|
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_fingerprint. |
|
20
|
|
|
|
|
21
|
|
|
This module contains unit tests for abydos.fingerprint |
|
22
|
|
|
""" |
|
23
|
|
|
|
|
24
|
|
|
from __future__ import unicode_literals |
|
25
|
|
|
|
|
26
|
|
|
import unittest |
|
27
|
|
|
|
|
28
|
|
|
import abydos.phonetic as phonetic |
|
29
|
|
|
from abydos.fingerprint import str_fingerprint, omission_key, \ |
|
30
|
|
|
phonetic_fingerprint, qgram_fingerprint, skeleton_key |
|
31
|
|
|
|
|
32
|
|
|
from six.moves import range |
|
33
|
|
|
|
|
34
|
|
|
|
|
35
|
|
|
NIALL = ('Niall', 'Neal', 'Neil', 'Njall', 'Njáll', 'Nigel', 'Neel', 'Nele', |
|
36
|
|
|
'Nigelli', 'Nel', 'Kneale', 'Uí Néill', 'O\'Neill', 'MacNeil', |
|
37
|
|
|
'MacNele', 'Niall Noígíallach') |
|
38
|
|
|
|
|
39
|
|
|
|
|
40
|
|
|
class FingerprintTestCases(unittest.TestCase): |
|
41
|
|
|
"""Test fingerprint functions. |
|
42
|
|
|
|
|
43
|
|
|
abydos.clustering.str_fingerprint, abydos.clustering.qgram_fingerprint, & |
|
44
|
|
|
abydos.clustering.phonetic_fingerprint |
|
45
|
|
|
""" |
|
46
|
|
|
|
|
47
|
|
|
_testset = ('À noite, vovô Kowalsky vê o ímã cair no pé do pingüim \ |
|
48
|
|
|
queixoso e vovó põe açúcar no chá de tâmaras do jabuti feliz.', ) |
|
49
|
|
|
_anssetw = ('a acucar cair cha de do e feliz ima jabuti kowalsky no noite \ |
|
50
|
|
|
o pe pinguim poe queixoso tamaras ve vovo', ) |
|
51
|
|
|
_anssetq2 = ('abacadaialamanarasbucachcudedoeaedeieleoetevfeguhaifiminirit\ |
|
52
|
|
|
ixizjakokylilsmamqngnoocoeoiojokoposovowpepipoqurarnsdsksotatetiucueuiutvevowa\ |
|
53
|
|
|
xoyv', ) |
|
54
|
|
|
_anssetq1 = ('abcdefghijklmnopqrstuvwxyz', ) |
|
55
|
|
|
|
|
56
|
|
|
def test_str_fingerprint(self): |
|
57
|
|
|
"""Test abydos.clustering.str_fingerprint.""" |
|
58
|
|
|
self.assertEqual(str_fingerprint(''), '') |
|
59
|
|
|
for i in range(len(self._testset)): |
|
60
|
|
|
self.assertEqual(str_fingerprint(self._testset[i]), |
|
61
|
|
|
self._anssetw[i]) |
|
62
|
|
|
|
|
63
|
|
|
def test_qgram_fingerprint(self): |
|
64
|
|
|
"""Test abydos.clustering.qgram_fingerprint.""" |
|
65
|
|
|
self.assertEqual(qgram_fingerprint(''), '') |
|
66
|
|
|
for i in range(len(self._testset)): |
|
67
|
|
|
self.assertEqual(qgram_fingerprint(self._testset[i], 1), |
|
68
|
|
|
self._anssetq1[i]) |
|
69
|
|
|
self.assertEqual(qgram_fingerprint(self._testset[i], 2), |
|
70
|
|
|
self._anssetq2[i]) |
|
71
|
|
|
self.assertEqual(qgram_fingerprint(self._testset[i]), |
|
72
|
|
|
self._anssetq2[i]) |
|
73
|
|
|
|
|
74
|
|
|
qgram_fp_niall = ('aliallni', 'aleane', 'eiilne', 'aljallnj', |
|
75
|
|
|
'aljallnj', 'elgeigni', 'eeelne', 'ellene', |
|
76
|
|
|
'elgeiglillni', 'elne', 'aleaknlene', 'eiilinllneui', |
|
77
|
|
|
'eiilllneon', 'accneiilmane', 'accnellemane', |
|
78
|
|
|
'acalchgiiaiglalllnninooi') |
|
79
|
|
|
for i in range(len(NIALL)): |
|
80
|
|
|
self.assertEqual(qgram_fingerprint(NIALL[i]), qgram_fp_niall[i]) |
|
81
|
|
|
|
|
82
|
|
|
def test_phonetic_fingerprint(self): |
|
83
|
|
|
"""Test abydos.clustering.phonetic_fingerprint.""" |
|
84
|
|
|
self.assertEqual(phonetic_fingerprint(''), '') |
|
85
|
|
|
|
|
86
|
|
|
self.assertEqual(phonetic_fingerprint(' '.join(NIALL)), |
|
87
|
|
|
'a anl mknl njl nklk nl') |
|
88
|
|
|
self.assertEqual(phonetic_fingerprint(' '.join(NIALL), |
|
89
|
|
|
phonetic.phonet), |
|
90
|
|
|
'knile makneil maknele neil nel nele nial nigeli ' + |
|
91
|
|
|
'nigl nil noigialach oneil ui') |
|
92
|
|
|
self.assertEqual(phonetic_fingerprint(' '.join(NIALL), |
|
93
|
|
|
phonetic.soundex), |
|
94
|
|
|
'k540 m254 n240 n242 n400 o540 u000') |
|
95
|
|
|
|
|
96
|
|
|
|
|
97
|
|
|
class SPEEDCOPTestCases(unittest.TestCase): |
|
98
|
|
|
"""Test SPEEDCOP functions. |
|
99
|
|
|
|
|
100
|
|
|
abydos.clustering.skeleton_key & abydos.clustering.omission_key |
|
101
|
|
|
""" |
|
102
|
|
|
|
|
103
|
|
|
def test_skeleton_key(self): |
|
104
|
|
|
"""Test abydos.clustering.skeleton_key.""" |
|
105
|
|
|
self.assertEqual(skeleton_key(''), '') |
|
106
|
|
|
|
|
107
|
|
|
# http://dl.acm.org/citation.cfm?id=358048 |
|
108
|
|
|
self.assertEqual(skeleton_key('chemogenic'), 'CHMGNEOI') |
|
109
|
|
|
self.assertEqual(skeleton_key('chemomagnetic'), 'CHMGNTEOAI') |
|
110
|
|
|
self.assertEqual(skeleton_key('chemcal'), 'CHMLEA') |
|
111
|
|
|
self.assertEqual(skeleton_key('chemcial'), 'CHMLEIA') |
|
112
|
|
|
self.assertEqual(skeleton_key('chemical'), 'CHMLEIA') |
|
113
|
|
|
self.assertEqual(skeleton_key('chemicial'), 'CHMLEIA') |
|
114
|
|
|
self.assertEqual(skeleton_key('chimical'), 'CHMLIA') |
|
115
|
|
|
self.assertEqual(skeleton_key('chemiluminescence'), 'CHMLNSEIU') |
|
116
|
|
|
self.assertEqual(skeleton_key('chemiluminescent'), 'CHMLNSTEIU') |
|
117
|
|
|
self.assertEqual(skeleton_key('chemicals'), 'CHMLSEIA') |
|
118
|
|
|
self.assertEqual(skeleton_key('chemically'), 'CHMLYEIA') |
|
119
|
|
|
|
|
120
|
|
|
def test_omission_key(self): |
|
121
|
|
|
"""Test abydos.clustering.omission_key.""" |
|
122
|
|
|
self.assertEqual(omission_key(''), '') |
|
123
|
|
|
|
|
124
|
|
|
# http://dl.acm.org/citation.cfm?id=358048 |
|
125
|
|
|
self.assertEqual(omission_key('microelectronics'), 'MCLNTSRIOE') |
|
126
|
|
|
self.assertEqual(omission_key('circumstantial'), 'MCLNTSRIUA') |
|
127
|
|
|
self.assertEqual(omission_key('luminescent'), 'MCLNTSUIE') |
|
128
|
|
|
self.assertEqual(omission_key('multinucleate'), 'MCLNTUIEA') |
|
129
|
|
|
self.assertEqual(omission_key('multinucleon'), 'MCLNTUIEO') |
|
130
|
|
|
self.assertEqual(omission_key('cumulene'), 'MCLNUE') |
|
131
|
|
|
self.assertEqual(omission_key('luminance'), 'MCLNUIAE') |
|
132
|
|
|
self.assertEqual(omission_key('coelomic'), 'MCLOEI') |
|
133
|
|
|
self.assertEqual(omission_key('molecule'), 'MCLOEU') |
|
134
|
|
|
self.assertEqual(omission_key('cameral'), 'MCLRAE') |
|
135
|
|
|
self.assertEqual(omission_key('caramel'), 'MCLRAE') |
|
136
|
|
|
self.assertEqual(omission_key('maceral'), 'MCLRAE') |
|
137
|
|
|
self.assertEqual(omission_key('lacrimal'), 'MCLRAI') |
|
138
|
|
|
|
|
139
|
|
|
|
|
140
|
|
|
if __name__ == '__main__': |
|
141
|
|
|
unittest.main() |
|
142
|
|
|
|
chrislit /
abydos
