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.phonetic._phonetic. |
20
|
|
|
|
21
|
|
|
The phonetic._phonetic module implements abstract class Phonetic. |
22
|
|
|
""" |
23
|
|
|
|
24
|
1 |
|
from __future__ import unicode_literals |
25
|
|
|
|
26
|
1 |
|
from itertools import groupby |
27
|
|
|
|
28
|
|
|
|
29
|
1 |
|
class Phonetic(object): |
|
|
|
|
30
|
|
|
"""Abstract Phonetic class.""" |
31
|
|
|
|
32
|
1 |
|
_uc_set = set('ABCDEFGHIJKLMNOPQRSTUVWXYZ') |
33
|
1 |
|
_lc_set = set('abcdefghijklmnopqrstuvwxyz') |
34
|
1 |
|
_uc_v_set = set('AEIOU') |
35
|
1 |
|
_lc_v_set = set('aeiou') |
36
|
1 |
|
_uc_vy_set = set('AEIOUY') |
37
|
1 |
|
_lc_vy_set = set('aeiouy') |
38
|
|
|
|
39
|
1 |
|
def _delete_consecutive_repeats(self, word): |
|
|
|
|
40
|
|
|
"""Delete consecutive repeated characters in a word. |
41
|
|
|
|
42
|
|
|
:param str word: the word to transform |
43
|
|
|
:returns: word with consecutive repeating characters collapsed to |
44
|
|
|
a single instance |
45
|
|
|
:rtype: str |
46
|
|
|
|
47
|
|
|
>>> pe = Phonetic() |
48
|
|
|
>>> pe._delete_consecutive_repeats('REDDEE') |
49
|
|
|
'REDE' |
50
|
|
|
>>> pe._delete_consecutive_repeats('AEIOU') |
51
|
|
|
'AEIOU' |
52
|
|
|
>>> pe._delete_consecutive_repeats('AAACCCTTTGGG') |
53
|
|
|
'ACTG' |
54
|
|
|
""" |
55
|
1 |
|
return ''.join(char for char, _ in groupby(word)) |
56
|
|
|
|
57
|
1 |
|
def encode(self, word): |
58
|
|
|
"""Encode phonetically. |
59
|
|
|
|
60
|
|
|
:param word: word to encode |
61
|
|
|
:return: |
62
|
|
|
""" |
63
|
|
|
pass |
64
|
|
|
|
65
|
1 |
|
def encode_alpha(self, word): |
66
|
|
|
"""Encode phonetically using alphabetic characters. |
67
|
|
|
|
68
|
|
|
:param word: word to encode |
69
|
|
|
:return: |
70
|
|
|
""" |
71
|
|
|
return self.encode(word) |
72
|
|
|
|
73
|
|
|
|
74
|
|
|
if __name__ == '__main__': |
75
|
|
|
import doctest |
76
|
|
|
|
77
|
|
|
doctest.testmod() |
78
|
|
|
|