1 /*
2  *	$OpenBSD: locate.bigram.c,v 1.15 2015/12/09 01:58:34 jsg 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  * 	$Id: locate.bigram.c,v 1.15 2015/12/09 01:58:34 jsg Exp $
36  */
37 
38 /*
39  *  bigram < sorted_file_names | sort -nr |
40  *  	awk 'NR <= 128 { printf $2 }' > bigrams
41  *
42  * List bigrams for 'updatedb' script.
43  * Use 'code' to encode a file using this output.
44  */
45 
46 #include <stdio.h>
47 #include <stdlib.h>
48 #include <limits.h>
49 #include <unistd.h>
50 #include <err.h>
51 #include "locate.h"
52 
53 u_char buf1[PATH_MAX] = " ";
54 u_char buf2[PATH_MAX];
55 u_int bigram[UCHAR_MAX + 1][UCHAR_MAX + 1];
56 
57 int
58 main(void)
59 {
60 	u_char *cp;
61 	u_char *oldpath = buf1, *path = buf2;
62 	u_int i, j;
63 
64 	if (pledge("stdio", NULL) == -1)
65 		err(1, "pledge");
66 
67 	while (fgets(path, sizeof(buf2), stdin) != NULL) {
68 
69 		/*
70 		 * We don't need remove newline character '\n'.
71 		 * '\n' is less than ASCII_MIN and will be later
72 		 * ignored at output.
73 		 */
74 
75 
76 		/* skip longest common prefix */
77 		for (cp = path; *cp == *oldpath; cp++, oldpath++)
78 			if (*cp == '\0')
79 				break;
80 
81 		while (*cp != '\0' && *(cp + 1) != '\0') {
82 			bigram[(u_char)*cp][(u_char)*(cp + 1)]++;
83 			cp += 2;
84 		}
85 
86 		/* swap pointers */
87 		if (path == buf1) {
88 			path = buf2;
89 			oldpath = buf1;
90 		} else {
91 			path = buf1;
92 			oldpath = buf2;
93 		}
94 	}
95 
96 	/* output, boundary check */
97 	for (i = ASCII_MIN; i <= ASCII_MAX; i++)
98 		for (j = ASCII_MIN; j <= ASCII_MAX; j++)
99 			if (bigram[i][j] != 0)
100 				(void)printf("%4u\t%c%c\n", bigram[i][j], i, j);
101 
102 	exit(0);
103 }
104