parse.c revision 1.9 1 /* $NetBSD: parse.c,v 1.9 2000/09/22 08:19:21 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
39 static char sccsid[] = "@(#)parse.c 8.2 (Berkeley) 4/28/95";
40 #else
41 __RCSID("$NetBSD: parse.c,v 1.9 2000/09/22 08:19:21 jsm Exp $");
42 #endif
43 #endif /* not lint */
44
45 #include "extern.h"
46
47 void
48 wordinit()
49 {
50 struct wlist *w;
51
52 for (w = wlist; w->string; w++)
53 install(w);
54 }
55
56 int
57 hash(s)
58 const char *s;
59 {
60 int hashval = 0;
61
62 while (*s) {
63 hashval += *s++;
64 hashval *= HASHMUL;
65 hashval &= HASHMASK;
66 }
67 return hashval;
68 }
69
70 struct wlist *
71 lookup(s)
72 const char *s;
73 {
74 struct wlist *wp;
75
76 for (wp = hashtab[hash(s)]; wp != NULL; wp = wp->next)
77 if (*s == *wp->string && strcmp(s, wp->string) == 0)
78 return wp;
79 return NULL;
80 }
81
82 void
83 install(wp)
84 struct wlist *wp;
85 {
86 int hashval;
87
88 if (lookup(wp->string) == NULL) {
89 hashval = hash(wp->string);
90 wp->next = hashtab[hashval];
91 hashtab[hashval] = wp;
92 } else
93 printf("Multiply defined %s.\n", wp->string);
94 }
95
96 void
97 parse()
98 {
99 struct wlist *wp;
100 int n;
101 int flag;
102
103 wordnumber = 0; /* for cypher */
104 for (n = 0; n <= wordcount; n++) {
105 if ((wp = lookup(words[n])) == NULL) {
106 wordvalue[n] = -1;
107 wordtype[n] = -1;
108 } else {
109 wordvalue[n] = wp->value;
110 wordtype[n] = wp->article;
111 }
112 }
113 /* We never use adjectives for anything, so yank them all. */
114 for (n = 1; n < wordcount; n++)
115 if (wordtype[n] == ADJS) {
116 int i;
117 for (i = n + 1; i < wordcount; i++) {
118 wordtype[i - 1] = wordtype[i];
119 wordvalue[i - 1] = wordvalue[i];
120 strcpy(words[i - 1], words[i]);
121 }
122 wordcount--;
123 }
124 /* Don't let a comma mean AND if followed by a verb. */
125 for (n = 0; n < wordcount; n++)
126 if (wordvalue[n] == AND && words[n][0] == ','
127 && wordtype[n + 1] == VERB) {
128 wordvalue[n] = -1;
129 wordtype[n] = -1;
130 }
131 /* Trim "AND AND" which can happen naturally at the end of a
132 * comma-delimited list.
133 */
134 for (n = 1; n < wordcount; n++)
135 if (wordvalue[n - 1] == AND && wordvalue[n] == AND) {
136 int i;
137 for (i = n + 1; i < wordcount; i++) {
138 wordtype[i - 1] = wordtype[i];
139 wordvalue[i - 1] = wordvalue[i];
140 strcpy(words[i - 1], words[i]);
141 }
142 wordcount--;
143 }
144
145 /* If there is a sequence (NOUN | OBJECT) AND EVERYTHING
146 * then move all the EVERYTHINGs to the beginning, since that's where
147 * they're expected. We can't get rid of the NOUNs and OBJECTs in
148 * case they aren't in EVERYTHING (i.e. not here or nonexistant).
149 */
150 flag = 1;
151 while (flag) {
152 flag = 0;
153 for (n = 1; n < wordcount; n++)
154 if ((wordtype[n - 1] == NOUNS || wordtype[n - 1] == OBJECT) &&
155 wordvalue[n] == AND && wordvalue[n + 1] == EVERYTHING) {
156 char tmpword[WORDLEN];
157 wordvalue[n + 1] = wordvalue[n - 1];
158 wordvalue[n - 1] = EVERYTHING;
159 wordtype[n + 1] = wordtype[n - 1];
160 wordtype[n - 1] = OBJECT;
161 strcpy(tmpword, words[n - 1]);
162 strcpy(words[n - 1], words[n + 1]);
163 strcpy(words[n + 1], tmpword);
164 flag = 1;
165 }
166 /* And trim EVERYTHING AND EVERYTHING. */
167 for (n = 1; n < wordcount; n++)
168 if (wordvalue[n - 1] == EVERYTHING &&
169 wordvalue[n] == AND && wordvalue[n + 1] == EVERYTHING) {
170 int i;
171 for (i = n + 1; i < wordcount; i++) {
172 wordtype[i - 1] = wordtype[i + 1];
173 wordvalue[i - 1] = wordvalue[i + 1];
174 strcpy(words[i - 1], words[i + 1]);
175 }
176 wordcount--;
177 wordcount--;
178 flag = 1;
179 }
180 }
181 }
182