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(void)46 main(void)
47 {
48 int clen, rlen, prev;
49 long off, start;
50 char buf[MAXWORDLEN + 1];
51
52 prev = '\0';
53 off = start = 0L;
54 while (nextword(stdin, buf, &clen, &rlen) != NULL) {
55 if (*buf != prev) {
56 if (prev != '\0')
57 printf("%c %6ld %6ld\n", prev, start, off - 1);
58 prev = *buf;
59 start = off;
60 }
61 off += clen + 1;
62 }
63 printf("%c %6ld %6ld\n", prev, start, off - 1);
64 return 0;
65 }
66
67 /*
68 * Return the next word in the compressed dictionary in 'buffer' or
69 * NULL on end-of-file
70 * Also set clen to the length of the compressed word (for mkindex) and
71 * rlen to the strlen() of the real word
72 */
73 char *
nextword(FILE * fp,char * buffer,int * clen,int * rlen)74 nextword(FILE *fp, char *buffer, int *clen, int *rlen)
75 {
76 int ch, pcount;
77 char *p, *q;
78 static char buf[MAXWORDLEN + 1];
79 static int first = 1;
80 static int lastch = 0;
81
82 if (first) {
83 if ((pcount = getc(fp)) == EOF)
84 return (NULL);
85 first = 0;
86 }
87 else if ((pcount = lastch) == EOF)
88 return (NULL);
89
90 p = buf + (*clen = pcount);
91
92 while ((ch = getc(fp)) != EOF && ch >= 'a')
93 *p++ = ch;
94 lastch = ch;
95 *p = '\0';
96
97 *rlen = (int) (p - buf);
98 *clen = *rlen - *clen;
99
100 p = buf;
101 q = buffer;
102 while ((*q++ = *p) != '\0') {
103 if (*p++ == 'q')
104 *q++ = 'u';
105 }
106 return (buffer);
107 }
108