2 * Copyright (c) 1995 Wolfram Schneider <wosch@FreeBSD.org>. Berlin.
3 * Copyright (c) 1989, 1993
4 * The Regents of the University of California. All rights reserved.
6 * This code is derived from software contributed to Berkeley by
9 * Redistribution and use in source and binary forms, with or without
10 * modification, are permitted provided that the following conditions
12 * 1. Redistributions of source code must retain the above copyright
13 * notice, this list of conditions and the following disclaimer.
14 * 2. Redistributions in binary form must reproduce the above copyright
15 * notice, this list of conditions and the following disclaimer in the
16 * documentation and/or other materials provided with the distribution.
17 * 3. All advertising materials mentioning features or use of this software
18 * must display the following acknowledgement:
19 * This product includes software developed by the University of
20 * California, Berkeley and its contributors.
21 * 4. Neither the name of the University nor the names of its contributors
22 * may be used to endorse or promote products derived from this software
23 * without specific prior written permission.
25 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
26 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
27 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
28 * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
29 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
30 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
31 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
32 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
33 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
34 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
37 * $FreeBSD: src/usr.bin/locate/bigram/locate.bigram.c,v 1.11 1999/08/28 01:02:54 peter Exp $
39 * @(#) Copyright (c) 1989, 1993 The Regents of the University of California. All rights reserved.
40 * @(#)locate.bigram.c 8.1 (Berkeley) 6/6/93
44 * bigram < sorted_file_names | sort -nr |
45 * awk 'NR <= 128 { printf $2 }' > bigrams
47 * List bigrams for 'updatedb' script.
48 * Use 'code' to encode a file using this output.
53 #include <sys/param.h> /* for MAXPATHLEN */
56 static u_char buf1
[MAXPATHLEN
] = " ";
57 static u_char buf2
[MAXPATHLEN
];
58 static u_int bigram
[UCHAR_MAX
+ 1][UCHAR_MAX
+ 1];
64 u_char
*oldpath
= buf1
, *path
= buf2
;
67 while (fgets(path
, sizeof(buf2
), stdin
) != NULL
) {
70 * We don't need remove newline character '\n'.
71 * '\n' is less than ASCII_MIN and will be later
76 /* skip longest common prefix */
77 for (cp
= path
; *cp
== *oldpath
; cp
++, oldpath
++)
81 while (*cp
!= '\0' && *(cp
+ 1) != '\0') {
82 bigram
[(u_char
)*cp
][(u_char
)*(cp
+ 1)]++;
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 %c%c\n", bigram
[i
][j
], i
, j
);