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.phonetic._sound_d. |
20
|
|
|
|
21
|
|
|
The phonetic._sound_d module implements the SoundD phonetic algorithm. |
22
|
|
|
""" |
23
|
|
|
|
24
|
1 |
|
from __future__ import unicode_literals |
25
|
|
|
|
26
|
1 |
|
from unicodedata import normalize as unicode_normalize |
27
|
|
|
|
28
|
1 |
|
from six import text_type |
29
|
|
|
|
30
|
1 |
|
from ._util import _delete_consecutive_repeats |
31
|
|
|
|
32
|
1 |
|
__all__ = ['sound_d'] |
33
|
|
|
|
34
|
|
|
|
35
|
1 |
|
def sound_d(word, max_length=4): |
36
|
|
|
"""Return the SoundD code. |
37
|
|
|
|
38
|
|
|
SoundD is defined in :cite:`Varol:2012`. |
39
|
|
|
|
40
|
|
|
:param str word: the word to transform |
41
|
|
|
:param int max_length: the length of the code returned (defaults to 4) |
42
|
|
|
:returns: the SoundD code |
43
|
|
|
:rtype: str |
44
|
|
|
|
45
|
|
|
>>> sound_d('Gough') |
46
|
|
|
'2000' |
47
|
|
|
>>> sound_d('pneuma') |
48
|
|
|
'5500' |
49
|
|
|
>>> sound_d('knight') |
50
|
|
|
'5300' |
51
|
|
|
>>> sound_d('trice') |
52
|
|
|
'3620' |
53
|
|
|
>>> sound_d('judge') |
54
|
|
|
'2200' |
55
|
|
|
""" |
56
|
1 |
|
_ref_soundd_translation = dict( |
57
|
|
|
zip( |
58
|
|
|
(ord(_) for _ in 'ABCDEFGHIJKLMNOPQRSTUVWXYZ'), |
|
|
|
|
59
|
|
|
'01230120022455012623010202', |
60
|
|
|
) |
61
|
|
|
) |
62
|
|
|
|
63
|
1 |
|
word = unicode_normalize('NFKD', text_type(word.upper())) |
64
|
1 |
|
word = word.replace('ß', 'SS') |
65
|
1 |
|
word = ''.join( |
66
|
|
|
c |
67
|
|
|
for c in word |
68
|
|
|
if c |
69
|
|
|
in { |
70
|
|
|
'A', |
71
|
|
|
'B', |
72
|
|
|
'C', |
73
|
|
|
'D', |
74
|
|
|
'E', |
75
|
|
|
'F', |
76
|
|
|
'G', |
77
|
|
|
'H', |
78
|
|
|
'I', |
79
|
|
|
'J', |
80
|
|
|
'K', |
81
|
|
|
'L', |
82
|
|
|
'M', |
83
|
|
|
'N', |
84
|
|
|
'O', |
85
|
|
|
'P', |
86
|
|
|
'Q', |
87
|
|
|
'R', |
88
|
|
|
'S', |
89
|
|
|
'T', |
90
|
|
|
'U', |
91
|
|
|
'V', |
92
|
|
|
'W', |
93
|
|
|
'X', |
94
|
|
|
'Y', |
95
|
|
|
'Z', |
96
|
|
|
} |
97
|
|
|
) |
98
|
|
|
|
99
|
1 |
|
if word[:2] in {'KN', 'GN', 'PN', 'AC', 'WR'}: |
100
|
1 |
|
word = word[1:] |
101
|
1 |
|
elif word[:1] == 'X': |
102
|
1 |
|
word = 'S' + word[1:] |
103
|
1 |
|
elif word[:2] == 'WH': |
104
|
1 |
|
word = 'W' + word[2:] |
105
|
|
|
|
106
|
1 |
|
word = word.replace('DGE', '20').replace('DGI', '20').replace('GH', '0') |
107
|
|
|
|
108
|
1 |
|
word = word.translate(_ref_soundd_translation) |
109
|
1 |
|
word = _delete_consecutive_repeats(word) |
110
|
1 |
|
word = word.replace('0', '') |
111
|
|
|
|
112
|
1 |
|
if max_length != -1: |
113
|
1 |
|
if len(word) < max_length: |
114
|
1 |
|
word += '0' * (max_length - len(word)) |
115
|
|
|
else: |
116
|
1 |
|
word = word[:max_length] |
117
|
|
|
|
118
|
1 |
|
return word |
119
|
|
|
|
120
|
|
|
|
121
|
|
|
if __name__ == '__main__': |
122
|
|
|
import doctest |
123
|
|
|
|
124
|
|
|
doctest.testmod() |
125
|
|
|
|