1 /* $NetBSD: locate.code.c,v 1.11 2011/09/04 20:28:40 joerg 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. Neither the name of the University nor the names of its contributors 19 * may be used to endorse or promote products derived from this software 20 * without specific prior written permission. 21 * 22 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND 23 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE 24 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE 25 * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE 26 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL 27 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS 28 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) 29 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT 30 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY 31 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF 32 * SUCH DAMAGE. 33 */ 34 35 #include <sys/cdefs.h> 36 #ifndef lint 37 __COPYRIGHT("@(#) Copyright (c) 1989, 1993\ 38 The Regents of the University of California. All rights reserved."); 39 #endif /* not lint */ 40 41 #ifndef lint 42 #if 0 43 static char sccsid[] = "@(#)locate.code.c 8.4 (Berkeley) 5/4/95"; 44 #endif 45 __RCSID("$NetBSD: locate.code.c,v 1.11 2011/09/04 20:28:40 joerg Exp $"); 46 #endif /* not lint */ 47 48 /* 49 * PURPOSE: sorted list compressor (works with a modified 'find' 50 * to encode/decode a filename database) 51 * 52 * USAGE: bigram < list > bigrams 53 * process bigrams (see updatedb) > common_bigrams 54 * code common_bigrams < list > squozen_list 55 * 56 * METHOD: Uses 'front compression' (see ";login:", Volume 8, Number 1 57 * February/March 1983, p. 8). Output format is, per line, an 58 * offset differential count byte followed by a partially bigram- 59 * encoded ascii residue. A bigram is a two-character sequence, 60 * the first 128 most common of which are encoded in one byte. 61 * 62 * EXAMPLE: For simple front compression with no bigram encoding, 63 * if the input is... then the output is... 64 * 65 * /usr/src 0 /usr/src 66 * /usr/src/cmd/aardvark.c 8 /cmd/aardvark.c 67 * /usr/src/cmd/armadillo.c 14 armadillo.c 68 * /usr/tmp/zoo 5 tmp/zoo 69 * 70 * The codes are: 71 * 72 * 0-28 likeliest differential counts + offset to make nonnegative 73 * 30 switch code for out-of-range count to follow in next word 74 * 128-255 bigram codes (128 most common, as determined by 'updatedb') 75 * 32-127 single character (printable) ascii residue (ie, literal) 76 * 77 * SEE ALSO: updatedb.csh, bigram.c 78 * 79 * AUTHOR: James A. Woods, Informatics General Corp., 80 * NASA Ames Research Center, 10/82 81 */ 82 83 #include <sys/param.h> 84 85 #include <err.h> 86 #include <errno.h> 87 #include <stdio.h> 88 #include <stdlib.h> 89 #include <string.h> 90 #include <unistd.h> 91 92 #include "locate.h" 93 94 #define BGBUFSIZE (NBG * 2) /* size of bigram buffer */ 95 96 static char buf1[MAXPATHLEN] = " "; 97 static char buf2[MAXPATHLEN]; 98 static char bigrams[BGBUFSIZE + 1] = { 0 }; 99 100 static int bgindex(char *); 101 __dead static void usage(void); 102 103 int 104 main(int argc, char *argv[]) 105 { 106 char *cp, *oldpath, *path; 107 int ch, code, count, diffcount, oldcount; 108 109 while ((ch = getopt(argc, argv, "")) != -1) 110 switch(ch) { 111 case '?': 112 default: 113 usage(); 114 } 115 argc -= optind; 116 argv += optind; 117 118 if (argc != 1) 119 usage(); 120 121 /* First copy bigram array to stdout. */ 122 strncpy(bigrams, argv[0], BGBUFSIZE + 1); 123 if (fwrite(bigrams, 1, BGBUFSIZE, stdout) != BGBUFSIZE) 124 err(1, "stdout"); 125 126 oldpath = buf1; 127 path = buf2; 128 oldcount = 0; 129 while (fgets(path, sizeof(buf2), stdin) != NULL) { 130 /* Truncate newline. */ 131 cp = path + strlen(path) - 1; 132 if (cp > path && *cp == '\n') 133 *cp = '\0'; 134 135 /* Squelch characters that would botch the decoding. */ 136 for (cp = path; *cp != '\0'; cp++) { 137 *cp &= PARITY-1; 138 if (*cp <= SWITCH) 139 *cp = '?'; 140 } 141 142 /* Skip longest common prefix. */ 143 for (cp = path; *cp == *oldpath; cp++, oldpath++) 144 if (*oldpath == '\0') 145 break; 146 count = cp - path; 147 diffcount = count - oldcount + OFFSET; 148 oldcount = count; 149 if (diffcount < 0 || diffcount > 2 * OFFSET) { 150 if (putchar(SWITCH) == EOF || 151 putw(diffcount, stdout) == EOF) 152 err(1, "stdout"); 153 } else 154 if (putchar(diffcount) == EOF) 155 err(1, "stdout"); 156 157 while (*cp != '\0') { 158 if (*(cp + 1) == '\0') { 159 if (putchar(*cp) == EOF) 160 err(1, "stdout"); 161 break; 162 } 163 if ((code = bgindex(cp)) < 0) { 164 if (putchar(*cp++) == EOF || 165 putchar(*cp++) == EOF) 166 err(1, "stdout"); 167 } else { 168 /* Found, so mark byte with parity bit. */ 169 if (putchar((code / 2) | PARITY) == EOF) 170 err(1, "stdout"); 171 cp += 2; 172 } 173 } 174 if (path == buf1) { /* swap pointers */ 175 path = buf2; 176 oldpath = buf1; 177 } else { 178 path = buf1; 179 oldpath = buf2; 180 } 181 } 182 /* Non-zero status if there were errors */ 183 if (fflush(stdout) != 0 || ferror(stdout)) 184 exit(1); 185 exit(0); 186 } 187 188 static int 189 bgindex(char *bg) /* Return location of bg in bigrams or -1. */ 190 { 191 char bg0, bg1, *p; 192 193 bg0 = bg[0]; 194 bg1 = bg[1]; 195 for (p = bigrams; *p != '\0'; p += 2) 196 if (p[0] == bg0 && p[1] == bg1) 197 break; 198 return (*p == '\0' ? -1 : p - bigrams); 199 } 200 201 static void 202 usage(void) 203 { 204 (void)fprintf(stderr, 205 "usage: locate.code common_bigrams < list > squozen_list\n"); 206 exit(1); 207 } 208