1 /*- 2 * Copyright (c) 1993 3 * The Regents of the University of California. All rights reserved. 4 * 5 * This code is derived from software contributed to Berkeley by 6 * Barry Brachman. 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. All advertising materials mentioning features or use of this software 17 * must display the following acknowledgement: 18 * This product includes software developed by the University of 19 * California, Berkeley and its contributors. 20 * 4. Neither the name of the University nor the names of its contributors 21 * may be used to endorse or promote products derived from this software 22 * without specific prior written permission. 23 * 24 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND 25 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE 26 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE 27 * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE 28 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL 29 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS 30 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) 31 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT 32 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY 33 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF 34 * SUCH DAMAGE. 35 */ 36 37 #ifndef lint 38 static char copyright[] = 39 "@(#) Copyright (c) 1993\n\ 40 The Regents of the University of California. All rights reserved.\n"; 41 #endif /* not lint */ 42 43 #ifndef lint 44 static char sccsid[] = "@(#)mkindex.c 8.1 (Berkeley) 6/11/93"; 45 #endif /* not lint */ 46 47 #include <stdio.h> 48 49 #include "bog.h" 50 51 char *nextword __P((FILE *, char *, int *, int *)); 52 53 int 54 main(argc, argv) 55 int argc; 56 char *argv[]; 57 { 58 int clen, rlen, prev; 59 long off, start; 60 char buf[MAXWORDLEN + 1]; 61 62 prev = '\0'; 63 off = start = 0L; 64 while (nextword(stdin, buf, &clen, &rlen) != NULL) { 65 if (*buf != prev) { 66 if (prev != '\0') 67 printf("%c %6ld %6ld\n", prev, start, off - 1); 68 prev = *buf; 69 start = off; 70 } 71 off += clen + 1; 72 } 73 printf("%c %6ld %6ld\n", prev, start, off - 1); 74 exit(0); 75 } 76 77 /* 78 * Return the next word in the compressed dictionary in 'buffer' or 79 * NULL on end-of-file 80 * Also set clen to the length of the compressed word (for mkindex) and 81 * rlen to the strlen() of the real word 82 */ 83 char * 84 nextword(fp, buffer, clen, rlen) 85 FILE *fp; 86 char *buffer; 87 int *clen, *rlen; 88 { 89 register int ch, pcount; 90 register char *p, *q; 91 static char buf[MAXWORDLEN + 1]; 92 static int first = 1; 93 static int lastch = 0; 94 95 if (first) { 96 if ((pcount = getc(fp)) == EOF) 97 return (NULL); 98 first = 0; 99 } 100 else if ((pcount = lastch) == EOF) 101 return (NULL); 102 103 p = buf + (*clen = pcount); 104 105 while ((ch = getc(fp)) != EOF && ch >= 'a') 106 *p++ = ch; 107 lastch = ch; 108 *p = '\0'; 109 110 *rlen = (int) (p - buf); 111 *clen = *rlen - *clen; 112 113 p = buf; 114 q = buffer; 115 while ((*q++ = *p) != '\0') { 116 if (*p++ == 'q') 117 *q++ = 'u'; 118 } 119 return (buffer); 120 } 121