|
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.fingerprint._occurrence_halved. |
|
20
|
|
|
|
|
21
|
|
|
Cisłak & Grabowski's occurrence halved fingerprint |
|
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 MOST_COMMON_LETTERS_CG, _Fingerprint |
|
32
|
|
|
|
|
33
|
1 |
|
__all__ = ['OccurrenceHalved', 'occurrence_halved_fingerprint'] |
|
34
|
|
|
|
|
35
|
|
|
|
|
36
|
1 |
|
class OccurrenceHalved(_Fingerprint): |
|
|
|
|
|
|
37
|
|
|
"""Occurrence Halved Fingerprint. |
|
38
|
|
|
|
|
39
|
|
|
Based on the occurrence halved fingerprint from :cite:`Cislak:2017`. |
|
40
|
|
|
""" |
|
41
|
|
|
|
|
42
|
1 |
|
def fingerprint(self, word, n_bits=16, most_common=MOST_COMMON_LETTERS_CG): |
|
|
|
|
|
|
43
|
|
|
"""Return the occurrence halved fingerprint. |
|
44
|
|
|
|
|
45
|
|
|
Based on the occurrence halved fingerprint from :cite:`Cislak:2017`. |
|
46
|
|
|
|
|
47
|
|
|
Parameters |
|
48
|
|
|
---------- |
|
49
|
|
|
word : str |
|
50
|
|
|
The word to fingerprint |
|
51
|
|
|
n_bits : int |
|
52
|
|
|
Number of bits in the fingerprint returned |
|
53
|
|
|
most_common : list |
|
54
|
|
|
The most common tokens in the target language, ordered by frequency |
|
55
|
|
|
|
|
56
|
|
|
Returns |
|
57
|
|
|
------- |
|
58
|
|
|
int |
|
59
|
|
|
The occurrence halved fingerprint |
|
60
|
|
|
|
|
61
|
|
|
Examples |
|
62
|
|
|
-------- |
|
63
|
|
|
>>> ohf = OccurrenceHalved() |
|
64
|
|
|
>>> bin(ohf.fingerprint('hat')) |
|
65
|
|
|
'0b1010000000010' |
|
66
|
|
|
>>> bin(ohf.fingerprint('niall')) |
|
67
|
|
|
'0b10010100000' |
|
68
|
|
|
>>> bin(ohf.fingerprint('colin')) |
|
69
|
|
|
'0b1001010000' |
|
70
|
|
|
>>> bin(ohf.fingerprint('atcg')) |
|
71
|
|
|
'0b10100000000000' |
|
72
|
|
|
>>> bin(ohf.fingerprint('entreatment')) |
|
73
|
|
|
'0b1111010000110000' |
|
74
|
|
|
|
|
75
|
|
|
""" |
|
76
|
1 |
|
if n_bits % 2: |
|
77
|
1 |
|
n_bits += 1 |
|
78
|
|
|
|
|
79
|
1 |
|
w_len = len(word) // 2 |
|
80
|
1 |
|
w_1 = set(word[:w_len]) |
|
81
|
1 |
|
w_2 = set(word[w_len:]) |
|
82
|
1 |
|
fingerprint = 0 |
|
83
|
|
|
|
|
84
|
1 |
|
for letter in most_common: |
|
85
|
1 |
|
if n_bits: |
|
86
|
1 |
|
fingerprint <<= 1 |
|
87
|
1 |
|
if letter in w_1: |
|
88
|
1 |
|
fingerprint += 1 |
|
89
|
1 |
|
fingerprint <<= 1 |
|
90
|
1 |
|
if letter in w_2: |
|
91
|
1 |
|
fingerprint += 1 |
|
92
|
1 |
|
n_bits -= 2 |
|
93
|
|
|
else: |
|
94
|
1 |
|
break |
|
95
|
|
|
|
|
96
|
1 |
|
if n_bits > 0: |
|
97
|
1 |
|
fingerprint <<= n_bits |
|
98
|
|
|
|
|
99
|
1 |
|
return fingerprint |
|
100
|
|
|
|
|
101
|
|
|
|
|
102
|
1 |
|
def occurrence_halved_fingerprint( |
|
103
|
|
|
word, n_bits=16, most_common=MOST_COMMON_LETTERS_CG |
|
|
|
|
|
|
104
|
|
|
): |
|
105
|
|
|
"""Return the occurrence halved fingerprint. |
|
106
|
|
|
|
|
107
|
|
|
This is a wrapper for :py:meth:`OccurrenceHalved.fingerprint`. |
|
108
|
|
|
|
|
109
|
|
|
Parameters |
|
110
|
|
|
---------- |
|
111
|
|
|
word : str |
|
112
|
|
|
The word to fingerprint |
|
113
|
|
|
n_bits : int |
|
114
|
|
|
Number of bits in the fingerprint returned |
|
115
|
|
|
most_common : list |
|
116
|
|
|
The most common tokens in the target language, ordered by frequency |
|
117
|
|
|
|
|
118
|
|
|
Returns |
|
119
|
|
|
------- |
|
120
|
|
|
int |
|
121
|
|
|
The occurrence halved fingerprint |
|
122
|
|
|
|
|
123
|
|
|
Examples |
|
124
|
|
|
-------- |
|
125
|
|
|
>>> bin(occurrence_halved_fingerprint('hat')) |
|
126
|
|
|
'0b1010000000010' |
|
127
|
|
|
>>> bin(occurrence_halved_fingerprint('niall')) |
|
128
|
|
|
'0b10010100000' |
|
129
|
|
|
>>> bin(occurrence_halved_fingerprint('colin')) |
|
130
|
|
|
'0b1001010000' |
|
131
|
|
|
>>> bin(occurrence_halved_fingerprint('atcg')) |
|
132
|
|
|
'0b10100000000000' |
|
133
|
|
|
>>> bin(occurrence_halved_fingerprint('entreatment')) |
|
134
|
|
|
'0b1111010000110000' |
|
135
|
|
|
|
|
136
|
|
|
""" |
|
137
|
1 |
|
return OccurrenceHalved().fingerprint(word, n_bits, most_common) |
|
138
|
|
|
|
|
139
|
|
|
|
|
140
|
|
|
if __name__ == '__main__': |
|
141
|
|
|
import doctest |
|
142
|
|
|
|
|
143
|
|
|
doctest.testmod() |
|
144
|
|
|
|
chrislit /
abydos
Loading history...