1 /* $OpenBSD: parse.c,v 1.16 2015/12/31 17:51:19 mestre Exp $ */
2 /* $NetBSD: parse.c,v 1.3 1995/03/21 15:07:48 cgd Exp $ */
3
4 /*
5 * Copyright (c) 1983, 1993
6 * The Regents of the University of California. All rights reserved.
7 *
8 * Redistribution and use in source and binary forms, with or without
9 * modification, are permitted provided that the following conditions
10 * are met:
11 * 1. Redistributions of source code must retain the above copyright
12 * notice, this list of conditions and the following disclaimer.
13 * 2. Redistributions in binary form must reproduce the above copyright
14 * notice, this list of conditions and the following disclaimer in the
15 * documentation and/or other materials provided with the distribution.
16 * 3. Neither the name of the University nor the names of its contributors
17 * may be used to endorse or promote products derived from this software
18 * without specific prior written permission.
19 *
20 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
21 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
22 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
23 * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
24 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
25 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
26 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
27 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
28 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
29 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
30 * SUCH DAMAGE.
31 */
32
33 #include <stdio.h>
34 #include <string.h>
35
36 #include "extern.h"
37
38 #define HASHSIZE 256
39 #define HASHMUL 81
40 #define HASHMASK (HASHSIZE - 1)
41
42 static int hash(const char *);
43 static void install(struct wlist *);
44 static struct wlist *lookup(const char *);
45
46 struct wlist *hashtab[HASHSIZE];
47
48 void
wordinit(void)49 wordinit(void)
50 {
51 struct wlist *w;
52
53 for (w = wlist; w->string; w++)
54 install(w);
55 }
56
57 static int
hash(const char * s)58 hash(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 static struct wlist *
lookup(const char * s)71 lookup(const char *s)
72 {
73 struct wlist *wp;
74
75 for (wp = hashtab[hash(s)]; wp != NULL; wp = wp->next)
76 if (*s == *wp->string && strcmp(s, wp->string) == 0)
77 return wp;
78 return NULL;
79 }
80
81 static void
install(struct wlist * wp)82 install(struct wlist *wp)
83 {
84 int hashval;
85
86 if (lookup(wp->string) == NULL) {
87 hashval = hash(wp->string);
88 wp->next = hashtab[hashval];
89 hashtab[hashval] = wp;
90 } else
91 printf("Multiply defined %s.\n", wp->string);
92 }
93
94 void
parse(void)95 parse(void)
96 {
97 struct wlist *wp;
98 int n;
99 int flag;
100
101 wordnumber = 0; /* for cypher */
102 for (n = 0; n <= wordcount; n++) {
103 if ((wp = lookup(words[n])) == NULL) {
104 wordvalue[n] = -1;
105 wordtype[n] = -1;
106 } else {
107 wordvalue[n] = wp->value;
108 wordtype[n] = wp->article;
109 }
110 }
111 /* We never use adjectives, so yank them all; disambiguation
112 * code would need to go before this.
113 */
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 strlcpy(words[i - 1], words[i], WORDLEN);
121 }
122 wordcount--;
123 n--;
124 }
125 /* Don't let a comma mean AND if followed by a verb. */
126 for (n = 0; n < wordcount; n++)
127 if (wordvalue[n] == AND && words[n][0] == ','
128 && wordtype[n + 1] == VERB) {
129 wordvalue[n] = -1;
130 wordtype[n] = -1;
131 }
132 /* Trim "AND AND" which can happen naturally at the end of a
133 * comma-delimited list.
134 */
135 for (n = 1; n < wordcount; n++)
136 if (wordvalue[n - 1] == AND && wordvalue[n] == AND) {
137 int i;
138 for (i = n + 1; i <= wordcount; i++) {
139 wordtype[i - 1] = wordtype[i];
140 wordvalue[i - 1] = wordvalue[i];
141 strlcpy(words[i - 1], words[i], WORDLEN);
142 }
143 wordcount--;
144 }
145
146 /* If there is a sequence (NOUN | OBJECT) AND EVERYTHING
147 * then move all the EVERYTHINGs to the beginning, since that's where
148 * they're expected. We can't get rid of the NOUNs and OBJECTs in
149 * case they aren't in EVERYTHING (i.e. not here or nonexistent).
150 */
151 flag = 1;
152 while (flag) {
153 flag = 0;
154 for (n = 1; n < wordcount; n++)
155 if ((wordtype[n - 1] == NOUNS || wordtype[n - 1] == OBJECT) &&
156 wordvalue[n] == AND && wordvalue[n + 1] == EVERYTHING) {
157 char tmpword[WORDLEN];
158 wordvalue[n + 1] = wordvalue[n - 1];
159 wordvalue[n - 1] = EVERYTHING;
160 wordtype[n + 1] = wordtype[n - 1];
161 wordtype[n - 1] = OBJECT;
162 strlcpy(tmpword, words[n - 1], WORDLEN);
163 strlcpy(words[n - 1], words[n + 1], WORDLEN);
164 strlcpy(words[n + 1], tmpword, WORDLEN);
165 flag = 1;
166 }
167 /* And trim EVERYTHING AND EVERYTHING */
168 for (n = 1; n < wordcount; n++)
169 if (wordvalue[n - 1] == EVERYTHING &&
170 wordvalue[n] == AND && wordvalue[n + 1] == EVERYTHING) {
171 int i;
172 for (i = n + 1; i < wordcount; i++) {
173 wordtype[i - 1] = wordtype[i + 1];
174 wordvalue[i - 1] = wordvalue[i + 1];
175 strlcpy(words[i - 1], words[i + 1], WORDLEN);
176 }
177 wordcount--;
178 wordcount--;
179 flag = 1;
180 }
181 }
182 }
183