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 * $Id: locate.code.c,v 1.5 1996/08/31 14:51:18 wosch Exp $ 38 */ 39 40 #ifndef lint 41 static char copyright[] = 42 "@(#) Copyright (c) 1989, 1993\n\ 43 The Regents of the University of California. All rights reserved.\n"; 44 #endif /* not lint */ 45 46 #ifndef lint 47 static char sccsid[] = "@(#)locate.code.c 8.1 (Berkeley) 6/6/93"; 48 #endif /* not lint */ 49 50 /* 51 * PURPOSE: sorted list compressor (works with a modified 'find' 52 * to encode/decode a filename database) 53 * 54 * USAGE: bigram < list > bigrams 55 * process bigrams (see updatedb) > common_bigrams 56 * code common_bigrams < list > squozen_list 57 * 58 * METHOD: Uses 'front compression' (see ";login:", Volume 8, Number 1 59 * February/March 1983, p. 8). Output format is, per line, an 60 * offset differential count byte followed by a partially bigram- 61 * encoded ascii residue. A bigram is a two-character sequence, 62 * the first 128 most common of which are encoded in one byte. 63 * 64 * EXAMPLE: For simple front compression with no bigram encoding, 65 * if the input is... then the output is... 66 * 67 * /usr/src 0 /usr/src 68 * /usr/src/cmd/aardvark.c 8 /cmd/aardvark.c 69 * /usr/src/cmd/armadillo.c 14 armadillo.c 70 * /usr/tmp/zoo 5 tmp/zoo 71 * 72 * The codes are: 73 * 74 * 0-28 likeliest differential counts + offset to make nonnegative 75 * 30 switch code for out-of-range count to follow in next word 76 * 31 an 8 bit char followed 77 * 128-255 bigram codes (128 most common, as determined by 'updatedb') 78 * 32-127 single character (printable) ascii residue (ie, literal) 79 * 80 * The locate database store any character except newline ('\n') 81 * and NUL ('\0'). The 8-bit character support don't wast extra 82 * space until you have characters in file names less than 32 83 * or greather than 127. 84 * 85 * 86 * SEE ALSO: updatedb.sh, ../bigram/locate.bigram.c 87 * 88 * AUTHOR: James A. Woods, Informatics General Corp., 89 * NASA Ames Research Center, 10/82 90 * 8-bit file names characters: 91 * Wolfram Schneider, Berlin September 1996 92 */ 93 94 #include <sys/param.h> 95 #include <err.h> 96 #include <errno.h> 97 #include <stdlib.h> 98 #include <string.h> 99 #include <stdio.h> 100 #include "locate.h" 101 102 #define BGBUFSIZE (NBG * 2) /* size of bigram buffer */ 103 104 u_char buf1[MAXPATHLEN] = " "; 105 u_char buf2[MAXPATHLEN]; 106 u_char bigrams[BGBUFSIZE + 1] = { 0 }; 107 108 #define LOOKUP 1 /* use a lookup array instead a function, 3x faster */ 109 110 #ifdef LOOKUP 111 #define BGINDEX(x) (big[(u_char)*x][(u_char)*(x + 1)]) 112 typedef short bg_t; 113 bg_t big[UCHAR_MAX + 1][UCHAR_MAX + 1]; 114 #else 115 #define BGINDEX(x) bgindex(x) 116 typedef int bg_t; 117 int bgindex __P((char *)); 118 #endif /* LOOKUP */ 119 120 121 void usage __P((void)); 122 extern int optind; 123 extern int optopt; 124 125 int 126 main(argc, argv) 127 int argc; 128 char *argv[]; 129 { 130 register u_char *cp, *oldpath, *path; 131 int ch, code, count, diffcount, oldcount; 132 FILE *fp; 133 register int i, j; 134 135 while ((ch = getopt(argc, argv, "")) != EOF) 136 switch(ch) { 137 default: 138 usage(); 139 } 140 argc -= optind; 141 argv += optind; 142 143 if (argc != 1) 144 usage(); 145 146 if ((fp = fopen(argv[0], "r")) == NULL) 147 err(1, "%s", argv[0]); 148 149 /* First copy bigram array to stdout. */ 150 (void)fgets(bigrams, BGBUFSIZE + 1, fp); 151 152 if (fwrite(bigrams, 1, BGBUFSIZE, stdout) != BGBUFSIZE) 153 err(1, "stdout"); 154 (void)fclose(fp); 155 156 #ifdef LOOKUP 157 /* init lookup table */ 158 for (i = 0; i < UCHAR_MAX + 1; i++) 159 for (j = 0; j < UCHAR_MAX + 1; j++) 160 big[i][j] = (bg_t)-1; 161 162 for (cp = bigrams, i = 0; *cp != '\0'; i += 2, cp += 2) 163 big[(u_char)*cp][(u_char)*(cp + 1)] = (bg_t)i; 164 165 #endif /* LOOKUP */ 166 167 oldpath = buf1; 168 path = buf2; 169 oldcount = 0; 170 171 while (fgets(path, sizeof(buf2), stdin) != NULL) { 172 173 /* skip empty lines */ 174 if (*path == '\n') 175 continue; 176 177 /* remove newline */ 178 for (cp = path; *cp != '\0'; cp++) { 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