('CAYETTE', 'KAYETE'),
('CARINE', 'KARINE'),
('LUC', 'LUK'),
('LEBLANC', 'LEBLEN'),
('VICTOR', 'VIKTOR'),
('LACCOULINE', 'LAKOULINE'),
('MACCIMILIEN', 'MAXIMILIEN'),
('MAGELLA', 'MAJELA'),
('GINETTE', 'JINETE'),
('GANDET', 'GANDET'),
('GEORGES', 'JORJES'),
('GEOFFROID', 'JOFROID'),
('PAGEAU', 'PAJO'),
('GAGNION', 'GAGNON'),
('MIGNIER', 'MIGNER'),
('HALLEY', 'ALE'),
('GAUTHIER', 'GOTIER'),
('CHARTIER', 'CHARTIER'),
('JEANNE', 'JANE'),
('MACGREGOR', 'MACGREGOR'),
('MACKAY', 'MACKE'),
('MCNICOL', 'MACNICOL'),
('MCNEIL', 'MACNEIL'),
('PHANEUF', 'FANEUF'),
('PHILIPPE', 'FILIPE'),
('QUENNEVILLE', 'KENEVILLE'),
('LAROCQUE', 'LAROKE'),
('SCIPION', 'SIPION'),
('ASCELIN', 'ASSELIN'),
('VASCO', 'VASKO'),
('PASCALINE', 'PASKALINE'),
('ESHEMBACK', 'ECHENBAK'),
('ASHED', 'ACHED'),
('GRATIA', 'GRASSIA'),
('PATRITIA', 'PATRISSIA'),
('BERTIO', 'BERTIO'),
('MATIEU', 'MATIEU'),
('BERTIAUME', 'BERTIOME'),
('MUNROW', 'MUNRO'),
('BRANISLAW', 'BRANISLA'),
('LOWMEN', 'LOMEN'),
('ANDREW', 'ENDREW'),
('EXCEL', 'EXEL'),
('EXCERINE', 'EXERINE'),
('EXSILDA', 'EXILDA'),
('EXZELDA', 'EXELDA'),
('CAZEAU', 'KASO'),
('BRAZEAU', 'BRASO'),
('FITZPATRICK', 'FITSPATRIK'),
('SINGELAIS', 'ST-JELAIS'),
('CINQMARS', 'ST-MARS'),
('SAINT-AMAND', 'ST-AMEN'),
('SAINTECROIX', 'STE-KROIX'),
('ST-HILAIRE', 'ST-ILAIRE'),
('STE-CROIX', 'STE-KROIX'),
('LAVALLEE', 'LAVALE'),
('CORINNE', 'KORINE'),
('DUTILE', 'DUTILLE'),
)
for name, encoding in test_cases:
self.assertEqual(self.pa.encode(name), encoding)
# Test wrapper
self.assertEqual(fonem('MARCEAU'), 'MARSO')
'daitch_mokotoff_soundex': lambda _: ', '.join(sorted(daitch_mokotoff.encode(_))), 'davidson': Davidson().encode, 'dolby': Dolby().encode, 'dolby_ml4': Dolby(max_length=4).encode, 'dolby_vowels': Dolby(keep_vowels=True).encode, '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': (
SoundexBR,
SpanishMetaphone,
StatisticsCanada,
)
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()