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
|
#include <string.h>
#include <stdlib.h>
#include <stdio.h>
#include "hyphen.h"
#include "csutil.h"
#define BUFSIZE 1000
void help() {
fprintf(stderr,"correct syntax is:\n");
fprintf(stderr,"example [-d | -dd] hyphen_dictionary_file file_of_words_to_check\n");
fprintf(stderr,"-o = use old algorithm (without non-standard hyphenation)\n");
fprintf(stderr,"-d = hyphenation with listing of the possible hyphenations\n");
}
/* get a pointer to the nth 8-bit or UTF-8 character of the word */
char * hindex(char * word, int n, int utf8) {
int j = 0;
while (j < n) {
j++;
word++;
while (utf8 && ((((unsigned char) *word) >> 6) == 2)) word++;
}
return word;
}
/* list possible hyphenations with -dd option (example for the usage of the hyphenate2() function) */
void single_hyphenations(char * word, char * hyphen, char ** rep, int * pos, int * cut, int utf8) {
int i, k, j = 0;
char r;
for (i = 0; (i + 1) < strlen(word); i++) {
if (utf8 && ((((unsigned char) word[i]) >> 6) == 2)) continue;
if ((hyphen[j] & 1)) {
if (rep && rep[j]) {
k = hindex(word, j - pos[j] + 1, utf8) - word;
r = word[k];
word[k] = 0;
printf(" - %s%s", word, rep[j]);
word[k] = r;
printf("%s\n", hindex(word + k, cut[j], utf8));
} else {
k = hindex(word, j + 1, utf8) - word;
r = word[k];
word[k] = 0;
printf(" - %s=", word);
word[k] = r;
printf("%s\n", word + k);
}
}
j++;
}
}
int
main(int argc, char** argv)
{
HyphenDict *dict;
int df;
int wtc;
FILE* wtclst;
int k, n, i, j, c;
char buf[BUFSIZE + 1];
int nHyphCount;
char *hyphens;
char *lcword;
char *hyphword;
char hword[BUFSIZE * 2];
int arg = 1;
int optd = 1;
int optdd = 0;
char ** rep;
int * pos;
int * cut;
/* first parse the command line options */
/* arg1 - hyphen dictionary file, arg2 - file of words to check */
if (argv[arg]) {
if (strcmp(argv[arg], "-o") == 0) {
optd = 0;
arg++;
}
if (argv[arg] && strcmp(argv[arg], "-d") == 0) {
optd = 1;
optdd = 1;
arg++;
}
}
if (argv[arg]) {
df = arg++;
} else {
help();
exit(1);
}
if (argv[arg]) {
wtc = arg++;
} else {
help();
exit(1);
}
/* load the hyphenation dictionary */
if ((dict = hnj_hyphen_load(argv[df])) == NULL) {
fprintf(stderr, "Couldn't find file %s\n", argv[df]);
fflush(stderr);
exit(1);
}
/* open the words to check list */
wtclst = fopen(argv[wtc],"r");
if (!wtclst) {
fprintf(stderr,"Error - could not open file of words to check\n");
exit(1);
}
/* now read each word from the wtc file */
while(fgets(buf,BUFSIZE,wtclst)) {
k = strlen(buf);
if (buf[k - 1] == '\n') buf[k - 1] = '\0';
if (*buf && buf[k - 2] == '\r') buf[k-- - 2] = '\0';
/* set aside some buffers to hold lower cased */
/* and hyphen information */
lcword = (char *) malloc(k+1);
hyphens = (char *)malloc(k+5);
if (dict->utf8) {
strcpy(lcword, buf);
} else {
enmkallsmall(lcword,buf,dict->cset);
}
/* first remove any trailing periods */
n = k-1;
while((n >=0) && (lcword[n] == '.')) n--;
n++;
/* now actually try to hyphenate the word */
rep = NULL;
pos = NULL;
cut = NULL;
hword[0] = '\0';
if ((!optd && hnj_hyphen_hyphenate(dict, lcword, n-1, hyphens)) ||
(optd && hnj_hyphen_hyphenate2(dict, lcword, n-1, hyphens, hword, &rep, &pos, &cut))) {
free(hyphens);
free(lcword);
fprintf(stderr, "hyphenation error\n");
exit(1);
}
if (!optd) {
/* now backfill hyphens[] for any removed periods */
for (c = n; c < k; c++) hyphens[c] = '0';
hyphens[k] = '\0';
/* now create a new char string showing hyphenation positions */
/* count the hyphens and allocate space for the new hypehanted string */
nHyphCount = 0;
for (i = 0; i < n; i++)
if (hyphens[i]&1)
nHyphCount++;
hyphword = (char *) malloc(k+1+nHyphCount);
j = 0;
for (i = 0; i < n; i++) {
hyphword[j++] = buf[i];
if (hyphens[i]&1) {
hyphword[j++] = '-';
}
}
hyphword[j] = '\0';
fprintf(stdout,"%s\n",hyphword);
fflush(stdout);
free(hyphword);
} else {
/* fprintf(stderr, "vasz: %s", hyphens); */
fprintf(stdout,"%s\n", hword);
if (optdd) single_hyphenations(lcword, hyphens, rep, pos, cut, dict->utf8);
if (rep) {
for (i = 0; i < n - 1; i++) {
if (rep[i]) free(rep[i]);
}
free(rep);
free(pos);
free(cut);
}
}
free(hyphens);
free(lcword);
}
fclose(wtclst);
hnj_hyphen_free(dict);
return 0;
}
|
