|
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.fingerprint._phonetic. |
|
18
|
|
|
|
|
19
|
1 |
|
phonetic fingerprint |
|
20
|
|
|
""" |
|
21
|
|
|
|
|
22
|
|
|
from ._string import String |
|
23
|
|
|
from ..phonetic import DoubleMetaphone |
|
24
|
1 |
|
from ..phonetic._phonetic import _Phonetic |
|
25
|
|
|
|
|
26
|
|
|
|
|
27
|
|
|
__all__ = ['Phonetic'] |
|
28
|
|
|
|
|
29
|
|
|
|
|
30
|
|
|
class Phonetic(String): |
|
31
|
1 |
|
"""Phonetic Fingerprint. |
|
32
|
|
|
|
|
33
|
1 |
|
A phonetic fingerprint is identical to a standard string fingerprint, as |
|
34
|
|
|
implemented in :py:class:`.String`, but performs the fingerprinting |
|
35
|
1 |
|
function after converting the string to its phonetic form, as determined by |
|
36
|
1 |
|
some phonetic algorithm. This fingerprint is described at |
|
37
|
1 |
|
:cite:`OpenRefine:2012`. |
|
38
|
1 |
|
|
|
39
|
|
|
.. versionadded:: 0.3.6 |
|
40
|
|
|
""" |
|
41
|
1 |
|
|
|
42
|
|
|
def __init__(self, phonetic_algorithm=None, joiner=' '): |
|
43
|
|
|
"""Initialize Phonetic instance. |
|
44
|
1 |
|
|
|
45
|
|
|
phonetic_algorithm : function |
|
46
|
|
|
A phonetic algorithm that takes a string and returns a string |
|
47
|
|
|
(presumably a phonetic representation of the original string). By |
|
48
|
|
|
default, this function uses :py:func:`.double_metaphone`. |
|
49
|
|
|
joiner : str |
|
50
|
|
|
The string that will be placed between each word |
|
51
|
|
|
|
|
52
|
|
|
|
|
53
|
|
|
.. versionadded:: 0.4.0 |
|
54
|
|
|
|
|
55
|
|
|
""" |
|
56
|
1 |
|
self._phonetic_algorithm = phonetic_algorithm |
|
57
|
|
|
if phonetic_algorithm is None: |
|
58
|
|
|
self._phonetic_algorithm = DoubleMetaphone() |
|
59
|
|
|
|
|
60
|
|
|
self._joiner = joiner |
|
61
|
|
|
|
|
62
|
|
|
def fingerprint(self, phrase): |
|
63
|
|
|
"""Return the phonetic fingerprint of a phrase. |
|
64
|
|
|
|
|
65
|
|
|
Parameters |
|
66
|
|
|
---------- |
|
67
|
|
|
phrase : str |
|
68
|
|
|
The string from which to calculate the phonetic fingerprint |
|
69
|
|
|
|
|
70
|
1 |
|
Returns |
|
71
|
1 |
|
------- |
|
72
|
1 |
|
str |
|
73
|
|
|
The phonetic fingerprint of the phrase |
|
74
|
1 |
|
|
|
75
|
|
|
Examples |
|
76
|
1 |
|
-------- |
|
77
|
|
|
>>> pf = Phonetic() |
|
78
|
|
|
>>> pf.fingerprint('The quick brown fox jumped over the lazy dog.') |
|
79
|
|
|
'0 afr fks jmpt kk ls prn tk' |
|
80
|
|
|
|
|
81
|
|
|
>>> from abydos.phonetic import Soundex |
|
82
|
|
|
>>> pf = Phonetic(Soundex()) |
|
83
|
|
|
>>> pf.fingerprint('The quick brown fox jumped over the lazy dog.') |
|
84
|
|
|
'b650 d200 f200 j513 l200 o160 q200 t000' |
|
85
|
|
|
|
|
86
|
|
|
|
|
87
|
|
|
.. versionadded:: 0.1.0 |
|
88
|
|
|
.. versionchanged:: 0.3.6 |
|
89
|
|
|
Encapsulated in class |
|
90
|
|
|
|
|
91
|
|
|
""" |
|
92
|
|
|
phonetic = '' |
|
93
|
|
|
for word in phrase.split(): |
|
94
|
|
|
if isinstance(self._phonetic_algorithm, _Phonetic): |
|
95
|
|
|
word = self._phonetic_algorithm.encode(word) |
|
96
|
|
|
else: |
|
97
|
|
|
word = self._phonetic_algorithm(word) |
|
98
|
|
|
if not isinstance(word, str) and hasattr(word, '__iter__'): |
|
99
|
|
|
word = word[0] |
|
100
|
|
|
phonetic += word + self._joiner |
|
101
|
|
|
phonetic = phonetic[: -len(self._joiner)] |
|
102
|
|
|
return super(Phonetic, self).fingerprint(phonetic) |
|
103
|
|
|
|
|
104
|
|
|
|
|
105
|
|
|
if __name__ == '__main__': |
|
106
|
1 |
|
import doctest |
|
107
|
1 |
|
|
|
108
|
|
|
doctest.testmod() |
|
109
|
|
|
|
chrislit /
abydos
