usr.bin/locate/bigram/locate.bigram.c

   1 /*
   2  * SPDX-License-Identifier: BSD-4-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. All advertising materials mentioning features or use of this software
  20  *    must display the following acknowledgement:
  21  *      This product includes software developed by the University of
  22  *      California, Berkeley and its contributors.
  23  * 4. Neither the name of the University nor the names of its contributors
  24  *    may be used to endorse or promote products derived from this software
  25  *    without specific prior written permission.
  26  *
  27  * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
  28  * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
  29  * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
  30  * ARE DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
  31  * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
  32  * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
  33  * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
  34  * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
  35  * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
  36  * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
  37  * SUCH DAMAGE.
  38  *
  39  * $FreeBSD: head/usr.bin/locate/bigram/locate.bigram.c 325966 2017-11-18 14:26:50Z pfg $
  40  *
  41  * @(#) Copyright (c) 1989, 1993 The Regents of the University of California.  All rights reserved.
  42  * @(#)locate.bigram.c  8.1 (Berkeley) 6/6/93
  43  */
  44
  45 /*
  46  *  bigram < sorted_file_names | sort -nr |
  47  *      awk 'NR <= 128 { printf $2 }' > bigrams
  48  *
  49  * List bigrams for 'updatedb' script.
  50  * Use 'code' to encode a file using this output.
  51  */
  52
  53 #include <stdio.h>
  54 #include <stdlib.h>
  55 #include <sys/param.h>                  /* for MAXPATHLEN */
  56 #include "locate.h"
  57
  58 static u_char buf1[MAXPATHLEN] = " ";
  59 static u_char buf2[MAXPATHLEN];
  60 static u_int bigram[UCHAR_MAX + 1][UCHAR_MAX + 1];
  61
  62 int
  63 main(void)
  64 {
  65         u_char *cp;
  66         u_char *oldpath = buf1, *path = buf2;
  67         u_int i, j;
  68
  69         while (fgets(path, sizeof(buf2), stdin) != NULL) {
  70
  71                 /*
  72                  * We don't need remove newline character '\n'.
  73                  * '\n' is less than ASCII_MIN and will be later
  74                  * ignored at output.
  75                  */
  76
  77
  78                 /* skip longest common prefix */
  79                 for (cp = path; *cp == *oldpath; cp++, oldpath++)
  80                         if (*cp == '\0')
  81                                 break;
  82
  83                 while (*cp != '\0' && *(cp + 1) != '\0') {
  84                         bigram[(u_char)*cp][(u_char)*(cp + 1)]++;
  85                         cp += 2;
  86                 }
  87
  88                 /* swap pointers */
  89                 if (path == buf1) {
  90                         path = buf2;
  91                         oldpath = buf1;
  92                 } else {
  93                         path = buf1;
  94                         oldpath = buf2;
  95                 }
  96         }
  97
  98         /* output, boundary check */
  99         for (i = ASCII_MIN; i <= ASCII_MAX; i++)
 100                 for (j = ASCII_MIN; j <= ASCII_MAX; j++)
 101                         if (bigram[i][j] != 0)
 102                                 (void)printf("%4u %c%c\n", bigram[i][j], i, j);
 103
 104         exit(0);
 105 }