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
|
/* $NetBSD: word.c,v 1.10 2021/05/02 12:50:43 rillig Exp $ */
/*-
* Copyright (c) 1993
* The Regents of the University of California. All rights reserved.
*
* This code is derived from software contributed to Berkeley by
* Barry Brachman.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* 2. 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.
* 3. Neither the name of the University 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 REGENTS 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 REGENTS 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.
*/
#include <sys/cdefs.h>
#ifndef lint
#if 0
static char sccsid[] = "@(#)word.c 8.1 (Berkeley) 6/11/93";
#else
__RCSID("$NetBSD: word.c,v 1.10 2021/05/02 12:50:43 rillig Exp $");
#endif
#endif /* not lint */
#include <sys/types.h>
#include <sys/stat.h>
#include <err.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include "bog.h"
#include "extern.h"
static char *dictspace, *dictend;
static char *sp;
static int first = 1, lastch = 0;
extern struct dictindex dictindex[];
extern int wordlen;
/*
* Return the next word in the compressed dictionary in 'buffer' or
* NULL on end-of-file
*/
char *
nextword(FILE *fp)
{
int ch, pcount;
char *p;
static char buf[MAXWORDLEN + 1];
if (fp == NULL) {
if (sp == dictend)
return (NULL);
p = buf + (int) *sp++;
/*
* The dictionary ends with a null byte
*/
while (*sp >= 'a')
if ((*p++ = *sp++) == 'q')
*p++ = 'u';
} else {
if (first) {
if ((pcount = getc(fp)) == EOF)
return (NULL);
first = 0;
} else if ((pcount = lastch) == EOF)
return (NULL);
p = buf + pcount;
while ((ch = getc(fp)) != EOF && ch >= 'a')
if ((*p++ = ch) == 'q')
*p++ = 'u';
lastch = ch;
}
wordlen = (int) (p - buf);
*p = '\0';
return (buf);
}
/*
* Reset the state of nextword() and do the fseek()
*/
long
dictseek(FILE *fp, long offset, int ptrname)
{
if (fp == NULL) {
if ((sp = dictspace + offset) >= dictend)
return (-1);
return (0);
}
first = 1;
return (fseek(fp, offset, ptrname));
}
FILE *
opendict(const char *dict)
{
FILE *fp;
if ((fp = fopen(dict, "r")) == NULL)
return (NULL);
return (fp);
}
/*
* Load the given dictionary and initialize the pointers
*/
int
loaddict(FILE *fp)
{
struct stat statb;
long n;
int st;
char *p;
if (fstat(fileno(fp), &statb) < 0) {
(void)fclose(fp);
return (-1);
}
/*
* An extra character (a sentinel) is allocated and set to null
* to improve the expansion loop in nextword().
*/
if ((dictspace = malloc(statb.st_size + 1)) == NULL) {
(void)fclose(fp);
return (-1);
}
n = (long)statb.st_size;
sp = dictspace;
dictend = dictspace + n;
p = dictspace;
st = -1;
while (n > 0 && (st = fread(p, 1, BUFSIZ, fp)) > 0) {
p += st;
n -= st;
}
if (st < 0) {
(void)fclose(fp);
warnx("Error reading dictionary");
return (-1);
}
*p = '\0';
return (0);
}
/*
* Dependent on the exact format of the index file:
* Starting offset field begins in column 1 and length field in column 9
* Taking the easy way out, the input buffer is made "large" and a check
* is made for lines that are too long
*/
int
loadindex(const char *indexfile)
{
int i, j;
char buf[BUFSIZ];
FILE *fp;
if ((fp = fopen(indexfile, "r")) == NULL) {
warn("Can't open '%s'", indexfile);
return (-1);
}
i = 0;
while (fgets(buf, sizeof(buf), fp) != NULL) {
if (strchr(buf, '\n') == NULL) {
warnx("A line in the index file is too long");
(void) fclose(fp);
return(-1);
}
j = *buf - 'a';
if (i != j) {
warnx("Bad index order");
(void) fclose(fp);
return(-1);
}
dictindex[j].start = atol(buf + 1);
dictindex[j].length = atol(buf + 9) - dictindex[j].start;
i++;
}
(void) fclose(fp);
if (i != 26) {
warnx("Bad index length");
return(-1);
}
return(0);
}
|
