parse.c revision 1.10 
1/*	$NetBSD: parse.c,v 1.10 2000/09/24 09:46:28 jsm Exp $	*/
2
3/*
4 * Copyright (c) 1983, 1993
5 *	The Regents of the University of California.  All rights reserved.
6 *
7 * Redistribution and use in source and binary forms, with or without
8 * modification, are permitted provided that the following conditions
9 * are met:
10 * 1. Redistributions of source code must retain the above copyright
11 *    notice, this list of conditions and the following disclaimer.
12 * 2. Redistributions in binary form must reproduce the above copyright
13 *    notice, this list of conditions and the following disclaimer in the
14 *    documentation and/or other materials provided with the distribution.
15 * 3. All advertising materials mentioning features or use of this software
16 *    must display the following acknowledgement:
17 *	This product includes software developed by the University of
18 *	California, Berkeley and its contributors.
19 * 4. Neither the name of the University nor the names of its contributors
20 *    may be used to endorse or promote products derived from this software
21 *    without specific prior written permission.
22 *
23 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
24 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
25 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
26 * ARE DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
27 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
28 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
29 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
30 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
31 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
32 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
33 * SUCH DAMAGE.
34 */
35
36#include <sys/cdefs.h>
37#ifndef lint
38#if 0
39static char sccsid[] = "@(#)parse.c	8.2 (Berkeley) 4/28/95";
40#else
41__RCSID("$NetBSD: parse.c,v 1.10 2000/09/24 09:46:28 jsm Exp $");
42#endif
43#endif				/* not lint */
44
45#include "extern.h"
46
47static int hash __P((const char *));
48static void install __P((struct wlist *));
49static struct wlist *lookup __P((const char *));
50
51void
52wordinit()
53{
54	struct wlist *w;
55
56	for (w = wlist; w->string; w++)
57		install(w);
58}
59
60static int
61hash(s)
62	const char   *s;
63{
64	int     hashval = 0;
65
66	while (*s) {
67		hashval += *s++;
68		hashval *= HASHMUL;
69		hashval &= HASHMASK;
70	}
71	return hashval;
72}
73
74static struct wlist *
75lookup(s)
76	const char   *s;
77{
78	struct wlist *wp;
79
80	for (wp = hashtab[hash(s)]; wp != NULL; wp = wp->next)
81		if (*s == *wp->string && strcmp(s, wp->string) == 0)
82			return wp;
83	return NULL;
84}
85
86static void
87install(wp)
88	struct wlist *wp;
89{
90	int     hashval;
91
92	if (lookup(wp->string) == NULL) {
93		hashval = hash(wp->string);
94		wp->next = hashtab[hashval];
95		hashtab[hashval] = wp;
96	} else
97		printf("Multiply defined %s.\n", wp->string);
98}
99
100void
101parse()
102{
103	struct wlist *wp;
104	int     n;
105	int     flag;
106
107	wordnumber = 0;		/* for cypher */
108	for (n = 0; n <= wordcount; n++) {
109		if ((wp = lookup(words[n])) == NULL) {
110			wordvalue[n] = -1;
111			wordtype[n] = -1;
112		} else {
113			wordvalue[n] = wp->value;
114			wordtype[n] = wp->article;
115		}
116	}
117	/* We never use adjectives for anything, so yank them all. */
118	for (n = 1; n < wordcount; n++)
119		if (wordtype[n] == ADJS) {
120			int i;
121			for (i = n + 1; i < wordcount; i++) {
122				wordtype[i - 1] = wordtype[i];
123				wordvalue[i - 1] = wordvalue[i];
124				strcpy(words[i - 1], words[i]);
125			}
126			wordcount--;
127		}
128	/* Don't let a comma mean AND if followed by a verb. */
129	for (n = 0; n < wordcount; n++)
130		if (wordvalue[n] == AND && words[n][0] == ','
131		    && wordtype[n + 1] == VERB) {
132			wordvalue[n] = -1;
133			wordtype[n] = -1;
134		}
135	/* Trim "AND AND" which can happen naturally at the end of a
136	 * comma-delimited list.
137	 */
138	for (n = 1; n < wordcount; n++)
139		if (wordvalue[n - 1] == AND && wordvalue[n] == AND) {
140			int i;
141			for (i = n + 1; i < wordcount; i++) {
142				wordtype[i - 1] = wordtype[i];
143				wordvalue[i - 1] = wordvalue[i];
144				strcpy(words[i - 1], words[i]);
145			}
146			wordcount--;
147		}
148
149	/* If there is a sequence (NOUN | OBJECT) AND EVERYTHING
150	 * then move all the EVERYTHINGs to the beginning, since that's where
151	 * they're expected.  We can't get rid of the NOUNs and OBJECTs in
152	 * case they aren't in EVERYTHING (i.e. not here or nonexistant).
153	 */
154	flag = 1;
155	while (flag) {
156		flag = 0;
157		for (n = 1; n < wordcount; n++)
158			if ((wordtype[n - 1] == NOUNS || wordtype[n - 1] == OBJECT) &&
159			    wordvalue[n] == AND && wordvalue[n + 1] == EVERYTHING) {
160				char tmpword[WORDLEN];
161				wordvalue[n + 1] = wordvalue[n - 1];
162				wordvalue[n - 1] = EVERYTHING;
163				wordtype[n + 1] = wordtype[n - 1];
164				wordtype[n - 1] = OBJECT;
165				strcpy(tmpword, words[n - 1]);
166				strcpy(words[n - 1], words[n + 1]);
167				strcpy(words[n + 1], tmpword);
168				flag = 1;
169		}
170		/* And trim EVERYTHING AND EVERYTHING. */
171		for (n = 1; n < wordcount; n++)
172			if (wordvalue[n - 1] == EVERYTHING &&
173			    wordvalue[n] == AND && wordvalue[n + 1] == EVERYTHING) {
174				int i;
175				for (i = n + 1; i < wordcount; i++) {
176					wordtype[i - 1] = wordtype[i + 1];
177					wordvalue[i - 1] = wordvalue[i + 1];
178					strcpy(words[i - 1], words[i + 1]);
179				}
180				wordcount--;
181				wordcount--;
182				flag = 1;
183			}
184	}
185}
186