|
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._parmar_kumbharana. |
|
20
|
|
|
|
|
21
|
|
|
The phonetic._parmar_kumbharana module implements the Parmar-Kumbharana |
|
22
|
|
|
phonetic algorithm. |
|
23
|
|
|
""" |
|
24
|
|
|
|
|
25
|
1 |
|
from __future__ import unicode_literals |
|
26
|
|
|
|
|
27
|
1 |
|
from six.moves import range |
|
28
|
|
|
|
|
29
|
1 |
|
from ._util import _delete_consecutive_repeats |
|
30
|
|
|
|
|
31
|
1 |
|
__all__ = ['parmar_kumbharana'] |
|
32
|
|
|
|
|
33
|
|
|
|
|
34
|
1 |
|
def parmar_kumbharana(word): |
|
35
|
|
|
"""Return the Parmar-Kumbharana encoding of a word. |
|
36
|
|
|
|
|
37
|
|
|
This is based on the phonetic algorithm proposed in :cite:`Parmar:2014`. |
|
38
|
|
|
|
|
39
|
|
|
:param str word: the word to transform |
|
40
|
|
|
:returns: the Parmar-Kumbharana encoding |
|
41
|
|
|
:rtype: str |
|
42
|
|
|
|
|
43
|
|
|
>>> parmar_kumbharana('Gough') |
|
44
|
|
|
'GF' |
|
45
|
|
|
>>> parmar_kumbharana('pneuma') |
|
46
|
|
|
'NM' |
|
47
|
|
|
>>> parmar_kumbharana('knight') |
|
48
|
|
|
'NT' |
|
49
|
|
|
>>> parmar_kumbharana('trice') |
|
50
|
|
|
'TRS' |
|
51
|
|
|
>>> parmar_kumbharana('judge') |
|
52
|
|
|
'JJ' |
|
53
|
|
|
""" |
|
54
|
1 |
|
rule_table = { |
|
55
|
|
|
4: {'OUGH': 'F'}, |
|
56
|
|
|
3: {'DGE': 'J', 'OUL': 'U', 'GHT': 'T'}, |
|
57
|
|
|
2: { |
|
58
|
|
|
'CE': 'S', |
|
59
|
|
|
'CI': 'S', |
|
60
|
|
|
'CY': 'S', |
|
61
|
|
|
'GE': 'J', |
|
62
|
|
|
'GI': 'J', |
|
63
|
|
|
'GY': 'J', |
|
64
|
|
|
'WR': 'R', |
|
65
|
|
|
'GN': 'N', |
|
66
|
|
|
'KN': 'N', |
|
67
|
|
|
'PN': 'N', |
|
68
|
|
|
'CK': 'K', |
|
69
|
|
|
'SH': 'S', |
|
70
|
|
|
}, |
|
71
|
|
|
} |
|
72
|
1 |
|
vowel_trans = {65: '', 69: '', 73: '', 79: '', 85: '', 89: ''} |
|
73
|
|
|
|
|
74
|
1 |
|
word = word.upper() # Rule 3 |
|
75
|
1 |
|
word = _delete_consecutive_repeats(word) # Rule 4 |
|
76
|
|
|
|
|
77
|
|
|
# Rule 5 |
|
78
|
1 |
|
i = 0 |
|
79
|
1 |
|
while i < len(word): |
|
80
|
1 |
|
for match_len in range(4, 1, -1): |
|
81
|
1 |
|
if word[i : i + match_len] in rule_table[match_len]: |
|
82
|
1 |
|
repl = rule_table[match_len][word[i : i + match_len]] |
|
83
|
1 |
|
word = word[:i] + repl + word[i + match_len :] |
|
84
|
1 |
|
i += len(repl) |
|
85
|
1 |
|
break |
|
86
|
|
|
else: |
|
87
|
1 |
|
i += 1 |
|
88
|
|
|
|
|
89
|
1 |
|
word = word[:1] + word[1:].translate(vowel_trans) # Rule 6 |
|
90
|
1 |
|
return word |
|
91
|
|
|
|
|
92
|
|
|
|
|
93
|
|
|
if __name__ == '__main__': |
|
94
|
|
|
import doctest |
|
95
|
|
|
|
|
96
|
|
|
doctest.testmod() |
|
97
|
|
|
|
chrislit /
abydos
