1 /* $NetBSD: mkdict.c,v 1.10 2005/04/19 20:19:09 rillig Exp $ */
5 * The Regents of the University of California. All rights reserved.
7 * This code is derived from software contributed to Berkeley by
10 * Redistribution and use in source and binary forms, with or without
11 * modification, are permitted provided that the following conditions
13 * 1. Redistributions of source code must retain the above copyright
14 * notice, this list of conditions and the following disclaimer.
15 * 2. Redistributions in binary form must reproduce the above copyright
16 * notice, this list of conditions and the following disclaimer in the
17 * documentation and/or other materials provided with the distribution.
18 * 3. Neither the name of the University nor the names of its contributors
19 * may be used to endorse or promote products derived from this software
20 * without specific prior written permission.
22 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
23 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
24 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
25 * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
26 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
27 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
28 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
29 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
30 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
31 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
36 static const char copyright
[] =
37 "@(#) Copyright (c) 1993\n\
38 The Regents of the University of California. All rights reserved.\n";
40 static char sccsid
[] = "@(#)mkdict.c 8.1 (Berkeley) 6/11/93";
42 static const char rcsid
[] =
43 "$NetBSD: mkdict.c,v 1.10 2005/04/19 20:19:09 rillig Exp $";
48 * Filter out words that:
49 * 1) Are not completely made up of lower case letters
50 * 2) Contain a 'q' not immediately followed by a 'u'
51 * 3) Are less that 3 characters long
52 * 4) Are greater than MAXWORDLEN characters long
63 main(int argc
, char *argv
[])
66 int ch
, common
, nwords
;
67 int current
, len
, prev
, qcount
;
68 char buf
[2][MAXWORDLEN
+ 1];
75 fgets(buf
[current
], MAXWORDLEN
+ 1, stdin
) != NULL
; ++nwords
) {
76 if ((p
= strchr(buf
[current
], '\n')) == NULL
) {
77 fprintf(stderr
, "word too long: %s\n", buf
[current
]);
78 while ((ch
= getc(stdin
)) != EOF
&& ch
!= '\n')
85 for (p
= buf
[current
]; *p
!= '\n'; p
++) {
86 if (!islower((unsigned char)*p
))
93 while ((*q
= *(q
+ 1)))
100 if (*p
!= '\n' || len
< 3 || len
> MAXWORDLEN
)
102 if (argc
== 2 && nwords
% atoi(argv
[1]))
109 while ((ch
= *p
++) == *q
++ && ch
!= '\0')
112 common
= p
- buf
[current
] - 1;
113 printf("%c%s", common
+ qcount
, p
- 1);
117 fprintf(stderr
, "%d words\n", nwords
);
119 if (ferror(stdout
)) {
120 perror("error writing standard output");