locate.bigram.c revision 17592 
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
37#ifndef lint
38static char copyright[] =
39"@(#) Copyright (c) 1989, 1993\n\
40	The Regents of the University of California.  All rights reserved.\n";
41#endif /* not lint */
42
43#ifndef lint
44static char sccsid[] = "@(#)locate.bigram.c	8.1 (Berkeley) 6/6/93";
45#endif /* not lint */
46
47/*
48 *  bigram < text > bigrams
49 *
50 * List bigrams for 'updatedb' script.
51 * Use 'code' to encode a file using this output.
52 */
53
54#include <stdio.h>
55#include <sys/param.h>			/* for MAXPATHLEN */
56#include <string.h>			/* memchr */
57#include "locate.h"
58
59u_char buf1[MAXPATHLEN] = " ";
60u_char buf2[MAXPATHLEN];
61unsigned int bigram[UCHAR_MAX][UCHAR_MAX];
62
63
64void main ( )
65{
66  	register u_char *cp;
67	register u_char *oldpath = buf1, *path = buf2;
68	register int i, j;
69
70	/* init bigram buffer */
71	for (i = 0; i < UCHAR_MAX; i++)
72	    	for (j = 0; j < UCHAR_MAX; j++)
73			bigram[i][j] = 0;
74
75     	while ( fgets ( path, sizeof(buf2), stdin ) != NULL ) {
76
77	    	/* skip empty lines */
78		if (*path == '\n')
79			continue;
80
81		/* Squelch characters that would botch the decoding. */
82		for (cp = path; *cp != NULL; cp++) {
83			/* chop newline */
84			if (*cp == '\n')
85				*cp = NULL;
86			/* range */
87			else if (*cp < ASCII_MIN || *cp > ASCII_MAX)
88				*cp = '?';
89		}
90
91
92		/* skip longest common prefix */
93		for (cp = path; *cp == *oldpath && *cp; cp++, oldpath++);
94
95		/*
96		 * output post-residue bigrams only
97		 */
98
99		/* check later for boundary */
100		while ( *cp != NULL && *(cp + 1) != NULL ) {
101			bigram[*cp][*(cp+1)]++;
102			cp += 2;
103		}
104
105		if ( path == buf1 )		/* swap pointers */
106			path = buf2, oldpath = buf1;
107		else
108			path = buf1, oldpath = buf2;
109   	}
110
111	/* output, boundary check */
112	for (i = ASCII_MIN; i <= ASCII_MAX; i++)
113		for (j = ASCII_MIN; j <= ASCII_MAX; j++)
114			if (bigram[i][j] != 0)
115				fprintf(stdout, "%4d %c%c\n",
116					bigram[i][j], i, j);
117}
118