|
1
|
|
|
# Copyright 2019-2020 by Christopher C. Little. |
|
2
|
|
|
# This file is part of Abydos. |
|
3
|
|
|
# |
|
4
|
|
|
# Abydos is free software: you can redistribute it and/or modify |
|
5
|
|
|
# it under the terms of the GNU General Public License as published by |
|
6
|
|
|
# the Free Software Foundation, either version 3 of the License, or |
|
7
|
|
|
# (at your option) any later version. |
|
8
|
|
|
# |
|
9
|
|
|
# Abydos is distributed in the hope that it will be useful, |
|
10
|
|
|
# but WITHOUT ANY WARRANTY; without even the implied warranty of |
|
11
|
|
|
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
|
12
|
|
|
# GNU General Public License for more details. |
|
13
|
|
|
# |
|
14
|
|
|
# You should have received a copy of the GNU General Public License |
|
15
|
|
|
# along with Abydos. If not, see <http://www.gnu.org/licenses/>. |
|
16
|
|
|
|
|
17
|
|
|
"""abydos.fingerprint._lacss. |
|
18
|
|
|
|
|
19
|
1 |
|
L.A. County Sheriff's System fingerprint |
|
20
|
|
|
""" |
|
21
|
|
|
|
|
22
|
|
|
from ._fingerprint import _Fingerprint |
|
23
|
|
|
|
|
24
|
1 |
|
__all__ = ['LACSS'] |
|
25
|
|
|
|
|
26
|
|
|
|
|
27
|
|
|
class LACSS(_Fingerprint): |
|
28
|
|
|
"""L.A. County Sheriff's System fingerprint. |
|
29
|
|
|
|
|
30
|
|
|
Based on the description from :cite:`Taft:1970`. |
|
31
|
1 |
|
|
|
32
|
|
|
.. versionadded:: 0.4.1 |
|
33
|
1 |
|
""" |
|
34
|
|
|
|
|
35
|
|
|
_vowels = set('AEIOUYWH') |
|
36
|
1 |
|
|
|
37
|
|
|
_t1 = {_[0]: _[1] for _ in zip('RNLTSCMDKAGBPFVZXJQ', range(1, 20))} |
|
38
|
|
|
_t1.update({_: 0 for _ in _vowels}) |
|
39
|
|
|
|
|
40
|
|
|
_t2 = {_[0]: _[1] for _ in zip('ABCDEFGHIJKLMNOPQRSTUVWXYZ', range(1, 27))} |
|
41
|
|
|
|
|
42
|
|
|
def fingerprint(self, word: str) -> str: |
|
43
|
|
|
"""Return the LACSS coding. |
|
44
|
1 |
|
|
|
45
|
|
|
Parameters |
|
46
|
1 |
|
---------- |
|
47
|
1 |
|
word : str |
|
48
|
|
|
The word to fingerprint |
|
49
|
1 |
|
|
|
50
|
|
|
Returns |
|
51
|
1 |
|
------- |
|
52
|
|
|
str |
|
53
|
|
|
The L.A. County Sheriff's System fingerprint |
|
54
|
|
|
|
|
55
|
|
|
Examples |
|
56
|
|
|
-------- |
|
57
|
|
|
>>> cf = LACSS() |
|
58
|
|
|
>>> cf.fingerprint('hat') |
|
59
|
|
|
'4911211' |
|
60
|
|
|
>>> cf.fingerprint('niall') |
|
61
|
|
|
'6488374' |
|
62
|
|
|
>>> cf.fingerprint('colin') |
|
63
|
|
|
'3015957' |
|
64
|
|
|
>>> cf.fingerprint('atcg') |
|
65
|
|
|
'1772371' |
|
66
|
|
|
>>> cf.fingerprint('entreatment') |
|
67
|
|
|
'3882324' |
|
68
|
|
|
|
|
69
|
|
|
|
|
70
|
|
|
.. versionadded:: 0.4.1 |
|
71
|
|
|
.. versionchanged:: 0.6.0 |
|
72
|
|
|
Changed to return a str and added fingerprint_int method |
|
73
|
|
|
|
|
74
|
|
|
""" |
|
75
|
|
|
return str(self.fingerprint_int(word)) |
|
76
|
|
|
|
|
77
|
|
|
def fingerprint_int(self, word: str) -> int: |
|
78
|
|
|
"""Return the LACSS coding. |
|
79
|
|
|
|
|
80
|
|
|
Parameters |
|
81
|
|
|
---------- |
|
82
|
|
|
word : str |
|
83
|
1 |
|
The word to fingerprint |
|
84
|
|
|
|
|
85
|
|
|
Returns |
|
86
|
1 |
|
------- |
|
87
|
1 |
|
int |
|
88
|
|
|
The L.A. County Sheriff's System fingerprint as an int |
|
89
|
|
|
|
|
90
|
1 |
|
Examples |
|
91
|
1 |
|
-------- |
|
92
|
1 |
|
>>> cf = LACSS() |
|
93
|
1 |
|
>>> cf.fingerprint_int('hat') |
|
94
|
1 |
|
4911211 |
|
95
|
1 |
|
>>> cf.fingerprint_int('niall') |
|
96
|
|
|
6488374 |
|
97
|
1 |
|
>>> cf.fingerprint_int('colin') |
|
98
|
1 |
|
3015957 |
|
99
|
1 |
|
>>> cf.fingerprint_int('atcg') |
|
100
|
1 |
|
1772371 |
|
101
|
1 |
|
>>> cf.fingerprint_int('entreatment') |
|
102
|
1 |
|
3882324 |
|
103
|
1 |
|
|
|
104
|
|
|
|
|
105
|
1 |
|
.. versionadded:: 0.6.0 |
|
106
|
1 |
|
|
|
107
|
|
|
""" |
|
108
|
1 |
|
# uppercase |
|
109
|
|
|
word = word.upper() |
|
110
|
|
|
|
|
111
|
|
|
# remove vowels |
|
112
|
|
|
word = word[:1] + ''.join(_ for _ in word[1:] if _ not in 'AEIOUWHY') |
|
113
|
|
|
word += 12 * 'A' |
|
114
|
|
|
|
|
115
|
|
|
# step 1 |
|
116
|
|
|
code = 0 |
|
117
|
|
|
i = 0 |
|
118
|
|
|
while (not code) and (i < len(word)): |
|
119
|
|
|
if word[i] in self._t2: |
|
120
|
|
|
code = self._t2[word[i]] * 10 |
|
121
|
|
|
i += 1 |
|
122
|
|
|
|
|
123
|
|
|
letters = 11 |
|
124
|
|
|
while letters and i < len(word): |
|
125
|
|
|
if word[i] in self._t1: |
|
126
|
|
|
code *= 10 |
|
127
|
|
|
code += self._t1[word[i]] |
|
128
|
|
|
letters -= 1 |
|
129
|
|
|
i += 1 |
|
130
|
|
|
|
|
131
|
|
|
code *= 3 |
|
132
|
|
|
code = int(code ** 0.5) |
|
133
|
|
|
|
|
134
|
|
|
return code |
|
135
|
|
|
|
|
136
|
|
|
|
|
137
|
|
|
if __name__ == '__main__': |
|
138
|
|
|
import doctest |
|
139
|
|
|
|
|
140
|
|
|
doctest.testmod() |
|
141
|
|
|
|
chrislit /
abydos
