|
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._clef_german_plus. |
|
20
|
|
|
|
|
21
|
|
|
CLEF German plus 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 ._stemmer import _Stemmer |
|
36
|
|
|
|
|
37
|
1 |
|
__all__ = ['CLEFGermanPlus', 'clef_german_plus'] |
|
38
|
|
|
|
|
39
|
|
|
|
|
40
|
1 |
|
class CLEFGermanPlus(_Stemmer): |
|
|
|
|
|
|
41
|
|
|
"""CLEF German stemmer plus. |
|
42
|
|
|
|
|
43
|
|
|
The CLEF German stemmer plus is defined at :cite:`Savoy:2005`. |
|
44
|
|
|
""" |
|
45
|
|
|
|
|
46
|
1 |
|
_st_ending = {'b', 'd', 'f', 'g', 'h', 'k', 'l', 'm', 'n', 't'} |
|
47
|
|
|
|
|
48
|
1 |
|
_accents = dict( |
|
49
|
|
|
zip((ord(_) for _ in 'äàáâöòóôïìíîüùúû'), 'aaaaooooiiiiuuuu') |
|
|
|
|
|
|
50
|
|
|
) |
|
51
|
|
|
|
|
52
|
1 |
|
def stem(self, word): |
|
|
|
|
|
|
53
|
|
|
"""Return 'CLEF German stemmer plus' stem. |
|
54
|
|
|
|
|
55
|
|
|
Parameters |
|
56
|
|
|
---------- |
|
57
|
|
|
word : str |
|
58
|
|
|
The word to stem |
|
59
|
|
|
|
|
60
|
|
|
Returns |
|
61
|
|
|
------- |
|
62
|
|
|
str |
|
63
|
|
|
Word stem |
|
64
|
|
|
|
|
65
|
|
|
Examples |
|
66
|
|
|
-------- |
|
67
|
|
|
>>> stmr = CLEFGermanPlus() |
|
68
|
|
|
>>> clef_german_plus('lesen') |
|
69
|
|
|
'les' |
|
70
|
|
|
>>> clef_german_plus('graues') |
|
71
|
|
|
'grau' |
|
72
|
|
|
>>> clef_german_plus('buchstabieren') |
|
73
|
|
|
'buchstabi' |
|
74
|
|
|
|
|
75
|
|
|
""" |
|
76
|
|
|
# lowercase, normalize, and compose |
|
77
|
1 |
|
word = normalize('NFC', text_type(word.lower())) |
|
78
|
|
|
|
|
79
|
|
|
# remove umlauts |
|
80
|
1 |
|
word = word.translate(self._accents) |
|
81
|
|
|
|
|
82
|
|
|
# Step 1 |
|
83
|
1 |
|
wlen = len(word) - 1 |
|
84
|
1 |
|
if wlen > 4 and word[-3:] == 'ern': |
|
85
|
1 |
|
word = word[:-3] |
|
86
|
1 |
|
elif wlen > 3 and word[-2:] in {'em', 'en', 'er', 'es'}: |
|
87
|
1 |
|
word = word[:-2] |
|
88
|
1 |
|
elif wlen > 2 and ( |
|
89
|
|
|
word[-1] == 'e' |
|
|
|
|
|
|
90
|
|
|
or (word[-1] == 's' and word[-2] in self._st_ending) |
|
|
|
|
|
|
91
|
|
|
): |
|
92
|
1 |
|
word = word[:-1] |
|
93
|
|
|
|
|
94
|
|
|
# Step 2 |
|
95
|
1 |
|
wlen = len(word) - 1 |
|
96
|
1 |
|
if wlen > 4 and word[-3:] == 'est': |
|
97
|
1 |
|
word = word[:-3] |
|
98
|
1 |
|
elif wlen > 3 and ( |
|
99
|
|
|
word[-2:] in {'er', 'en'} |
|
|
|
|
|
|
100
|
|
|
or (word[-2:] == 'st' and word[-3] in self._st_ending) |
|
|
|
|
|
|
101
|
|
|
): |
|
102
|
1 |
|
word = word[:-2] |
|
103
|
|
|
|
|
104
|
1 |
|
return word |
|
105
|
|
|
|
|
106
|
|
|
|
|
107
|
1 |
|
def clef_german_plus(word): |
|
108
|
|
|
"""Return 'CLEF German stemmer plus' stem. |
|
109
|
|
|
|
|
110
|
|
|
This is a wrapper for :py:meth:`CLEFGermanPlus.stem`. |
|
111
|
|
|
|
|
112
|
|
|
Parameters |
|
113
|
|
|
---------- |
|
114
|
|
|
word : str |
|
115
|
|
|
The word to stem |
|
116
|
|
|
|
|
117
|
|
|
Returns |
|
118
|
|
|
------- |
|
119
|
|
|
str |
|
120
|
|
|
Word stem |
|
121
|
|
|
|
|
122
|
|
|
Examples |
|
123
|
|
|
-------- |
|
124
|
|
|
>>> stmr = CLEFGermanPlus() |
|
125
|
|
|
>>> clef_german_plus('lesen') |
|
126
|
|
|
'les' |
|
127
|
|
|
>>> clef_german_plus('graues') |
|
128
|
|
|
'grau' |
|
129
|
|
|
>>> clef_german_plus('buchstabieren') |
|
130
|
|
|
'buchstabi' |
|
131
|
|
|
|
|
132
|
|
|
""" |
|
133
|
1 |
|
return CLEFGermanPlus().stem(word) |
|
134
|
|
|
|
|
135
|
|
|
|
|
136
|
|
|
if __name__ == '__main__': |
|
137
|
|
|
import doctest |
|
138
|
|
|
|
|
139
|
|
|
doctest.testmod() |
|
140
|
|
|
|
chrislit /
abydos
Loading history...