1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
|
/* ----------------------------------------------------------------- */
/* The Japanese TTS System "Open JTalk" */
/* developed by HTS Working Group */
/* http://open-jtalk.sourceforge.net/ */
/* ----------------------------------------------------------------- */
/* */
/* Copyright (c) 2008-2016 Nagoya Institute of Technology */
/* Department of Computer Science */
/* */
/* All rights reserved. */
/* */
/* Redistribution and use in source and binary forms, with or */
/* without modification, are permitted provided that the following */
/* conditions are met: */
/* */
/* - Redistributions of source code must retain the above copyright */
/* notice, this list of conditions and the following disclaimer. */
/* - Redistributions in binary form must reproduce the above */
/* copyright notice, this list of conditions and the following */
/* disclaimer in the documentation and/or other materials provided */
/* with the distribution. */
/* - Neither the name of the HTS working group nor the names of its */
/* contributors may be used to endorse or promote products derived */
/* from this software without specific prior written permission. */
/* */
/* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND */
/* CONTRIBUTORS "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, */
/* INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF */
/* MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE */
/* DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS */
/* BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, */
/* EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED */
/* TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, */
/* DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON */
/* ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, */
/* OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY */
/* OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE */
/* POSSIBILITY OF SUCH DAMAGE. */
/* ----------------------------------------------------------------- */
#ifndef NJD_SET_ACCENT_PHRASE_C
#define NJD_SET_ACCENT_PHRASE_C
#ifdef __cplusplus
#define NJD_SET_ACCENT_PHRASE_C_START extern "C" {
#define NJD_SET_ACCENT_PHRASE_C_END }
#else
#define NJD_SET_ACCENT_PHRASE_C_START
#define NJD_SET_ACCENT_PHRASE_C_END
#endif /* __CPLUSPLUS */
NJD_SET_ACCENT_PHRASE_C_START;
#include <stdio.h>
#include <string.h>
#include "njd.h"
#include "njd_set_accent_phrase.h"
#ifdef ASCII_HEADER
#if defined(CHARSET_EUC_JP)
#include "njd_set_accent_phrase_rule_ascii_for_euc_jp.h"
#elif defined(CHARSET_SHIFT_JIS)
#include "njd_set_accent_phrase_rule_ascii_for_shift_jis.h"
#elif defined(CHARSET_UTF_8)
#include "njd_set_accent_phrase_rule_ascii_for_utf_8.h"
#else
#error CHARSET is not specified
#endif
#else
#if defined(CHARSET_EUC_JP)
#include "njd_set_accent_phrase_rule_euc_jp.h"
#elif defined(CHARSET_SHIFT_JIS)
#include "njd_set_accent_phrase_rule_shift_jis.h"
#elif defined(CHARSET_UTF_8)
#include "njd_set_accent_phrase_rule_utf_8.h"
#else
#error CHARSET is not specified
#endif
#endif
static int strtopcmp(const char *str, const char *pattern)
{
int i;
for (i = 0;; i++) {
if (pattern[i] == '\0')
return i;
if (str[i] == '\0')
return -1;
if (str[i] != pattern[i])
return -1;
}
}
void njd_set_accent_phrase(NJD * njd)
{
NJDNode *node;
if (njd == NULL || njd->head == NULL)
return;
for (node = njd->head->next; node != NULL; node = node->next) {
if (NJDNode_get_chain_flag(node) < 0) {
/* Rule 01 */
NJDNode_set_chain_flag(node, 1);
/* Rule 02 */
if (strcmp(NJDNode_get_pos(node->prev), NJD_SET_ACCENT_PHRASE_MEISHI) == 0)
if (strcmp(NJDNode_get_pos(node), NJD_SET_ACCENT_PHRASE_MEISHI) == 0)
NJDNode_set_chain_flag(node, 1);
/* Rule 03 */
if (strcmp(NJDNode_get_pos(node->prev), NJD_SET_ACCENT_PHRASE_KEIYOUSHI) == 0)
if (strcmp(NJDNode_get_pos(node), NJD_SET_ACCENT_PHRASE_MEISHI) == 0)
NJDNode_set_chain_flag(node, 0);
/* Rule 04 */
if (strcmp(NJDNode_get_pos(node->prev), NJD_SET_ACCENT_PHRASE_MEISHI) == 0)
if (strcmp
(NJDNode_get_pos_group1(node->prev), NJD_SET_ACCENT_PHRASE_KEIYOUDOUSHI_GOKAN) == 0)
if (strcmp(NJDNode_get_pos(node), NJD_SET_ACCENT_PHRASE_MEISHI) == 0)
NJDNode_set_chain_flag(node, 0);
/* Rule 05 */
if (strcmp(NJDNode_get_pos(node->prev), NJD_SET_ACCENT_PHRASE_DOUSHI) == 0) {
if (strcmp(NJDNode_get_pos(node), NJD_SET_ACCENT_PHRASE_KEIYOUSHI) == 0)
NJDNode_set_chain_flag(node, 0);
else if (strcmp(NJDNode_get_pos(node), NJD_SET_ACCENT_PHRASE_MEISHI) == 0)
NJDNode_set_chain_flag(node, 0);
}
/* Rule 06 */
if (strcmp(NJDNode_get_pos(node), NJD_SET_ACCENT_PHRASE_FUKUSHI) == 0
|| strcmp(NJDNode_get_pos(node->prev), NJD_SET_ACCENT_PHRASE_FUKUSHI) == 0
|| strcmp(NJDNode_get_pos(node), NJD_SET_ACCENT_PHRASE_SETSUZOKUSHI) == 0
|| strcmp(NJDNode_get_pos(node->prev), NJD_SET_ACCENT_PHRASE_SETSUZOKUSHI) == 0
|| strcmp(NJDNode_get_pos(node), NJD_SET_ACCENT_PHRASE_RENTAISHI) == 0
|| strcmp(NJDNode_get_pos(node->prev), NJD_SET_ACCENT_PHRASE_RENTAISHI) == 0)
NJDNode_set_chain_flag(node, 0);
/* Rule 07 */
if (strcmp(NJDNode_get_pos(node->prev), NJD_SET_ACCENT_PHRASE_MEISHI) == 0)
if (strcmp(NJDNode_get_pos_group1(node->prev), NJD_SET_ACCENT_PHRASE_FUKUSHI_KANOU)
== 0)
NJDNode_set_chain_flag(node, 0);
if (strcmp(NJDNode_get_pos(node), NJD_SET_ACCENT_PHRASE_MEISHI) == 0)
if (strcmp(NJDNode_get_pos_group1(node), NJD_SET_ACCENT_PHRASE_FUKUSHI_KANOU) == 0)
NJDNode_set_chain_flag(node, 0);
/* Rule 08 */
if (strcmp(NJDNode_get_pos(node), NJD_SET_ACCENT_PHRASE_JODOUSHI) == 0)
NJDNode_set_chain_flag(node, 1);
if (strcmp(NJDNode_get_pos(node), NJD_SET_ACCENT_PHRASE_JOSHI) == 0)
NJDNode_set_chain_flag(node, 1);
/* Rule 09 */
if (strcmp(NJDNode_get_pos(node->prev), NJD_SET_ACCENT_PHRASE_JODOUSHI) == 0)
if (strcmp(NJDNode_get_pos(node), NJD_SET_ACCENT_PHRASE_JODOUSHI) != 0 &&
strcmp(NJDNode_get_pos(node), NJD_SET_ACCENT_PHRASE_JOSHI) != 0)
NJDNode_set_chain_flag(node, 0);
if (strcmp(NJDNode_get_pos(node->prev), NJD_SET_ACCENT_PHRASE_JOSHI) == 0)
if (strcmp(NJDNode_get_pos(node), NJD_SET_ACCENT_PHRASE_JODOUSHI) != 0 &&
strcmp(NJDNode_get_pos(node), NJD_SET_ACCENT_PHRASE_JOSHI) != 0)
NJDNode_set_chain_flag(node, 0);
/* Rule 10 */
if (strcmp(NJDNode_get_pos_group1(node->prev), NJD_SET_ACCENT_PHRASE_SETSUBI) == 0)
if (strcmp(NJDNode_get_pos(node), NJD_SET_ACCENT_PHRASE_MEISHI) == 0)
NJDNode_set_chain_flag(node, 0);
/* Rule 11 */
if (strcmp(NJDNode_get_pos(node), NJD_SET_ACCENT_PHRASE_KEIYOUSHI) == 0)
if (strcmp(NJDNode_get_pos_group1(node), NJD_SET_ACCENT_PHRASE_HIJIRITSU) == 0) {
if (strcmp(NJDNode_get_pos(node->prev), NJD_SET_ACCENT_PHRASE_DOUSHI) == 0) {
if (strtopcmp(NJDNode_get_cform(node->prev), NJD_SET_ACCENT_PHRASE_RENYOU) != -1)
NJDNode_set_chain_flag(node, 1);
} else if (strcmp(NJDNode_get_pos(node->prev), NJD_SET_ACCENT_PHRASE_KEIYOUSHI)
== 0) {
if (strtopcmp(NJDNode_get_cform(node->prev), NJD_SET_ACCENT_PHRASE_RENYOU) != -1)
NJDNode_set_chain_flag(node, 1);
} else if (strcmp(NJDNode_get_pos(node->prev), NJD_SET_ACCENT_PHRASE_JOSHI) == 0) {
if (strcmp
(NJDNode_get_pos_group1(node->prev),
NJD_SET_ACCENT_PHRASE_SETSUZOKUJOSHI) == 0) {
if (strcmp(NJDNode_get_string(node->prev), NJD_SET_ACCENT_PHRASE_TE) == 0)
NJDNode_set_chain_flag(node, 1);
else if (strcmp(NJDNode_get_string(node->prev), NJD_SET_ACCENT_PHRASE_DE) == 0)
NJDNode_set_chain_flag(node, 1);
}
}
}
/* Rule 12 */
if (strcmp(NJDNode_get_pos(node), NJD_SET_ACCENT_PHRASE_DOUSHI) == 0)
if (strcmp(NJDNode_get_pos_group1(node), NJD_SET_ACCENT_PHRASE_HIJIRITSU) == 0) {
if (strcmp(NJDNode_get_pos(node->prev), NJD_SET_ACCENT_PHRASE_DOUSHI) == 0) {
if (strtopcmp(NJDNode_get_cform(node->prev), NJD_SET_ACCENT_PHRASE_RENYOU) != -1)
NJDNode_set_chain_flag(node, 1);
} else if (strcmp(NJDNode_get_pos(node->prev), NJD_SET_ACCENT_PHRASE_MEISHI) == 0) {
if (strcmp
(NJDNode_get_pos_group1(node->prev),
NJD_SET_ACCENT_PHRASE_SAHEN_SETSUZOKU) == 0)
NJDNode_set_chain_flag(node, 1);
}
}
/* Rule 13 */
if (strcmp(NJDNode_get_pos(node->prev), NJD_SET_ACCENT_PHRASE_MEISHI) == 0) {
if (strcmp(NJDNode_get_pos(node), NJD_SET_ACCENT_PHRASE_DOUSHI) == 0 ||
strcmp(NJDNode_get_pos(node), NJD_SET_ACCENT_PHRASE_KEIYOUSHI) == 0 ||
strcmp(NJDNode_get_pos_group1(node), NJD_SET_ACCENT_PHRASE_KEIYOUDOUSHI_GOKAN) == 0)
NJDNode_set_chain_flag(node, 0);
}
/* Rule 14 */
if (strcmp(NJDNode_get_pos(node), NJD_SET_ACCENT_PHRASE_KIGOU) == 0 ||
strcmp(NJDNode_get_pos(node->prev), NJD_SET_ACCENT_PHRASE_KIGOU) == 0)
NJDNode_set_chain_flag(node, 0);
/* Rule 15 */
if (strcmp(NJDNode_get_pos(node), NJD_SET_ACCENT_PHRASE_SETTOUSHI) == 0)
NJDNode_set_chain_flag(node, 0);
/* Rule 16 */
if (strcmp(NJDNode_get_pos_group3(node->prev), NJD_SET_ACCENT_PHRASE_SEI) == 0
&& strcmp(NJDNode_get_pos(node), NJD_SET_ACCENT_PHRASE_MEISHI) == 0)
NJDNode_set_chain_flag(node, 0);
/* Rule 17 */
if (strcmp(NJDNode_get_pos(node->prev), NJD_SET_ACCENT_PHRASE_MEISHI) == 0
&& strcmp(NJDNode_get_pos_group3(node), NJD_SET_ACCENT_PHRASE_MEI) == 0)
NJDNode_set_chain_flag(node, 0);
/* Rule 18 */
if (strcmp(NJDNode_get_pos_group1(node), NJD_SET_ACCENT_PHRASE_SETSUBI) == 0)
NJDNode_set_chain_flag(node, 1);
}
}
}
NJD_SET_ACCENT_PHRASE_C_END;
#endif /* !NJD_SET_ACCENT_PHRASE_C */
|
