1/* bigram -- list bigrams for locate
2   Copyright (C) 1994, 2000, 2003, 2004, 2005, 2007 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#if defined(HAVE_STRING_H) || defined(STDC_HEADERS)
36#include <string.h>
37#else
38#include <strings.h>
39#endif
40
41#ifdef STDC_HEADERS
42#include <stdlib.h>
43#endif
44#include <sys/types.h>
45
46#include <xalloc.h>
47#include "closeout.h"
48
49/* The name this program was run with.  */
50char *program_name;
51
52/* Return the length of the longest common prefix of strings S1 and S2. */
53
54static int
55prefix_length (char *s1, char *s2)
56{
57  register char *start;
58
59  for (start = s1; *s1 == *s2 && *s1 != '\0'; s1++, s2++)
60    ;
61  return s1 - start;
62}
63
64int
65main (int argc, char **argv)
66{
67  char *path;			/* The current input entry.  */
68  char *oldpath;		/* The previous input entry.  */
69  size_t pathsize, oldpathsize;	/* Amounts allocated for them.  */
70  int line_len;			/* Length of input line.  */
71
72  program_name = argv[0];
73  (void) argc;
74  atexit (close_stdout);
75
76  pathsize = oldpathsize = 1026; /* Increased as necessary by getline.  */
77  path = xmalloc (pathsize);
78  oldpath = xmalloc (oldpathsize);
79
80  /* Set to empty string, to force the first prefix count to 0.  */
81  oldpath[0] = '\0';
82
83  while ((line_len = getline (&path, &pathsize, stdin)) > 0)
84    {
85      register int count;	/* The prefix length.  */
86      register int j;		/* Index into input line.  */
87
88      path[line_len - 1] = '\0'; /* Remove the newline. */
89
90      /* Output bigrams in the remainder only. */
91      count = prefix_length (oldpath, path);
92      for (j = count; path[j] != '\0' && path[j + 1] != '\0'; j += 2)
93	{
94	  putchar (path[j]);
95	  putchar (path[j + 1]);
96	  putchar ('\n');
97	}
98
99      {
100	/* Swap path and oldpath and their sizes.  */
101	char *tmppath = oldpath;
102	size_t tmppathsize = oldpathsize;
103	oldpath = path;
104	oldpathsize = pathsize;
105	path = tmppath;
106	pathsize = tmppathsize;
107      }
108    }
109
110  free (path);
111  free (oldpath);
112
113  return 0;
114}
115