locate.bigram.c revision 18300 
1/*
2 * Copyright (c) 1989, 1993
3 *	The Regents of the University of California.  All rights reserved.
4 *
5 * This code is derived from software contributed to Berkeley by
6 * James A. Woods.
7 *
8 * Redistribution and use in source and binary forms, with or without
9 * modification, are permitted provided that the following conditions
10 * are met:
11 * 1. Redistributions of source code must retain the above copyright
12 *    notice, this list of conditions and the following disclaimer.
13 * 2. Redistributions in binary form must reproduce the above copyright
14 *    notice, this list of conditions and the following disclaimer in the
15 *    documentation and/or other materials provided with the distribution.
16 * 3. All advertising materials mentioning features or use of this software
17 *    must display the following acknowledgement:
18 *	This product includes software developed by the University of
19 *	California, Berkeley and its contributors.
20 * 4. Neither the name of the University nor the names of its contributors
21 *    may be used to endorse or promote products derived from this software
22 *    without specific prior written permission.
23 *
24 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
25 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
26 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
27 * ARE DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
28 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
29 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
30 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
31 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
32 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
33 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
34 * SUCH DAMAGE.
35 *
36 * 	$Id: locate.bigram.c,v 1.1 1996/09/13 13:23:48 wosch Exp wosch $
37 */
38
39#ifndef lint
40static char copyright[] =
41"@(#) Copyright (c) 1989, 1993\n\
42	The Regents of the University of California.  All rights reserved.\n";
43#endif /* not lint */
44
45#ifndef lint
46static char sccsid[] = "@(#)locate.bigram.c	8.1 (Berkeley) 6/6/93";
47#endif /* not lint */
48
49/*
50 *  bigram < sorted_file_names | sort -nr |
51 *  	awk 'NR <= 128 { printf $2 }' > bigrams
52 *
53 * List bigrams for 'updatedb' script.
54 * Use 'code' to encode a file using this output.
55 */
56
57#include <stdio.h>
58#include <sys/param.h>			/* for MAXPATHLEN */
59#include "locate.h"
60
61u_char buf1[MAXPATHLEN] = " ";
62u_char buf2[MAXPATHLEN];
63u_int bigram[UCHAR_MAX][UCHAR_MAX];
64
65int
66main(void)
67{
68  	register u_char *cp;
69	register u_char *oldpath = buf1, *path = buf2;
70	register u_int i, j;
71
72     	while (fgets(path, sizeof(buf2), stdin) != NULL) {
73
74		/*
75		 * We don't need remove newline character '\n'.
76		 * '\n' is less than ASCII_MIN and will be later
77		 * ignored at output.
78		 */
79
80
81		/* skip longest common prefix */
82		for (cp = path; *cp == *oldpath; cp++, oldpath++)
83			if (*cp == '\0')
84				break;
85
86		while (*cp != '\0' && *(cp + 1) != '\0') {
87			bigram[(u_int)*cp][(u_int)*(cp + 1)]++;
88			cp += 2;
89		}
90
91		/* swap pointers */
92		if (path == buf1) {
93			path = buf2;
94			oldpath = buf1;
95		} else {
96			path = buf1;
97			oldpath = buf2;
98		}
99   	}
100
101	/* output, boundary check */
102	for (i = ASCII_MIN; i <= ASCII_MAX; i++)
103		for (j = ASCII_MIN; j <= ASCII_MAX; j++)
104			if (bigram[i][j] != 0)
105				(void)printf("%4u %c%c\n", bigram[i][j], i, j);
106
107	exit(0);
108}
109