1 /* $NetBSD: parse.c,v 1.18 2021/05/02 12:50:43 rillig 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
35 static char sccsid[] = "@(#)parse.c 8.2 (Berkeley) 4/28/95";
36 #else
37 __RCSID("$NetBSD: parse.c,v 1.18 2021/05/02 12:50:43 rillig 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
47 static int hash(const char *);
48 static void install(struct wlist *);
49 static struct wlist *lookup(const char *);
50
51 static struct wlist *hashtab[HASHSIZE];
52
53 void
wordinit(void)54 wordinit(void)
55 {
56 struct wlist *w;
57
58 for (w = wlist; w->string; w++)
59 install(w);
60 }
61
62 static int
hash(const char * s)63 hash(const char *s)
64 {
65 int hashval = 0;
66
67 while (*s) {
68 hashval += *s++;
69 hashval *= HASHMUL;
70 hashval &= HASHMASK;
71 }
72 return hashval;
73 }
74
75 static struct wlist *
lookup(const char * s)76 lookup(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
86 static void
install(struct wlist * wp)87 install(struct wlist *wp)
88 {
89 int hashval;
90
91 if (lookup(wp->string) == NULL) {
92 hashval = hash(wp->string);
93 wp->next = hashtab[hashval];
94 hashtab[hashval] = wp;
95 } else
96 printf("Multiply defined %s.\n", wp->string);
97 }
98
99 void
parse(void)100 parse(void)
101 {
102 struct wlist *wp;
103 int n;
104 int flag;
105
106 wordnumber = 0; /* for cypher */
107 for (n = 0; n <= wordcount; n++) {
108 if ((wp = lookup(words[n])) == NULL) {
109 wordvalue[n] = -1;
110 wordtype[n] = -1;
111 } else {
112 wordvalue[n] = wp->value;
113 wordtype[n] = wp->article;
114 }
115 }
116 /* We never use adjectives for anything, so yank them all. */
117 for (n = 1; n < wordcount; n++)
118 if (wordtype[n] == ADJS) {
119 int i;
120 for (i = n + 1; i < wordcount; i++) {
121 wordtype[i - 1] = wordtype[i];
122 wordvalue[i - 1] = wordvalue[i];
123 strlcpy(words[i - 1], words[i], WORDLEN);
124 }
125 wordcount--;
126 }
127 /* Don't let a comma mean AND if followed by a verb. */
128 for (n = 0; n < wordcount; n++)
129 if (wordvalue[n] == AND && words[n][0] == ','
130 && wordtype[n + 1] == VERB) {
131 wordvalue[n] = -1;
132 wordtype[n] = -1;
133 }
134 /* Trim "AND AND" which can happen naturally at the end of a
135 * comma-delimited list.
136 */
137 for (n = 1; n < wordcount; n++)
138 if (wordvalue[n - 1] == AND && wordvalue[n] == AND) {
139 int i;
140 for (i = n + 1; i < wordcount; i++) {
141 wordtype[i - 1] = wordtype[i];
142 wordvalue[i - 1] = wordvalue[i];
143 strlcpy(words[i - 1], words[i], WORDLEN);
144 }
145 wordcount--;
146 }
147
148 /* If there is a sequence (NOUN | OBJECT) AND EVERYTHING
149 * then move all the EVERYTHINGs to the beginning, since that's where
150 * they're expected. We can't get rid of the NOUNs and OBJECTs in
151 * case they aren't in EVERYTHING (i.e. not here or nonexistent).
152 */
153 flag = 1;
154 while (flag) {
155 flag = 0;
156 for (n = 1; n < wordcount; n++)
157 if ((wordtype[n - 1] == NOUNS ||
158 wordtype[n - 1] == OBJECT) &&
159 wordvalue[n] == AND &&
160 wordvalue[n + 1] == EVERYTHING) {
161 char tmpword[WORDLEN];
162 wordvalue[n + 1] = wordvalue[n - 1];
163 wordvalue[n - 1] = EVERYTHING;
164 wordtype[n + 1] = wordtype[n - 1];
165 wordtype[n - 1] = OBJECT;
166 strcpy(tmpword, words[n - 1]);
167 strlcpy(words[n - 1], words[n + 1], WORDLEN);
168 strcpy(words[n + 1], tmpword);
169 flag = 1;
170 }
171 /* And trim EVERYTHING AND EVERYTHING. */
172 for (n = 1; n < wordcount; n++)
173 if (wordvalue[n - 1] == EVERYTHING &&
174 wordvalue[n] == AND &&
175 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 strlcpy(words[i - 1], words[i + 1], WORDLEN);
181 }
182 wordcount--;
183 wordcount--;
184 flag = 1;
185 }
186 }
187 }
188