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
|
#include <assert.h>
#include <stdio.h>
#include <string.h>
FILE *discard;
typedef unsigned char uchar_t;
#define CERTAIN 1
#define UNCERTAIN 2
char state[32000];
#define kanji_code(s) ((s)[0]*256 + (s)[1])
uchar_t orig_kanji[50];
void
output (header, header_yomi, str)
uchar_t *header, *header_yomi, *str;
{
uchar_t this_header[30], kanji_yomi[30], *this_trailer;
unsigned code;
uchar_t *delim = strchr(str, '<');
uchar_t *rdelim = strchr(str, '>');
uchar_t new_header[30];
uchar_t new_header_yomi[30];
if (!delim) {
char buf[200];
strcpy(buf, header_yomi);
strcat(buf, str);
if (!strcmp(orig_kanji, buf)) {
fprintf(discard, "%s\n", orig_kanji);
} else {
printf("%s%s %s%s\n", header_yomi, str, header, str);
}
return;
}
strncpy(this_header, str, delim-str-2); this_header[delim-str-2] = 0;
code = kanji_code(delim-2);
assert(rdelim);
strncpy(kanji_yomi, delim+1, rdelim-delim-1); kanji_yomi[rdelim-delim-1] = 0;
this_trailer = rdelim+1;
sprintf(new_header, "%s%s%c%c", header, this_header, delim[-2], delim[-1]);
if (state[code-0x8080] == 0) {
sprintf(new_header_yomi, "%s%s%s", header_yomi, this_header, kanji_yomi);
output(new_header, new_header_yomi, this_trailer);
} else if (state[code-0x8080] & CERTAIN) {
sprintf(new_header_yomi, "%s%s%c%c", header_yomi, this_header,
delim[-2], delim[-1]);
output(new_header, new_header_yomi, this_trailer);
} else {
sprintf(new_header_yomi, "%s%s%s", header_yomi, this_header, kanji_yomi);
output(new_header, new_header_yomi, this_trailer);
sprintf(new_header_yomi, "%s%s%c%c", header_yomi, this_header,
delim[-2], delim[-1]);
output(new_header, new_header_yomi, this_trailer);
}
}
unsigned
read_next_code (f)
FILE *f;
{
char buf[BUFSIZ];
int dummy1;
uchar_t kanji[5];
char stroke[3];
int dummy2;
if (!fgets(buf, BUFSIZ, f)) return 0;
if (!sscanf(buf, "%d %s %x %s", &dummy1, stroke, &dummy2, kanji) == 4)
return -1;
return kanji_code(kanji);
}
void
read_certain_file(path, val)
char *path;
int val;
{
FILE *f;
int linenum;
char buf[BUFSIZ];
if (!(f = fopen(path, "r"))) {
perror(path);
exit(1);
}
linenum = 0;
while (fgets(buf, BUFSIZ, f)) {
uchar_t *s = strtok(buf, " \t\n");
unsigned code = s ? kanji_code(s) : 0;
linenum++;
if (!(code >= 0x8080 && code <= 0xffff)) {
fprintf(stderr, "%s:%d:ignoring %s.\n", path, linenum, s);
} else {
state[code-0x8080] = val;
}
while (s = strtok(NULL, " \t\n")) {
code = kanji_code(s);
if (!(code >= 0x8080 && code <= 0xffff)) {
fprintf(stderr, "%s:%d:ignoring %s.\n", path, linenum, s);
} else {
state[code-0x8080] = val;
}
}
}
fclose(f);
}
int
main (argc, argv)
int argc;
char **argv;
{
FILE *f;
uchar_t buf[BUFSIZ];
unsigned code;
int line;
if (argc < 3) {
fprintf(stderr, "reduce dictionary\n");
fprintf(stderr, "Usage: reduce file1 file2 <dictionary\n");
fprintf(stderr, " file1: certainly memorized t-code\n");
fprintf(stderr, " file2: uncertainly memorized t-code\n");
exit(1);
}
discard = fopen("discard", "w");
assert(discard);
read_certain_file(argv[1], CERTAIN);
read_certain_file(argv[2], UNCERTAIN);
f = stdin;
while (fgets(buf, BUFSIZ, f)) {
uchar_t *delim;
uchar_t header[30];
uchar_t *dest = orig_kanji, *src = buf;
buf[strlen(buf)-1] = '\0';
while (*src) {
if (*src == '<') {
while (*src != '>') src++;
src++;
}
*dest++ = *src++;
}
*dest = 0;
delim = strchr(buf, '<');
assert(delim >= buf+2); /* '<'$B$NA0$K$OA43Q0lJ8;z0J>e$J$-$c$$$1$J$$(B */
memset(header, 0, sizeof header);
strncpy(header, buf, (delim - buf - 2));
output(header, header, delim-2);
}
exit(0);
}
|
