1
|
|
|
# -*- coding: utf-8 -*- |
2
|
|
|
|
3
|
|
|
# Copyright 2014-2018 by Christopher C. Little. |
4
|
|
|
# This file is part of Abydos. |
5
|
|
|
# |
6
|
|
|
# Abydos is free software: you can redistribute it and/or modify |
7
|
|
|
# it under the terms of the GNU General Public License as published by |
8
|
|
|
# the Free Software Foundation, either version 3 of the License, or |
9
|
|
|
# (at your option) any later version. |
10
|
|
|
# |
11
|
|
|
# Abydos is distributed in the hope that it will be useful, |
12
|
|
|
# but WITHOUT ANY WARRANTY; without even the implied warranty of |
13
|
|
|
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
14
|
|
|
# GNU General Public License for more details. |
15
|
|
|
# |
16
|
|
|
# You should have received a copy of the GNU General Public License |
17
|
|
|
# along with Abydos. If not, see <http://www.gnu.org/licenses/>. |
18
|
|
|
|
19
|
|
|
"""abydos.tests.test_phonetic_dm. |
20
|
|
|
|
21
|
|
|
This module contains unit tests for abydos.phonetic.dm |
22
|
|
|
""" |
23
|
|
|
|
24
|
|
|
from __future__ import unicode_literals |
25
|
|
|
|
26
|
|
|
import unittest |
27
|
|
|
|
28
|
|
|
from abydos.phonetic.dm import dm_soundex |
29
|
|
|
|
30
|
|
|
|
31
|
|
|
class DMSoundexTestCases(unittest.TestCase): |
32
|
|
|
"""Test Daitch-Mokotoff Soundex functions. |
33
|
|
|
|
34
|
|
|
test cases for abydos.phonetic.dm_soundex |
35
|
|
|
""" |
36
|
|
|
|
37
|
|
|
def test_dm_soundex(self): |
38
|
|
|
"""Test abydos.phonetic.dm_soundex (Daitch-Mokotoff Soundex).""" |
39
|
|
|
# D-M tests |
40
|
|
|
self.assertEqual(dm_soundex(''), {'000000'}) |
41
|
|
|
|
42
|
|
|
# http://www.avotaynu.com/soundex.htm |
43
|
|
|
self.assertEqual(dm_soundex('Augsburg'), {'054795'}) |
44
|
|
|
self.assertEqual(dm_soundex('Breuer'), {'791900'}) |
45
|
|
|
self.assertEqual(dm_soundex('Halberstadt'), {'587943', '587433'}) |
46
|
|
|
self.assertEqual(dm_soundex('Mannheim'), {'665600'}) |
47
|
|
|
self.assertEqual(dm_soundex('Chernowitz'), {'496740', '596740'}) |
48
|
|
|
self.assertEqual(dm_soundex('Cherkassy'), {'495400', '595400'}) |
49
|
|
|
self.assertEqual(dm_soundex('Kleinman'), {'586660'}) |
50
|
|
|
self.assertEqual(dm_soundex('Berlin'), {'798600'}) |
51
|
|
|
|
52
|
|
|
self.assertEqual(dm_soundex('Ceniow'), {'467000', '567000'}) |
53
|
|
|
self.assertEqual(dm_soundex('Tsenyuv'), {'467000'}) |
54
|
|
|
self.assertEqual(dm_soundex('Holubica'), {'587400', '587500'}) |
55
|
|
|
self.assertEqual(dm_soundex('Golubitsa'), {'587400'}) |
56
|
|
|
self.assertEqual(dm_soundex('Przemysl'), {'746480', '794648'}) |
57
|
|
|
self.assertEqual(dm_soundex('Pshemeshil'), {'746480'}) |
58
|
|
|
self.assertEqual(dm_soundex('Rosochowaciec'), |
59
|
|
|
{'944744', '945744', '944755', '944754', '944745', |
60
|
|
|
'945745', '945754', '945755'}) |
61
|
|
|
self.assertEqual(dm_soundex('Rosokhovatsets'), {'945744'}) |
62
|
|
|
|
63
|
|
|
# https://en.wikipedia.org/wiki/Daitch%E2%80%93Mokotoff_Soundex |
64
|
|
|
self.assertEqual(dm_soundex('Peters'), {'739400', '734000'}) |
65
|
|
|
self.assertEqual(dm_soundex('Peterson'), {'739460', '734600'}) |
66
|
|
|
self.assertEqual(dm_soundex('Moskowitz'), {'645740'}) |
67
|
|
|
self.assertEqual(dm_soundex('Moskovitz'), {'645740'}) |
68
|
|
|
self.assertEqual(dm_soundex('Auerbach'), {'097500', '097400'}) |
69
|
|
|
self.assertEqual(dm_soundex('Uhrbach'), {'097500', '097400'}) |
70
|
|
|
self.assertEqual(dm_soundex('Jackson'), |
71
|
|
|
{'154600', '454600', '145460', '445460'}) |
72
|
|
|
self.assertEqual(dm_soundex('Jackson-Jackson'), |
73
|
|
|
{'154654', '454654', '145465', '445465', |
74
|
|
|
'154645', '454645', '145464', '445464', |
75
|
|
|
'154644', '454644'}) |
76
|
|
|
|
77
|
|
|
# http://www.jewishgen.org/infofiles/soundex.html |
78
|
|
|
self.assertEqual(dm_soundex('OHRBACH'), {'097500', '097400'}) |
79
|
|
|
self.assertEqual(dm_soundex('LIPSHITZ'), {'874400'}) |
80
|
|
|
self.assertEqual(dm_soundex('LIPPSZYC'), {'874400', '874500'}) |
81
|
|
|
self.assertEqual(dm_soundex('LEWINSKY'), {'876450'}) |
82
|
|
|
self.assertEqual(dm_soundex('LEVINSKI'), {'876450'}) |
83
|
|
|
self.assertEqual(dm_soundex('SZLAMAWICZ'), {'486740'}) |
84
|
|
|
self.assertEqual(dm_soundex('SHLAMOVITZ'), {'486740'}) |
85
|
|
|
|
86
|
|
|
# http://community.actian.com/wiki/OME_soundex_dm() |
87
|
|
|
self.assertEqual(dm_soundex('Schwarzenegger'), |
88
|
|
|
{'479465', '474659'}) |
89
|
|
|
self.assertEqual(dm_soundex('Shwarzenegger'), |
90
|
|
|
{'479465', '474659'}) |
91
|
|
|
self.assertEqual(dm_soundex('Schwartsenegger'), {'479465'}) |
92
|
|
|
|
93
|
|
|
# max_length bounds tests |
94
|
|
|
self.assertEqual(dm_soundex('Niall', max_length=-1), {'68'+'0'*62}) |
95
|
|
|
self.assertEqual(dm_soundex('Niall', max_length=0), {'680000'}) |
96
|
|
|
|
97
|
|
|
# zero_pad tests |
98
|
|
|
self.assertEqual(dm_soundex('Niall', max_length=-1, zero_pad=False), |
99
|
|
|
{'68'}) |
100
|
|
|
self.assertEqual(dm_soundex('Niall', max_length=0, zero_pad=False), |
101
|
|
|
{'68'}) |
102
|
|
|
self.assertEqual(dm_soundex('Niall', max_length=0, zero_pad=True), |
103
|
|
|
{'680000'}) |
104
|
|
|
self.assertEqual(dm_soundex('', max_length=6, zero_pad=False), |
105
|
|
|
{'0'}) |
106
|
|
|
self.assertEqual(dm_soundex('', max_length=6, zero_pad=True), |
107
|
|
|
{'000000'}) |
108
|
|
|
|
109
|
|
|
|
110
|
|
|
if __name__ == '__main__': |
111
|
|
|
unittest.main() |
112
|
|
|
|