|
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. |
|
20
|
|
|
|
|
21
|
|
|
Snowball Stemmer base class |
|
22
|
|
|
""" |
|
23
|
|
|
|
|
24
|
1 |
|
from __future__ import ( |
|
25
|
|
|
absolute_import, |
|
26
|
|
|
division, |
|
27
|
|
|
print_function, |
|
28
|
|
|
unicode_literals, |
|
29
|
|
|
) |
|
30
|
|
|
|
|
31
|
1 |
|
from six.moves import range |
|
32
|
|
|
|
|
33
|
1 |
|
from ._stemmer import _Stemmer |
|
34
|
|
|
|
|
35
|
|
|
|
|
36
|
1 |
|
class _Snowball(_Stemmer): |
|
|
|
|
|
|
37
|
|
|
"""Snowball stemmer base class.""" |
|
38
|
|
|
|
|
39
|
1 |
|
_vowels = set('aeiouy') |
|
40
|
1 |
|
_codanonvowels = set('\'bcdfghjklmnpqrstvz') |
|
41
|
|
|
|
|
42
|
1 |
|
def _sb_r1(self, term, r1_prefixes=None): |
|
43
|
|
|
"""Return the R1 region, as defined in the Porter2 specification. |
|
44
|
|
|
|
|
45
|
|
|
Args: |
|
46
|
|
|
term (str): The term to examine |
|
47
|
|
|
r1_prefixes (set): Prefixes to consider |
|
48
|
|
|
|
|
49
|
|
|
Returns: |
|
50
|
|
|
int: Length of the R1 region |
|
51
|
|
|
|
|
52
|
|
|
""" |
|
53
|
1 |
|
vowel_found = False |
|
54
|
1 |
|
if hasattr(r1_prefixes, '__iter__'): |
|
55
|
1 |
|
for prefix in r1_prefixes: |
|
56
|
1 |
|
if term[: len(prefix)] == prefix: |
|
57
|
1 |
|
return len(prefix) |
|
58
|
|
|
|
|
59
|
1 |
|
for i in range(len(term)): |
|
|
|
|
|
|
60
|
1 |
|
if not vowel_found and term[i] in self._vowels: |
|
61
|
1 |
|
vowel_found = True |
|
62
|
1 |
|
elif vowel_found and term[i] not in self._vowels: |
|
63
|
1 |
|
return i + 1 |
|
64
|
1 |
|
return len(term) |
|
65
|
|
|
|
|
66
|
1 |
|
def _sb_r2(self, term, r1_prefixes=None): |
|
67
|
|
|
"""Return the R2 region, as defined in the Porter2 specification. |
|
68
|
|
|
|
|
69
|
|
|
Args: |
|
70
|
|
|
term (str): The term to examine |
|
71
|
|
|
r1_prefixes (set): Prefixes to consider |
|
72
|
|
|
|
|
73
|
|
|
Returns: |
|
74
|
|
|
int: Length of the R1 region |
|
75
|
|
|
|
|
76
|
|
|
""" |
|
77
|
1 |
|
r1_start = self._sb_r1(term, r1_prefixes) |
|
78
|
1 |
|
return r1_start + self._sb_r1(term[r1_start:]) |
|
79
|
|
|
|
|
80
|
1 |
|
def _sb_ends_in_short_syllable(self, term): |
|
81
|
|
|
"""Return True iff term ends in a short syllable. |
|
82
|
|
|
|
|
83
|
|
|
(...according to the Porter2 specification.) |
|
84
|
|
|
|
|
85
|
|
|
NB: This is akin to the CVC test from the Porter stemmer. The |
|
86
|
|
|
description is unfortunately poor/ambiguous. |
|
87
|
|
|
|
|
88
|
|
|
Args: |
|
89
|
|
|
term (str): The term to examine |
|
90
|
|
|
|
|
91
|
|
|
Returns: |
|
92
|
|
|
bool: True iff term ends in a short syllable |
|
93
|
|
|
|
|
94
|
|
|
""" |
|
95
|
1 |
|
if not term: |
|
96
|
1 |
|
return False |
|
97
|
1 |
|
if len(term) == 2: |
|
98
|
1 |
|
if term[-2] in self._vowels and term[-1] not in self._vowels: |
|
99
|
1 |
|
return True |
|
100
|
1 |
|
elif len(term) >= 3: |
|
101
|
1 |
|
if ( |
|
102
|
|
|
term[-3] not in self._vowels |
|
|
|
|
|
|
103
|
|
|
and term[-2] in self._vowels |
|
|
|
|
|
|
104
|
|
|
and term[-1] in self._codanonvowels |
|
|
|
|
|
|
105
|
|
|
): |
|
106
|
1 |
|
return True |
|
107
|
1 |
|
return False |
|
108
|
|
|
|
|
109
|
1 |
|
def _sb_short_word(self, term, r1_prefixes=None): |
|
110
|
|
|
"""Return True iff term is a short word. |
|
111
|
|
|
|
|
112
|
|
|
(...according to the Porter2 specification.) |
|
113
|
|
|
|
|
114
|
|
|
Args: |
|
115
|
|
|
term (str): The term to examine |
|
116
|
|
|
r1_prefixes (set): Prefixes to consider |
|
117
|
|
|
|
|
118
|
|
|
Returns: |
|
119
|
|
|
bool: True iff term is a short word |
|
120
|
|
|
|
|
121
|
|
|
""" |
|
122
|
1 |
|
if self._sb_r1(term, r1_prefixes) == len( |
|
123
|
|
|
term |
|
|
|
|
|
|
124
|
|
|
) and self._sb_ends_in_short_syllable(term): |
|
125
|
1 |
|
return True |
|
126
|
1 |
|
return False |
|
127
|
|
|
|
|
128
|
1 |
|
def _sb_has_vowel(self, term): |
|
129
|
|
|
"""Return Porter helper function _sb_has_vowel value. |
|
130
|
|
|
|
|
131
|
|
|
Args: |
|
132
|
|
|
term (str): The term to examine |
|
133
|
|
|
|
|
134
|
|
|
Returns: |
|
135
|
|
|
bool: True iff a vowel exists in the term (as defined in the Porter |
|
136
|
|
|
stemmer definition) |
|
137
|
|
|
|
|
138
|
|
|
""" |
|
139
|
1 |
|
for letter in term: |
|
140
|
1 |
|
if letter in self._vowels: |
|
141
|
1 |
|
return True |
|
142
|
1 |
|
return False |
|
143
|
|
|
|
|
144
|
|
|
|
|
145
|
|
|
if __name__ == '__main__': |
|
146
|
|
|
import doctest |
|
147
|
|
|
|
|
148
|
|
|
doctest.testmod() |
|
149
|
|
|
|
chrislit /
abydos
Loading history...