|
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.statistics_canada. |
|
20
|
|
|
|
|
21
|
|
|
The phonetic.statistics_canada module implements the Statistics Canada phonetic |
|
22
|
|
|
encoding. |
|
23
|
|
|
""" |
|
24
|
|
|
|
|
25
|
1 |
|
from __future__ import unicode_literals |
|
26
|
|
|
|
|
27
|
1 |
|
from unicodedata import normalize as unicode_normalize |
|
28
|
|
|
|
|
29
|
1 |
|
from six import text_type |
|
30
|
|
|
|
|
31
|
1 |
|
from . import _delete_consecutive_repeats |
|
32
|
|
|
|
|
33
|
1 |
|
__all__ = ['statistics_canada'] |
|
34
|
|
|
|
|
35
|
|
|
|
|
36
|
1 |
|
def statistics_canada(word, max_length=4): |
|
37
|
|
|
"""Return the Statistics Canada code for a word. |
|
38
|
|
|
|
|
39
|
|
|
The original description of this algorithm could not be located, and |
|
40
|
|
|
may only have been specified in an unpublished TR. The coding does not |
|
41
|
|
|
appear to be in use by Statistics Canada any longer. In its place, this is |
|
42
|
|
|
an implementation of the "Census modified Statistics Canada name coding |
|
43
|
|
|
procedure". |
|
44
|
|
|
|
|
45
|
|
|
The modified version of this algorithm is described in Appendix B of |
|
46
|
|
|
:cite:`Moore:1977`. |
|
47
|
|
|
|
|
48
|
|
|
:param str word: the word to transform |
|
49
|
|
|
:param int max_length: the maximum length (default 4) of the code to return |
|
50
|
|
|
:returns: the Statistics Canada name code value |
|
51
|
|
|
:rtype: str |
|
52
|
|
|
|
|
53
|
|
|
>>> statistics_canada('Christopher') |
|
54
|
|
|
'CHRS' |
|
55
|
|
|
>>> statistics_canada('Niall') |
|
56
|
|
|
'NL' |
|
57
|
|
|
>>> statistics_canada('Smith') |
|
58
|
|
|
'SMTH' |
|
59
|
|
|
>>> statistics_canada('Schmidt') |
|
60
|
|
|
'SCHM' |
|
61
|
|
|
""" |
|
62
|
|
|
# uppercase, normalize, decompose, and filter non-A-Z out |
|
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
|
1 |
|
if not word: |
|
99
|
1 |
|
return '' |
|
100
|
|
|
|
|
101
|
1 |
|
code = word[1:] |
|
102
|
1 |
|
for vowel in {'A', 'E', 'I', 'O', 'U', 'Y'}: |
|
103
|
1 |
|
code = code.replace(vowel, '') |
|
104
|
1 |
|
code = word[0] + code |
|
105
|
1 |
|
code = _delete_consecutive_repeats(code) |
|
106
|
1 |
|
code = code.replace(' ', '') |
|
107
|
|
|
|
|
108
|
1 |
|
return code[:max_length] |
|
109
|
|
|
|
|
110
|
|
|
|
|
111
|
|
|
if __name__ == '__main__': |
|
112
|
|
|
import doctest |
|
113
|
|
|
|
|
114
|
|
|
doctest.testmod() |
|
115
|
|
|
|
chrislit /
abydos
