def test_soundex_census(self):
"""Test abydos.phonetic.Soundex(Census variant method)."""
pa_census = Soundex(var='Census')
self.assertEqual(pa_census.encode('Vandeusen'), ('V532', 'D250'))
self.assertEqual(pa_census.encode('van Deusen'), ('V532', 'D250'))
self.assertEqual(pa_census.encode('McDonald'), 'M235')
self.assertEqual(pa_census.encode('la Cruz'), ('L262', 'C620'))
self.assertEqual(pa_census.encode('vanDamme'), ('V535', 'D500'))
def test_soundex_special(self):
"""Test abydos.phonetic.Soundex (special 1880-1910 variant method)."""
pa_special = Soundex(var='special')
self.assertEqual(pa_special.encode('Ashcroft'), 'A226')
self.assertEqual(pa_special.encode('Asicroft'), 'A226')
self.assertEqual(pa_special.encode('AsWcroft'), 'A226')
self.assertEqual(pa_special.encode('Rupert'), 'R163')
self.assertEqual(pa_special.encode('Rubin'), 'R150')
def test_soundex_census(self):
"""Test abydos.phonetic.Soundex(Census variant method)."""
pa_census = Soundex(var='Census')
self.assertEqual(pa_census.encode('Vandeusen'), ('V532', 'D250'))
self.assertEqual(pa_census.encode('van Deusen'), ('V532', 'D250'))
self.assertEqual(pa_census.encode('McDonald'), 'M235')
self.assertEqual(pa_census.encode('la Cruz'), ('L262', 'C620'))
self.assertEqual(pa_census.encode('vanDamme'), ('V535', 'D500'))
def test_soundex_special(self):
"""Test abydos.phonetic.Soundex (special 1880-1910 variant method)."""
pa_special = Soundex(var='special')
self.assertEqual(pa_special.encode('Ashcroft'), 'A226')
self.assertEqual(pa_special.encode('Asicroft'), 'A226')
self.assertEqual(pa_special.encode('AsWcroft'), 'A226')
self.assertEqual(pa_special.encode('Rupert'), 'R163')
self.assertEqual(pa_special.encode('Rubin'), 'R150')
def test_caversham(self):
"""Test using Caversham test set (SoundEx, Metaphone, & Caverphone)."""
soundex = Soundex()
metaphone = Metaphone()
with open(_corpus_file('variantNames.csv')) as cav_testset:
next(cav_testset)
for cav_line in cav_testset:
(
name1,
soundex1,
metaphone1,
caverphone1,
name2,
soundex2,
metaphone2,
caverphone2,
soundex_same,
metaphone_same,
caverphone_same,
) = cav_line.strip().split(',')
self.assertEqual(soundex.encode(name1), soundex1)
self.assertEqual(soundex.encode(name2), soundex2)
if soundex_same == '1':
self.assertEqual(
soundex.encode(name1), soundex.encode(name2)
)
else:
self.assertNotEqual(
soundex.encode(name1), soundex.encode(name2)
)
self.assertEqual(metaphone.encode(name1), metaphone1)
self.assertEqual(metaphone.encode(name2), metaphone2)
if metaphone_same == '1':
self.assertEqual(
metaphone.encode(name1), metaphone.encode(name2)
)
else:
self.assertNotEqual(
metaphone.encode(name1), metaphone.encode(name2)
)
self.assertEqual(self.pa.encode(name1), caverphone1)
self.assertEqual(self.pa.encode(name2), caverphone2)
if caverphone_same == '1':
self.assertEqual(
self.pa.encode(name1), self.pa.encode(name2)
)
else:
self.assertNotEqual(
self.pa.encode(name1), self.pa.encode(name2)
)
'sfinxbis_ml6': lambda _: ', '.join(sfinxbis_6.encode(_)), 'sound_d': SoundD().encode, 'sound_d_ml8': SoundD(max_length=8).encode, 'soundex': Soundex().encode, 'soundex_reverse': Soundex(reverse=True).encode, 'soundex_0pad_ml6': Soundex(zero_pad=True, max_length=6).encode, 'soundex_special': Soundex(var='special').encode, 'soundex_census': lambda _: ', '.join(soundex_census.encode(_)), 'soundex_br': SoundexBR().encode, 'spanish_metaphone': SpanishMetaphone().encode, 'spanish_metaphone_modified': SpanishMetaphone(modified=True).encode, 'spanish_metaphone_ml4': SpanishMetaphone(max_length=4).encode, 'spfc': lambda _: spfc.encode(_ + ' ' + _), 'statistics_canada': StatisticsCanada().encode, 'statistics_canada_ml8': StatisticsCanada(max_length=8).encode, 'waahlin':
spanish_metaphone = SpanishMetaphone()
spfc = SPFC()
statistics_canada = StatisticsCanada()
algorithms = {
'russell_index':
lambda _: str(russell.encode(_)),
'russell_index_num_to_alpha':
lambda _: russell._to_alpha( # noqa: SF01
russell.encode(_)),
'russell_index_alpha':
russell.encode_alpha,
'soundex':
soundex.encode,
'reverse_soundex':
lambda _: soundex.encode(_, reverse=True),
'soundex_0pad_ml6':
lambda _: soundex.encode(_, zero_pad=True, max_length=6),
'soundex_special':
lambda _: soundex.encode(_, var='special'),
'soundex_census':
lambda _: ', '.join(soundex.encode(_, var='Census')),
'refined_soundex':
refined_soundex.encode,
'refined_soundex_vowels':
lambda _: refined_soundex.encode(_, retain_vowels=True),
'refined_soundex_0pad_ml6':
lambda _: refined_soundex.encode(_, zero_pad=True, max_length=6),
'dm_soundex':
lambda _: ', '.join(sorted(dm.encode(_))),
'koelner_phonetik':