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
|
/* コーパスから遷移行列を作るためのコード
*
* Copyright (C) 2005-2006 TABATA Yusuke
* Copyright (C) 2005-2006 YOSHIDA Yuichi
*
*/
/*
This library is free software; you can redistribute it and/or
modify it under the terms of the GNU Lesser General Public
License as published by the Free Software Foundation; either
version 2 of the License, or (at your option) any later version.
This library is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
Lesser General Public License for more details.
You should have received a copy of the GNU Lesser General Public
License along with this library; if not, write to the Free Software
Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*/
#include <stdio.h>
#include <string.h>
#include <stdlib.h>
#include <anthy/anthy.h>
/* for print_context_info() */
#include <anthy/convdb.h>
struct test_context {
anthy_context_t ac;
};
static void read_file(struct test_context *tc, const char *fn);
extern void anthy_reload_record(void);
int verbose;
int use_utf8;
/**/
static void
init_test_context(struct test_context *tc)
{
tc->ac = anthy_create_context();
anthy_set_reconversion_mode(tc->ac, ANTHY_RECONVERT_ALWAYS);
if (use_utf8) {
anthy_context_set_encoding(tc->ac, ANTHY_UTF8_ENCODING);
}
anthy_reload_record();
}
static void
conv_sentence(struct test_context *tc, const char *str)
{
anthy_set_string(tc->ac, str);
if (verbose) {
anthy_print_context(tc->ac);
}
/**/
print_context_info(tc->ac, NULL);
}
/* 行末の改行を削除 */
static void
chomp(char *buf)
{
int len = strlen(buf);
while (len > 0) {
char c = buf[len - 1];
if (c == '\n' || c == '\r' || c == ' ' || c == '\t') {
buf[len - 1] = 0;
len --;
} else {
return ;
}
}
}
static void
read_fp(struct test_context *tc, FILE *fp)
{
char buf[1024];
while (fgets(buf, 1024, fp)) {
if (buf[0] == '#') {
continue;
}
if (!strncmp(buf, "\\include ", 9)) {
read_file(tc, &buf[9]);
continue;
}
chomp(buf);
conv_sentence(tc, buf);
}
}
static void
read_file(struct test_context *tc, const char *fn)
{
FILE *fp;
fp = fopen(fn, "r");
if (!fp) {
printf("failed to open (%s)\n", fn);
return ;
}
read_fp(tc, fp);
fclose(fp);
}
static void
print_usage(void)
{
printf("morphological analyzer\n");
printf(" $ ./morphological analyzer < [text-file]\n or");
printf(" $ ./morphological analyzer [text-file]\n");
exit(0);
}
static void
parse_args(int argc, char **argv)
{
int i;
for (i = 1; i < argc; i++) {
char *arg = argv[i];
if (!strcmp(arg, "--utf8")) {
use_utf8 = 1;
} else if (arg[i] == '-') {
print_usage();
}
}
}
int
main(int argc, char **argv)
{
struct test_context tc;
int i, nr;
anthy_init();
anthy_set_personality("");
init_test_context(&tc);
/*read_file(&tc, "index.txt");*/
parse_args(argc, argv);
nr = 0;
for (i = 1; i < argc; i++) {
read_file(&tc, argv[i]);
nr ++;
}
if (nr == 0) {
read_fp(&tc, stdin);
}
return 0;
}
|
