|
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.distance._token_distance. |
|
20
|
|
|
|
|
21
|
|
|
The distance._TokenDistance module implements abstract class _TokenDistance. |
|
22
|
|
|
""" |
|
23
|
|
|
|
|
24
|
1 |
|
from __future__ import ( |
|
25
|
|
|
absolute_import, |
|
26
|
|
|
division, |
|
27
|
|
|
print_function, |
|
28
|
|
|
unicode_literals, |
|
29
|
|
|
) |
|
30
|
|
|
|
|
31
|
1 |
|
from collections import Counter |
|
32
|
|
|
|
|
33
|
1 |
|
from ._distance import _Distance |
|
34
|
1 |
|
from ..tokenizer import QGrams |
|
35
|
|
|
|
|
36
|
|
|
|
|
37
|
1 |
|
class _TokenDistance(_Distance): |
|
38
|
|
|
"""Abstract Token Distance class.""" |
|
39
|
|
|
|
|
40
|
1 |
|
def _get_qgrams(self, src, tar, qval=0, skip=0): |
|
41
|
|
|
"""Return the Q-Grams in src & tar. |
|
42
|
|
|
|
|
43
|
|
|
Parameters |
|
44
|
|
|
---------- |
|
45
|
|
|
src : str |
|
46
|
|
|
Source string (or QGrams/Counter objects) for comparison |
|
47
|
|
|
tar : str |
|
48
|
|
|
Target string (or QGrams/Counter objects) for comparison |
|
49
|
|
|
qval : int |
|
50
|
|
|
The length of each q-gram; 0 for non-q-gram version |
|
51
|
|
|
skip : int |
|
52
|
|
|
The number of characters to skip (only works when src and tar are |
|
53
|
|
|
strings) |
|
54
|
|
|
|
|
55
|
|
|
Returns |
|
56
|
|
|
------- |
|
57
|
|
|
tuple of Counters |
|
58
|
|
|
Q-Grams |
|
59
|
|
|
|
|
60
|
|
|
Examples |
|
61
|
|
|
-------- |
|
62
|
|
|
>>> pe = _TokenDistance() |
|
63
|
|
|
>>> pe._get_qgrams('AT', 'TT', qval=2) |
|
64
|
|
|
(QGrams({'$A': 1, 'AT': 1, 'T#': 1}), |
|
65
|
|
|
QGrams({'$T': 1, 'TT': 1, 'T#': 1})) |
|
66
|
|
|
|
|
67
|
|
|
""" |
|
68
|
1 |
|
if isinstance(src, Counter) and isinstance(tar, Counter): |
|
69
|
1 |
|
return src, tar |
|
70
|
1 |
|
if qval > 0: |
|
71
|
1 |
|
return QGrams(src, qval, '$#', skip), QGrams(tar, qval, '$#', skip) |
|
72
|
1 |
|
return Counter(src.strip().split()), Counter(tar.strip().split()) |
|
73
|
|
|
|
|
74
|
|
|
|
|
75
|
|
|
if __name__ == '__main__': |
|
76
|
|
|
import doctest |
|
77
|
|
|
|
|
78
|
|
|
doctest.testmod() |
|
79
|
|
|
|
chrislit /
abydos
