|
1
|
|
|
# -*- coding: utf-8 -*- |
|
2
|
|
|
|
|
3
|
|
|
# Copyright 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_distance.sift4. |
|
20
|
|
|
|
|
21
|
|
|
This module contains unit tests for abydos.distance.sift4 |
|
22
|
|
|
""" |
|
23
|
|
|
|
|
24
|
|
|
from __future__ import division, unicode_literals |
|
25
|
|
|
|
|
26
|
|
|
import unittest |
|
27
|
|
|
|
|
28
|
|
|
from abydos.distance.sift4 import dist_sift4, sift4_common, sift4_simplest, \ |
|
29
|
|
|
sim_sift4 |
|
30
|
|
|
|
|
31
|
|
|
|
|
32
|
|
|
class Sift4TestCases(unittest.TestCase): |
|
33
|
|
|
"""Test Sift4 functions. |
|
34
|
|
|
|
|
35
|
|
|
abydos.distance.sift4_simplest, sift4_common, sim_sift4, & sim_sift4 |
|
36
|
|
|
""" |
|
37
|
|
|
|
|
38
|
|
|
def test_sift4_simplest(self): |
|
39
|
|
|
"""Test abydos.distance.sift4_simplest.""" |
|
40
|
|
|
# tests copied from Lukas Benedix's post at |
|
41
|
|
|
# https://siderite.blogspot.com/2014/11/super-fast-and-accurate-string-distance.html |
|
42
|
|
|
self.assertEqual(sift4_simplest('', ''), 0) |
|
43
|
|
|
self.assertEqual(sift4_simplest('a', ''), 1) |
|
44
|
|
|
self.assertEqual(sift4_simplest('', 'a'), 1) |
|
45
|
|
|
self.assertEqual(sift4_simplest('abc', ''), 3) |
|
46
|
|
|
self.assertEqual(sift4_simplest('', 'abc'), 3) |
|
47
|
|
|
|
|
48
|
|
|
self.assertEqual(sift4_simplest('a', 'a'), 0) |
|
49
|
|
|
self.assertEqual(sift4_simplest('abc', 'abc'), 0) |
|
50
|
|
|
|
|
51
|
|
|
self.assertEqual(sift4_simplest('a', 'ab'), 1) |
|
52
|
|
|
self.assertEqual(sift4_simplest('ac', 'abc'), 1) |
|
53
|
|
|
self.assertEqual(sift4_simplest('abcdefg', 'xabxcdxxefxgx'), 10) |
|
54
|
|
|
|
|
55
|
|
|
self.assertEqual(sift4_simplest('ab', 'b'), 1) |
|
56
|
|
|
self.assertEqual(sift4_simplest('ab', 'a'), 1) |
|
57
|
|
|
self.assertEqual(sift4_simplest('abc', 'ac'), 1) |
|
58
|
|
|
self.assertEqual(sift4_simplest('xabxcdxxefxgx', 'abcdefg'), 10) |
|
59
|
|
|
|
|
60
|
|
|
self.assertEqual(sift4_simplest('a', 'b'), 1) |
|
61
|
|
|
self.assertEqual(sift4_simplest('ab', 'ac'), 1) |
|
62
|
|
|
self.assertEqual(sift4_simplest('ac', 'bc'), 1) |
|
63
|
|
|
self.assertEqual(sift4_simplest('abc', 'axc'), 1) |
|
64
|
|
|
self.assertEqual(sift4_simplest('xabxcdxxefxgx', '1ab2cd34ef5g6'), 6) |
|
65
|
|
|
|
|
66
|
|
|
self.assertEqual(sift4_simplest('example', 'samples'), 2) |
|
67
|
|
|
self.assertEqual(sift4_simplest('sturgeon', 'urgently'), 4) |
|
68
|
|
|
self.assertEqual(sift4_simplest('levenshtein', 'frankenstein'), 10) |
|
69
|
|
|
self.assertEqual(sift4_simplest('distance', 'difference'), 7) |
|
70
|
|
|
|
|
71
|
|
|
# Tests copied from |
|
72
|
|
|
# https://github.com/tdebatty/java-string-similarity/blob/master/src/test/java/info/debatty/java/stringsimilarity/experimental/Sift4Test.java |
|
73
|
|
|
self.assertEqual(sift4_simplest('This is the first string', |
|
74
|
|
|
'And this is another string', 5), 13) |
|
75
|
|
|
self.assertEqual(sift4_simplest('Lorem ipsum dolor sit amet, ' + |
|
76
|
|
|
'consectetur adipiscing elit.', |
|
77
|
|
|
'Amet Lorm ispum dolor sit amet, ' + |
|
78
|
|
|
'consetetur adixxxpiscing elit.', |
|
79
|
|
|
10), 20) |
|
80
|
|
|
|
|
81
|
|
|
def test_sift4_common(self): |
|
82
|
|
|
"""Test abydos.distance.sift4_common.""" |
|
83
|
|
|
# tests copied from Lukas Benedix's post at |
|
84
|
|
|
# https://siderite.blogspot.com/2014/11/super-fast-and-accurate-string-distance.html |
|
85
|
|
|
self.assertEqual(sift4_common('', ''), 0) |
|
86
|
|
|
self.assertEqual(sift4_common('a', ''), 1) |
|
87
|
|
|
self.assertEqual(sift4_common('', 'a'), 1) |
|
88
|
|
|
self.assertEqual(sift4_common('abc', ''), 3) |
|
89
|
|
|
self.assertEqual(sift4_common('', 'abc'), 3) |
|
90
|
|
|
|
|
91
|
|
|
self.assertEqual(sift4_common('a', 'a'), 0) |
|
92
|
|
|
self.assertEqual(sift4_common('abc', 'abc'), 0) |
|
93
|
|
|
|
|
94
|
|
|
self.assertEqual(sift4_common('a', 'ab'), 1) |
|
95
|
|
|
self.assertEqual(sift4_common('ac', 'abc'), 1) |
|
96
|
|
|
self.assertEqual(sift4_common('abcdefg', 'xabxcdxxefxgx'), 7) |
|
97
|
|
|
|
|
98
|
|
|
self.assertEqual(sift4_common('ab', 'b'), 1) |
|
99
|
|
|
self.assertEqual(sift4_common('ab', 'a'), 1) |
|
100
|
|
|
self.assertEqual(sift4_common('abc', 'ac'), 1) |
|
101
|
|
|
self.assertEqual(sift4_common('xabxcdxxefxgx', 'abcdefg'), 7) |
|
102
|
|
|
|
|
103
|
|
|
self.assertEqual(sift4_common('a', 'b'), 1) |
|
104
|
|
|
self.assertEqual(sift4_common('ab', 'ac'), 1) |
|
105
|
|
|
self.assertEqual(sift4_common('ac', 'bc'), 1) |
|
106
|
|
|
self.assertEqual(sift4_common('abc', 'axc'), 1) |
|
107
|
|
|
self.assertEqual(sift4_common('xabxcdxxefxgx', '1ab2cd34ef5g6'), 6) |
|
108
|
|
|
|
|
109
|
|
|
self.assertEqual(sift4_common('example', 'samples'), 2) |
|
110
|
|
|
self.assertEqual(sift4_common('sturgeon', 'urgently'), 3) |
|
111
|
|
|
self.assertEqual(sift4_common('levenshtein', 'frankenstein'), 6) |
|
112
|
|
|
self.assertEqual(sift4_common('distance', 'difference'), 5) |
|
113
|
|
|
|
|
114
|
|
|
# Tests copied from |
|
115
|
|
|
# https://github.com/tdebatty/java-string-similarity/blob/master/src/test/java/info/debatty/java/stringsimilarity/experimental/Sift4Test.java |
|
116
|
|
|
self.assertEqual(sift4_common('This is the first string', |
|
117
|
|
|
'And this is another string', 5), 11) |
|
118
|
|
|
self.assertEqual(sift4_common('Lorem ipsum dolor sit amet, ' + |
|
119
|
|
|
'consectetur adipiscing elit.', |
|
120
|
|
|
'Amet Lorm ispum dolor sit amet, ' + |
|
121
|
|
|
'consetetur adixxxpiscing elit.', |
|
122
|
|
|
10), 12) |
|
123
|
|
|
|
|
124
|
|
|
# cases with max_distance |
|
125
|
|
|
self.assertEqual(sift4_common('example', 'samples', 5, 5), 5) |
|
126
|
|
|
self.assertEqual(sift4_common('sturgeon', 'urgently', 5, 5), 5) |
|
127
|
|
|
self.assertEqual(sift4_common('levenshtein', 'frankenstein', 5, 5), 5) |
|
128
|
|
|
self.assertEqual(sift4_common('distance', 'difference', 5, 5), 5) |
|
129
|
|
|
|
|
130
|
|
|
def test_dist_sift4(self): |
|
131
|
|
|
"""Test abydos.distance.dist_sift4.""" |
|
132
|
|
|
# tests copied from Lukas Benedix's post at |
|
133
|
|
|
# https://siderite.blogspot.com/2014/11/super-fast-and-accurate-string-distance.html |
|
134
|
|
|
self.assertEqual(dist_sift4('', ''), 0) |
|
135
|
|
|
self.assertEqual(dist_sift4('a', ''), 1) |
|
136
|
|
|
self.assertEqual(dist_sift4('', 'a'), 1) |
|
137
|
|
|
self.assertEqual(dist_sift4('abc', ''), 1) |
|
138
|
|
|
self.assertEqual(dist_sift4('', 'abc'), 1) |
|
139
|
|
|
|
|
140
|
|
|
self.assertEqual(dist_sift4('a', 'a'), 0) |
|
141
|
|
|
self.assertEqual(dist_sift4('abc', 'abc'), 0) |
|
142
|
|
|
|
|
143
|
|
|
self.assertEqual(dist_sift4('a', 'ab'), 0.5) |
|
144
|
|
|
self.assertEqual(dist_sift4('ac', 'abc'), 1/3) |
|
145
|
|
|
self.assertAlmostEqual(dist_sift4('abcdefg', 'xabxcdxxefxgx'), |
|
146
|
|
|
0.538461538) |
|
147
|
|
|
|
|
148
|
|
|
self.assertEqual(dist_sift4('ab', 'b'), 0.5) |
|
149
|
|
|
self.assertEqual(dist_sift4('ab', 'a'), 0.5) |
|
150
|
|
|
self.assertEqual(dist_sift4('abc', 'ac'), 1/3) |
|
151
|
|
|
self.assertAlmostEqual(dist_sift4('xabxcdxxefxgx', 'abcdefg'), |
|
152
|
|
|
0.538461538) |
|
153
|
|
|
|
|
154
|
|
|
self.assertEqual(dist_sift4('a', 'b'), 1) |
|
155
|
|
|
self.assertEqual(dist_sift4('ab', 'ac'), 0.5) |
|
156
|
|
|
self.assertEqual(dist_sift4('ac', 'bc'), 0.5) |
|
157
|
|
|
self.assertEqual(dist_sift4('abc', 'axc'), 1/3) |
|
158
|
|
|
self.assertAlmostEqual(dist_sift4('xabxcdxxefxgx', '1ab2cd34ef5g6'), |
|
159
|
|
|
0.461538461) |
|
160
|
|
|
|
|
161
|
|
|
self.assertAlmostEqual(dist_sift4('example', 'samples'), 0.285714285) |
|
162
|
|
|
self.assertAlmostEqual(dist_sift4('sturgeon', 'urgently'), 0.375) |
|
163
|
|
|
self.assertAlmostEqual(dist_sift4('levenshtein', 'frankenstein'), 0.5) |
|
164
|
|
|
self.assertAlmostEqual(dist_sift4('distance', 'difference'), 0.5) |
|
165
|
|
|
|
|
166
|
|
|
# Tests copied from |
|
167
|
|
|
# https://github.com/tdebatty/java-string-similarity/blob/master/src/test/java/info/debatty/java/stringsimilarity/experimental/Sift4Test.java |
|
168
|
|
|
self.assertAlmostEqual(dist_sift4('This is the first string', |
|
169
|
|
|
'And this is another string', |
|
170
|
|
|
5), 0.423076923) |
|
171
|
|
|
self.assertAlmostEqual(dist_sift4('Lorem ipsum dolor sit amet, ' + |
|
172
|
|
|
'consectetur adipiscing elit.', |
|
173
|
|
|
'Amet Lorm ispum dolor sit amet, ' + |
|
174
|
|
|
'consetetur adixxxpiscing elit.', |
|
175
|
|
|
10), 0.193548387) |
|
176
|
|
|
|
|
177
|
|
|
# cases with max_distance |
|
178
|
|
|
self.assertAlmostEqual(dist_sift4('example', 'samples', 5, 5), |
|
179
|
|
|
0.714285714) |
|
180
|
|
|
self.assertAlmostEqual(dist_sift4('sturgeon', 'urgently', 5, 5), 0.625) |
|
181
|
|
|
self.assertAlmostEqual(dist_sift4('levenshtein', 'frankenstein', 5, 5), |
|
182
|
|
|
0.416666666) |
|
183
|
|
|
self.assertAlmostEqual(dist_sift4('distance', 'difference', 5, 5), 0.5) |
|
184
|
|
|
|
|
185
|
|
|
def test_sim_sift4(self): |
|
186
|
|
|
"""Test abydos.distance.sim_sift4.""" |
|
187
|
|
|
# tests copied from Lukas Benedix's post at |
|
188
|
|
|
# https://siderite.blogspot.com/2014/11/super-fast-and-accurate-string-distance.html |
|
189
|
|
|
self.assertEqual(sim_sift4('', ''), 1) |
|
190
|
|
|
self.assertEqual(sim_sift4('a', ''), 0) |
|
191
|
|
|
self.assertEqual(sim_sift4('', 'a'), 0) |
|
192
|
|
|
self.assertEqual(sim_sift4('abc', ''), 0) |
|
193
|
|
|
self.assertEqual(sim_sift4('', 'abc'), 0) |
|
194
|
|
|
|
|
195
|
|
|
self.assertEqual(sim_sift4('a', 'a'), 1) |
|
196
|
|
|
self.assertEqual(sim_sift4('abc', 'abc'), 1) |
|
197
|
|
|
|
|
198
|
|
|
self.assertEqual(sim_sift4('a', 'ab'), 0.5) |
|
199
|
|
|
self.assertAlmostEqual(sim_sift4('ac', 'abc'), 2/3) |
|
200
|
|
|
self.assertAlmostEqual(sim_sift4('abcdefg', 'xabxcdxxefxgx'), |
|
201
|
|
|
0.461538461) |
|
202
|
|
|
|
|
203
|
|
|
self.assertEqual(sim_sift4('ab', 'b'), 0.5) |
|
204
|
|
|
self.assertEqual(sim_sift4('ab', 'a'), 0.5) |
|
205
|
|
|
self.assertAlmostEqual(sim_sift4('abc', 'ac'), 2/3) |
|
206
|
|
|
self.assertAlmostEqual(sim_sift4('xabxcdxxefxgx', 'abcdefg'), |
|
207
|
|
|
0.461538461) |
|
208
|
|
|
|
|
209
|
|
|
self.assertEqual(sim_sift4('a', 'b'), 0) |
|
210
|
|
|
self.assertEqual(sim_sift4('ab', 'ac'), 0.5) |
|
211
|
|
|
self.assertEqual(sim_sift4('ac', 'bc'), 0.5) |
|
212
|
|
|
self.assertAlmostEqual(sim_sift4('abc', 'axc'), 2/3) |
|
213
|
|
|
self.assertAlmostEqual(sim_sift4('xabxcdxxefxgx', '1ab2cd34ef5g6'), |
|
214
|
|
|
0.538461538) |
|
215
|
|
|
|
|
216
|
|
|
self.assertAlmostEqual(sim_sift4('example', 'samples'), 0.714285714) |
|
217
|
|
|
self.assertAlmostEqual(sim_sift4('sturgeon', 'urgently'), 0.625) |
|
218
|
|
|
self.assertAlmostEqual(sim_sift4('levenshtein', 'frankenstein'), 0.5) |
|
219
|
|
|
self.assertAlmostEqual(sim_sift4('distance', 'difference'), 0.5) |
|
220
|
|
|
|
|
221
|
|
|
# Tests copied from |
|
222
|
|
|
# https://github.com/tdebatty/java-string-similarity/blob/master/src/test/java/info/debatty/java/stringsimilarity/experimental/Sift4Test.java |
|
223
|
|
|
self.assertAlmostEqual(sim_sift4('This is the first string', |
|
224
|
|
|
'And this is another string', |
|
225
|
|
|
5), 0.576923077) |
|
226
|
|
|
self.assertAlmostEqual(sim_sift4('Lorem ipsum dolor sit amet, ' + |
|
227
|
|
|
'consectetur adipiscing elit.', |
|
228
|
|
|
'Amet Lorm ispum dolor sit amet, ' + |
|
229
|
|
|
'consetetur adixxxpiscing elit.', |
|
230
|
|
|
10), 0.806451613) |
|
231
|
|
|
|
|
232
|
|
|
# cases with max_distance |
|
233
|
|
|
self.assertAlmostEqual(sim_sift4('example', 'samples', 5, 5), |
|
234
|
|
|
0.285714286) |
|
235
|
|
|
self.assertAlmostEqual(sim_sift4('sturgeon', 'urgently', 5, 5), 0.375) |
|
236
|
|
|
self.assertAlmostEqual(sim_sift4('levenshtein', 'frankenstein', 5, 5), |
|
237
|
|
|
0.583333333) |
|
238
|
|
|
self.assertAlmostEqual(sim_sift4('distance', 'difference', 5, 5), 0.5) |
|
239
|
|
|
|
|
240
|
|
|
|
|
241
|
|
|
if __name__ == '__main__': |
|
242
|
|
|
unittest.main() |
|
243
|
|
|
|