xref: /freebsd/usr.bin/locate/bigram/locate.bigram.c (revision 0b8224d1cc9dc6c9778ba04a75b2c8d47e5d7481)
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  * locate.bigram - list bigrams for /usr/libexec/locate.mklocatedb script
36  */
37 
38 #include <capsicum_helpers.h>
39 #include <err.h>
40 #include <stdio.h>
41 #include <stdlib.h>
42 #include "locate.h"
43 
44 u_char buf1[LOCATE_PATH_MAX] = " ";
45 u_char buf2[LOCATE_PATH_MAX];
46 unsigned long bigram[UCHAR_MAX + 1][UCHAR_MAX + 1];
47 
48 int
main(void)49 main(void)
50 {
51 	u_char *cp;
52 	u_char *oldpath = buf1, *path = buf2;
53 	u_int i, j;
54 
55 	if (caph_limit_stdio() < 0 || caph_enter() < 0)
56 		err(1, "capsicum");
57 
58      	while (fgets(path, sizeof(buf2), stdin) != NULL) {
59 
60 		/*
61 		 * We don't need remove newline character '\n'.
62 		 * '\n' is less than ASCII_MIN and will be later
63 		 * ignored at output.
64 		 */
65 
66 
67 		/* skip longest common prefix */
68 		for (cp = path; *cp == *oldpath; cp++, oldpath++)
69 			if (*cp == '\0')
70 				break;
71 
72 		while (*cp != '\0' && *(cp + 1) != '\0') {
73 			bigram[(u_char)*cp][(u_char)*(cp + 1)]++;
74 			cp += 2;
75 		}
76 
77 		/* swap pointers */
78 		if (path == buf1) {
79 			path = buf2;
80 			oldpath = buf1;
81 		} else {
82 			path = buf1;
83 			oldpath = buf2;
84 		}
85    	}
86 	if (!feof(stdin) || ferror(stdin))
87 		err(1, "stdin");
88 
89 
90 	/* output, boundary check */
91 	for (i = ASCII_MIN; i <= ASCII_MAX; i++)
92 		for (j = ASCII_MIN; j <= ASCII_MAX; j++)
93 			if (bigram[i][j] != 0)
94 				printf("%lu %c%c\n", bigram[i][j], i, j);
95 
96 	exit(0);
97 }
98