mkdict.c revision 1.2 1 1.2 cgd /* $NetBSD: mkdict.c,v 1.2 1995/03/21 12:14:49 cgd Exp $ */
2 1.2 cgd
3 1.1 jtc /*-
4 1.1 jtc * Copyright (c) 1993
5 1.1 jtc * The Regents of the University of California. All rights reserved.
6 1.1 jtc *
7 1.1 jtc * This code is derived from software contributed to Berkeley by
8 1.1 jtc * Barry Brachman.
9 1.1 jtc *
10 1.1 jtc * Redistribution and use in source and binary forms, with or without
11 1.1 jtc * modification, are permitted provided that the following conditions
12 1.1 jtc * are met:
13 1.1 jtc * 1. Redistributions of source code must retain the above copyright
14 1.1 jtc * notice, this list of conditions and the following disclaimer.
15 1.1 jtc * 2. Redistributions in binary form must reproduce the above copyright
16 1.1 jtc * notice, this list of conditions and the following disclaimer in the
17 1.1 jtc * documentation and/or other materials provided with the distribution.
18 1.1 jtc * 3. All advertising materials mentioning features or use of this software
19 1.1 jtc * must display the following acknowledgement:
20 1.1 jtc * This product includes software developed by the University of
21 1.1 jtc * California, Berkeley and its contributors.
22 1.1 jtc * 4. Neither the name of the University nor the names of its contributors
23 1.1 jtc * may be used to endorse or promote products derived from this software
24 1.1 jtc * without specific prior written permission.
25 1.1 jtc *
26 1.1 jtc * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
27 1.1 jtc * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
28 1.1 jtc * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
29 1.1 jtc * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
30 1.1 jtc * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
31 1.1 jtc * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
32 1.1 jtc * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
33 1.1 jtc * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
34 1.1 jtc * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
35 1.1 jtc * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
36 1.1 jtc * SUCH DAMAGE.
37 1.1 jtc */
38 1.1 jtc
39 1.1 jtc #ifndef lint
40 1.1 jtc static char copyright[] =
41 1.1 jtc "@(#) Copyright (c) 1993\n\
42 1.1 jtc The Regents of the University of California. All rights reserved.\n";
43 1.1 jtc #endif /* not lint */
44 1.1 jtc
45 1.1 jtc #ifndef lint
46 1.2 cgd #if 0
47 1.1 jtc static char sccsid[] = "@(#)mkdict.c 8.1 (Berkeley) 6/11/93";
48 1.2 cgd #else
49 1.2 cgd static char rcsid[] = "$NetBSD: mkdict.c,v 1.2 1995/03/21 12:14:49 cgd Exp $";
50 1.2 cgd #endif
51 1.1 jtc #endif /* not lint */
52 1.1 jtc
53 1.1 jtc /*
54 1.1 jtc * Filter out words that:
55 1.1 jtc * 1) Are not completely made up of lower case letters
56 1.1 jtc * 2) Contain a 'q' not immediately followed by a 'u'
57 1.1 jtc * 3) Are less that 3 characters long
58 1.1 jtc * 4) Are greater than MAXWORDLEN characters long
59 1.1 jtc */
60 1.1 jtc
61 1.1 jtc #include <ctype.h>
62 1.1 jtc #include <stdio.h>
63 1.1 jtc #include <stdlib.h>
64 1.1 jtc #include <string.h>
65 1.1 jtc
66 1.1 jtc #include "bog.h"
67 1.1 jtc
68 1.1 jtc int
69 1.1 jtc main(argc, argv)
70 1.1 jtc int argc;
71 1.1 jtc char *argv[];
72 1.1 jtc {
73 1.1 jtc register char *p, *q;
74 1.1 jtc register int ch, common, n, nwords;
75 1.1 jtc int current, len, prev, qcount;
76 1.1 jtc char buf[2][MAXWORDLEN + 1];
77 1.1 jtc
78 1.1 jtc prev = 0;
79 1.1 jtc current = 1;
80 1.1 jtc buf[prev][0] = '\0';
81 1.1 jtc if (argc == 2)
82 1.1 jtc n = atoi(argv[1]);
83 1.1 jtc
84 1.1 jtc for (nwords = 1;
85 1.1 jtc fgets(buf[current], MAXWORDLEN + 1, stdin) != NULL; ++nwords) {
86 1.1 jtc if ((p = index(buf[current], '\n')) == NULL) {
87 1.1 jtc fprintf(stderr,
88 1.1 jtc "mkdict: word too long: %s\n", buf[current]);
89 1.1 jtc while ((ch = getc(stdin)) != EOF && ch != '\n')
90 1.1 jtc ;
91 1.1 jtc if (ch == EOF)
92 1.1 jtc break;
93 1.1 jtc continue;
94 1.1 jtc }
95 1.1 jtc len = 0;
96 1.1 jtc for (p = buf[current]; *p != '\n'; p++) {
97 1.1 jtc if (!islower(*p))
98 1.1 jtc break;
99 1.1 jtc if (*p == 'q') {
100 1.1 jtc q = p + 1;
101 1.1 jtc if (*q != 'u')
102 1.1 jtc break;
103 1.1 jtc else {
104 1.1 jtc while (*q = *(q + 1))
105 1.1 jtc q++;
106 1.1 jtc }
107 1.1 jtc len++;
108 1.1 jtc }
109 1.1 jtc len++;
110 1.1 jtc }
111 1.1 jtc if (*p != '\n' || len < 3 || len > MAXWORDLEN)
112 1.1 jtc continue;
113 1.1 jtc if (argc == 2 && nwords % n)
114 1.1 jtc continue;
115 1.1 jtc
116 1.1 jtc *p = '\0';
117 1.1 jtc p = buf[current];
118 1.1 jtc q = buf[prev];
119 1.1 jtc qcount = 0;
120 1.1 jtc while ((ch = *p++) == *q++ && ch != '\0')
121 1.1 jtc if (ch == 'q')
122 1.1 jtc qcount++;
123 1.1 jtc common = p - buf[current] - 1;
124 1.1 jtc printf("%c%s", common + qcount, p - 1);
125 1.1 jtc prev = !prev;
126 1.1 jtc current = !current;
127 1.1 jtc }
128 1.1 jtc fprintf(stderr, "%d words\n", nwords);
129 1.1 jtc exit(0);
130 1.1 jtc }
131