1 /* $OpenBSD: mkindex.c,v 1.9 2016/01/07 16:00:31 tb Exp $ */
2 /* $NetBSD: mkindex.c,v 1.2 1995/03/21 12:14:52 cgd Exp $ */
3
4 /*-
5 * Copyright (c) 1993
6 * The Regents of the University of California. All rights reserved.
7 *
8 * This code is derived from software contributed to Berkeley by
9 * Barry Brachman.
10 *
11 * Redistribution and use in source and binary forms, with or without
12 * modification, are permitted provided that the following conditions
13 * are met:
14 * 1. Redistributions of source code must retain the above copyright
15 * notice, this list of conditions and the following disclaimer.
16 * 2. Redistributions in binary form must reproduce the above copyright
17 * notice, this list of conditions and the following disclaimer in the
18 * documentation and/or other materials provided with the distribution.
19 * 3. Neither the name of the University nor the names of its contributors
20 * may be used to endorse or promote products derived from this software
21 * without specific prior written permission.
22 *
23 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
24 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
25 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
26 * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
27 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
28 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
29 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
30 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
31 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
32 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
33 * SUCH DAMAGE.
34 */
35
36 #include <err.h>
37 #include <stdio.h>
38 #include <stdlib.h>
39 #include <unistd.h>
40
41 #include "bog.h"
42
43 char *nextword(FILE *, char *, int *, int *);
44
45 int
main(int argc,char * argv[])46 main(int argc, char *argv[])
47 {
48 int clen, rlen, prev;
49 long off, start;
50 char buf[MAXWORDLEN + 1];
51
52 if (pledge("stdio", NULL) == -1)
53 err(1, "pledge");
54
55 prev = '\0';
56 off = start = 0L;
57 while (nextword(stdin, buf, &clen, &rlen) != NULL) {
58 if (*buf != prev) {
59 if (prev != '\0')
60 printf("%c %6ld %6ld\n", prev, start, off - 1);
61 prev = *buf;
62 start = off;
63 }
64 off += clen + 1;
65 }
66 printf("%c %6ld %6ld\n", prev, start, off - 1);
67 return 0;
68 }
69
70 /*
71 * Return the next word in the compressed dictionary in 'buffer' or
72 * NULL on end-of-file
73 * Also set clen to the length of the compressed word (for mkindex) and
74 * rlen to the strlen() of the real word
75 */
76 char *
nextword(FILE * fp,char * buffer,int * clen,int * rlen)77 nextword(FILE *fp, char *buffer, int *clen, int *rlen)
78 {
79 int ch, pcount;
80 char *p, *q;
81 static char buf[MAXWORDLEN + 1];
82 static int first = 1;
83 static int lastch = 0;
84
85 if (first) {
86 if ((pcount = getc(fp)) == EOF)
87 return (NULL);
88 first = 0;
89 }
90 else if ((pcount = lastch) == EOF)
91 return (NULL);
92
93 p = buf + (*clen = pcount);
94
95 while ((ch = getc(fp)) != EOF && ch >= 'a')
96 *p++ = ch;
97 lastch = ch;
98 *p = '\0';
99
100 *rlen = (int) (p - buf);
101 *clen = *rlen - *clen;
102
103 p = buf;
104 q = buffer;
105 while ((*q++ = *p) != '\0') {
106 if (*p++ == 'q')
107 *q++ = 'u';
108 }
109 return (buffer);
110 }
111