|
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_qgram. |
|
20
|
|
|
|
|
21
|
|
|
This module contains unit tests for abydos.qgram |
|
22
|
|
|
""" |
|
23
|
|
|
|
|
24
|
|
|
from __future__ import unicode_literals |
|
25
|
|
|
|
|
26
|
|
|
import unittest |
|
27
|
|
|
|
|
28
|
|
|
from abydos.qgram import QGrams |
|
29
|
|
|
|
|
30
|
|
|
|
|
31
|
|
|
class QgramTestCases(unittest.TestCase): |
|
32
|
|
|
"""Test abydos.qgram.""" |
|
33
|
|
|
|
|
34
|
|
|
def test_qgrams(self): |
|
35
|
|
|
"""Test abydos.qgram.QGrams.""" |
|
36
|
|
|
self.assertEqual(sorted(QGrams('').elements()), []) |
|
37
|
|
|
self.assertEqual(sorted(QGrams('a', 2).elements()), []) |
|
38
|
|
|
self.assertEqual(sorted(QGrams('NELSON', 0).elements()), []) |
|
39
|
|
|
self.assertEqual(sorted(QGrams('NELSON', -1).elements()), []) |
|
40
|
|
|
|
|
41
|
|
|
self.assertEqual(sorted(QGrams('NELSON', 3).elements()), |
|
42
|
|
|
sorted(['$$N', '$NE', 'NEL', 'ELS', 'LSO', 'SON', |
|
43
|
|
|
'ON#', 'N##'])) |
|
44
|
|
|
self.assertEqual(sorted(QGrams('NELSON', 7).elements()), sorted([])) |
|
45
|
|
|
|
|
46
|
|
|
# http://www.sound-ex.com/alternative_qgram.htm |
|
47
|
|
|
self.assertEqual(sorted(QGrams('NELSON').elements()), |
|
48
|
|
|
sorted(['$N', 'NE', 'EL', 'LS', 'SO', 'ON', 'N#'])) |
|
49
|
|
|
self.assertEqual(sorted(QGrams('NEILSEN').elements()), |
|
50
|
|
|
sorted(['$N', 'NE', 'EI', 'IL', 'LS', 'SE', 'EN', |
|
51
|
|
|
'N#'])) |
|
52
|
|
|
self.assertEqual(sorted(QGrams('NELSON', start_stop='').elements()), |
|
53
|
|
|
sorted(['NE', 'EL', 'LS', 'SO', 'ON'])) |
|
54
|
|
|
self.assertEqual(sorted(QGrams('NEILSEN', start_stop='').elements()), |
|
55
|
|
|
sorted(['NE', 'EI', 'IL', 'LS', 'SE', 'EN'])) |
|
56
|
|
|
|
|
57
|
|
|
# qval=(1,2) |
|
58
|
|
|
self.assertEqual(sorted(QGrams('NELSON', qval=(1, 2)).elements()), |
|
59
|
|
|
sorted(['$N', 'E', 'EL', 'L', 'LS', 'N', 'N', 'N#', |
|
60
|
|
|
'NE', 'O', 'ON', 'S', 'SO'])) |
|
61
|
|
|
self.assertEqual(sorted(QGrams('NELSON', qval=(2, 1)).elements()), |
|
62
|
|
|
sorted(['$N', 'E', 'EL', 'L', 'LS', 'N', 'N', 'N#', |
|
63
|
|
|
'NE', 'O', 'ON', 'S', 'SO'])) |
|
64
|
|
|
self.assertEqual(sorted(QGrams('NELSON', qval=range(3)).elements()), |
|
65
|
|
|
sorted(['$N', 'E', 'EL', 'L', 'LS', 'N', 'N', 'N#', |
|
66
|
|
|
'NE', 'O', 'ON', 'S', 'SO'])) |
|
67
|
|
|
self.assertEqual(QGrams('NELSON', qval=(1,2)).count(), 13) |
|
68
|
|
|
|
|
69
|
|
|
# skip=(1,2) |
|
70
|
|
|
self.assertEqual(sorted(QGrams('NELSON', skip=(2,1,0)).elements()), |
|
71
|
|
|
sorted(['$E', '$L', '$N', 'EL', 'EO', 'ES', 'LN', |
|
72
|
|
|
'LO', 'LS', 'N', 'N', 'N#', 'NE', 'NL', 'NS', |
|
73
|
|
|
'O', 'O#', 'ON', 'S#', 'SN', 'SO'])) |
|
74
|
|
|
self.assertEqual(sorted(QGrams('NELSON', skip=(2,1,0)).elements()), |
|
75
|
|
|
sorted(['$E', '$L', '$N', 'EL', 'EO', 'ES', 'LN', |
|
76
|
|
|
'LO', 'LS', 'N', 'N', 'N#', 'NE', 'NL', 'NS', |
|
77
|
|
|
'O', 'O#', 'ON', 'S#', 'SN', 'SO'])) |
|
78
|
|
|
self.assertEqual(sorted(QGrams('NELSON', skip=range(3)).elements()), |
|
79
|
|
|
sorted(['$E', '$L', '$N', 'EL', 'EO', 'ES', 'LN', |
|
80
|
|
|
'LO', 'LS', 'N', 'N', 'N#', 'NE', 'NL', 'NS', |
|
81
|
|
|
'O', 'O#', 'ON', 'S#', 'SN', 'SO'])) |
|
82
|
|
|
self.assertEqual(QGrams('NELSON', skip=(0, 1, 2)).count(), 21) |
|
83
|
|
|
|
|
84
|
|
|
def test_qgram_intersections(self): |
|
85
|
|
|
"""Test abydos.qgram.QGrams intersections.""" |
|
86
|
|
|
self.assertEqual(sorted(QGrams('NELSON') & QGrams('')), []) |
|
87
|
|
|
self.assertEqual(sorted(QGrams('') & QGrams('NEILSEN')), []) |
|
88
|
|
|
self.assertEqual(sorted(QGrams('NELSON') & QGrams('NEILSEN')), |
|
89
|
|
|
sorted(['$N', 'NE', 'LS', 'N#'])) |
|
90
|
|
|
self.assertEqual(sorted(QGrams('NELSON') & QGrams('NOSLEN')), |
|
91
|
|
|
sorted(['$N', 'N#'])) |
|
92
|
|
|
self.assertEqual(sorted(QGrams('NAIL') & QGrams('LIAN')), []) |
|
93
|
|
|
|
|
94
|
|
|
self.assertEqual(sorted(QGrams('NELSON', start_stop='') & |
|
95
|
|
|
QGrams('NEILSEN', start_stop='')), |
|
96
|
|
|
sorted(['NE', 'LS'])) |
|
97
|
|
|
self.assertEqual(sorted(QGrams('NELSON', start_stop='') & |
|
98
|
|
|
QGrams('NOSLEN', start_stop='')), []) |
|
99
|
|
|
self.assertEqual(sorted(QGrams('NAIL', start_stop='') & |
|
100
|
|
|
QGrams('LIAN', start_stop='')), []) |
|
101
|
|
|
|
|
102
|
|
|
def test_qgram_counts(self): |
|
103
|
|
|
"""Test abydos.qgram.QGrams counts.""" |
|
104
|
|
|
self.assertEqual(QGrams('').count(), 0) |
|
105
|
|
|
self.assertEqual(len(QGrams('').ordered_list), 0) |
|
106
|
|
|
|
|
107
|
|
|
self.assertEqual(QGrams('NEILSEN').count(), 8) |
|
108
|
|
|
self.assertEqual(QGrams('NELSON').count(), 7) |
|
109
|
|
|
self.assertEqual(QGrams('NEILSEN', start_stop='').count(), 6) |
|
110
|
|
|
self.assertEqual(QGrams('NELSON', start_stop='').count(), 5) |
|
111
|
|
|
|
|
112
|
|
|
self.assertEqual(len(QGrams('NEILSEN').ordered_list), 8) |
|
113
|
|
|
self.assertEqual(len(QGrams('NELSON').ordered_list), 7) |
|
114
|
|
|
self.assertEqual(len(QGrams('NEILSEN', start_stop='').ordered_list), 6) |
|
115
|
|
|
self.assertEqual(len(QGrams('NELSON', start_stop='').ordered_list), 5) |
|
116
|
|
|
|
|
117
|
|
|
|
|
118
|
|
|
if __name__ == '__main__': |
|
119
|
|
|
unittest.main() |
|
120
|
|
|
|
chrislit /
abydos
