locate/bigram/locate.bigram.c

   1 /*
   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.
   5  *
   6  * This code is derived from software contributed to Berkeley by
   7  * James A. Woods.
   8  *
   9  * Redistribution and use in source and binary forms, with or without
  10  * modification, are permitted provided that the following conditions
  11  * are met:
  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.
  24  *
  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
  35  * SUCH DAMAGE.
  36  *
  37  * $FreeBSD: src/usr.bin/locate/bigram/locate.bigram.c,v 1.12 2005/02/09 09:13:36 stefanf Exp $
  38  */
  39
  40 #ifndef lint
  41 static char copyright[] =
  42 "@(#) Copyright (c) 1989, 1993\n\
  43         The Regents of the University of California.  All rights reserved.\n";
  44 #endif /* not lint */
  45
  46 #ifndef lint
  47 static char sccsid[] = "@(#)locate.bigram.c     8.1 (Berkeley) 6/6/93";
  48 #endif /* not lint */
  49
  50 /*
  51  *  bigram < sorted_file_names | sort -nr |
  52  *      awk 'NR <= 128 { printf $2 }' > bigrams
  53  *
  54  * List bigrams for 'updatedb' script.
  55  * Use 'code' to encode a file using this output.
  56  */
  57
  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
  68 main(void)
  69 {
  70         register u_char *cp;
  71         register u_char *oldpath = buf1, *path = buf2;
  72         register u_int i, j;
  73
  74         while (fgets(path, sizeof(buf2), stdin) != NULL) {
  75
  76                 /*
  77                  * We don't need remove newline character '\n'.
  78                  * '\n' is less than ASCII_MIN and will be later
  79                  * ignored at output.
  80                  */
  81
  82
  83                 /* skip longest common prefix */
  84                 for (cp = path; *cp == *oldpath; cp++, oldpath++)
  85                         if (*cp == '\0')
  86                                 break;
  87
  88                 while (*cp != '\0' && *(cp + 1) != '\0') {
  89                         bigram[(u_char)*cp][(u_char)*(cp + 1)]++;
  90                         cp += 2;
  91                 }
  92
  93                 /* swap pointers */
  94                 if (path == buf1) {
  95                         path = buf2;
  96                         oldpath = buf1;
  97                 } else {
  98                         path = buf1;
  99                         oldpath = buf2;
 100                 }
 101         }
 102
 103         /* output, boundary check */
 104         for (i = ASCII_MIN; i <= ASCII_MAX; i++)
 105                 for (j = ASCII_MIN; j <= ASCII_MAX; j++)
 106                         if (bigram[i][j] != 0)
 107                                 (void)printf("%4u %c%c\n", bigram[i][j], i, j);
 108
 109         exit(0);
 110 }