xref: /freebsd/usr.bin/locate/bigram/locate.bigram.c (revision 2828dafcf3e7b225b70cbb380eb8c7dae452493e)
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  * $FreeBSD$
38  */
39 
40 #if 0
41 #ifndef lint
42 static char copyright[] =
43 "@(#) Copyright (c) 1989, 1993\n\
44 	The Regents of the University of California.  All rights reserved.\n";
45 #endif /* not lint */
46 
47 #ifndef lint
48 static char sccsid[] = "@(#)locate.bigram.c	8.1 (Berkeley) 6/6/93";
49 #endif /* not lint */
50 #endif
51 
52 /*
53  *  bigram < sorted_file_names | sort -nr |
54  *  	awk 'NR <= 128 { printf $2 }' > bigrams
55  *
56  * List bigrams for 'updatedb' script.
57  * Use 'code' to encode a file using this output.
58  */
59 
60 #include <capsicum_helpers.h>
61 #include <err.h>
62 #include <errno.h>
63 #include <stdio.h>
64 #include <stdlib.h>
65 #include <sys/param.h>			/* for MAXPATHLEN */
66 #include "locate.h"
67 
68 u_char buf1[MAXPATHLEN] = " ";
69 u_char buf2[MAXPATHLEN];
70 u_int bigram[UCHAR_MAX + 1][UCHAR_MAX + 1];
71 
72 int
73 main(void)
74 {
75 	u_char *cp;
76 	u_char *oldpath = buf1, *path = buf2;
77 	u_int i, j;
78 
79 	if (caph_limit_stdio() < 0 || (cap_enter() < 0 && errno != ENOSYS))
80 		err(1, "capsicum");
81 
82      	while (fgets(path, sizeof(buf2), stdin) != NULL) {
83 
84 		/*
85 		 * We don't need remove newline character '\n'.
86 		 * '\n' is less than ASCII_MIN and will be later
87 		 * ignored at output.
88 		 */
89 
90 
91 		/* skip longest common prefix */
92 		for (cp = path; *cp == *oldpath; cp++, oldpath++)
93 			if (*cp == '\0')
94 				break;
95 
96 		while (*cp != '\0' && *(cp + 1) != '\0') {
97 			bigram[(u_char)*cp][(u_char)*(cp + 1)]++;
98 			cp += 2;
99 		}
100 
101 		/* swap pointers */
102 		if (path == buf1) {
103 			path = buf2;
104 			oldpath = buf1;
105 		} else {
106 			path = buf1;
107 			oldpath = buf2;
108 		}
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 				(void)printf("%4u %c%c\n", bigram[i][j], i, j);
116 
117 	exit(0);
118 }
119