locate/bigram.c

   1 /* bigram -- list bigrams for locate
   2    Copyright (C) 1994, 2007, 2009, 2010 Free Software Foundation, Inc.
   3
   4    This program is free software: you can redistribute it and/or modify
   5    it under the terms of the GNU General Public License as published by
   6    the Free Software Foundation, either version 3 of the License, or
   7    (at your option) any later version.
   8
   9    This program is distributed in the hope that it will be useful,
  10    but WITHOUT ANY WARRANTY; without even the implied warranty of
  11    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  12    GNU General Public License for more details.
  13
  14    You should have received a copy of the GNU General Public License
  15    along with this program.  If not, see <http://www.gnu.org/licenses/>.
  16 */
  17
  18 /* Usage: bigram < text > bigrams
  19    Use `code' to encode a file using this output.
  20
  21    Read a file from stdin and write out the bigrams (pairs of
  22    adjacent characters), one bigram per line, to stdout.  To reduce
  23    needless duplication in the output, it starts finding the
  24    bigrams on each input line at the character where that line
  25    first differs from the previous line (i.e., in the ASCII
  26    remainder).  Therefore, the input should be sorted in order to
  27    get the least redundant output.
  28
  29    Written by James A. Woods <jwoods@adobe.com>.
  30    Modified by David MacKenzie <djm@gnu.ai.mit.edu>.  */
  31
  32 #include <config.h>
  33 #include <stdio.h>
  34
  35 #include <string.h>
  36 #include <stdlib.h>
  37
  38 #include <sys/types.h>
  39
  40 #include <xalloc.h>
  41 #include "progname.h"
  42 #include "closeout.h"
  43
  44 /* Return the length of the longest common prefix of strings S1 and S2. */
  45
  46 static int
  47 prefix_length (char *s1, char *s2)
  48 {
  49   register char *start;
  50
  51   for (start = s1; *s1 == *s2 && *s1 != '\0'; s1++, s2++)
  52     ;
  53   return s1 - start;
  54 }
  55
  56 int
  57 main (int argc, char **argv)
  58 {
  59   char *path;                   /* The current input entry.  */
  60   char *oldpath;                /* The previous input entry.  */
  61   size_t pathsize, oldpathsize; /* Amounts allocated for them.  */
  62   int line_len;                 /* Length of input line.  */
  63
  64   if (argv[0])
  65     set_program_name (argv[0]);
  66   else
  67     set_program_name ("bigram");
  68
  69   (void) argc;
  70   atexit (close_stdout);
  71
  72   pathsize = oldpathsize = 1026; /* Increased as necessary by getline.  */
  73   path = xmalloc (pathsize);
  74   oldpath = xmalloc (oldpathsize);
  75
  76   /* Set to empty string, to force the first prefix count to 0.  */
  77   oldpath[0] = '\0';
  78
  79   while ((line_len = getline (&path, &pathsize, stdin)) > 0)
  80     {
  81       register int count;       /* The prefix length.  */
  82       register int j;           /* Index into input line.  */
  83
  84       path[line_len - 1] = '\0'; /* Remove the newline. */
  85
  86       /* Output bigrams in the remainder only. */
  87       count = prefix_length (oldpath, path);
  88       for (j = count; path[j] != '\0' && path[j + 1] != '\0'; j += 2)
  89         {
  90           putchar (path[j]);
  91           putchar (path[j + 1]);
  92           putchar ('\n');
  93         }
  94
  95       {
  96         /* Swap path and oldpath and their sizes.  */
  97         char *tmppath = oldpath;
  98         size_t tmppathsize = oldpathsize;
  99         oldpath = path;
 100         oldpathsize = pathsize;
 101         path = tmppath;
 102         pathsize = tmppathsize;
 103       }
 104     }
 105
 106   free (path);
 107   free (oldpath);
 108
 109   return 0;
 110 }