1 /* $OpenBSD: parse.c,v 1.12 2003/06/03 03:01:38 millert 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 #ifndef lint 34 #if 0 35 static char sccsid[] = "@(#)parse.c 8.2 (Berkeley) 4/28/95"; 36 #else 37 static char rcsid[] = "$OpenBSD: parse.c,v 1.12 2003/06/03 03:01:38 millert 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 struct wlist *hashtab[HASHSIZE]; 52 53 void 54 wordinit() 55 { 56 struct wlist *w; 57 58 for (w = wlist; w->string; w++) 59 install(w); 60 } 61 62 static int 63 hash(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 76 static struct wlist * 77 lookup(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 88 static void 89 install(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 } 101 102 void 103 parse() 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, so yank them all; disambiguation 120 * code would need to go before this. 121 */ 122 for (n = 1; n < wordcount; n++) 123 if (wordtype[n] == ADJS) { 124 int i; 125 for (i = n + 1; i <= wordcount; i++) { 126 wordtype[i - 1] = wordtype[i]; 127 wordvalue[i - 1] = wordvalue[i]; 128 strlcpy(words[i - 1], words[i], WORDLEN); 129 } 130 wordcount--; 131 n--; 132 } 133 /* Don't let a comma mean AND if followed by a verb. */ 134 for (n = 0; n < wordcount; n++) 135 if (wordvalue[n] == AND && words[n][0] == ',' 136 && wordtype[n + 1] == VERB) { 137 wordvalue[n] = -1; 138 wordtype[n] = -1; 139 } 140 /* Trim "AND AND" which can happen naturally at the end of a 141 * comma-delimited list. 142 */ 143 for (n = 1; n < wordcount; n++) 144 if (wordvalue[n - 1] == AND && wordvalue[n] == AND) { 145 int i; 146 for (i = n + 1; i <= wordcount; i++) { 147 wordtype[i - 1] = wordtype[i]; 148 wordvalue[i - 1] = wordvalue[i]; 149 strlcpy(words[i - 1], words[i], WORDLEN); 150 } 151 wordcount--; 152 } 153 154 /* If there is a sequence (NOUN | OBJECT) AND EVERYTHING 155 * then move all the EVERYTHINGs to the beginning, since that's where 156 * they're expected. We can't get rid of the NOUNs and OBJECTs in 157 * case they aren't in EVERYTHING (i.e. not here or nonexistant). 158 */ 159 flag = 1; 160 while (flag) { 161 flag = 0; 162 for (n = 1; n < wordcount; n++) 163 if ((wordtype[n - 1] == NOUNS || wordtype[n - 1] == OBJECT) && 164 wordvalue[n] == AND && wordvalue[n + 1] == EVERYTHING) { 165 char tmpword[WORDLEN]; 166 wordvalue[n + 1] = wordvalue[n - 1]; 167 wordvalue[n - 1] = EVERYTHING; 168 wordtype[n + 1] = wordtype[n - 1]; 169 wordtype[n - 1] = OBJECT; 170 strlcpy(tmpword, words[n - 1], WORDLEN); 171 strlcpy(words[n - 1], words[n + 1], WORDLEN); 172 strlcpy(words[n + 1], tmpword, WORDLEN); 173 flag = 1; 174 } 175 /* And trim EVERYTHING AND EVERYTHING */ 176 for (n = 1; n < wordcount; n++) 177 if (wordvalue[n - 1] == EVERYTHING && 178 wordvalue[n] == AND && wordvalue[n + 1] == EVERYTHING) { 179 int i; 180 for (i = n + 1; i < wordcount; i++) { 181 wordtype[i - 1] = wordtype[i + 1]; 182 wordvalue[i - 1] = wordvalue[i + 1]; 183 strlcpy(words[i - 1], words[i + 1], WORDLEN); 184 } 185 wordcount--; 186 wordcount--; 187 flag = 1; 188 } 189 } 190 } 191