|
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._basic. |
|
20
|
|
|
|
|
21
|
|
|
The fingerprint.basic module implements string fingerprints described at |
|
22
|
|
|
:cite:`OpenRefine:2012`: |
|
23
|
|
|
|
|
24
|
|
|
- string fingerprint |
|
25
|
|
|
- q-gram fingerprint |
|
26
|
|
|
- phonetic fingerprint |
|
27
|
|
|
""" |
|
28
|
|
|
|
|
29
|
1 |
|
from __future__ import unicode_literals |
|
30
|
|
|
|
|
31
|
1 |
|
from unicodedata import normalize as unicode_normalize |
|
32
|
|
|
|
|
33
|
1 |
|
from six import text_type |
|
34
|
|
|
|
|
35
|
1 |
|
from ..phonetic import double_metaphone |
|
36
|
1 |
|
from ..tokenizer import QGrams |
|
37
|
|
|
|
|
38
|
1 |
|
__all__ = ['phonetic_fingerprint', 'qgram_fingerprint', 'str_fingerprint'] |
|
39
|
|
|
|
|
40
|
|
|
|
|
41
|
1 |
|
def str_fingerprint(phrase, joiner=' '): |
|
42
|
|
|
"""Return string fingerprint. |
|
43
|
|
|
|
|
44
|
|
|
The fingerprint of a string is a string consisting of all of the unique |
|
45
|
|
|
words in a string, alphabetized & concatenated with intervening joiners. |
|
46
|
|
|
This fingerprint is described at :cite:`OpenRefine:2012`. |
|
47
|
|
|
|
|
48
|
|
|
:param str phrase: the string from which to calculate the fingerprint |
|
49
|
|
|
:param str joiner: the string that will be placed between each word |
|
50
|
|
|
:returns: the fingerprint of the phrase |
|
51
|
|
|
:rtype: str |
|
52
|
|
|
|
|
53
|
|
|
>>> str_fingerprint('The quick brown fox jumped over the lazy dog.') |
|
54
|
|
|
'brown dog fox jumped lazy over quick the' |
|
55
|
|
|
""" |
|
56
|
1 |
|
phrase = unicode_normalize('NFKD', text_type(phrase.strip().lower())) |
|
57
|
1 |
|
phrase = ''.join([c for c in phrase if c.isalnum() or c.isspace()]) |
|
58
|
1 |
|
phrase = joiner.join(sorted(list(set(phrase.split())))) |
|
59
|
1 |
|
return phrase |
|
60
|
|
|
|
|
61
|
|
|
|
|
62
|
1 |
|
def qgram_fingerprint(phrase, qval=2, start_stop='', joiner=''): |
|
63
|
|
|
"""Return Q-Gram fingerprint. |
|
64
|
|
|
|
|
65
|
|
|
A q-gram fingerprint is a string consisting of all of the unique q-grams |
|
66
|
|
|
in a string, alphabetized & concatenated. This fingerprint is described at |
|
67
|
|
|
:cite:`OpenRefine:2012`. |
|
68
|
|
|
|
|
69
|
|
|
:param str phrase: the string from which to calculate the q-gram |
|
70
|
|
|
fingerprint |
|
71
|
|
|
:param int qval: the length of each q-gram (by default 2) |
|
72
|
|
|
:param str start_stop: the start & stop symbol(s) to concatenate on either |
|
73
|
|
|
end of the phrase, as defined in abydos.util.qgram() |
|
74
|
|
|
:param str joiner: the string that will be placed between each word |
|
75
|
|
|
:returns: the q-gram fingerprint of the phrase |
|
76
|
|
|
:rtype: str |
|
77
|
|
|
|
|
78
|
|
|
>>> qgram_fingerprint('The quick brown fox jumped over the lazy dog.') |
|
79
|
|
|
'azbrckdoedeleqerfoheicjukblampnfogovowoxpequrortthuiumvewnxjydzy' |
|
80
|
|
|
>>> qgram_fingerprint('Christopher') |
|
81
|
|
|
'cherhehrisopphristto' |
|
82
|
|
|
>>> qgram_fingerprint('Niall') |
|
83
|
|
|
'aliallni' |
|
84
|
|
|
""" |
|
85
|
1 |
|
phrase = unicode_normalize('NFKD', text_type(phrase.strip().lower())) |
|
86
|
1 |
|
phrase = ''.join(c for c in phrase if c.isalnum()) |
|
87
|
1 |
|
phrase = QGrams(phrase, qval, start_stop) |
|
88
|
1 |
|
phrase = joiner.join(sorted(phrase)) |
|
89
|
1 |
|
return phrase |
|
90
|
|
|
|
|
91
|
|
|
|
|
92
|
1 |
|
def phonetic_fingerprint( |
|
93
|
|
|
phrase, phonetic_algorithm=double_metaphone, joiner=' ', *args |
|
|
|
|
|
|
94
|
|
|
): |
|
95
|
|
|
"""Return the phonetic fingerprint of a phrase. |
|
96
|
|
|
|
|
97
|
|
|
A phonetic fingerprint is identical to a standard string fingerprint, as |
|
98
|
|
|
implemented in abydos.clustering.fingerprint(), but performs the |
|
99
|
|
|
fingerprinting function after converting the string to its phonetic form, |
|
100
|
|
|
as determined by some phonetic algorithm. This fingerprint is described at |
|
101
|
|
|
:cite:`OpenRefine:2012`. |
|
102
|
|
|
|
|
103
|
|
|
:param str phrase: the string from which to calculate the phonetic |
|
104
|
|
|
fingerprint |
|
105
|
|
|
:param function phonetic_algorithm: a phonetic algorithm that takes a |
|
106
|
|
|
string and returns a string (presumably a phonetic representation of |
|
107
|
|
|
the original string) By default, this function uses |
|
108
|
|
|
abydos.phonetic.double_metaphone() |
|
109
|
|
|
:param str joiner: the string that will be placed between each word |
|
110
|
|
|
:param args: additional arguments to pass to the phonetic algorithm, |
|
111
|
|
|
along with the phrase itself |
|
112
|
|
|
:returns: the phonetic fingerprint of the phrase |
|
113
|
|
|
:rtype: str |
|
114
|
|
|
|
|
115
|
|
|
>>> phonetic_fingerprint('The quick brown fox jumped over the lazy dog.') |
|
116
|
|
|
'0 afr fks jmpt kk ls prn tk' |
|
117
|
|
|
>>> from abydos.phonetic import soundex |
|
118
|
|
|
>>> phonetic_fingerprint('The quick brown fox jumped over the lazy dog.', |
|
119
|
|
|
... phonetic_algorithm=soundex) |
|
120
|
|
|
'b650 d200 f200 j513 l200 o160 q200 t000' |
|
121
|
|
|
""" |
|
122
|
1 |
|
phonetic = '' |
|
123
|
1 |
|
for word in phrase.split(): |
|
124
|
1 |
|
word = phonetic_algorithm(word, *args) |
|
125
|
1 |
|
if not isinstance(word, text_type) and hasattr(word, '__iter__'): |
|
126
|
1 |
|
word = word[0] |
|
127
|
1 |
|
phonetic += word + joiner |
|
128
|
1 |
|
phonetic = phonetic[: -len(joiner)] |
|
129
|
1 |
|
return str_fingerprint(phonetic) |
|
130
|
|
|
|
|
131
|
|
|
|
|
132
|
|
|
if __name__ == '__main__': |
|
133
|
|
|
import doctest |
|
134
|
|
|
|
|
135
|
|
|
doctest.testmod() |
|
136
|
|
|
|
chrislit /
abydos
Loading history...