|
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
|
1 |
|
"""abydos.stemmer._snowball_norwegian. |
|
20
|
|
|
|
|
21
|
|
|
Snowball Norwegian stemmer |
|
22
|
|
|
""" |
|
23
|
|
|
|
|
24
|
1 |
|
from __future__ import ( |
|
25
|
|
|
absolute_import, |
|
26
|
|
|
division, |
|
27
|
|
|
print_function, |
|
28
|
|
|
unicode_literals, |
|
29
|
|
|
) |
|
30
|
|
|
|
|
31
|
1 |
|
from unicodedata import normalize |
|
32
|
|
|
|
|
33
|
1 |
|
from six import text_type |
|
34
|
|
|
|
|
35
|
1 |
|
from ._snowball import _Snowball |
|
36
|
|
|
|
|
37
|
1 |
|
__all__ = ['SnowballNorwegian', 'sb_norwegian'] |
|
38
|
|
|
|
|
39
|
|
|
|
|
40
|
1 |
|
class SnowballNorwegian(_Snowball): |
|
|
|
|
|
|
41
|
|
|
"""Snowball Norwegian stemmer. |
|
42
|
|
|
|
|
43
|
|
|
The Snowball Norwegian stemmer is defined at: |
|
44
|
|
|
http://snowball.tartarus.org/algorithms/norwegian/stemmer.html |
|
45
|
|
|
""" |
|
46
|
|
|
|
|
47
|
1 |
|
_vowels = {'a', 'e', 'i', 'o', 'u', 'y', 'å', 'æ', 'ø'} |
|
48
|
1 |
|
_s_endings = { |
|
49
|
|
|
'b', |
|
50
|
|
|
'c', |
|
51
|
|
|
'd', |
|
52
|
|
|
'f', |
|
53
|
|
|
'g', |
|
54
|
|
|
'h', |
|
55
|
|
|
'j', |
|
56
|
|
|
'l', |
|
57
|
|
|
'm', |
|
58
|
|
|
'n', |
|
59
|
|
|
'o', |
|
60
|
|
|
'p', |
|
61
|
|
|
'r', |
|
62
|
|
|
't', |
|
63
|
|
|
'v', |
|
64
|
|
|
'y', |
|
65
|
|
|
'z', |
|
66
|
|
|
} |
|
67
|
|
|
|
|
68
|
1 |
|
def stem(self, word): |
|
|
|
|
|
|
69
|
|
|
"""Return Snowball Norwegian stem. |
|
70
|
|
|
|
|
71
|
|
|
Args: |
|
72
|
|
|
word (str): The word to stem |
|
73
|
|
|
|
|
74
|
|
|
Returns: |
|
75
|
|
|
str: Word stem |
|
76
|
|
|
|
|
77
|
|
|
Examples: |
|
78
|
|
|
>>> stmr = SnowballNorwegian() |
|
79
|
|
|
>>> stmr.stem('lese') |
|
80
|
|
|
'les' |
|
81
|
|
|
>>> stmr.stem('suspensjon') |
|
82
|
|
|
'suspensjon' |
|
83
|
|
|
>>> stmr.stem('sikkerhet') |
|
84
|
|
|
'sikker' |
|
85
|
|
|
|
|
86
|
|
|
""" |
|
87
|
|
|
# lowercase, normalize, and compose |
|
88
|
1 |
|
word = normalize('NFC', text_type(word.lower())) |
|
89
|
|
|
|
|
90
|
1 |
|
r1_start = min(max(3, self._sb_r1(word)), len(word)) |
|
91
|
|
|
|
|
92
|
|
|
# Step 1 |
|
93
|
1 |
|
_r1 = word[r1_start:] |
|
94
|
1 |
|
if _r1[-7:] == 'hetenes': |
|
95
|
1 |
|
word = word[:-7] |
|
96
|
1 |
|
elif _r1[-6:] in {'hetene', 'hetens'}: |
|
97
|
1 |
|
word = word[:-6] |
|
98
|
1 |
|
elif _r1[-5:] in {'heten', 'heter', 'endes'}: |
|
99
|
1 |
|
word = word[:-5] |
|
100
|
1 |
|
elif _r1[-4:] in {'ande', 'ende', 'edes', 'enes', 'erte'}: |
|
101
|
1 |
|
if word[-4:] == 'erte': |
|
102
|
1 |
|
word = word[:-2] |
|
103
|
|
|
else: |
|
104
|
1 |
|
word = word[:-4] |
|
105
|
1 |
|
elif _r1[-3:] in { |
|
106
|
|
|
'ede', |
|
|
|
|
|
|
107
|
|
|
'ane', |
|
|
|
|
|
|
108
|
|
|
'ene', |
|
|
|
|
|
|
109
|
|
|
'ens', |
|
|
|
|
|
|
110
|
|
|
'ers', |
|
|
|
|
|
|
111
|
|
|
'ets', |
|
|
|
|
|
|
112
|
|
|
'het', |
|
|
|
|
|
|
113
|
|
|
'ast', |
|
|
|
|
|
|
114
|
|
|
'ert', |
|
|
|
|
|
|
115
|
|
|
}: |
|
116
|
1 |
|
if word[-3:] == 'ert': |
|
117
|
1 |
|
word = word[:-1] |
|
118
|
|
|
else: |
|
119
|
1 |
|
word = word[:-3] |
|
120
|
1 |
|
elif _r1[-2:] in {'en', 'ar', 'er', 'as', 'es', 'et'}: |
|
121
|
1 |
|
word = word[:-2] |
|
122
|
1 |
|
elif _r1[-1:] in {'a', 'e'}: |
|
123
|
1 |
|
word = word[:-1] |
|
124
|
1 |
|
elif _r1[-1:] == 's': |
|
125
|
1 |
|
if (len(word) > 1 and word[-2] in self._s_endings) or ( |
|
126
|
|
|
len(word) > 2 |
|
|
|
|
|
|
127
|
|
|
and word[-2] == 'k' |
|
|
|
|
|
|
128
|
|
|
and word[-3] not in self._vowels |
|
|
|
|
|
|
129
|
|
|
): |
|
130
|
1 |
|
word = word[:-1] |
|
131
|
|
|
|
|
132
|
|
|
# Step 2 |
|
133
|
1 |
|
if word[r1_start:][-2:] in {'dt', 'vt'}: |
|
134
|
1 |
|
word = word[:-1] |
|
135
|
|
|
|
|
136
|
|
|
# Step 3 |
|
137
|
1 |
|
_r1 = word[r1_start:] |
|
138
|
1 |
|
if _r1[-7:] == 'hetslov': |
|
139
|
1 |
|
word = word[:-7] |
|
140
|
1 |
|
elif _r1[-4:] in {'eleg', 'elig', 'elov', 'slov'}: |
|
141
|
1 |
|
word = word[:-4] |
|
142
|
1 |
|
elif _r1[-3:] in {'leg', 'eig', 'lig', 'els', 'lov'}: |
|
143
|
1 |
|
word = word[:-3] |
|
144
|
1 |
|
elif _r1[-2:] == 'ig': |
|
145
|
1 |
|
word = word[:-2] |
|
146
|
|
|
|
|
147
|
1 |
|
return word |
|
148
|
|
|
|
|
149
|
|
|
|
|
150
|
1 |
|
def sb_norwegian(word): |
|
151
|
|
|
"""Return Snowball Norwegian stem. |
|
152
|
|
|
|
|
153
|
|
|
This is a wrapper for :py:meth:`SnowballNorwegian.stem`. |
|
154
|
|
|
|
|
155
|
|
|
Args: |
|
156
|
|
|
word (str): The word to stem |
|
157
|
|
|
|
|
158
|
|
|
Returns: |
|
159
|
|
|
str: Word stem |
|
160
|
|
|
|
|
161
|
|
|
Examples: |
|
162
|
|
|
>>> sb_norwegian('lese') |
|
163
|
|
|
'les' |
|
164
|
|
|
>>> sb_norwegian('suspensjon') |
|
165
|
|
|
'suspensjon' |
|
166
|
|
|
>>> sb_norwegian('sikkerhet') |
|
167
|
|
|
'sikker' |
|
168
|
|
|
|
|
169
|
|
|
""" |
|
170
|
1 |
|
return SnowballNorwegian().stem(word) |
|
171
|
|
|
|
|
172
|
|
|
|
|
173
|
|
|
if __name__ == '__main__': |
|
174
|
|
|
import doctest |
|
175
|
|
|
|
|
176
|
|
|
doctest.testmod() |
|
177
|
|
|
|
chrislit /
abydos
Loading history...