parse.c revision 1.14 
1/*	$NetBSD: parse.c,v 1.14 2004/01/27 20:30:29 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. Neither the name of the University nor the names of its contributors
16 *    may be used to endorse or promote products derived from this software
17 *    without specific prior written permission.
18 *
19 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
20 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
21 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
22 * ARE DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
23 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
24 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
25 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
26 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
27 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
28 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
29 * SUCH DAMAGE.
30 */
31
32#include <sys/cdefs.h>
33#ifndef lint
34#if 0
35static char sccsid[] = "@(#)parse.c	8.2 (Berkeley) 4/28/95";
36#else
37__RCSID("$NetBSD: parse.c,v 1.14 2004/01/27 20:30:29 jsm Exp $");
38#endif
39#endif				/* not lint */
40
41#include "extern.h"
42
43#define HASHSIZE	256
44#define HASHMUL		81
45#define HASHMASK	(HASHSIZE - 1)
46
47static int hash(const char *);
48static void install(struct wlist *);
49static struct wlist *lookup(const char *);
50
51static struct wlist *hashtab[HASHSIZE];
52
53void
54wordinit()
55{
56	struct wlist *w;
57
58	for (w = wlist; w->string; w++)
59		install(w);
60}
61
62static int
63hash(s)
64	const char   *s;
65{
66	int     hashval = 0;
67
68	while (*s) {
69		hashval += *s++;
70		hashval *= HASHMUL;
71		hashval &= HASHMASK;
72	}
73	return hashval;
74}
75
76static struct wlist *
77lookup(s)
78	const char   *s;
79{
80	struct wlist *wp;
81
82	for (wp = hashtab[hash(s)]; wp != NULL; wp = wp->next)
83		if (*s == *wp->string && strcmp(s, wp->string) == 0)
84			return wp;
85	return NULL;
86}
87
88static void
89install(wp)
90	struct wlist *wp;
91{
92	int     hashval;
93
94	if (lookup(wp->string) == NULL) {
95		hashval = hash(wp->string);
96		wp->next = hashtab[hashval];
97		hashtab[hashval] = wp;
98	} else
99		printf("Multiply defined %s.\n", wp->string);
100}
101
102void
103parse()
104{
105	struct wlist *wp;
106	int     n;
107	int     flag;
108
109	wordnumber = 0;		/* for cypher */
110	for (n = 0; n <= wordcount; n++) {
111		if ((wp = lookup(words[n])) == NULL) {
112			wordvalue[n] = -1;
113			wordtype[n] = -1;
114		} else {
115			wordvalue[n] = wp->value;
116			wordtype[n] = wp->article;
117		}
118	}
119	/* We never use adjectives for anything, so yank them all. */
120	for (n = 1; n < wordcount; n++)
121		if (wordtype[n] == ADJS) {
122			int i;
123			for (i = n + 1; i < wordcount; i++) {
124				wordtype[i - 1] = wordtype[i];
125				wordvalue[i - 1] = wordvalue[i];
126				strcpy(words[i - 1], words[i]);
127			}
128			wordcount--;
129		}
130	/* Don't let a comma mean AND if followed by a verb. */
131	for (n = 0; n < wordcount; n++)
132		if (wordvalue[n] == AND && words[n][0] == ','
133		    && wordtype[n + 1] == VERB) {
134			wordvalue[n] = -1;
135			wordtype[n] = -1;
136		}
137	/* Trim "AND AND" which can happen naturally at the end of a
138	 * comma-delimited list.
139	 */
140	for (n = 1; n < wordcount; n++)
141		if (wordvalue[n - 1] == AND && wordvalue[n] == AND) {
142			int i;
143			for (i = n + 1; i < wordcount; i++) {
144				wordtype[i - 1] = wordtype[i];
145				wordvalue[i - 1] = wordvalue[i];
146				strcpy(words[i - 1], words[i]);
147			}
148			wordcount--;
149		}
150
151	/* If there is a sequence (NOUN | OBJECT) AND EVERYTHING
152	 * then move all the EVERYTHINGs to the beginning, since that's where
153	 * they're expected.  We can't get rid of the NOUNs and OBJECTs in
154	 * case they aren't in EVERYTHING (i.e. not here or nonexistent).
155	 */
156	flag = 1;
157	while (flag) {
158		flag = 0;
159		for (n = 1; n < wordcount; n++)
160			if ((wordtype[n - 1] == NOUNS || wordtype[n - 1] == OBJECT) &&
161			    wordvalue[n] == AND && wordvalue[n + 1] == EVERYTHING) {
162				char tmpword[WORDLEN];
163				wordvalue[n + 1] = wordvalue[n - 1];
164				wordvalue[n - 1] = EVERYTHING;
165				wordtype[n + 1] = wordtype[n - 1];
166				wordtype[n - 1] = OBJECT;
167				strcpy(tmpword, words[n - 1]);
168				strcpy(words[n - 1], words[n + 1]);
169				strcpy(words[n + 1], tmpword);
170				flag = 1;
171		}
172		/* And trim EVERYTHING AND EVERYTHING. */
173		for (n = 1; n < wordcount; n++)
174			if (wordvalue[n - 1] == EVERYTHING &&
175			    wordvalue[n] == AND && wordvalue[n + 1] == EVERYTHING) {
176				int i;
177				for (i = n + 1; i < wordcount; i++) {
178					wordtype[i - 1] = wordtype[i + 1];
179					wordvalue[i - 1] = wordvalue[i + 1];
180					strcpy(words[i - 1], words[i + 1]);
181				}
182				wordcount--;
183				wordcount--;
184				flag = 1;
185			}
186	}
187}
188