1 /*
2 * SPDX-License-Identifier: BSD-3-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. 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
36 #if 0
37 #ifndef lint
38 static char copyright[] =
39 "@(#) Copyright (c) 1989, 1993\n\
40 The Regents of the University of California. All rights reserved.\n";
41 #endif /* not lint */
42
43 #ifndef lint
44 static char sccsid[] = "@(#)locate.bigram.c 8.1 (Berkeley) 6/6/93";
45 #endif /* not lint */
46 #endif
47
48 /*
49 * bigram < sorted_file_names | sort -nr |
50 * awk 'NR <= 128 { printf $2 }' > bigrams
51 *
52 * List bigrams for 'updatedb' script.
53 * Use 'code' to encode a file using this output.
54 */
55
56 #include <capsicum_helpers.h>
57 #include <err.h>
58 #include <stdio.h>
59 #include <stdlib.h>
60 #include <sys/param.h> /* for MAXPATHLEN */
61 #include "locate.h"
62
63 u_char buf1[MAXPATHLEN] = " ";
64 u_char buf2[MAXPATHLEN];
65 u_int bigram[UCHAR_MAX + 1][UCHAR_MAX + 1];
66
67 int
main(void)68 main(void)
69 {
70 u_char *cp;
71 u_char *oldpath = buf1, *path = buf2;
72 u_int i, j;
73
74 if (caph_limit_stdio() < 0 || caph_enter() < 0)
75 err(1, "capsicum");
76
77 while (fgets(path, sizeof(buf2), stdin) != NULL) {
78
79 /*
80 * We don't need remove newline character '\n'.
81 * '\n' is less than ASCII_MIN and will be later
82 * ignored at output.
83 */
84
85
86 /* skip longest common prefix */
87 for (cp = path; *cp == *oldpath; cp++, oldpath++)
88 if (*cp == '\0')
89 break;
90
91 while (*cp != '\0' && *(cp + 1) != '\0') {
92 bigram[(u_char)*cp][(u_char)*(cp + 1)]++;
93 cp += 2;
94 }
95
96 /* swap pointers */
97 if (path == buf1) {
98 path = buf2;
99 oldpath = buf1;
100 } else {
101 path = buf1;
102 oldpath = buf2;
103 }
104 }
105
106 /* output, boundary check */
107 for (i = ASCII_MIN; i <= ASCII_MAX; i++)
108 for (j = ASCII_MIN; j <= ASCII_MAX; j++)
109 if (bigram[i][j] != 0)
110 (void)printf("%4u %c%c\n", bigram[i][j], i, j);
111
112 exit(0);
113 }
114