xref: /freebsd/usr.bin/locate/bigram/locate.bigram.c (revision ebacd8013fe5f7fdf9f6a5b286f6680dd2891036)
1 /*
2  * SPDX-License-Identifier: BSD-3-Clause
3  *
4  * Copyright (c) 1995-2022 Wolfram Schneider <wosch@FreeBSD.org>
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. Neither the name of the University nor the names of its contributors
20  *    may be used to endorse or promote products derived from this software
21  *    without specific prior written permission.
22  *
23  * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
24  * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
25  * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
26  * ARE DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
27  * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
28  * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
29  * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
30  * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
31  * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
32  * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
33  * SUCH DAMAGE.
34  *
35  * $FreeBSD$
36  *
37  * locate.bigram - list bigrams for /usr/libexec/locate.mklocatedb script
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 #include <capsicum_helpers.h>
54 #include <err.h>
55 #include <stdio.h>
56 #include <stdlib.h>
57 #include "locate.h"
58 
59 u_char buf1[LOCATE_PATH_MAX] = " ";
60 u_char buf2[LOCATE_PATH_MAX];
61 unsigned long bigram[UCHAR_MAX + 1][UCHAR_MAX + 1];
62 
63 int
64 main(void)
65 {
66 	u_char *cp;
67 	u_char *oldpath = buf1, *path = buf2;
68 	u_int i, j;
69 
70 	if (caph_limit_stdio() < 0 || caph_enter() < 0)
71 		err(1, "capsicum");
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 	if (!feof(stdin) || ferror(stdin))
102 		err(1, "stdin");
103 
104 
105 	/* output, boundary check */
106 	for (i = ASCII_MIN; i <= ASCII_MAX; i++)
107 		for (j = ASCII_MIN; j <= ASCII_MAX; j++)
108 			if (bigram[i][j] != 0)
109 				printf("%lu %c%c\n", bigram[i][j], i, j);
110 
111 	exit(0);
112 }
113