1 /* $NetBSD: mkindex.c,v 1.8 2000/07/31 11:29:48 simonb Exp $ */ 2 3 /*- 4 * Copyright (c) 1993 5 * The Regents of the University of California. All rights reserved. 6 * 7 * This code is derived from software contributed to Berkeley by 8 * Barry Brachman. 9 * 10 * Redistribution and use in source and binary forms, with or without 11 * modification, are permitted provided that the following conditions 12 * are met: 13 * 1. Redistributions of source code must retain the above copyright 14 * notice, this list of conditions and the following disclaimer. 15 * 2. Redistributions in binary form must reproduce the above copyright 16 * notice, this list of conditions and the following disclaimer in the 17 * documentation and/or other materials provided with the distribution. 18 * 3. All advertising materials mentioning features or use of this software 19 * must display the following acknowledgement: 20 * This product includes software developed by the University of 21 * California, Berkeley and its contributors. 22 * 4. Neither the name of the University nor the names of its contributors 23 * may be used to endorse or promote products derived from this software 24 * without specific prior written permission. 25 * 26 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND 27 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE 28 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE 29 * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE 30 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL 31 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS 32 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) 33 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT 34 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY 35 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF 36 * SUCH DAMAGE. 37 */ 38 39 #ifndef lint 40 static char copyright[] = "@(#) Copyright (c) 1993\n\ 41 The Regents of the University of California. All rights reserved.\n"; 42 43 #if 0 44 static char sccsid[] = "@(#)mkindex.c 8.1 (Berkeley) 6/11/93"; 45 #else 46 static char rcsid[] = 47 "$NetBSD: mkindex.c,v 1.8 2000/07/31 11:29:48 simonb Exp $"; 48 #endif 49 #endif /* not lint */ 50 51 #include <stdio.h> 52 #include <stdlib.h> 53 54 #include "bog.h" 55 56 int main(void); 57 char *nextword(FILE *, char *, int *, int *); 58 59 int 60 main(void) 61 { 62 int clen, rlen, prev, i; 63 long off, start; 64 char buf[MAXWORDLEN + 1]; 65 66 prev = '\0'; 67 off = start = 0L; 68 while (nextword(stdin, buf, &clen, &rlen) != NULL) { 69 if (*buf != prev) { 70 /* 71 * Boggle expects a full index even if the dictionary 72 * had no words beginning with some letters. 73 * So we write out entries for every letter from prev 74 * to *buf. 75 */ 76 if (prev != '\0') 77 printf("%c %6ld %6ld\n", prev, start, off - 1); 78 for (i = (prev ? prev + 1 : 'a'); i < *buf; i++) 79 printf("%c %6ld %6ld\n", i, off, off - 1); 80 prev = *buf; 81 start = off; 82 } 83 off += clen + 1; 84 } 85 printf("%c %6ld %6ld\n", prev, start, off - 1); 86 for (i = prev + 1; i <= 'z'; i++) 87 printf("%c %6ld %6ld\n", i, off, off - 1); 88 fflush(stdout); 89 if (ferror(stdout)) { 90 perror("error writing standard output"); 91 exit(1); 92 } 93 exit(0); 94 } 95 96 /* 97 * Return the next word in the compressed dictionary in 'buffer' or 98 * NULL on end-of-file 99 * Also set clen to the length of the compressed word (for mkindex) and 100 * rlen to the strlen() of the real word 101 */ 102 char * 103 nextword(fp, buffer, clen, rlen) 104 FILE *fp; 105 char *buffer; 106 int *clen, *rlen; 107 { 108 int ch, pcount; 109 char *p, *q; 110 static char buf[MAXWORDLEN + 1]; 111 static int first = 1; 112 static int lastch = 0; 113 114 if (first) { 115 if ((pcount = getc(fp)) == EOF) 116 return (NULL); 117 first = 0; 118 } 119 else if ((pcount = lastch) == EOF) 120 return (NULL); 121 122 p = buf + (*clen = pcount); 123 124 while ((ch = getc(fp)) != EOF && ch >= 'a') 125 *p++ = ch; 126 lastch = ch; 127 *p = '\0'; 128 129 *rlen = (int) (p - buf); 130 *clen = *rlen - *clen; 131 132 p = buf; 133 q = buffer; 134 while ((*q++ = *p) != '\0') { 135 if (*p++ == 'q') 136 *q++ = 'u'; 137 } 138 return (buffer); 139 } 140