|
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_stemmer. |
|
20
|
|
|
|
|
21
|
|
|
This module contains unit tests for abydos.stemmer |
|
22
|
|
|
""" |
|
23
|
|
|
|
|
24
|
|
|
from __future__ import unicode_literals |
|
25
|
|
|
|
|
26
|
|
|
import unittest |
|
27
|
|
|
|
|
28
|
|
|
from abydos.stemmer.s_stemmer import s_stemmer |
|
29
|
|
|
|
|
30
|
|
|
|
|
31
|
|
|
class SStemmerTestCases(unittest.TestCase): |
|
32
|
|
|
"""Test S-stemmer functions. |
|
33
|
|
|
|
|
34
|
|
|
abydos.stemmer.s_stemmer |
|
35
|
|
|
""" |
|
36
|
|
|
|
|
37
|
|
|
def test_s_stemmer(self): |
|
38
|
|
|
"""Test abydos.stemmer.s_stemmer.""" |
|
39
|
|
|
# Base case |
|
40
|
|
|
self.assertEqual(s_stemmer(''), '') |
|
41
|
|
|
|
|
42
|
|
|
# Tests from Harman paper |
|
43
|
|
|
self.assertEqual(s_stemmer('panels'), 'panel') |
|
44
|
|
|
self.assertEqual(s_stemmer('subjected'), 'subjected') |
|
45
|
|
|
self.assertEqual(s_stemmer('aerodynamics'), 'aerodynamic') |
|
46
|
|
|
self.assertEqual(s_stemmer('heating'), 'heating') |
|
47
|
|
|
|
|
48
|
|
|
# Additional tests to complete coverage |
|
49
|
|
|
self.assertEqual(s_stemmer('dairies'), 'dairy') |
|
50
|
|
|
self.assertEqual(s_stemmer('census'), 'census') |
|
51
|
|
|
self.assertEqual(s_stemmer('boss'), 'boss') |
|
52
|
|
|
self.assertEqual(s_stemmer('bosses'), 'bosse') |
|
53
|
|
|
self.assertEqual(s_stemmer('raises'), 'raise') |
|
54
|
|
|
self.assertEqual(s_stemmer('fees'), 'fee') |
|
55
|
|
|
self.assertEqual(s_stemmer('attourneies'), 'attourneie') |
|
56
|
|
|
self.assertEqual(s_stemmer('portemonnaies'), 'portemonnaie') |
|
57
|
|
|
self.assertEqual(s_stemmer('foes'), 'foe') |
|
58
|
|
|
self.assertEqual(s_stemmer('sundaes'), 'sundae') |
|
59
|
|
|
|
|
60
|
|
|
|
|
61
|
|
|
if __name__ == '__main__': |
|
62
|
|
|
unittest.main() |
|
63
|
|
|
|