|
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._davidson. |
|
20
|
|
|
|
|
21
|
|
|
The phonetic._davidson module implements Davidson's Consonant Code. |
|
22
|
|
|
""" |
|
23
|
|
|
|
|
24
|
1 |
|
from __future__ import unicode_literals |
|
25
|
|
|
|
|
26
|
1 |
|
from six import text_type |
|
27
|
|
|
|
|
28
|
1 |
|
from ._util import _delete_consecutive_repeats |
|
29
|
|
|
|
|
30
|
1 |
|
__all__ = ['davidson'] |
|
31
|
|
|
|
|
32
|
|
|
|
|
33
|
1 |
|
def davidson(lname, fname='.', omit_fname=False): |
|
34
|
|
|
"""Return Davidson's Consonant Code. |
|
35
|
|
|
|
|
36
|
|
|
This is based on the name compression system described in |
|
37
|
|
|
:cite:`Davidson:1962`. |
|
38
|
|
|
|
|
39
|
|
|
:cite:`Dolby:1970` identifies this as having been the name compression |
|
40
|
|
|
algorithm used by SABRE. |
|
41
|
|
|
|
|
42
|
|
|
:param str lname: Last name (or word) to be encoded |
|
43
|
|
|
:param str fname: First name (optional), of which the first character is |
|
44
|
|
|
included in the code. |
|
45
|
|
|
:param bool omit_fname: Set to True to completely omit the first character |
|
46
|
|
|
of the first name |
|
47
|
|
|
:returns: Davidson's Consonant Code |
|
48
|
|
|
:rtype: str |
|
49
|
|
|
|
|
50
|
|
|
>>> davidson('Gough') |
|
51
|
|
|
'G .' |
|
52
|
|
|
>>> davidson('pneuma') |
|
53
|
|
|
'PNM .' |
|
54
|
|
|
>>> davidson('knight') |
|
55
|
|
|
'KNGT.' |
|
56
|
|
|
>>> davidson('trice') |
|
57
|
|
|
'TRC .' |
|
58
|
|
|
>>> davidson('judge') |
|
59
|
|
|
'JDG .' |
|
60
|
|
|
>>> davidson('Smith', 'James') |
|
61
|
|
|
'SMT J' |
|
62
|
|
|
>>> davidson('Wasserman', 'Tabitha') |
|
63
|
|
|
'WSRMT' |
|
64
|
|
|
""" |
|
65
|
1 |
|
trans = {65: '', 69: '', 73: '', 79: '', 85: '', 72: '', 87: '', 89: ''} |
|
66
|
|
|
|
|
67
|
1 |
|
lname = text_type(lname.upper()) |
|
68
|
1 |
|
code = _delete_consecutive_repeats(lname[:1] + lname[1:].translate(trans)) |
|
69
|
1 |
|
code = code[:4] + (4 - len(code)) * ' ' |
|
70
|
|
|
|
|
71
|
1 |
|
if not omit_fname: |
|
72
|
1 |
|
code += fname[:1].upper() |
|
73
|
|
|
|
|
74
|
1 |
|
return code |
|
75
|
|
|
|
|
76
|
|
|
|
|
77
|
|
|
if __name__ == '__main__': |
|
78
|
|
|
import doctest |
|
79
|
|
|
|
|
80
|
|
|
doctest.testmod() |
|
81
|
|
|
|
chrislit /
abydos
