xref: /freebsd/usr.bin/locate/bigram/locate.bigram.c (revision 7672a0148f79063eac8f8e0beb0db5350d02d5d4)
1 /*
2  * SPDX-License-Identifier: BSD-4-Clause
3  *
4  * Copyright (c) 1995 Wolfram Schneider <wosch@FreeBSD.org>. Berlin.
5  * Copyright (c) 1989, 1993
6  *	The Regents of the University of California.  All rights reserved.
7  *
8  * This code is derived from software contributed to Berkeley by
9  * James A. Woods.
10  *
11  * Redistribution and use in source and binary forms, with or without
12  * modification, are permitted provided that the following conditions
13  * are met:
14  * 1. Redistributions of source code must retain the above copyright
15  *    notice, this list of conditions and the following disclaimer.
16  * 2. Redistributions in binary form must reproduce the above copyright
17  *    notice, this list of conditions and the following disclaimer in the
18  *    documentation and/or other materials provided with the distribution.
19  * 3. All advertising materials mentioning features or use of this software
20  *    must display the following acknowledgement:
21  *	This product includes software developed by the University of
22  *	California, Berkeley and its contributors.
23  * 4. Neither the name of the University nor the names of its contributors
24  *    may be used to endorse or promote products derived from this software
25  *    without specific prior written permission.
26  *
27  * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
28  * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
29  * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
30  * ARE DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
31  * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
32  * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
33  * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
34  * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
35  * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
36  * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
37  * SUCH DAMAGE.
38  *
39  * $FreeBSD$
40  */
41 
42 #if 0
43 #ifndef lint
44 static char copyright[] =
45 "@(#) Copyright (c) 1989, 1993\n\
46 	The Regents of the University of California.  All rights reserved.\n";
47 #endif /* not lint */
48 
49 #ifndef lint
50 static char sccsid[] = "@(#)locate.bigram.c	8.1 (Berkeley) 6/6/93";
51 #endif /* not lint */
52 #endif
53 
54 /*
55  *  bigram < sorted_file_names | sort -nr |
56  *  	awk 'NR <= 128 { printf $2 }' > bigrams
57  *
58  * List bigrams for 'updatedb' script.
59  * Use 'code' to encode a file using this output.
60  */
61 
62 #include <capsicum_helpers.h>
63 #include <err.h>
64 #include <stdio.h>
65 #include <stdlib.h>
66 #include <sys/param.h>			/* for MAXPATHLEN */
67 #include "locate.h"
68 
69 u_char buf1[MAXPATHLEN] = " ";
70 u_char buf2[MAXPATHLEN];
71 u_int bigram[UCHAR_MAX + 1][UCHAR_MAX + 1];
72 
73 int
74 main(void)
75 {
76 	u_char *cp;
77 	u_char *oldpath = buf1, *path = buf2;
78 	u_int i, j;
79 
80 	if (caph_limit_stdio() < 0 || caph_enter() < 0)
81 		err(1, "capsicum");
82 
83      	while (fgets(path, sizeof(buf2), stdin) != NULL) {
84 
85 		/*
86 		 * We don't need remove newline character '\n'.
87 		 * '\n' is less than ASCII_MIN and will be later
88 		 * ignored at output.
89 		 */
90 
91 
92 		/* skip longest common prefix */
93 		for (cp = path; *cp == *oldpath; cp++, oldpath++)
94 			if (*cp == '\0')
95 				break;
96 
97 		while (*cp != '\0' && *(cp + 1) != '\0') {
98 			bigram[(u_char)*cp][(u_char)*(cp + 1)]++;
99 			cp += 2;
100 		}
101 
102 		/* swap pointers */
103 		if (path == buf1) {
104 			path = buf2;
105 			oldpath = buf1;
106 		} else {
107 			path = buf1;
108 			oldpath = buf2;
109 		}
110    	}
111 
112 	/* output, boundary check */
113 	for (i = ASCII_MIN; i <= ASCII_MAX; i++)
114 		for (j = ASCII_MIN; j <= ASCII_MAX; j++)
115 			if (bigram[i][j] != 0)
116 				(void)printf("%4u %c%c\n", bigram[i][j], i, j);
117 
118 	exit(0);
119 }
120