|
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._fonem. |
|
20
|
|
|
|
|
21
|
|
|
FONEM |
|
22
|
|
|
""" |
|
23
|
|
|
|
|
24
|
1 |
|
from __future__ import ( |
|
25
|
|
|
absolute_import, |
|
26
|
|
|
division, |
|
27
|
|
|
print_function, |
|
28
|
|
|
unicode_literals, |
|
29
|
|
|
) |
|
30
|
|
|
|
|
31
|
1 |
|
from re import compile as re_compile |
|
32
|
1 |
|
from unicodedata import normalize as unicode_normalize |
|
33
|
|
|
|
|
34
|
1 |
|
from six import text_type |
|
35
|
|
|
|
|
36
|
1 |
|
from ._phonetic import _Phonetic |
|
37
|
|
|
|
|
38
|
1 |
|
__all__ = ['FONEM', 'fonem'] |
|
39
|
|
|
|
|
40
|
|
|
|
|
41
|
1 |
|
class FONEM(_Phonetic): |
|
|
|
|
|
|
42
|
|
|
"""FONEM. |
|
43
|
|
|
|
|
44
|
|
|
FONEM is a phonetic algorithm designed for French (particularly surnames in |
|
45
|
|
|
Saguenay, Canada), defined in :cite:`Bouchard:1981`. |
|
46
|
|
|
|
|
47
|
|
|
Guillaume Plique's Javascript implementation :cite:`Plique:2018` at |
|
48
|
|
|
https://github.com/Yomguithereal/talisman/blob/master/src/phonetics/french/fonem.js |
|
49
|
|
|
was also consulted for this implementation. |
|
50
|
|
|
""" |
|
51
|
|
|
|
|
52
|
|
|
# I don't see a sane way of doing this without regexps :( |
|
53
|
1 |
|
_rule_table = { |
|
54
|
|
|
# Vowels & groups of vowels |
|
55
|
|
|
'V-1': (re_compile('E?AU'), 'O'), |
|
56
|
|
|
'V-2,5': (re_compile('(E?AU|O)L[TX]$'), 'O'), |
|
57
|
|
|
'V-3,4': (re_compile('E?AU[TX]$'), 'O'), |
|
58
|
|
|
'V-6': (re_compile('E?AUL?D$'), 'O'), |
|
59
|
|
|
'V-7': (re_compile(r'(?<!G)AY$'), 'E'), |
|
60
|
|
|
'V-8': (re_compile('EUX$'), 'EU'), |
|
61
|
|
|
'V-9': (re_compile('EY(?=$|[BCDFGHJKLMNPQRSTVWXZ])'), 'E'), |
|
62
|
|
|
'V-10': ('Y', 'I'), |
|
63
|
|
|
'V-11': (re_compile('(?<=[AEIOUY])I(?=[AEIOUY])'), 'Y'), |
|
64
|
|
|
'V-12': (re_compile('(?<=[AEIOUY])ILL'), 'Y'), |
|
65
|
|
|
'V-13': (re_compile('OU(?=[AEOU]|I(?!LL))'), 'W'), |
|
66
|
|
|
'V-14': (re_compile(r'([AEIOUY])(?=\1)'), ''), |
|
67
|
|
|
# Nasal vowels |
|
68
|
|
|
'V-15': (re_compile('[AE]M(?=[BCDFGHJKLMPQRSTVWXZ])(?!$)'), 'EN'), |
|
69
|
|
|
'V-16': (re_compile('OM(?=[BCDFGHJKLMPQRSTVWXZ])'), 'ON'), |
|
70
|
|
|
'V-17': (re_compile('AN(?=[BCDFGHJKLMNPQRSTVWXZ])'), 'EN'), |
|
71
|
|
|
'V-18': (re_compile('(AI[MN]|EIN)(?=[BCDFGHJKLMNPQRSTVWXZ]|$)'), 'IN'), |
|
72
|
|
|
'V-19': (re_compile('B(O|U|OU)RNE?$'), 'BURN'), |
|
73
|
|
|
'V-20': ( |
|
74
|
|
|
re_compile( |
|
75
|
|
|
'(^IM|(?<=[BCDFGHJKLMNPQRSTVWXZ])' |
|
76
|
|
|
+ 'IM(?=[BCDFGHJKLMPQRSTVWXZ]))' |
|
77
|
|
|
), |
|
78
|
|
|
'IN', |
|
79
|
|
|
), |
|
80
|
|
|
# Consonants and groups of consonants |
|
81
|
|
|
'C-1': ('BV', 'V'), |
|
82
|
|
|
'C-2': (re_compile('(?<=[AEIOUY])C(?=[EIY])'), 'SS'), |
|
83
|
|
|
'C-3': (re_compile('(?<=[BDFGHJKLMNPQRSTVWZ])C(?=[EIY])'), 'S'), |
|
84
|
|
|
'C-4': (re_compile('^C(?=[EIY])'), 'S'), |
|
85
|
|
|
'C-5': (re_compile('^C(?=[OUA])'), 'K'), |
|
86
|
|
|
'C-6': (re_compile('(?<=[AEIOUY])C$'), 'K'), |
|
87
|
|
|
'C-7': (re_compile('C(?=[BDFGJKLMNPQRSTVWXZ])'), 'K'), |
|
88
|
|
|
'C-8': (re_compile('CC(?=[AOU])'), 'K'), |
|
89
|
|
|
'C-9': (re_compile('CC(?=[EIY])'), 'X'), |
|
90
|
|
|
'C-10': (re_compile('G(?=[EIY])'), 'J'), |
|
91
|
|
|
'C-11': (re_compile('GA(?=I?[MN])'), 'G#'), |
|
92
|
|
|
'C-12': (re_compile('GE(O|AU)'), 'JO'), |
|
93
|
|
|
'C-13': (re_compile('GNI(?=[AEIOUY])'), 'GN'), |
|
94
|
|
|
'C-14': (re_compile('(?<![PCS])H'), ''), |
|
95
|
|
|
'C-15': ('JEA', 'JA'), |
|
96
|
|
|
'C-16': (re_compile('^MAC(?=[BCDFGHJKLMNPQRSTVWXZ])'), 'MA#'), |
|
97
|
|
|
'C-17': (re_compile('^MC'), 'MA#'), |
|
98
|
|
|
'C-18': ('PH', 'F'), |
|
99
|
|
|
'C-19': ('QU', 'K'), |
|
100
|
|
|
'C-20': (re_compile('^SC(?=[EIY])'), 'S'), |
|
101
|
|
|
'C-21': (re_compile('(?<=.)SC(?=[EIY])'), 'SS'), |
|
102
|
|
|
'C-22': (re_compile('(?<=.)SC(?=[AOU])'), 'SK'), |
|
103
|
|
|
'C-23': ('SH', 'CH'), |
|
104
|
|
|
'C-24': (re_compile('TIA$'), 'SSIA'), |
|
105
|
|
|
'C-25': (re_compile('(?<=[AIOUY])W'), ''), |
|
106
|
|
|
'C-26': (re_compile('X[CSZ]'), 'X'), |
|
107
|
|
|
'C-27': ( |
|
108
|
|
|
re_compile( |
|
109
|
|
|
'(?<=[AEIOUY])Z|(?<=[BCDFGHJKLMNPQRSTVWXZ])' |
|
110
|
|
|
+ 'Z(?=[BCDFGHJKLMNPQRSTVWXZ])' |
|
111
|
|
|
), |
|
112
|
|
|
'S', |
|
113
|
|
|
), |
|
114
|
|
|
'C-28': (re_compile(r'([BDFGHJKMNPQRTVWXZ])\1'), r'\1'), |
|
115
|
|
|
'C-28a': (re_compile('CC(?=[BCDFGHJKLMNPQRSTVWXZ]|$)'), 'C'), |
|
116
|
|
|
'C-28b': (re_compile('((?<=[BCDFGHJKLMNPQRSTVWXZ])|^)SS'), 'S'), |
|
117
|
|
|
'C-28bb': (re_compile('SS(?=[BCDFGHJKLMNPQRSTVWXZ]|$)'), 'S'), |
|
118
|
|
|
'C-28c': (re_compile('((?<=[^I])|^)LL'), 'L'), |
|
119
|
|
|
'C-28d': (re_compile('ILE$'), 'ILLE'), |
|
120
|
|
|
'C-29': ( |
|
121
|
|
|
re_compile( |
|
122
|
|
|
'(ILS|[CS]H|[MN]P|R[CFKLNSX])$|([BCDFGHJKL' |
|
123
|
|
|
+ 'MNPQRSTVWXZ])[BCDFGHJKLMNPQRSTVWXZ]$' |
|
124
|
|
|
), |
|
125
|
|
|
lambda m: (m.group(1) or '') + (m.group(2) or ''), |
|
126
|
|
|
), |
|
127
|
|
|
'C-30,32': (re_compile('^(SA?INT?|SEI[NM]|CINQ?|ST)(?!E)-?'), 'ST-'), |
|
128
|
|
|
'C-31,33': (re_compile('^(SAINTE|STE)-?'), 'STE-'), |
|
129
|
|
|
# Rules to undo rule bleeding prevention in C-11, C-16, C-17 |
|
130
|
|
|
'C-34': ('G#', 'GA'), |
|
131
|
|
|
'C-35': ('MA#', 'MAC'), |
|
132
|
|
|
} |
|
133
|
1 |
|
_rule_order = ( |
|
134
|
|
|
'V-14', |
|
135
|
|
|
'C-28', |
|
136
|
|
|
'C-28a', |
|
137
|
|
|
'C-28b', |
|
138
|
|
|
'C-28bb', |
|
139
|
|
|
'C-28c', |
|
140
|
|
|
'C-28d', |
|
141
|
|
|
'C-12', |
|
142
|
|
|
'C-8', |
|
143
|
|
|
'C-9', |
|
144
|
|
|
'C-10', |
|
145
|
|
|
'C-16', |
|
146
|
|
|
'C-17', |
|
147
|
|
|
'C-2', |
|
148
|
|
|
'C-3', |
|
149
|
|
|
'C-7', |
|
150
|
|
|
'V-2,5', |
|
151
|
|
|
'V-3,4', |
|
152
|
|
|
'V-6', |
|
153
|
|
|
'V-1', |
|
154
|
|
|
'C-14', |
|
155
|
|
|
'C-31,33', |
|
156
|
|
|
'C-30,32', |
|
157
|
|
|
'C-11', |
|
158
|
|
|
'V-15', |
|
159
|
|
|
'V-17', |
|
160
|
|
|
'V-18', |
|
161
|
|
|
'V-7', |
|
162
|
|
|
'V-8', |
|
163
|
|
|
'V-9', |
|
164
|
|
|
'V-10', |
|
165
|
|
|
'V-11', |
|
166
|
|
|
'V-12', |
|
167
|
|
|
'V-13', |
|
168
|
|
|
'V-16', |
|
169
|
|
|
'V-19', |
|
170
|
|
|
'V-20', |
|
171
|
|
|
'C-1', |
|
172
|
|
|
'C-4', |
|
173
|
|
|
'C-5', |
|
174
|
|
|
'C-6', |
|
175
|
|
|
'C-13', |
|
176
|
|
|
'C-15', |
|
177
|
|
|
'C-18', |
|
178
|
|
|
'C-19', |
|
179
|
|
|
'C-20', |
|
180
|
|
|
'C-21', |
|
181
|
|
|
'C-22', |
|
182
|
|
|
'C-23', |
|
183
|
|
|
'C-24', |
|
184
|
|
|
'C-25', |
|
185
|
|
|
'C-26', |
|
186
|
|
|
'C-27', |
|
187
|
|
|
'C-29', |
|
188
|
|
|
'V-14', |
|
189
|
|
|
'C-28', |
|
190
|
|
|
'C-28a', |
|
191
|
|
|
'C-28b', |
|
192
|
|
|
'C-28bb', |
|
193
|
|
|
'C-28c', |
|
194
|
|
|
'C-28d', |
|
195
|
|
|
'C-34', |
|
196
|
|
|
'C-35', |
|
197
|
|
|
) |
|
198
|
|
|
|
|
199
|
1 |
|
_uc_set = set('ABCDEFGHIJKLMNOPQRSTUVWXYZ-') |
|
200
|
|
|
|
|
201
|
1 |
|
def encode(self, word): |
|
202
|
|
|
"""Return the FONEM code of a word. |
|
203
|
|
|
|
|
204
|
|
|
Parameters |
|
205
|
|
|
---------- |
|
206
|
|
|
word : str |
|
207
|
|
|
The word to transform |
|
208
|
|
|
|
|
209
|
|
|
Returns |
|
210
|
|
|
------- |
|
211
|
|
|
str |
|
212
|
|
|
The FONEM code |
|
213
|
|
|
|
|
214
|
|
|
Examples |
|
215
|
|
|
-------- |
|
216
|
|
|
>>> pe = FONEM() |
|
217
|
|
|
>>> pe.encode('Marchand') |
|
218
|
|
|
'MARCHEN' |
|
219
|
|
|
>>> pe.encode('Beaulieu') |
|
220
|
|
|
'BOLIEU' |
|
221
|
|
|
>>> pe.encode('Beaumont') |
|
222
|
|
|
'BOMON' |
|
223
|
|
|
>>> pe.encode('Legrand') |
|
224
|
|
|
'LEGREN' |
|
225
|
|
|
>>> pe.encode('Pelletier') |
|
226
|
|
|
'PELETIER' |
|
227
|
|
|
|
|
228
|
|
|
""" |
|
229
|
|
|
# normalize, upper-case, and filter non-French letters |
|
230
|
1 |
|
word = unicode_normalize('NFKD', text_type(word.upper())) |
|
231
|
1 |
|
word = word.translate({198: 'AE', 338: 'OE'}) |
|
232
|
1 |
|
word = ''.join(c for c in word if c in self._uc_set) |
|
233
|
|
|
|
|
234
|
1 |
|
for rule in self._rule_order: |
|
235
|
1 |
|
regex, repl = self._rule_table[rule] |
|
236
|
1 |
|
if isinstance(regex, text_type): |
|
237
|
1 |
|
word = word.replace(regex, repl) |
|
238
|
|
|
else: |
|
239
|
1 |
|
word = regex.sub(repl, word) |
|
240
|
|
|
|
|
241
|
1 |
|
return word |
|
242
|
|
|
|
|
243
|
|
|
|
|
244
|
1 |
|
def fonem(word): |
|
245
|
|
|
"""Return the FONEM code of a word. |
|
246
|
|
|
|
|
247
|
|
|
This is a wrapper for :py:meth:`FONEM.encode`. |
|
248
|
|
|
|
|
249
|
|
|
Parameters |
|
250
|
|
|
---------- |
|
251
|
|
|
word : str |
|
252
|
|
|
The word to transform |
|
253
|
|
|
|
|
254
|
|
|
Returns |
|
255
|
|
|
------- |
|
256
|
|
|
str |
|
257
|
|
|
The FONEM code |
|
258
|
|
|
|
|
259
|
|
|
Examples |
|
260
|
|
|
-------- |
|
261
|
|
|
>>> fonem('Marchand') |
|
262
|
|
|
'MARCHEN' |
|
263
|
|
|
>>> fonem('Beaulieu') |
|
264
|
|
|
'BOLIEU' |
|
265
|
|
|
>>> fonem('Beaumont') |
|
266
|
|
|
'BOMON' |
|
267
|
|
|
>>> fonem('Legrand') |
|
268
|
|
|
'LEGREN' |
|
269
|
|
|
>>> fonem('Pelletier') |
|
270
|
|
|
'PELETIER' |
|
271
|
|
|
|
|
272
|
|
|
""" |
|
273
|
1 |
|
return FONEM().encode(word) |
|
274
|
|
|
|
|
275
|
|
|
|
|
276
|
|
|
if __name__ == '__main__': |
|
277
|
|
|
import doctest |
|
278
|
|
|
|
|
279
|
|
|
doctest.testmod() |
|
280
|
|
|
|
chrislit /
abydos
Loading history...