|
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._consonant. |
|
20
|
|
|
|
|
21
|
|
|
Taft's consonant coding |
|
22
|
|
|
""" |
|
23
|
|
|
|
|
24
|
1 |
|
from __future__ import ( |
|
25
|
|
|
absolute_import, |
|
26
|
|
|
division, |
|
27
|
|
|
print_function, |
|
28
|
|
|
unicode_literals, |
|
29
|
|
|
) |
|
30
|
|
|
|
|
31
|
1 |
|
from itertools import groupby |
|
32
|
|
|
|
|
33
|
1 |
|
from ._fingerprint import _Fingerprint |
|
34
|
|
|
|
|
35
|
1 |
|
__all__ = ['Consonant'] |
|
36
|
|
|
|
|
37
|
|
|
|
|
38
|
1 |
|
class Consonant(_Fingerprint): |
|
39
|
|
|
"""Consonant Coding Fingerprint. |
|
40
|
|
|
|
|
41
|
|
|
Based on the consonant coding from :cite:`Taft:1970`, variants 1, 2, 3, |
|
42
|
|
|
1-D, 2-D, and 3-D. |
|
43
|
|
|
|
|
44
|
|
|
.. versionadded:: 0.4.1 |
|
45
|
|
|
""" |
|
46
|
|
|
|
|
47
|
1 |
|
def __init__(self, variant=1, doubles=True, vowels=None): |
|
48
|
|
|
"""Initialize Consonant instance. |
|
49
|
|
|
|
|
50
|
|
|
Parameters |
|
51
|
|
|
---------- |
|
52
|
|
|
variant : int |
|
53
|
|
|
Selects between Taft's 3 variants, which assign to the vowel set |
|
54
|
|
|
one of: |
|
55
|
|
|
|
|
56
|
|
|
1. A, E, I, O, & U |
|
57
|
|
|
2. A, E, I, O, U, W, & Y |
|
58
|
|
|
3. A, E, I, O, U, W, H, & Y |
|
59
|
|
|
|
|
60
|
|
|
doubles : bool |
|
61
|
|
|
If set to False, multiple consonants in a row are conflated to a |
|
62
|
|
|
single instance. |
|
63
|
|
|
vowels : list, set, or str |
|
64
|
|
|
Setting vowels to a non-None value overrides the variant setting |
|
65
|
|
|
and defines the set of letters to be removed from the input. |
|
66
|
|
|
|
|
67
|
|
|
|
|
68
|
|
|
.. versionadded:: 0.4.1 |
|
69
|
|
|
|
|
70
|
|
|
""" |
|
71
|
1 |
|
super(_Fingerprint, self).__init__() |
|
72
|
1 |
|
self._vowels = vowels |
|
73
|
1 |
|
self._doubles = doubles |
|
74
|
|
|
|
|
75
|
1 |
|
if self._vowels is None: |
|
76
|
1 |
|
self._vowels = set('AEIOU') |
|
77
|
1 |
|
if variant > 1: |
|
78
|
1 |
|
self._vowels.add('W') |
|
79
|
1 |
|
self._vowels.add('Y') |
|
80
|
1 |
|
if variant > 2: |
|
81
|
1 |
|
self._vowels.add('H') |
|
82
|
|
|
else: |
|
83
|
1 |
|
self._vowels = {_.upper() for _ in self._vowels} |
|
84
|
|
|
|
|
85
|
1 |
|
def fingerprint(self, word): |
|
86
|
|
|
"""Return the consonant coding. |
|
87
|
|
|
|
|
88
|
|
|
Parameters |
|
89
|
|
|
---------- |
|
90
|
|
|
word : str |
|
91
|
|
|
The word to fingerprint |
|
92
|
|
|
|
|
93
|
|
|
Returns |
|
94
|
|
|
------- |
|
95
|
|
|
int |
|
96
|
|
|
The consonant coding |
|
97
|
|
|
|
|
98
|
|
|
Examples |
|
99
|
|
|
-------- |
|
100
|
|
|
>>> cf = Consonant() |
|
101
|
|
|
>>> cf.fingerprint('hat') |
|
102
|
|
|
'HT' |
|
103
|
|
|
>>> cf.fingerprint('niall') |
|
104
|
|
|
'NLL' |
|
105
|
|
|
>>> cf.fingerprint('colin') |
|
106
|
|
|
'CLN' |
|
107
|
|
|
>>> cf.fingerprint('atcg') |
|
108
|
|
|
'ATCG' |
|
109
|
|
|
>>> cf.fingerprint('entreatment') |
|
110
|
|
|
'ENTRTMNT' |
|
111
|
|
|
|
|
112
|
|
|
|
|
113
|
|
|
.. versionadded:: 0.4.1 |
|
114
|
|
|
|
|
115
|
|
|
""" |
|
116
|
|
|
# uppercase |
|
117
|
1 |
|
word = word.upper() |
|
118
|
|
|
|
|
119
|
|
|
# remove repeats if in -D variant |
|
120
|
1 |
|
if not self._doubles: |
|
121
|
1 |
|
word = ''.join(char for char, _ in groupby(word)) |
|
122
|
|
|
|
|
123
|
|
|
# remove vowels |
|
124
|
1 |
|
word = word[:1] + ''.join(_ for _ in word[1:] if _ not in self._vowels) |
|
125
|
|
|
|
|
126
|
1 |
|
return word |
|
127
|
|
|
|
|
128
|
|
|
|
|
129
|
|
|
if __name__ == '__main__': |
|
130
|
|
|
import doctest |
|
131
|
|
|
|
|
132
|
|
|
doctest.testmod() |
|
133
|
|
|
|
chrislit /
abydos
