xref: /freebsd/usr.bin/locate/bigram/locate.bigram.c (revision 7f3dea244c40159a41ab22da77a434d7c5b5e85a)
1 /*
2  * Copyright (c) 1995 Wolfram Schneider <wosch@FreeBSD.org>. Berlin.
3  * Copyright (c) 1989, 1993
4  *	The Regents of the University of California.  All rights reserved.
5  *
6  * This code is derived from software contributed to Berkeley by
7  * James A. Woods.
8  *
9  * Redistribution and use in source and binary forms, with or without
10  * modification, are permitted provided that the following conditions
11  * are met:
12  * 1. Redistributions of source code must retain the above copyright
13  *    notice, this list of conditions and the following disclaimer.
14  * 2. Redistributions in binary form must reproduce the above copyright
15  *    notice, this list of conditions and the following disclaimer in the
16  *    documentation and/or other materials provided with the distribution.
17  * 3. All advertising materials mentioning features or use of this software
18  *    must display the following acknowledgement:
19  *	This product includes software developed by the University of
20  *	California, Berkeley and its contributors.
21  * 4. Neither the name of the University nor the names of its contributors
22  *    may be used to endorse or promote products derived from this software
23  *    without specific prior written permission.
24  *
25  * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
26  * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
27  * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
28  * ARE DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
29  * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
30  * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
31  * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
32  * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
33  * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
34  * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
35  * SUCH DAMAGE.
36  *
37  * 	$Id$
38  */
39 
40 #ifndef lint
41 static char copyright[] =
42 "@(#) Copyright (c) 1989, 1993\n\
43 	The Regents of the University of California.  All rights reserved.\n";
44 #endif /* not lint */
45 
46 #ifndef lint
47 static char sccsid[] = "@(#)locate.bigram.c	8.1 (Berkeley) 6/6/93";
48 #endif /* not lint */
49 
50 /*
51  *  bigram < sorted_file_names | sort -nr |
52  *  	awk 'NR <= 128 { printf $2 }' > bigrams
53  *
54  * List bigrams for 'updatedb' script.
55  * Use 'code' to encode a file using this output.
56  */
57 
58 #include <stdio.h>
59 #include <sys/param.h>			/* for MAXPATHLEN */
60 #include "locate.h"
61 
62 u_char buf1[MAXPATHLEN] = " ";
63 u_char buf2[MAXPATHLEN];
64 u_int bigram[UCHAR_MAX + 1][UCHAR_MAX + 1];
65 
66 int
67 main(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 		/*
76 		 * We don't need remove newline character '\n'.
77 		 * '\n' is less than ASCII_MIN and will be later
78 		 * ignored at output.
79 		 */
80 
81 
82 		/* skip longest common prefix */
83 		for (cp = path; *cp == *oldpath; cp++, oldpath++)
84 			if (*cp == '\0')
85 				break;
86 
87 		while (*cp != '\0' && *(cp + 1) != '\0') {
88 			bigram[(u_char)*cp][(u_char)*(cp + 1)]++;
89 			cp += 2;
90 		}
91 
92 		/* swap pointers */
93 		if (path == buf1) {
94 			path = buf2;
95 			oldpath = buf1;
96 		} else {
97 			path = buf1;
98 			oldpath = buf2;
99 		}
100    	}
101 
102 	/* output, boundary check */
103 	for (i = ASCII_MIN; i <= ASCII_MAX; i++)
104 		for (j = ASCII_MIN; j <= ASCII_MAX; j++)
105 			if (bigram[i][j] != 0)
106 				(void)printf("%4u %c%c\n", bigram[i][j], i, j);
107 
108 	exit(0);
109 }
110