1 /* 2 * Copyright (c) 1995 Wolfram Schneider <wosch@FreeBSD.org>. Berlin. 3 * Copyright (c) 1989, 1993 4 * The Regents of the University of California. All rights reserved. 5 * 6 * This code is derived from software contributed to Berkeley by 7 * James A. Woods. 8 * 9 * Redistribution and use in source and binary forms, with or without 10 * modification, are permitted provided that the following conditions 11 * are met: 12 * 1. Redistributions of source code must retain the above copyright 13 * notice, this list of conditions and the following disclaimer. 14 * 2. Redistributions in binary form must reproduce the above copyright 15 * notice, this list of conditions and the following disclaimer in the 16 * documentation and/or other materials provided with the distribution. 17 * 3. All advertising materials mentioning features or use of this software 18 * must display the following acknowledgement: 19 * This product includes software developed by the University of 20 * California, Berkeley and its contributors. 21 * 4. Neither the name of the University nor the names of its contributors 22 * may be used to endorse or promote products derived from this software 23 * without specific prior written permission. 24 * 25 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND 26 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE 27 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE 28 * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE 29 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL 30 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS 31 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) 32 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT 33 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY 34 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF 35 * SUCH DAMAGE. 36 * 37 * $FreeBSD: src/usr.bin/locate/code/locate.code.c,v 1.11.2.1 2001/03/04 08:46:46 kris Exp $ 38 * $DragonFly: src/usr.bin/locate/code/locate.code.c,v 1.3 2003/11/03 19:31:30 eirikn Exp $ 39 * 40 * @(#) Copyright (c) 1989, 1993 The Regents of the University of California. All rights reserved. 41 * @(#)locate.code.c 8.1 (Berkeley) 6/6/93 42 */ 43 44 /* 45 * PURPOSE: sorted list compressor (works with a modified 'find' 46 * to encode/decode a filename database) 47 * 48 * USAGE: bigram < list > bigrams 49 * process bigrams (see updatedb) > common_bigrams 50 * code common_bigrams < list > squozen_list 51 * 52 * METHOD: Uses 'front compression' (see ";login:", Volume 8, Number 1 53 * February/March 1983, p. 8). Output format is, per line, an 54 * offset differential count byte followed by a partially bigram- 55 * encoded ascii residue. A bigram is a two-character sequence, 56 * the first 128 most common of which are encoded in one byte. 57 * 58 * EXAMPLE: For simple front compression with no bigram encoding, 59 * if the input is... then the output is... 60 * 61 * /usr/src 0 /usr/src 62 * /usr/src/cmd/aardvark.c 8 /cmd/aardvark.c 63 * /usr/src/cmd/armadillo.c 14 armadillo.c 64 * /usr/tmp/zoo 5 tmp/zoo 65 * 66 * The codes are: 67 * 68 * 0-28 likeliest differential counts + offset to make nonnegative 69 * 30 switch code for out-of-range count to follow in next word 70 * 31 an 8 bit char followed 71 * 128-255 bigram codes (128 most common, as determined by 'updatedb') 72 * 32-127 single character (printable) ascii residue (ie, literal) 73 * 74 * The locate database store any character except newline ('\n') 75 * and NUL ('\0'). The 8-bit character support don't wast extra 76 * space until you have characters in file names less than 32 77 * or greather than 127. 78 * 79 * 80 * SEE ALSO: updatedb.sh, ../bigram/locate.bigram.c 81 * 82 * AUTHOR: James A. Woods, Informatics General Corp., 83 * NASA Ames Research Center, 10/82 84 * 8-bit file names characters: 85 * Wolfram Schneider, Berlin September 1996 86 */ 87 88 #include <sys/param.h> 89 #include <err.h> 90 #include <errno.h> 91 #include <stdlib.h> 92 #include <string.h> 93 #include <stdio.h> 94 #include <unistd.h> 95 #include "locate.h" 96 97 #define BGBUFSIZE (NBG * 2) /* size of bigram buffer */ 98 99 u_char buf1[MAXPATHLEN] = " "; 100 u_char buf2[MAXPATHLEN]; 101 u_char bigrams[BGBUFSIZE + 1] = { 0 }; 102 103 #define LOOKUP 1 /* use a lookup array instead a function, 3x faster */ 104 105 #ifdef LOOKUP 106 #define BGINDEX(x) (big[(u_char)*x][(u_char)*(x + 1)]) 107 typedef short bg_t; 108 bg_t big[UCHAR_MAX + 1][UCHAR_MAX + 1]; 109 #else 110 #define BGINDEX(x) bgindex(x) 111 typedef int bg_t; 112 int bgindex(char *); 113 #endif /* LOOKUP */ 114 115 116 void usage(void); 117 118 int 119 main(argc, argv) 120 int argc; 121 char *argv[]; 122 { 123 register u_char *cp, *oldpath, *path; 124 int ch, code, count, diffcount, oldcount; 125 FILE *fp; 126 register int i, j; 127 128 while ((ch = getopt(argc, argv, "")) != -1) 129 switch(ch) { 130 default: 131 usage(); 132 } 133 argc -= optind; 134 argv += optind; 135 136 if (argc != 1) 137 usage(); 138 139 if ((fp = fopen(argv[0], "r")) == NULL) 140 err(1, "%s", argv[0]); 141 142 /* First copy bigram array to stdout. */ 143 (void)fgets(bigrams, BGBUFSIZE + 1, fp); 144 145 if (fwrite(bigrams, 1, BGBUFSIZE, stdout) != BGBUFSIZE) 146 err(1, "stdout"); 147 (void)fclose(fp); 148 149 #ifdef LOOKUP 150 /* init lookup table */ 151 for (i = 0; i < UCHAR_MAX + 1; i++) 152 for (j = 0; j < UCHAR_MAX + 1; j++) 153 big[i][j] = (bg_t)-1; 154 155 for (cp = bigrams, i = 0; *cp != '\0'; i += 2, cp += 2) 156 big[(u_char)*cp][(u_char)*(cp + 1)] = (bg_t)i; 157 158 #endif /* LOOKUP */ 159 160 oldpath = buf1; 161 path = buf2; 162 oldcount = 0; 163 164 while (fgets(path, sizeof(buf2), stdin) != NULL) { 165 166 /* skip empty lines */ 167 if (*path == '\n') 168 continue; 169 170 /* remove newline */ 171 for (cp = path; *cp != '\0'; cp++) { 172 #ifndef LOCATE_CHAR30 173 /* old locate implementations core'd for char 30 */ 174 if (*cp == SWITCH) 175 *cp = '?'; 176 else 177 #endif /* !LOCATE_CHAR30 */ 178 179 /* chop newline */ 180 if (*cp == '\n') 181 *cp = '\0'; 182 } 183 184 /* Skip longest common prefix. */ 185 for (cp = path; *cp == *oldpath; cp++, oldpath++) 186 if (*cp == '\0') 187 break; 188 189 count = cp - path; 190 diffcount = count - oldcount + OFFSET; 191 oldcount = count; 192 if (diffcount < 0 || diffcount > 2 * OFFSET) { 193 if (putchar(SWITCH) == EOF || 194 putw(diffcount, stdout) == EOF) 195 err(1, "stdout"); 196 } else 197 if (putchar(diffcount) == EOF) 198 err(1, "stdout"); 199 200 while (*cp != '\0') { 201 /* print *two* characters */ 202 203 if ((code = BGINDEX(cp)) != (bg_t)-1) { 204 /* 205 * print *one* as bigram 206 * Found, so mark byte with 207 * parity bit. 208 */ 209 if (putchar((code / 2) | PARITY) == EOF) 210 err(1, "stdout"); 211 cp += 2; 212 } 213 214 else { 215 for (i = 0; i < 2; i++) { 216 if (*cp == '\0') 217 break; 218 219 /* print umlauts in file names */ 220 if (*cp < ASCII_MIN || 221 *cp > ASCII_MAX) { 222 if (putchar(UMLAUT) == EOF || 223 putchar(*cp++) == EOF) 224 err(1, "stdout"); 225 } 226 227 else { 228 /* normal character */ 229 if(putchar(*cp++) == EOF) 230 err(1, "stdout"); 231 } 232 } 233 234 } 235 } 236 237 if (path == buf1) { /* swap pointers */ 238 path = buf2; 239 oldpath = buf1; 240 } else { 241 path = buf1; 242 oldpath = buf2; 243 } 244 } 245 /* Non-zero status if there were errors */ 246 if (fflush(stdout) != 0 || ferror(stdout)) 247 exit(1); 248 exit(0); 249 } 250 251 #ifndef LOOKUP 252 int 253 bgindex(bg) /* Return location of bg in bigrams or -1. */ 254 char *bg; 255 { 256 register char bg0, bg1, *p; 257 258 bg0 = bg[0]; 259 bg1 = bg[1]; 260 for (p = bigrams; *p != NULL; p++) 261 if (*p++ == bg0 && *p == bg1) 262 break; 263 return (*p == NULL ? -1 : (--p - bigrams)); 264 } 265 #endif /* !LOOKUP */ 266 267 void 268 usage() 269 { 270 (void)fprintf(stderr, 271 "usage: locate.code common_bigrams < list > squozen_list\n"); 272 exit(1); 273 } 274