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
|
1 |
|
"""abydos.stemmer._s_stemmer. |
20
|
|
|
|
21
|
|
|
S-stemmer. |
22
|
|
|
""" |
23
|
|
|
|
24
|
1 |
|
from __future__ import ( |
25
|
|
|
absolute_import, |
26
|
|
|
division, |
27
|
|
|
print_function, |
28
|
|
|
unicode_literals, |
29
|
|
|
) |
30
|
|
|
|
31
|
1 |
|
from ._stemmer import _Stemmer |
32
|
|
|
|
33
|
1 |
|
__all__ = ['SStemmer', 's_stemmer'] |
34
|
|
|
|
35
|
|
|
|
36
|
1 |
|
class SStemmer(_Stemmer): |
|
|
|
|
37
|
|
|
"""S-stemmer. |
38
|
|
|
|
39
|
|
|
The S stemmer is defined in :cite:`Harman:1991`. |
40
|
|
|
""" |
41
|
|
|
|
42
|
1 |
|
def stem(self, word): |
|
|
|
|
43
|
|
|
"""Return the S-stemmed form of a word. |
44
|
|
|
|
45
|
|
|
Parameters |
46
|
|
|
---------- |
47
|
|
|
word : str |
48
|
|
|
The word to stem |
49
|
|
|
|
50
|
|
|
Returns |
51
|
|
|
------- |
52
|
|
|
str |
53
|
|
|
Word stem |
54
|
|
|
|
55
|
|
|
Examples |
56
|
|
|
-------- |
57
|
|
|
>>> stmr = SStemmer() |
58
|
|
|
>>> stmr.stem('summaries') |
59
|
|
|
'summary' |
60
|
|
|
>>> stmr.stem('summary') |
61
|
|
|
'summary' |
62
|
|
|
>>> stmr.stem('towers') |
63
|
|
|
'tower' |
64
|
|
|
>>> stmr.stem('reading') |
65
|
|
|
'reading' |
66
|
|
|
>>> stmr.stem('census') |
67
|
|
|
'census' |
68
|
|
|
|
69
|
|
|
""" |
70
|
1 |
|
lowered = word.lower() |
71
|
1 |
|
if lowered[-3:] == 'ies' and lowered[-4:-3] not in {'e', 'a'}: |
72
|
1 |
|
return word[:-3] + ('Y' if word[-1:].isupper() else 'y') |
73
|
1 |
|
if lowered[-2:] == 'es' and lowered[-3:-2] not in {'a', 'e', 'o'}: |
74
|
1 |
|
return word[:-1] |
75
|
1 |
|
if lowered[-1:] == 's' and lowered[-2:-1] not in {'u', 's'}: |
76
|
1 |
|
return word[:-1] |
77
|
1 |
|
return word |
78
|
|
|
|
79
|
|
|
|
80
|
1 |
|
def s_stemmer(word): |
81
|
|
|
"""Return the S-stemmed form of a word. |
82
|
|
|
|
83
|
|
|
This is a wrapper for :py:meth:`SStemmer.stem`. |
84
|
|
|
|
85
|
|
|
Parameters |
86
|
|
|
---------- |
87
|
|
|
word : str |
88
|
|
|
The word to stem |
89
|
|
|
|
90
|
|
|
Returns |
91
|
|
|
------- |
92
|
|
|
str |
93
|
|
|
Word stem |
94
|
|
|
|
95
|
|
|
Examples |
96
|
|
|
-------- |
97
|
|
|
>>> s_stemmer('summaries') |
98
|
|
|
'summary' |
99
|
|
|
>>> s_stemmer('summary') |
100
|
|
|
'summary' |
101
|
|
|
>>> s_stemmer('towers') |
102
|
|
|
'tower' |
103
|
|
|
>>> s_stemmer('reading') |
104
|
|
|
'reading' |
105
|
|
|
>>> s_stemmer('census') |
106
|
|
|
'census' |
107
|
|
|
|
108
|
|
|
""" |
109
|
1 |
|
return SStemmer().stem(word) |
110
|
|
|
|
111
|
|
|
|
112
|
|
|
if __name__ == '__main__': |
113
|
|
|
import doctest |
114
|
|
|
|
115
|
|
|
doctest.testmod() |
116
|
|
|
|