|
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.phonetic._phonex. |
|
20
|
|
|
|
|
21
|
|
|
Phonex |
|
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 as unicode_normalize |
|
32
|
|
|
|
|
33
|
1 |
|
from six import text_type |
|
34
|
1 |
|
from six.moves import range |
|
35
|
|
|
|
|
36
|
1 |
|
from ._phonetic import Phonetic |
|
37
|
|
|
|
|
38
|
1 |
|
__all__ = ['Phonex', 'phonex'] |
|
39
|
|
|
|
|
40
|
|
|
|
|
41
|
1 |
|
class Phonex(Phonetic): |
|
|
|
|
|
|
42
|
|
|
"""Phonex code. |
|
43
|
|
|
|
|
44
|
|
|
Phonex is an algorithm derived from Soundex, defined in :cite:`Lait:1996`. |
|
45
|
|
|
""" |
|
46
|
|
|
|
|
47
|
1 |
|
def encode(self, word, max_length=4, zero_pad=True): |
|
|
|
|
|
|
48
|
|
|
"""Return the Phonex code for a word. |
|
49
|
|
|
|
|
50
|
|
|
Args: |
|
51
|
|
|
word (str): The word to transform |
|
52
|
|
|
max_length (int): The length of the code returned (defaults to 4) |
|
53
|
|
|
zero_pad (bool): pad the end of the return value with 0s to achieve |
|
54
|
|
|
a max_length string |
|
55
|
|
|
|
|
56
|
|
|
Returns: |
|
57
|
|
|
str: The Phonex value |
|
58
|
|
|
|
|
59
|
|
|
Examples: |
|
60
|
|
|
>>> pe = Phonex() |
|
61
|
|
|
>>> pe.encode('Christopher') |
|
62
|
|
|
'C623' |
|
63
|
|
|
>>> pe.encode('Niall') |
|
64
|
|
|
'N400' |
|
65
|
|
|
>>> pe.encode('Schmidt') |
|
66
|
|
|
'S253' |
|
67
|
|
|
>>> pe.encode('Smith') |
|
68
|
|
|
'S530' |
|
69
|
|
|
|
|
70
|
|
|
""" |
|
71
|
1 |
|
name = unicode_normalize('NFKD', text_type(word.upper())) |
|
72
|
1 |
|
name = name.replace('ß', 'SS') |
|
73
|
|
|
|
|
74
|
|
|
# Clamp max_length to [4, 64] |
|
75
|
1 |
|
if max_length != -1: |
|
76
|
1 |
|
max_length = min(max(4, max_length), 64) |
|
77
|
|
|
else: |
|
78
|
1 |
|
max_length = 64 |
|
79
|
|
|
|
|
80
|
1 |
|
name_code = last = '' |
|
81
|
|
|
|
|
82
|
|
|
# Deletions effected by replacing with next letter which |
|
83
|
|
|
# will be ignored due to duplicate handling of Soundex code. |
|
84
|
|
|
# This is faster than 'moving' all subsequent letters. |
|
85
|
|
|
|
|
86
|
|
|
# Remove any trailing Ss |
|
87
|
1 |
|
while name[-1:] == 'S': |
|
88
|
1 |
|
name = name[:-1] |
|
89
|
|
|
|
|
90
|
|
|
# Phonetic equivalents of first 2 characters |
|
91
|
|
|
# Works since duplicate letters are ignored |
|
92
|
1 |
|
if name[:2] == 'KN': |
|
93
|
1 |
|
name = 'N' + name[2:] # KN.. == N.. |
|
94
|
1 |
|
elif name[:2] == 'PH': |
|
95
|
1 |
|
name = 'F' + name[2:] # PH.. == F.. (H ignored anyway) |
|
96
|
1 |
|
elif name[:2] == 'WR': |
|
97
|
1 |
|
name = 'R' + name[2:] # WR.. == R.. |
|
98
|
|
|
|
|
99
|
1 |
|
if name: |
|
100
|
|
|
# Special case, ignore H first letter (subsequent Hs ignored |
|
101
|
|
|
# anyway) |
|
102
|
|
|
# Works since duplicate letters are ignored |
|
103
|
1 |
|
if name[0] == 'H': |
|
104
|
1 |
|
name = name[1:] |
|
105
|
|
|
|
|
106
|
1 |
|
if name: |
|
107
|
|
|
# Phonetic equivalents of first character |
|
108
|
1 |
|
if name[0] in self._uc_vy_set: |
|
109
|
1 |
|
name = 'A' + name[1:] |
|
110
|
1 |
|
elif name[0] in {'B', 'P'}: |
|
111
|
1 |
|
name = 'B' + name[1:] |
|
112
|
1 |
|
elif name[0] in {'V', 'F'}: |
|
113
|
1 |
|
name = 'F' + name[1:] |
|
114
|
1 |
|
elif name[0] in {'C', 'K', 'Q'}: |
|
115
|
1 |
|
name = 'C' + name[1:] |
|
116
|
1 |
|
elif name[0] in {'G', 'J'}: |
|
117
|
1 |
|
name = 'G' + name[1:] |
|
118
|
1 |
|
elif name[0] in {'S', 'Z'}: |
|
119
|
1 |
|
name = 'S' + name[1:] |
|
120
|
|
|
|
|
121
|
1 |
|
name_code = last = name[0] |
|
122
|
|
|
|
|
123
|
|
|
# Modified Soundex code |
|
124
|
1 |
|
for i in range(1, len(name)): |
|
125
|
1 |
|
code = '0' |
|
126
|
1 |
|
if name[i] in {'B', 'F', 'P', 'V'}: |
|
127
|
1 |
|
code = '1' |
|
128
|
1 |
|
elif name[i] in {'C', 'G', 'J', 'K', 'Q', 'S', 'X', 'Z'}: |
|
129
|
1 |
|
code = '2' |
|
130
|
1 |
|
elif name[i] in {'D', 'T'}: |
|
131
|
1 |
|
if name[i + 1 : i + 2] != 'C': |
|
132
|
1 |
|
code = '3' |
|
133
|
1 |
|
elif name[i] == 'L': |
|
134
|
1 |
|
if name[i + 1 : i + 2] in self._uc_vy_set or i + 1 == len( |
|
135
|
|
|
name |
|
|
|
|
|
|
136
|
|
|
): |
|
137
|
1 |
|
code = '4' |
|
138
|
1 |
|
elif name[i] in {'M', 'N'}: |
|
139
|
1 |
|
if name[i + 1 : i + 2] in {'D', 'G'}: |
|
140
|
1 |
|
name = name[: i + 1] + name[i] + name[i + 2 :] |
|
141
|
1 |
|
code = '5' |
|
142
|
1 |
|
elif name[i] == 'R': |
|
143
|
1 |
|
if name[i + 1 : i + 2] in self._uc_vy_set or i + 1 == len( |
|
144
|
|
|
name |
|
|
|
|
|
|
145
|
|
|
): |
|
146
|
1 |
|
code = '6' |
|
147
|
|
|
|
|
148
|
1 |
|
if code != last and code != '0' and i != 0: |
|
149
|
1 |
|
name_code += code |
|
150
|
|
|
|
|
151
|
1 |
|
last = name_code[-1] |
|
152
|
|
|
|
|
153
|
1 |
|
if zero_pad: |
|
154
|
1 |
|
name_code += '0' * max_length |
|
155
|
1 |
|
if not name_code: |
|
156
|
1 |
|
name_code = '0' |
|
157
|
1 |
|
return name_code[:max_length] |
|
158
|
|
|
|
|
159
|
|
|
|
|
160
|
1 |
|
def phonex(word, max_length=4, zero_pad=True): |
|
161
|
|
|
"""Return the Phonex code for a word. |
|
162
|
|
|
|
|
163
|
|
|
This is a wrapper for :py:meth:`Phonex.encode`. |
|
164
|
|
|
|
|
165
|
|
|
Args: |
|
166
|
|
|
word (str): The word to transform |
|
167
|
|
|
max_length (int): The length of the code returned (defaults to 4) |
|
168
|
|
|
zero_pad (bool): pad the end of the return value with 0s to achieve |
|
169
|
|
|
a max_length string |
|
170
|
|
|
|
|
171
|
|
|
Returns: |
|
172
|
|
|
str: The Phonex value |
|
173
|
|
|
|
|
174
|
|
|
Examples: |
|
175
|
|
|
>>> phonex('Christopher') |
|
176
|
|
|
'C623' |
|
177
|
|
|
>>> phonex('Niall') |
|
178
|
|
|
'N400' |
|
179
|
|
|
>>> phonex('Schmidt') |
|
180
|
|
|
'S253' |
|
181
|
|
|
>>> phonex('Smith') |
|
182
|
|
|
'S530' |
|
183
|
|
|
|
|
184
|
|
|
""" |
|
185
|
1 |
|
return Phonex().encode(word, max_length, zero_pad) |
|
186
|
|
|
|
|
187
|
|
|
|
|
188
|
|
|
if __name__ == '__main__': |
|
189
|
|
|
import doctest |
|
190
|
|
|
|
|
191
|
|
|
doctest.testmod() |
|
192
|
|
|
|
chrislit /
abydos
Loading history...