|
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. |
|
20
|
|
|
|
|
21
|
|
|
Taft's extract letter list 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__ = ['Extract'] |
|
34
|
|
|
|
|
35
|
|
|
|
|
36
|
1 |
|
class Extract(_Fingerprint): |
|
37
|
|
|
"""Extract Letter List fingerprint. |
|
38
|
|
|
|
|
39
|
|
|
Based on the extract letter list coding from :cite:`Taft:1970`, |
|
40
|
|
|
for lists 1, 2, 3, & 4. |
|
41
|
|
|
|
|
42
|
|
|
.. versionadded:: 0.4.1 |
|
43
|
|
|
""" |
|
44
|
|
|
|
|
45
|
1 |
|
def __init__(self, letter_list=1): |
|
46
|
|
|
"""Initialize Extract instance. |
|
47
|
|
|
|
|
48
|
|
|
Parameters |
|
49
|
|
|
---------- |
|
50
|
|
|
letter_list : int or iterable |
|
51
|
|
|
If an integer (1-4) is supplied, Taft's specified letter lists are |
|
52
|
|
|
used. If an iterable is supplied, its values will be used as the |
|
53
|
|
|
list of letters to remove (in order). |
|
54
|
|
|
|
|
55
|
|
|
|
|
56
|
|
|
.. versionadded:: 0.4.1 |
|
57
|
|
|
|
|
58
|
|
|
""" |
|
59
|
1 |
|
letter_lists = [ |
|
60
|
|
|
'ETAONRISHDLFCMUGYPWBVKXJQZ', |
|
61
|
|
|
'ETASIONRHCDLPMFBUWGYKVJQZX', |
|
62
|
|
|
'ETAONISRHLDCUMFYWGPKBVXJQZ', |
|
63
|
|
|
'EARNLOISTHDMCBGUWYJKPFVZXQ', |
|
64
|
|
|
] |
|
65
|
|
|
|
|
66
|
1 |
|
super(_Fingerprint, self).__init__() |
|
67
|
1 |
|
self._letter_list = letter_list |
|
68
|
1 |
|
if isinstance(self._letter_list, int) and 1 <= self._letter_list <= 4: |
|
69
|
1 |
|
self._letter_list = list(letter_lists[self._letter_list - 1]) |
|
70
|
1 |
|
elif hasattr(self._letter_list, '__getitem__'): |
|
71
|
|
|
# TODO: revert the above to __iter__ after removing Py2.7 support |
|
72
|
1 |
|
self._letter_list = list(self._letter_list) |
|
73
|
|
|
else: |
|
74
|
1 |
|
self._letter_list = list(letter_lists[0]) |
|
75
|
|
|
|
|
76
|
1 |
|
def fingerprint(self, word): |
|
77
|
|
|
"""Return the extract letter list coding. |
|
78
|
|
|
|
|
79
|
|
|
Parameters |
|
80
|
|
|
---------- |
|
81
|
|
|
word : str |
|
82
|
|
|
The word to fingerprint |
|
83
|
|
|
|
|
84
|
|
|
Returns |
|
85
|
|
|
------- |
|
86
|
|
|
int |
|
87
|
|
|
The extract letter list coding |
|
88
|
|
|
|
|
89
|
|
|
Examples |
|
90
|
|
|
-------- |
|
91
|
|
|
>>> fp = Extract() |
|
92
|
|
|
>>> fp.fingerprint('hat') |
|
93
|
|
|
'HAT' |
|
94
|
|
|
>>> fp.fingerprint('niall') |
|
95
|
|
|
'NILL' |
|
96
|
|
|
>>> fp.fingerprint('colin') |
|
97
|
|
|
'CLIN' |
|
98
|
|
|
>>> fp.fingerprint('atcg') |
|
99
|
|
|
'ATCG' |
|
100
|
|
|
>>> fp.fingerprint('entreatment') |
|
101
|
|
|
'NRMN' |
|
102
|
|
|
|
|
103
|
|
|
|
|
104
|
|
|
.. versionadded:: 0.4.1 |
|
105
|
|
|
|
|
106
|
|
|
""" |
|
107
|
|
|
# uppercase & reverse |
|
108
|
1 |
|
word = word.upper()[::-1] |
|
109
|
|
|
|
|
110
|
1 |
|
for letter in self._letter_list: # pragma: no branch |
|
111
|
1 |
|
if len(word) < 5: |
|
112
|
1 |
|
break |
|
113
|
|
|
|
|
114
|
1 |
|
count = word.count(letter) |
|
115
|
1 |
|
if count: |
|
116
|
1 |
|
word = word.replace( |
|
117
|
|
|
letter, '', count - (4 - (len(word) - count)) |
|
118
|
|
|
) |
|
119
|
|
|
|
|
120
|
1 |
|
return word[::-1] |
|
121
|
|
|
|
|
122
|
|
|
|
|
123
|
|
|
if __name__ == '__main__': |
|
124
|
|
|
import doctest |
|
125
|
|
|
|
|
126
|
|
|
doctest.testmod() |
|
127
|
|
|
|
chrislit /
abydos
