|
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.fingerprint._extract_position_frequence. |
|
20
|
|
|
|
|
21
|
|
|
Taft's extract - position & frequency coding |
|
22
|
|
|
""" |
|
23
|
|
|
|
|
24
|
1 |
|
from __future__ import ( |
|
25
|
|
|
absolute_import, |
|
26
|
|
|
division, |
|
27
|
|
|
print_function, |
|
28
|
|
|
unicode_literals, |
|
29
|
|
|
) |
|
30
|
|
|
|
|
31
|
1 |
|
from ._fingerprint import _Fingerprint |
|
32
|
|
|
|
|
33
|
1 |
|
__all__ = ['ExtractPositionFrequency'] |
|
34
|
|
|
|
|
35
|
|
|
|
|
36
|
1 |
|
class ExtractPositionFrequency(_Fingerprint): |
|
37
|
|
|
"""Extract - Position & Frequency fingerprint. |
|
38
|
|
|
|
|
39
|
|
|
Based on the extract - position & frequency coding from :cite:`Taft:1970`. |
|
40
|
|
|
|
|
41
|
|
|
.. versionadded:: 0.4.1 |
|
42
|
|
|
""" |
|
43
|
|
|
|
|
44
|
1 |
|
_frequency = { |
|
45
|
|
|
x: y |
|
46
|
|
|
for x, y in zip( |
|
47
|
|
|
'ABCDEFGHIJKLMNOPQRSTUVWXYZ', |
|
48
|
|
|
( |
|
49
|
|
|
5, |
|
50
|
|
|
1, |
|
51
|
|
|
5, |
|
52
|
|
|
0, |
|
53
|
|
|
7, |
|
54
|
|
|
1, |
|
55
|
|
|
2, |
|
56
|
|
|
5, |
|
57
|
|
|
6, |
|
58
|
|
|
0, |
|
59
|
|
|
1, |
|
60
|
|
|
5, |
|
61
|
|
|
1, |
|
62
|
|
|
3, |
|
63
|
|
|
4, |
|
64
|
|
|
3, |
|
65
|
|
|
0, |
|
66
|
|
|
4, |
|
67
|
|
|
5, |
|
68
|
|
|
3, |
|
69
|
|
|
4, |
|
70
|
|
|
1, |
|
71
|
|
|
1, |
|
72
|
|
|
0, |
|
73
|
|
|
2, |
|
74
|
|
|
1, |
|
75
|
|
|
), |
|
76
|
|
|
) |
|
77
|
|
|
} |
|
78
|
1 |
|
_position = (0, 1, 2, 3, 4, 4, 5, 5, 5, 5, 6, 6, 6, 6, 6, 7) |
|
79
|
|
|
|
|
80
|
1 |
|
def fingerprint(self, word): |
|
81
|
|
|
"""Return the extract - position & frequency coding. |
|
82
|
|
|
|
|
83
|
|
|
Parameters |
|
84
|
|
|
---------- |
|
85
|
|
|
word : str |
|
86
|
|
|
The word to fingerprint |
|
87
|
|
|
|
|
88
|
|
|
Returns |
|
89
|
|
|
------- |
|
90
|
|
|
int |
|
91
|
|
|
The extract - position & frequency coding |
|
92
|
|
|
|
|
93
|
|
|
Examples |
|
94
|
|
|
-------- |
|
95
|
|
|
>>> fp = ExtractPositionFrequency() |
|
96
|
|
|
>>> fp.fingerprint('hat') |
|
97
|
|
|
'HAT' |
|
98
|
|
|
>>> fp.fingerprint('niall') |
|
99
|
|
|
'NILL' |
|
100
|
|
|
>>> fp.fingerprint('colin') |
|
101
|
|
|
'COLN' |
|
102
|
|
|
>>> fp.fingerprint('atcg') |
|
103
|
|
|
'ATCG' |
|
104
|
|
|
>>> fp.fingerprint('entreatment') |
|
105
|
|
|
'NMNT' |
|
106
|
|
|
|
|
107
|
|
|
|
|
108
|
|
|
.. versionadded:: 0.4.1 |
|
109
|
|
|
|
|
110
|
|
|
""" |
|
111
|
|
|
# uppercase & reverse |
|
112
|
1 |
|
word = [_ for _ in word.upper() if _ in self._frequency] |
|
113
|
1 |
|
scores = [[] for _ in range(len(word))] |
|
114
|
|
|
|
|
115
|
1 |
|
pos = 0 |
|
116
|
1 |
|
for i in range(len(word)): |
|
117
|
1 |
|
scores[pos].append(self._frequency[word[pos]]) |
|
118
|
1 |
|
scores[pos][0] += self._position[min(i, 15)] |
|
119
|
1 |
|
scores[pos].append(len(word) + pos if pos < 0 else pos) |
|
120
|
1 |
|
pos = -(pos if pos < 0 else pos + 1) |
|
121
|
1 |
|
positions = sorted(pos[1] for pos in sorted(scores, reverse=True)[-4:]) |
|
122
|
|
|
|
|
123
|
1 |
|
return ''.join(word[_] for _ in positions) |
|
124
|
|
|
|
|
125
|
|
|
|
|
126
|
|
|
if __name__ == '__main__': |
|
127
|
|
|
import doctest |
|
128
|
|
|
|
|
129
|
|
|
doctest.testmod() |
|
130
|
|
|
|
chrislit /
abydos
