1
|
|
|
# -*- coding: utf-8 -*- |
2
|
|
|
|
3
|
|
|
# Copyright 2019 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._phonic. |
20
|
|
|
|
21
|
|
|
Phonic |
22
|
|
|
""" |
23
|
|
|
|
24
|
1 |
|
from __future__ import ( |
25
|
|
|
absolute_import, |
26
|
|
|
division, |
27
|
|
|
print_function, |
28
|
|
|
unicode_literals, |
29
|
|
|
) |
30
|
|
|
|
31
|
1 |
|
from ._phonetic import _Phonetic |
32
|
|
|
|
33
|
1 |
|
__all__ = ['PHONIC'] |
34
|
|
|
|
35
|
|
|
|
36
|
1 |
|
class PHONIC(_Phonetic): |
37
|
|
|
"""PHONIC code. |
38
|
|
|
|
39
|
|
|
PHONIC is a Soundex-like algorithm defined in :cite:`Taft:1970`. |
40
|
|
|
|
41
|
|
|
|
42
|
|
|
.. versionadded:: 0.4.1 |
43
|
|
|
""" |
44
|
|
|
|
45
|
1 |
|
_trans2 = { |
46
|
|
|
'CH': '6', |
47
|
|
|
'SH': '6', |
48
|
|
|
'PH': '8', |
49
|
|
|
'CE': '0', |
50
|
|
|
'CI': '0', |
51
|
|
|
'CY': '0', |
52
|
|
|
} |
53
|
|
|
|
54
|
1 |
|
_trans1 = { |
55
|
|
|
'D': '1', |
56
|
|
|
'T': '1', |
57
|
|
|
'N': '2', |
58
|
|
|
'M': '3', |
59
|
|
|
'R': '4', |
60
|
|
|
'L': '5', |
61
|
|
|
'J': '6', |
62
|
|
|
'C': '7', |
63
|
|
|
'K': '7', |
64
|
|
|
'G': '7', |
65
|
|
|
'Q': '7', |
66
|
|
|
'X': '7', |
67
|
|
|
'F': '8', |
68
|
|
|
'V': '8', |
69
|
|
|
'B': '9', |
70
|
|
|
'P': '9', |
71
|
|
|
'S': '0', |
72
|
|
|
'Z': '0', |
73
|
|
|
} |
74
|
|
|
|
75
|
1 |
|
_alphabetic = dict(zip((ord(_) for _ in '0123456789'), 'STNMRLJKFP')) |
|
|
|
|
76
|
|
|
|
77
|
1 |
|
def __init__(self, max_length=5, zero_pad=True, extended=False): |
78
|
|
|
"""Initialize PHONIC instance. |
79
|
|
|
|
80
|
|
|
Parameters |
81
|
|
|
---------- |
82
|
|
|
max_length : int |
83
|
|
|
The length of the code returned (defaults to 5) |
84
|
|
|
zero_pad : bool |
85
|
|
|
Pad the end of the return value with 0s to achieve a max_length |
86
|
|
|
string |
87
|
|
|
extended : bool |
88
|
|
|
If True, this uses Taft's 'Extended PHONIC coding' mode, which |
89
|
|
|
simply omits the first character of the code. |
90
|
|
|
|
91
|
|
|
|
92
|
|
|
.. versionadded:: 0.4.1 |
93
|
|
|
|
94
|
|
|
""" |
95
|
|
|
# Require a max_length of at least 5 and not more than 64 |
96
|
1 |
|
if max_length != -1: |
97
|
1 |
|
self._max_length = min(max(5, max_length), 64) |
98
|
|
|
else: |
99
|
1 |
|
self._max_length = 64 |
100
|
|
|
|
101
|
1 |
|
self._zero_pad = zero_pad |
102
|
1 |
|
self._extended = extended |
103
|
|
|
|
104
|
1 |
|
def encode_alpha(self, word): |
105
|
|
|
"""Return the alphabetic PHONIC code for a word. |
106
|
|
|
|
107
|
|
|
Parameters |
108
|
|
|
---------- |
109
|
|
|
word : str |
110
|
|
|
The word to transform |
111
|
|
|
|
112
|
|
|
Returns |
113
|
|
|
------- |
114
|
|
|
str |
115
|
|
|
The alphabetic PHONIC value |
116
|
|
|
|
117
|
|
|
Examples |
118
|
|
|
-------- |
119
|
|
|
>>> pe = PHONIC() |
120
|
|
|
>>> pe.encode_alpha('Christopher') |
121
|
|
|
'JRSTF' |
122
|
|
|
>>> pe.encode_alpha('Niall') |
123
|
|
|
'NL' |
124
|
|
|
>>> pe.encode_alpha('Smith') |
125
|
|
|
'SMT' |
126
|
|
|
>>> pe.encode_alpha('Schmidt') |
127
|
|
|
'SJMT' |
128
|
|
|
|
129
|
|
|
|
130
|
|
|
.. versionadded:: 0.4.1 |
131
|
|
|
|
132
|
|
|
""" |
133
|
1 |
|
save_pad = self._zero_pad |
134
|
1 |
|
save_ext = self._extended |
135
|
1 |
|
self._zero_pad = False |
136
|
1 |
|
self._extended = True |
137
|
1 |
|
code = self.encode(word) |
138
|
1 |
|
self._zero_pad = save_pad |
139
|
1 |
|
self._extended = save_ext |
140
|
1 |
|
return code.translate(self._alphabetic) |
141
|
|
|
|
142
|
1 |
|
def encode(self, word): |
143
|
|
|
"""Return the PHONIC code for a word. |
144
|
|
|
|
145
|
|
|
Parameters |
146
|
|
|
---------- |
147
|
|
|
word : str |
148
|
|
|
The word to transform |
149
|
|
|
|
150
|
|
|
Returns |
151
|
|
|
------- |
152
|
|
|
str |
153
|
|
|
The PHONIC code |
154
|
|
|
|
155
|
|
|
Examples |
156
|
|
|
-------- |
157
|
|
|
>>> pe = PHONIC() |
158
|
|
|
>>> pe.encode('Christopher') |
159
|
|
|
'C6401' |
160
|
|
|
>>> pe.encode('Niall') |
161
|
|
|
'N2500' |
162
|
|
|
>>> pe.encode('Smith') |
163
|
|
|
'S0310' |
164
|
|
|
>>> pe.encode('Schmidt') |
165
|
|
|
'S0631' |
166
|
|
|
|
167
|
|
|
|
168
|
|
|
.. versionadded:: 0.4.1 |
169
|
|
|
|
170
|
|
|
""" |
171
|
|
|
# uppercase |
172
|
1 |
|
word = word.upper() |
173
|
|
|
|
174
|
1 |
|
code = [] |
175
|
1 |
|
pos = 0 |
176
|
1 |
|
while pos < len(word): |
177
|
1 |
|
if word[pos : pos + 2] in self._trans2: |
178
|
1 |
|
code.append(self._trans2[word[pos : pos + 2]]) |
179
|
1 |
|
pos += 1 |
180
|
1 |
|
elif word[pos] in self._trans1: |
181
|
1 |
|
code.append(self._trans1[word[pos]]) |
182
|
|
|
else: |
183
|
1 |
|
code.append('.') |
184
|
1 |
|
pos += 1 |
185
|
|
|
|
186
|
1 |
|
code = ''.join(code) |
187
|
1 |
|
code = self._delete_consecutive_repeats(code) |
188
|
1 |
|
code = code.replace('.', '') |
189
|
|
|
|
190
|
1 |
|
if self._zero_pad: |
191
|
1 |
|
code += '0' * (self._max_length - 1 - len(code)) |
192
|
|
|
|
193
|
1 |
|
if not self._extended: |
194
|
1 |
|
code = word[:1] + code |
195
|
|
|
|
196
|
1 |
|
return code[: self._max_length] |
197
|
|
|
|
198
|
|
|
|
199
|
|
|
if __name__ == '__main__': |
200
|
|
|
import doctest |
201
|
|
|
|
202
|
|
|
doctest.testmod() |
203
|
|
|
|