1
|
|
|
# Copyright 2014-2020 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.distance._ncd_lzma. |
18
|
|
|
|
19
|
1 |
|
NCD using LZMA |
20
|
|
|
""" |
21
|
|
|
|
22
|
|
|
import lzma |
23
|
|
|
|
24
|
1 |
|
from typing import Any |
25
|
|
|
|
26
|
|
|
from ._distance import _Distance |
27
|
|
|
|
28
|
|
|
|
29
|
|
|
__all__ = ['NCDlzma'] |
30
|
|
|
|
31
|
1 |
|
|
32
|
|
|
class NCDlzma(_Distance): |
33
|
1 |
|
"""Normalized Compression Distance using LZMA compression. |
34
|
1 |
|
|
35
|
|
|
Cf. https://en.wikipedia.org/wiki/Lempel-Ziv-Markov_chain_algorithm |
36
|
1 |
|
|
37
|
1 |
|
Normalized compression distance (NCD) :cite:`Cilibrasi:2005`. |
38
|
|
|
|
39
|
|
|
.. versionadded:: 0.3.6 |
40
|
|
|
""" |
41
|
|
|
|
42
|
|
|
_level = 6 |
43
|
1 |
|
|
44
|
|
|
def __init__(self, level: int = 6, **kwargs: Any) -> None: |
45
|
|
|
"""Initialize LZMA compressor. |
46
|
1 |
|
|
47
|
|
|
Parameters |
48
|
|
|
---------- |
49
|
|
|
level : int |
50
|
|
|
The compression level (0 to 9) |
51
|
|
|
|
52
|
|
|
|
53
|
|
|
.. versionadded:: 0.5.0 |
54
|
|
|
|
55
|
|
|
""" |
56
|
1 |
|
super().__init__(**kwargs) |
57
|
|
|
self._level = level |
58
|
|
|
|
59
|
|
|
def dist(self, src: str, tar: str) -> float: |
60
|
|
|
"""Return the NCD between two strings using LZMA compression. |
61
|
|
|
|
62
|
|
|
Parameters |
63
|
|
|
---------- |
64
|
|
|
src : str |
65
|
|
|
Source string for comparison |
66
|
|
|
tar : str |
67
|
|
|
Target string for comparison |
68
|
|
|
|
69
|
|
|
Returns |
70
|
|
|
------- |
71
|
|
|
float |
72
|
|
|
Compression distance |
73
|
|
|
|
74
|
|
|
Examples |
75
|
|
|
-------- |
76
|
|
|
>>> cmp = NCDlzma() |
77
|
|
|
>>> cmp.dist('cat', 'hat') |
78
|
|
|
0.08695652173913043 |
79
|
|
|
>>> cmp.dist('Niall', 'Neil') |
80
|
|
|
0.16 |
81
|
|
|
>>> cmp.dist('aluminum', 'Catalan') |
82
|
|
|
0.16 |
83
|
|
|
>>> cmp.dist('ATCG', 'TAGC') |
84
|
|
|
0.08695652173913043 |
85
|
|
|
|
86
|
|
|
|
87
|
|
|
.. versionadded:: 0.3.5 |
88
|
|
|
.. versionchanged:: 0.3.6 |
89
|
|
|
Encapsulated in class |
90
|
|
|
|
91
|
|
|
""" |
92
|
|
|
if src == tar: |
93
|
|
|
return 0.0 |
94
|
|
|
|
95
|
|
|
src_b = src.encode('utf-8') |
96
|
|
|
tar_b = tar.encode('utf-8') |
97
|
|
|
|
98
|
|
|
src_comp = lzma.compress(src_b, preset=self._level)[14:] |
99
|
|
|
tar_comp = lzma.compress(tar_b, preset=self._level)[14:] |
100
|
|
|
concat_comp = lzma.compress(src_b + tar_b, preset=self._level)[14:] |
101
|
|
|
concat_comp2 = lzma.compress(tar_b + src_b, preset=self._level)[14:] |
102
|
|
|
|
103
|
|
|
return ( |
104
|
|
|
min(len(concat_comp), len(concat_comp2)) |
105
|
|
|
- min(len(src_comp), len(tar_comp)) |
106
|
|
|
) / max(len(src_comp), len(tar_comp)) |
107
|
|
|
|
108
|
|
|
|
109
|
|
|
if __name__ == '__main__': |
110
|
|
|
import doctest |
111
|
|
|
|
112
|
|
|
doctest.testmod() |
113
|
|
|
|