locate.bigram.c revision 17776 
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 * 	$Id$
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 <string.h>			/* memchr */
60#include "locate.h"
61
62u_char buf1[MAXPATHLEN] = " ";
63u_char buf2[MAXPATHLEN];
64u_int bigram[UCHAR_MAX][UCHAR_MAX];
65
66int
67main(void)
68{
69  	register u_char *cp;
70	register u_char *oldpath = buf1, *path = buf2;
71	register u_int i, j;
72
73     	while (fgets(path, sizeof(buf2), stdin) != NULL) {
74
75	    	/* skip empty lines */
76		if (*path == '\n')
77			continue;
78
79		/* Squelch characters that would botch the decoding. */
80		for (cp = path; *cp != NULL; cp++) {
81			/* chop newline */
82			if (*cp == '\n')
83				*cp = NULL;
84			/* range */
85			else if (*cp < ASCII_MIN || *cp > ASCII_MAX)
86				*cp = '?';
87		}
88
89		/* skip longest common prefix */
90		for (cp = path; *cp == *oldpath && *cp != NULL; cp++, oldpath++);
91
92		while (*cp != NULL && *(cp+1) != NULL) {
93			bigram[*cp][*(cp+1)]++;
94			cp += 2;
95		}
96
97		/* swap pointers */
98		if (path == buf1) {
99			path = buf2;
100			oldpath = buf1;
101		} else {
102			path = buf1;
103			oldpath = buf2;
104		}
105   	}
106
107	/* output, (paranoid) boundary check */
108	for (i = ASCII_MIN; i <= ASCII_MAX; i++)
109		for (j = ASCII_MIN; j <= ASCII_MAX; j++)
110			if (bigram[i][j] != 0)
111				printf("%4u %c%c\n", bigram[i][j], i, j);
112
113	exit(0);
114}
115