1 /* $NetBSD: locate.bigram.c,v 1.9 2000/05/06 10:26:45 mycroft Exp $ */ 2 3 /* 4 * Copyright (c) 1989, 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 * James A. Woods. 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 #include <sys/cdefs.h> 40 #ifndef lint 41 __COPYRIGHT("@(#) Copyright (c) 1989, 1993\n\ 42 The Regents of the University of California. All rights reserved.\n"); 43 #endif /* not lint */ 44 45 #ifndef lint 46 #if 0 47 static char sccsid[] = "@(#)locate.bigram.c 8.2 (Berkeley) 4/28/95"; 48 #endif 49 __RCSID("$NetBSD: locate.bigram.c,v 1.9 2000/05/06 10:26:45 mycroft Exp $"); 50 #endif /* not lint */ 51 52 /* 53 * bigram < text > bigrams 54 * 55 * List bigrams for 'updatedb' script. 56 * Use 'code' to encode a file using this output. 57 */ 58 59 #include <stdio.h> 60 #include <stdlib.h> 61 #include <string.h> 62 #include <sys/param.h> /* for MAXPATHLEN */ 63 64 int main __P((int, char **)); 65 static int compare_bigrams __P((const void *, const void *)); 66 static void add_bigram __P((u_char, u_char)); 67 68 static char buf1[MAXPATHLEN] = " "; 69 static char buf2[MAXPATHLEN]; 70 71 struct bigram { 72 int count; 73 u_char b1, b2; /* needed for final sorting */ 74 }; 75 76 struct bigram bigrams[256 * 256]; 77 78 static void 79 add_bigram(i1, i2) 80 u_char i1, i2; 81 { 82 if (i1 != '\n' && i2 != '\n') 83 bigrams[(i1<<8)+i2].count++; 84 } 85 86 static int 87 compare_bigrams(item1, item2) 88 const void *item1, *item2; 89 { 90 const struct bigram *it1=item1, *it2=item2; 91 92 if (it1->count != it2->count) 93 return it2->count - it1->count; 94 else if (it1->b1 != it2->b1) 95 return it2->b1 - it1->b1; 96 else 97 return it2->b2 - it2->b2; 98 } 99 100 int 101 main(argc, argv) 102 int argc; 103 char *argv[]; 104 { 105 char *cp; 106 char *oldpath = buf1, *path = buf2; 107 struct bigram *bg; 108 int i; 109 110 /* initialize bigram array */ 111 memset(bigrams, 0, sizeof(bigrams)); 112 for(i=0; i < 65536; i++) { 113 bigrams[i].b1 = i / 256; 114 bigrams[i].b2 = i % 256; 115 } 116 117 while ( fgets ( path, sizeof(buf2), stdin ) != NULL ) { 118 119 /* skip longest common prefix */ 120 for ( cp = path; *cp == *oldpath; cp++, oldpath++ ) 121 if ( *oldpath == '\0' ) 122 break; 123 124 /* 125 * output post-residue bigrams only 126 */ 127 for(; cp[0] != '\0' && cp[1] != '\0'; cp += 2) 128 add_bigram((u_char)cp[0], (u_char)cp[1]); 129 130 if (path == buf1) /* swap pointers */ 131 path = buf2, oldpath = buf1; 132 else 133 path = buf1, oldpath = buf2; 134 } 135 136 /* sort the bigrams by how many times it appeared and their value */ 137 heapsort((void *)bigrams, 256 * 256, sizeof(struct bigram), 138 compare_bigrams); 139 140 /* write 128 most frequent bigrams out */ 141 bg = bigrams; 142 for (i = 0; i < 128 && bg->count > 0; i++, bg++) { 143 if (bg->b1 != '\0') 144 fputc(bg->b1, stdout); 145 if (bg->b2 != '\0') 146 fputc(bg->b2, stdout); 147 } 148 149 return (0); 150 } 151