|
1
|
|
|
# -*- coding: utf-8 -*- |
|
2
|
|
|
|
|
3
|
|
|
# Copyright 2014-2018 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.fingerprint._speedcop. |
|
20
|
|
|
|
|
21
|
|
|
The fingerprint.speedcop module implements string fingerprints developed by |
|
22
|
|
|
Pollock & Zomora in :cite:`Pollock:1984`: |
|
23
|
|
|
|
|
24
|
|
|
- skeleton key |
|
25
|
|
|
- omission key |
|
26
|
|
|
""" |
|
27
|
|
|
|
|
28
|
1 |
|
from __future__ import unicode_literals |
|
29
|
|
|
|
|
30
|
1 |
|
from unicodedata import normalize as unicode_normalize |
|
31
|
|
|
|
|
32
|
1 |
|
from six import text_type |
|
33
|
|
|
|
|
34
|
1 |
|
__all__ = ['omission_key', 'skeleton_key'] |
|
35
|
|
|
|
|
36
|
|
|
|
|
37
|
1 |
|
def skeleton_key(word): |
|
38
|
|
|
"""Return the skeleton key. |
|
39
|
|
|
|
|
40
|
|
|
The skeleton key of a word is defined in :cite:`Pollock:1984`. |
|
41
|
|
|
|
|
42
|
|
|
:param str word: the word to transform into its skeleton key |
|
43
|
|
|
:returns: the skeleton key |
|
44
|
|
|
:rtype: str |
|
45
|
|
|
|
|
46
|
|
|
>>> skeleton_key('The quick brown fox jumped over the lazy dog.') |
|
47
|
|
|
'THQCKBRWNFXJMPDVLZYGEUIOA' |
|
48
|
|
|
>>> skeleton_key('Christopher') |
|
49
|
|
|
'CHRSTPIOE' |
|
50
|
|
|
>>> skeleton_key('Niall') |
|
51
|
|
|
'NLIA' |
|
52
|
|
|
""" |
|
53
|
1 |
|
_vowels = {'A', 'E', 'I', 'O', 'U'} |
|
54
|
|
|
|
|
55
|
1 |
|
word = unicode_normalize('NFKD', text_type(word.upper())) |
|
56
|
1 |
|
word = ''.join( |
|
57
|
|
|
c |
|
58
|
|
|
for c in word |
|
59
|
|
|
if c |
|
60
|
|
|
in { |
|
61
|
|
|
'A', |
|
62
|
|
|
'B', |
|
63
|
|
|
'C', |
|
64
|
|
|
'D', |
|
65
|
|
|
'E', |
|
66
|
|
|
'F', |
|
67
|
|
|
'G', |
|
68
|
|
|
'H', |
|
69
|
|
|
'I', |
|
70
|
|
|
'J', |
|
71
|
|
|
'K', |
|
72
|
|
|
'L', |
|
73
|
|
|
'M', |
|
74
|
|
|
'N', |
|
75
|
|
|
'O', |
|
76
|
|
|
'P', |
|
77
|
|
|
'Q', |
|
78
|
|
|
'R', |
|
79
|
|
|
'S', |
|
80
|
|
|
'T', |
|
81
|
|
|
'U', |
|
82
|
|
|
'V', |
|
83
|
|
|
'W', |
|
84
|
|
|
'X', |
|
85
|
|
|
'Y', |
|
86
|
|
|
'Z', |
|
87
|
|
|
} |
|
88
|
|
|
) |
|
89
|
1 |
|
start = word[0:1] |
|
90
|
1 |
|
consonant_part = '' |
|
91
|
1 |
|
vowel_part = '' |
|
92
|
|
|
|
|
93
|
|
|
# add consonants & vowels to to separate strings |
|
94
|
|
|
# (omitting the first char & duplicates) |
|
95
|
1 |
|
for char in word[1:]: |
|
96
|
1 |
|
if char != start: |
|
97
|
1 |
|
if char in _vowels: |
|
98
|
1 |
|
if char not in vowel_part: |
|
99
|
1 |
|
vowel_part += char |
|
100
|
1 |
|
elif char not in consonant_part: |
|
101
|
1 |
|
consonant_part += char |
|
102
|
|
|
# return the first char followed by consonants followed by vowels |
|
103
|
1 |
|
return start + consonant_part + vowel_part |
|
104
|
|
|
|
|
105
|
|
|
|
|
106
|
1 |
|
def omission_key(word): |
|
107
|
|
|
"""Return the omission key. |
|
108
|
|
|
|
|
109
|
|
|
The omission key of a word is defined in :cite:`Pollock:1984`. |
|
110
|
|
|
|
|
111
|
|
|
:param str word: the word to transform into its omission key |
|
112
|
|
|
:returns: the omission key |
|
113
|
|
|
:rtype: str |
|
114
|
|
|
|
|
115
|
|
|
>>> omission_key('The quick brown fox jumped over the lazy dog.') |
|
116
|
|
|
'JKQXZVWYBFMGPDHCLNTREUIOA' |
|
117
|
|
|
>>> omission_key('Christopher') |
|
118
|
|
|
'PHCTSRIOE' |
|
119
|
|
|
>>> omission_key('Niall') |
|
120
|
|
|
'LNIA' |
|
121
|
|
|
""" |
|
122
|
1 |
|
_consonants = ( |
|
123
|
|
|
'J', |
|
124
|
|
|
'K', |
|
125
|
|
|
'Q', |
|
126
|
|
|
'X', |
|
127
|
|
|
'Z', |
|
128
|
|
|
'V', |
|
129
|
|
|
'W', |
|
130
|
|
|
'Y', |
|
131
|
|
|
'B', |
|
132
|
|
|
'F', |
|
133
|
|
|
'M', |
|
134
|
|
|
'G', |
|
135
|
|
|
'P', |
|
136
|
|
|
'D', |
|
137
|
|
|
'H', |
|
138
|
|
|
'C', |
|
139
|
|
|
'L', |
|
140
|
|
|
'N', |
|
141
|
|
|
'T', |
|
142
|
|
|
'S', |
|
143
|
|
|
'R', |
|
144
|
|
|
) |
|
145
|
|
|
|
|
146
|
1 |
|
word = unicode_normalize('NFKD', text_type(word.upper())) |
|
147
|
1 |
|
word = ''.join( |
|
148
|
|
|
c |
|
149
|
|
|
for c in word |
|
150
|
|
|
if c |
|
151
|
|
|
in { |
|
152
|
|
|
'A', |
|
153
|
|
|
'B', |
|
154
|
|
|
'C', |
|
155
|
|
|
'D', |
|
156
|
|
|
'E', |
|
157
|
|
|
'F', |
|
158
|
|
|
'G', |
|
159
|
|
|
'H', |
|
160
|
|
|
'I', |
|
161
|
|
|
'J', |
|
162
|
|
|
'K', |
|
163
|
|
|
'L', |
|
164
|
|
|
'M', |
|
165
|
|
|
'N', |
|
166
|
|
|
'O', |
|
167
|
|
|
'P', |
|
168
|
|
|
'Q', |
|
169
|
|
|
'R', |
|
170
|
|
|
'S', |
|
171
|
|
|
'T', |
|
172
|
|
|
'U', |
|
173
|
|
|
'V', |
|
174
|
|
|
'W', |
|
175
|
|
|
'X', |
|
176
|
|
|
'Y', |
|
177
|
|
|
'Z', |
|
178
|
|
|
} |
|
179
|
|
|
) |
|
180
|
|
|
|
|
181
|
1 |
|
key = '' |
|
182
|
|
|
|
|
183
|
|
|
# add consonants in order supplied by _consonants (no duplicates) |
|
184
|
1 |
|
for char in _consonants: |
|
185
|
1 |
|
if char in word: |
|
186
|
1 |
|
key += char |
|
187
|
|
|
|
|
188
|
|
|
# add vowels in order they appeared in the word (no duplicates) |
|
189
|
1 |
|
for char in word: |
|
190
|
1 |
|
if char not in _consonants and char not in key: |
|
191
|
1 |
|
key += char |
|
192
|
|
|
|
|
193
|
1 |
|
return key |
|
194
|
|
|
|
|
195
|
|
|
|
|
196
|
|
|
if __name__ == '__main__': |
|
197
|
|
|
import doctest |
|
198
|
|
|
|
|
199
|
|
|
doctest.testmod() |
|
200
|
|
|
|
chrislit /
abydos
