1 /* @(#)parse.c 8.2 (Berkeley) 4/28/95 */ 2 /* $NetBSD: parse.c,v 1.17 2020/02/06 22:09:43 fox 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 "extern.h" 34 35 #define HASHSIZE 256 36 #define HASHMUL 81 37 #define HASHMASK (HASHSIZE - 1) 38 39 static int hash(const char *); 40 static void install(struct wlist *); 41 static struct wlist *lookup(const char *); 42 43 static struct wlist *hashtab[HASHSIZE]; 44 45 void 46 wordinit(void) 47 { 48 struct wlist *w; 49 50 for (w = wlist; w->string; w++) 51 install(w); 52 } 53 54 static int 55 hash(const char *s) 56 { 57 int hashval = 0; 58 59 while (*s) { 60 hashval += *s++; 61 hashval *= HASHMUL; 62 hashval &= HASHMASK; 63 } 64 return hashval; 65 } 66 67 static struct wlist * 68 lookup(const char *s) 69 { 70 struct wlist *wp; 71 72 for (wp = hashtab[hash(s)]; wp != NULL; wp = wp->next) 73 if (*s == *wp->string && strcmp(s, wp->string) == 0) 74 return wp; 75 return NULL; 76 } 77 78 static void 79 install(struct wlist *wp) 80 { 81 int hashval; 82 83 if (lookup(wp->string) == NULL) { 84 hashval = hash(wp->string); 85 wp->next = hashtab[hashval]; 86 hashtab[hashval] = wp; 87 } else 88 printf("Multiply defined %s.\n", wp->string); 89 } 90 91 void 92 parse(void) 93 { 94 struct wlist *wp; 95 int n; 96 int flag; 97 98 wordnumber = 0; /* for cypher */ 99 for (n = 0; n <= wordcount; n++) { 100 if ((wp = lookup(words[n])) == NULL) { 101 wordvalue[n] = -1; 102 wordtype[n] = -1; 103 } else { 104 wordvalue[n] = wp->value; 105 wordtype[n] = wp->article; 106 } 107 } 108 /* We never use adjectives for anything, so yank them all. */ 109 for (n = 1; n < wordcount; n++) 110 if (wordtype[n] == ADJS) { 111 int i; 112 for (i = n + 1; i < wordcount; i++) { 113 wordtype[i - 1] = wordtype[i]; 114 wordvalue[i - 1] = wordvalue[i]; 115 strlcpy(words[i - 1], words[i], WORDLEN); 116 } 117 wordcount--; 118 } 119 /* Don't let a comma mean AND if followed by a verb. */ 120 for (n = 0; n < wordcount; n++) 121 if (wordvalue[n] == AND && words[n][0] == ',' 122 && wordtype[n + 1] == VERB) { 123 wordvalue[n] = -1; 124 wordtype[n] = -1; 125 } 126 /* Trim "AND AND" which can happen naturally at the end of a 127 * comma-delimited list. 128 */ 129 for (n = 1; n < wordcount; n++) 130 if (wordvalue[n - 1] == AND && wordvalue[n] == AND) { 131 int i; 132 for (i = n + 1; i < wordcount; i++) { 133 wordtype[i - 1] = wordtype[i]; 134 wordvalue[i - 1] = wordvalue[i]; 135 strlcpy(words[i - 1], words[i], WORDLEN); 136 } 137 wordcount--; 138 } 139 140 /* If there is a sequence (NOUN | OBJECT) AND EVERYTHING 141 * then move all the EVERYTHINGs to the beginning, since that's where 142 * they're expected. We can't get rid of the NOUNs and OBJECTs in 143 * case they aren't in EVERYTHING (i.e. not here or nonexistent). 144 */ 145 flag = 1; 146 while (flag) { 147 flag = 0; 148 for (n = 1; n < wordcount; n++) 149 if ((wordtype[n - 1] == NOUNS || 150 wordtype[n - 1] == OBJECT) && 151 wordvalue[n] == AND && 152 wordvalue[n + 1] == EVERYTHING) { 153 char tmpword[WORDLEN]; 154 wordvalue[n + 1] = wordvalue[n - 1]; 155 wordvalue[n - 1] = EVERYTHING; 156 wordtype[n + 1] = wordtype[n - 1]; 157 wordtype[n - 1] = OBJECT; 158 strcpy(tmpword, words[n - 1]); 159 strlcpy(words[n - 1], words[n + 1], WORDLEN); 160 strcpy(words[n + 1], tmpword); 161 flag = 1; 162 } 163 /* And trim EVERYTHING AND EVERYTHING. */ 164 for (n = 1; n < wordcount; n++) 165 if (wordvalue[n - 1] == EVERYTHING && 166 wordvalue[n] == AND && 167 wordvalue[n + 1] == EVERYTHING) { 168 int i; 169 for (i = n + 1; i < wordcount; i++) { 170 wordtype[i - 1] = wordtype[i + 1]; 171 wordvalue[i - 1] = wordvalue[i + 1]; 172 strlcpy(words[i - 1], words[i + 1], WORDLEN); 173 } 174 wordcount--; 175 wordcount--; 176 flag = 1; 177 } 178 } 179 } 180