parse.c revision 1.11
1/* $NetBSD: parse.c,v 1.11 2000/09/24 14:11:09 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 39static char sccsid[] = "@(#)parse.c 8.2 (Berkeley) 4/28/95"; 40#else 41__RCSID("$NetBSD: parse.c,v 1.11 2000/09/24 14:11:09 jsm Exp $"); 42#endif 43#endif /* not lint */ 44 45#include "extern.h" 46 47#define HASHSIZE 256 48#define HASHMUL 81 49#define HASHMASK (HASHSIZE - 1) 50 51static int hash __P((const char *)); 52static void install __P((struct wlist *)); 53static struct wlist *lookup __P((const char *)); 54 55static struct wlist *hashtab[HASHSIZE]; 56 57void 58wordinit() 59{ 60 struct wlist *w; 61 62 for (w = wlist; w->string; w++) 63 install(w); 64} 65 66static int 67hash(s) 68 const char *s; 69{ 70 int hashval = 0; 71 72 while (*s) { 73 hashval += *s++; 74 hashval *= HASHMUL; 75 hashval &= HASHMASK; 76 } 77 return hashval; 78} 79 80static struct wlist * 81lookup(s) 82 const char *s; 83{ 84 struct wlist *wp; 85 86 for (wp = hashtab[hash(s)]; wp != NULL; wp = wp->next) 87 if (*s == *wp->string && strcmp(s, wp->string) == 0) 88 return wp; 89 return NULL; 90} 91 92static void 93install(wp) 94 struct wlist *wp; 95{ 96 int hashval; 97 98 if (lookup(wp->string) == NULL) { 99 hashval = hash(wp->string); 100 wp->next = hashtab[hashval]; 101 hashtab[hashval] = wp; 102 } else 103 printf("Multiply defined %s.\n", wp->string); 104} 105 106void 107parse() 108{ 109 struct wlist *wp; 110 int n; 111 int flag; 112 113 wordnumber = 0; /* for cypher */ 114 for (n = 0; n <= wordcount; n++) { 115 if ((wp = lookup(words[n])) == NULL) { 116 wordvalue[n] = -1; 117 wordtype[n] = -1; 118 } else { 119 wordvalue[n] = wp->value; 120 wordtype[n] = wp->article; 121 } 122 } 123 /* We never use adjectives for anything, so yank them all. */ 124 for (n = 1; n < wordcount; n++) 125 if (wordtype[n] == ADJS) { 126 int i; 127 for (i = n + 1; i < wordcount; i++) { 128 wordtype[i - 1] = wordtype[i]; 129 wordvalue[i - 1] = wordvalue[i]; 130 strcpy(words[i - 1], words[i]); 131 } 132 wordcount--; 133 } 134 /* Don't let a comma mean AND if followed by a verb. */ 135 for (n = 0; n < wordcount; n++) 136 if (wordvalue[n] == AND && words[n][0] == ',' 137 && wordtype[n + 1] == VERB) { 138 wordvalue[n] = -1; 139 wordtype[n] = -1; 140 } 141 /* Trim "AND AND" which can happen naturally at the end of a 142 * comma-delimited list. 143 */ 144 for (n = 1; n < wordcount; n++) 145 if (wordvalue[n - 1] == AND && wordvalue[n] == AND) { 146 int i; 147 for (i = n + 1; i < wordcount; i++) { 148 wordtype[i - 1] = wordtype[i]; 149 wordvalue[i - 1] = wordvalue[i]; 150 strcpy(words[i - 1], words[i]); 151 } 152 wordcount--; 153 } 154 155 /* If there is a sequence (NOUN | OBJECT) AND EVERYTHING 156 * then move all the EVERYTHINGs to the beginning, since that's where 157 * they're expected. We can't get rid of the NOUNs and OBJECTs in 158 * case they aren't in EVERYTHING (i.e. not here or nonexistant). 159 */ 160 flag = 1; 161 while (flag) { 162 flag = 0; 163 for (n = 1; n < wordcount; n++) 164 if ((wordtype[n - 1] == NOUNS || wordtype[n - 1] == OBJECT) && 165 wordvalue[n] == AND && wordvalue[n + 1] == EVERYTHING) { 166 char tmpword[WORDLEN]; 167 wordvalue[n + 1] = wordvalue[n - 1]; 168 wordvalue[n - 1] = EVERYTHING; 169 wordtype[n + 1] = wordtype[n - 1]; 170 wordtype[n - 1] = OBJECT; 171 strcpy(tmpword, words[n - 1]); 172 strcpy(words[n - 1], words[n + 1]); 173 strcpy(words[n + 1], tmpword); 174 flag = 1; 175 } 176 /* And trim EVERYTHING AND EVERYTHING. */ 177 for (n = 1; n < wordcount; n++) 178 if (wordvalue[n - 1] == EVERYTHING && 179 wordvalue[n] == AND && wordvalue[n + 1] == EVERYTHING) { 180 int i; 181 for (i = n + 1; i < wordcount; i++) { 182 wordtype[i - 1] = wordtype[i + 1]; 183 wordvalue[i - 1] = wordvalue[i + 1]; 184 strcpy(words[i - 1], words[i + 1]); 185 } 186 wordcount--; 187 wordcount--; 188 flag = 1; 189 } 190 } 191} 192