|
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._caumanns. |
|
20
|
|
|
|
|
21
|
|
|
Caumanns German 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
|
1 |
|
from six.moves import range |
|
35
|
|
|
|
|
36
|
1 |
|
from ._stemmer import _Stemmer |
|
37
|
|
|
|
|
38
|
1 |
|
__all__ = ['Caumanns', 'caumanns'] |
|
39
|
|
|
|
|
40
|
|
|
|
|
41
|
1 |
|
class Caumanns(_Stemmer): |
|
|
|
|
|
|
42
|
|
|
"""Caumanns stemmer. |
|
43
|
|
|
|
|
44
|
|
|
Jörg Caumanns' stemmer is described in his article in |
|
45
|
|
|
:cite:`Caumanns:1999`. |
|
46
|
|
|
|
|
47
|
|
|
This implementation is based on the GermanStemFilter described at |
|
48
|
|
|
:cite:`Lang:2013`. |
|
49
|
|
|
""" |
|
50
|
|
|
|
|
51
|
1 |
|
_umlauts = dict(zip((ord(_) for _ in 'äöü'), 'aou')) |
|
|
|
|
|
|
52
|
|
|
|
|
53
|
1 |
|
def stem(self, word): |
|
|
|
|
|
|
54
|
|
|
"""Return Caumanns German stem. |
|
55
|
|
|
|
|
56
|
|
|
Parameters |
|
57
|
|
|
---------- |
|
58
|
|
|
word : str |
|
59
|
|
|
The word to stem |
|
60
|
|
|
|
|
61
|
|
|
Returns |
|
62
|
|
|
------- |
|
63
|
|
|
str |
|
64
|
|
|
Word stem |
|
65
|
|
|
|
|
66
|
|
|
Examples |
|
67
|
|
|
-------- |
|
68
|
|
|
>>> stmr = Caumanns() |
|
69
|
|
|
>>> stmr.stem('lesen') |
|
70
|
|
|
'les' |
|
71
|
|
|
>>> stmr.stem('graues') |
|
72
|
|
|
'grau' |
|
73
|
|
|
>>> stmr.stem('buchstabieren') |
|
74
|
|
|
'buchstabier' |
|
75
|
|
|
|
|
76
|
|
|
""" |
|
77
|
1 |
|
if not word: |
|
78
|
1 |
|
return '' |
|
79
|
|
|
|
|
80
|
1 |
|
upper_initial = word[0].isupper() |
|
81
|
1 |
|
word = normalize('NFC', text_type(word.lower())) |
|
82
|
|
|
|
|
83
|
|
|
# # Part 2: Substitution |
|
84
|
|
|
# 1. Change umlauts to corresponding vowels & ß to ss |
|
85
|
1 |
|
word = word.translate(self._umlauts) |
|
86
|
1 |
|
word = word.replace('ß', 'ss') |
|
87
|
|
|
|
|
88
|
|
|
# 2. Change second of doubled characters to * |
|
89
|
1 |
|
new_word = word[0] |
|
90
|
1 |
|
for i in range(1, len(word)): |
|
91
|
1 |
|
if new_word[i - 1] == word[i]: |
|
92
|
1 |
|
new_word += '*' |
|
93
|
|
|
else: |
|
94
|
1 |
|
new_word += word[i] |
|
95
|
1 |
|
word = new_word |
|
96
|
|
|
|
|
97
|
|
|
# 3. Replace sch, ch, ei, ie with $, §, %, & |
|
98
|
1 |
|
word = word.replace('sch', '$') |
|
99
|
1 |
|
word = word.replace('ch', '§') |
|
100
|
1 |
|
word = word.replace('ei', '%') |
|
101
|
1 |
|
word = word.replace('ie', '&') |
|
102
|
1 |
|
word = word.replace('ig', '#') |
|
103
|
1 |
|
word = word.replace('st', '!') |
|
104
|
|
|
|
|
105
|
|
|
# # Part 1: Recursive Context-Free Stripping |
|
106
|
|
|
# 1. Remove the following 7 suffixes recursively |
|
107
|
1 |
|
while len(word) > 3: |
|
108
|
1 |
|
if (len(word) > 4 and word[-2:] in {'em', 'er'}) or ( |
|
109
|
|
|
len(word) > 5 and word[-2:] == 'nd' |
|
|
|
|
|
|
110
|
|
|
): |
|
111
|
1 |
|
word = word[:-2] |
|
112
|
1 |
|
elif (word[-1] in {'e', 's', 'n'}) or ( |
|
113
|
|
|
not upper_initial and word[-1] in {'t', '!'} |
|
|
|
|
|
|
114
|
|
|
): |
|
115
|
1 |
|
word = word[:-1] |
|
116
|
|
|
else: |
|
117
|
1 |
|
break |
|
118
|
|
|
|
|
119
|
|
|
# Additional optimizations: |
|
120
|
1 |
|
if len(word) > 5 and word[-5:] == 'erin*': |
|
121
|
1 |
|
word = word[:-1] |
|
122
|
1 |
|
if word[-1] == 'z': |
|
123
|
1 |
|
word = word[:-1] + 'x' |
|
124
|
|
|
|
|
125
|
|
|
# Reverse substitutions: |
|
126
|
1 |
|
word = word.replace('$', 'sch') |
|
127
|
1 |
|
word = word.replace('§', 'ch') |
|
128
|
1 |
|
word = word.replace('%', 'ei') |
|
129
|
1 |
|
word = word.replace('&', 'ie') |
|
130
|
1 |
|
word = word.replace('#', 'ig') |
|
131
|
1 |
|
word = word.replace('!', 'st') |
|
132
|
|
|
|
|
133
|
|
|
# Expand doubled |
|
134
|
1 |
|
word = ''.join( |
|
135
|
|
|
[word[0]] |
|
136
|
|
|
+ [ |
|
137
|
|
|
word[i - 1] if word[i] == '*' else word[i] |
|
138
|
|
|
for i in range(1, len(word)) |
|
139
|
|
|
] |
|
140
|
|
|
) |
|
141
|
|
|
|
|
142
|
|
|
# Finally, convert gege to ge |
|
143
|
1 |
|
if len(word) > 4: |
|
144
|
1 |
|
word = word.replace('gege', 'ge', 1) |
|
145
|
|
|
|
|
146
|
1 |
|
return word |
|
147
|
|
|
|
|
148
|
|
|
|
|
149
|
1 |
|
def caumanns(word): |
|
150
|
|
|
"""Return Caumanns German stem. |
|
151
|
|
|
|
|
152
|
|
|
This is a wrapper for :py:meth:`Caumanns.stem`. |
|
153
|
|
|
|
|
154
|
|
|
Parameters |
|
155
|
|
|
---------- |
|
156
|
|
|
word : str |
|
157
|
|
|
The word to stem |
|
158
|
|
|
|
|
159
|
|
|
Returns |
|
160
|
|
|
------- |
|
161
|
|
|
str |
|
162
|
|
|
Word stem |
|
163
|
|
|
|
|
164
|
|
|
Examples |
|
165
|
|
|
-------- |
|
166
|
|
|
>>> caumanns('lesen') |
|
167
|
|
|
'les' |
|
168
|
|
|
>>> caumanns('graues') |
|
169
|
|
|
'grau' |
|
170
|
|
|
>>> caumanns('buchstabieren') |
|
171
|
|
|
'buchstabier' |
|
172
|
|
|
|
|
173
|
|
|
""" |
|
174
|
1 |
|
return Caumanns().stem(word) |
|
175
|
|
|
|
|
176
|
|
|
|
|
177
|
|
|
if __name__ == '__main__': |
|
178
|
|
|
import doctest |
|
179
|
|
|
|
|
180
|
|
|
doctest.testmod() |
|
181
|
|
|
|
chrislit /
abydos
Loading history...