1 /*
2  *	$OpenBSD: locate.bigram.c,v 1.16 2019/01/17 06:15:44 tedu Exp $
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 /*
37  *  bigram < sorted_file_names | sort -nr |
38  *  	awk 'NR <= 128 { printf $2 }' > bigrams
39  *
40  * List bigrams for 'updatedb' script.
41  * Use 'code' to encode a file using this output.
42  */
43 
44 #include <stdio.h>
45 #include <stdlib.h>
46 #include <limits.h>
47 #include <unistd.h>
48 #include <err.h>
49 #include "locate.h"
50 
51 u_char buf1[PATH_MAX] = " ";
52 u_char buf2[PATH_MAX];
53 u_int bigram[UCHAR_MAX + 1][UCHAR_MAX + 1];
54 
55 int
56 main(void)
57 {
58 	u_char *cp;
59 	u_char *oldpath = buf1, *path = buf2;
60 	u_int i, j;
61 
62 	if (pledge("stdio", NULL) == -1)
63 		err(1, "pledge");
64 
65 	while (fgets(path, sizeof(buf2), stdin) != NULL) {
66 
67 		/*
68 		 * We don't need remove newline character '\n'.
69 		 * '\n' is less than ASCII_MIN and will be later
70 		 * ignored at output.
71 		 */
72 
73 
74 		/* skip longest common prefix */
75 		for (cp = path; *cp == *oldpath; cp++, oldpath++)
76 			if (*cp == '\0')
77 				break;
78 
79 		while (*cp != '\0' && *(cp + 1) != '\0') {
80 			bigram[(u_char)*cp][(u_char)*(cp + 1)]++;
81 			cp += 2;
82 		}
83 
84 		/* swap pointers */
85 		if (path == buf1) {
86 			path = buf2;
87 			oldpath = buf1;
88 		} else {
89 			path = buf1;
90 			oldpath = buf2;
91 		}
92 	}
93 
94 	/* output, boundary check */
95 	for (i = ASCII_MIN; i <= ASCII_MAX; i++)
96 		for (j = ASCII_MIN; j <= ASCII_MAX; j++)
97 			if (bigram[i][j] != 0)
98 				(void)printf("%4u\t%c%c\n", bigram[i][j], i, j);
99 
100 	exit(0);
101 }
102