1 /* 2 * $OpenBSD: locate.code.c,v 1.20 2018/05/30 15:13:22 espie Exp $ 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 * $Id: locate.code.c,v 1.20 2018/05/30 15:13:22 espie Exp $ 35 */ 36 37 /* 38 * PURPOSE: sorted list compressor (works with a modified 'find' 39 * to encode/decode a filename database) 40 * 41 * USAGE: bigram < list > bigrams 42 * process bigrams (see updatedb) > common_bigrams 43 * code common_bigrams < list > squozen_list 44 * 45 * METHOD: Uses 'front compression' (see ";login:", Volume 8, Number 1 46 * February/March 1983, p. 8). Output format is, per line, an 47 * offset differential count byte followed by a partially bigram- 48 * encoded ascii residue. A bigram is a two-character sequence, 49 * the first 128 most common of which are encoded in one byte. 50 * 51 * EXAMPLE: For simple front compression with no bigram encoding, 52 * if the input is... then the output is... 53 * 54 * /usr/src 0 /usr/src 55 * /usr/src/cmd/aardvark.c 8 /cmd/aardvark.c 56 * /usr/src/cmd/armadillo.c 14 armadillo.c 57 * /usr/tmp/zoo 5 tmp/zoo 58 * 59 * The codes are: 60 * 61 * 0-28 likeliest differential counts + offset to make nonnegative 62 * 30 switch code for out-of-range count to follow in next word 63 * 31 an 8 bit char followed 64 * 128-255 bigram codes (128 most common, as determined by 'updatedb') 65 * 32-127 single character (printable) ascii residue (ie, literal) 66 * 67 * The locate database store any character except newline ('\n') 68 * and NUL ('\0'). The 8-bit character support don't wast extra 69 * space until you have characters in file names less than 32 70 * or greater than 127. 71 * 72 * 73 * SEE ALSO: updatedb.sh, ../bigram/locate.bigram.c 74 * 75 * AUTHOR: James A. Woods, Informatics General Corp., 76 * NASA Ames Research Center, 10/82 77 * 8-bit file names characters: 78 * Wolfram Schneider, Berlin September 1996 79 */ 80 81 #include <err.h> 82 #include <errno.h> 83 #include <stdio.h> 84 #include <stdlib.h> 85 #include <string.h> 86 #include <unistd.h> 87 #include <limits.h> 88 89 #include "locate.h" 90 91 #define BGBUFSIZE (NBG * 2) /* size of bigram buffer */ 92 93 u_char buf1[PATH_MAX] = " "; 94 u_char buf2[PATH_MAX]; 95 u_char bigrams[BGBUFSIZE + 1] = { 0 }; 96 97 #define LOOKUP 1 /* use a lookup array instead a function, 3x faster */ 98 99 #ifdef LOOKUP 100 #define BGINDEX(x) (big[(u_char)*x][(u_char)*(x + 1)]) 101 typedef short bg_t; 102 bg_t big[UCHAR_MAX + 1][UCHAR_MAX + 1]; 103 #else 104 #define BGINDEX(x) bgindex(x) 105 typedef int bg_t; 106 int bgindex(char *); 107 #endif /* LOOKUP */ 108 109 110 void usage(void); 111 extern int optind; 112 extern int optopt; 113 114 int 115 main(int argc, char *argv[]) 116 { 117 u_char *cp, *oldpath, *path; 118 int ch, code, count, diffcount, oldcount; 119 FILE *fp; 120 int i, j; 121 122 if (pledge("stdio rpath", NULL) == -1) 123 err(1, "pledge"); 124 125 while ((ch = getopt(argc, argv, "")) != -1) 126 switch (ch) { 127 default: 128 usage(); 129 } 130 argc -= optind; 131 argv += optind; 132 133 if (argc != 1) 134 usage(); 135 136 if ((fp = fopen(argv[0], "r")) == NULL) 137 err(1, "%s", argv[0]); 138 139 if (pledge("stdio", NULL) == -1) 140 err(1, "pledge"); 141 142 /* First copy bigram array to stdout. */ 143 if (fgets(bigrams, sizeof(bigrams), fp) == NULL) { 144 if (ferror(fp)) { 145 err(1, "fgets on %s", argv[0]); 146 } else { 147 errx(1, "premature end of bigram file %s", argv[0]); 148 } 149 } 150 151 if (strlen(bigrams) != BGBUFSIZE) 152 errx(1, "bigram array too small to build db, index more files"); 153 154 if (fputs(bigrams, stdout) == EOF) 155 err(1, "stdout"); 156 (void)fclose(fp); 157 158 #ifdef LOOKUP 159 /* init lookup table */ 160 for (i = 0; i < UCHAR_MAX + 1; i++) 161 for (j = 0; j < UCHAR_MAX + 1; j++) 162 big[i][j] = (bg_t)-1; 163 164 for (cp = bigrams, i = 0; *cp != '\0'; i += 2, cp += 2) 165 big[(u_char)*cp][(u_char)*(cp + 1)] = (bg_t)i; 166 167 #endif /* LOOKUP */ 168 169 oldpath = buf1; 170 path = buf2; 171 oldcount = 0; 172 173 while (fgets(path, sizeof(buf2), stdin) != NULL) { 174 175 /* skip empty lines */ 176 if (*path == '\n') 177 continue; 178 179 /* remove newline */ 180 for (cp = path; *cp != '\0'; cp++) { 181 /* chop newline */ 182 if (*cp == '\n') 183 *cp = '\0'; 184 } 185 186 /* Skip longest common prefix. */ 187 for (cp = path; *cp == *oldpath; cp++, oldpath++) 188 if (*cp == '\0') 189 break; 190 191 count = cp - path; 192 diffcount = count - oldcount + OFFSET; 193 oldcount = count; 194 if (diffcount < 0 || diffcount > 2 * OFFSET) { 195 if (putchar(SWITCH) == EOF || 196 putw(diffcount, stdout) == EOF) 197 err(1, "stdout"); 198 } else 199 if (putchar(diffcount) == EOF) 200 err(1, "stdout"); 201 202 while (*cp != '\0') { 203 /* print *two* characters */ 204 205 if ((code = BGINDEX(cp)) != (bg_t)-1) { 206 /* 207 * print *one* as bigram 208 * Found, so mark byte with 209 * parity bit. 210 */ 211 if (putchar((code / 2) | PARITY) == EOF) 212 err(1, "stdout"); 213 cp += 2; 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 } else { 226 /* normal character */ 227 if (putchar(*cp++) == EOF) 228 err(1, "stdout"); 229 } 230 } 231 232 } 233 } 234 235 if (path == buf1) { /* swap pointers */ 236 path = buf2; 237 oldpath = buf1; 238 } else { 239 path = buf1; 240 oldpath = buf2; 241 } 242 } 243 /* Non-zero status if there were errors */ 244 if (fflush(stdout) != 0 || ferror(stdout)) 245 exit(1); 246 exit(0); 247 } 248 249 #ifndef LOOKUP 250 int 251 bgindex(char *bg) /* Return location of bg in bigrams or -1. */ 252 { 253 char bg0, bg1, *p; 254 255 bg0 = bg[0]; 256 bg1 = bg[1]; 257 for (p = bigrams; *p != NULL; p++) 258 if (*p++ == bg0 && *p == bg1) 259 break; 260 return (*p == NULL ? -1 : (--p - bigrams)); 261 } 262 #endif /* !LOOKUP */ 263 264 void 265 usage(void) 266 { 267 (void)fprintf(stderr, 268 "usage: locate.code common_bigrams < list > squozen_list\n"); 269 exit(1); 270 } 271