1
|
|
|
# Copyright 2019-2020 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._lc_cutter. |
18
|
|
|
|
19
|
1 |
|
Library of Congress Cutter table encoding |
20
|
|
|
""" |
21
|
|
|
|
22
|
|
|
from ._fingerprint import _Fingerprint |
23
|
|
|
|
24
|
1 |
|
__all__ = ['LCCutter'] |
25
|
|
|
|
26
|
|
|
|
27
|
|
|
class LCCutter(_Fingerprint): |
28
|
|
|
"""Library of Congress Cutter table encoding. |
29
|
|
|
|
30
|
|
|
This is based on the Library of Congress Cutter table encoding scheme, as |
31
|
1 |
|
described at https://www.loc.gov/aba/pcc/053/table.html :cite:`LOC:2013`. |
32
|
|
|
Handling for numerals is not included. |
33
|
1 |
|
|
34
|
|
|
.. versionadded:: 0.4.1 |
35
|
|
|
""" |
36
|
1 |
|
|
37
|
|
|
_vowels = set('AEIOU') |
38
|
|
|
_after_initial_vowel = ['C', 'K', 'M', 'O', 'Q', 'R', 'T'] |
39
|
|
|
_after_initial_s = ['C', 'D', 'G', 'L', 'S', 'T', 'U'] |
40
|
|
|
_after_initial_qu = ['D', 'H', 'N', 'Q', 'S', 'X'] |
41
|
|
|
_after_initial_cons = ['D', 'H', 'N', 'Q', 'T', 'X'] |
42
|
|
|
|
43
|
|
|
_expansions = ['D', 'H', 'L', 'O', 'S', 'V'] |
44
|
|
|
|
45
|
|
|
def __init__(self, max_length: int = 64) -> None: |
46
|
1 |
|
"""Initialize LCCutter instance. |
47
|
1 |
|
|
48
|
1 |
|
Parameters |
49
|
1 |
|
---------- |
50
|
1 |
|
max_length : int |
51
|
|
|
The length of the code returned (defaults to 64) |
52
|
1 |
|
|
53
|
|
|
|
54
|
1 |
|
.. versionadded:: 0.4.1 |
55
|
|
|
|
56
|
|
|
""" |
57
|
|
|
super(LCCutter, self).__init__() |
58
|
|
|
# Require a max_length of at least 2 and not more than 64 |
59
|
|
|
if max_length != -1: |
60
|
|
|
self._max_length = min(max(2, max_length), 64) |
61
|
|
|
else: |
62
|
|
|
self._max_length = 64 |
63
|
|
|
|
64
|
|
|
def fingerprint(self, word: str) -> str: |
65
|
|
|
"""Return the Library of Congress Cutter table encoding of a word. |
66
|
|
|
|
67
|
1 |
|
Parameters |
68
|
1 |
|
---------- |
69
|
|
|
word : str |
70
|
1 |
|
The word to fingerprint |
71
|
|
|
|
72
|
1 |
|
Returns |
73
|
|
|
------- |
74
|
|
|
str |
75
|
|
|
The Library of Congress Cutter table encoding |
76
|
|
|
|
77
|
|
|
Examples |
78
|
|
|
-------- |
79
|
|
|
>>> cf = LCCutter() |
80
|
|
|
>>> cf.fingerprint('hat') |
81
|
|
|
'H38' |
82
|
|
|
>>> cf.fingerprint('niall') |
83
|
|
|
'N5355' |
84
|
|
|
>>> cf.fingerprint('colin') |
85
|
|
|
'C6556' |
86
|
|
|
>>> cf.fingerprint('atcg') |
87
|
|
|
'A834' |
88
|
|
|
>>> cf.fingerprint('entreatment') |
89
|
|
|
'E5874386468' |
90
|
|
|
|
91
|
|
|
|
92
|
|
|
.. versionadded:: 0.4.1 |
93
|
|
|
|
94
|
|
|
""" |
95
|
|
|
# uppercase |
96
|
|
|
uc = ''.join(letter for letter in word.upper() if letter.isalpha()) |
97
|
|
|
|
98
|
|
|
if not uc: |
99
|
|
|
return '' |
100
|
|
|
|
101
|
|
|
code = uc[0] |
102
|
|
|
|
103
|
|
|
# length 1 |
104
|
1 |
|
if len(uc) == 1: |
105
|
|
|
return code |
106
|
1 |
|
|
107
|
1 |
|
# length 2+ |
108
|
|
|
code_list = [code] |
109
|
1 |
|
|
110
|
|
|
# first cutter |
111
|
|
|
pos = 1 |
112
|
1 |
|
if uc[0] in self._vowels: |
113
|
1 |
|
cval = 2 |
114
|
|
|
for letter in self._after_initial_vowel: |
115
|
|
|
if uc[1] > letter: |
116
|
1 |
|
cval += 1 |
117
|
|
|
else: |
118
|
|
|
break |
119
|
1 |
|
elif uc[0] == 'S': |
120
|
1 |
|
cval = 2 |
121
|
1 |
|
for letter in self._after_initial_s: |
122
|
1 |
|
if uc[1] > letter: |
123
|
1 |
|
cval += 1 |
124
|
1 |
|
elif uc[1] == 'C' and uc[1:3] < 'CI': |
125
|
|
|
cval += 1 |
126
|
1 |
|
pos += 1 |
127
|
1 |
|
break |
128
|
1 |
|
else: |
129
|
1 |
|
break |
130
|
1 |
|
elif uc[0:2] == 'QU': |
131
|
1 |
|
cval = 3 |
132
|
1 |
|
pos += 1 |
133
|
1 |
|
for letter in self._after_initial_qu: |
134
|
1 |
|
if uc[2:3] > letter: |
135
|
1 |
|
cval += 1 |
136
|
|
|
else: |
137
|
1 |
|
break |
138
|
1 |
|
elif 'QA' <= uc[0:2] <= 'QT': |
139
|
1 |
|
cval = 2 |
140
|
1 |
|
else: |
141
|
1 |
|
cval = 3 |
142
|
1 |
|
for letter in self._after_initial_cons: |
143
|
1 |
|
if uc[1] > letter: |
144
|
|
|
cval += 1 |
145
|
1 |
|
else: |
146
|
1 |
|
break |
147
|
1 |
|
code_list.append(str(cval)) |
148
|
|
|
|
149
|
1 |
|
# length 3+ |
150
|
1 |
|
for ch in uc[pos + 1 :]: |
151
|
1 |
|
if len(code_list) >= self._max_length: |
152
|
1 |
|
break |
153
|
|
|
cval = 3 |
154
|
1 |
|
for letter in self._expansions: |
155
|
1 |
|
if ch > letter: |
156
|
|
|
cval += 1 |
157
|
|
|
else: |
158
|
1 |
|
break |
159
|
1 |
|
code_list.append(str(cval)) |
160
|
1 |
|
|
161
|
1 |
|
return ''.join(code_list[: self._max_length]) |
162
|
1 |
|
|
163
|
1 |
|
|
164
|
1 |
|
if __name__ == '__main__': |
165
|
|
|
import doctest |
166
|
1 |
|
|
167
|
|
|
doctest.testmod() |
168
|
|
|
|