1 /* 2 * SPDX-License-Identifier: BSD-3-Clause 3 * 4 * Copyright (c) 1995-2022 Wolfram Schneider <wosch@FreeBSD.org> 5 * Copyright (c) 1989, 1993 6 * The Regents of the University of California. All rights reserved. 7 * 8 * This code is derived from software contributed to Berkeley by 9 * James A. Woods. 10 * 11 * Redistribution and use in source and binary forms, with or without 12 * modification, are permitted provided that the following conditions 13 * are met: 14 * 1. Redistributions of source code must retain the above copyright 15 * notice, this list of conditions and the following disclaimer. 16 * 2. Redistributions in binary form must reproduce the above copyright 17 * notice, this list of conditions and the following disclaimer in the 18 * documentation and/or other materials provided with the distribution. 19 * 3. Neither the name of the University nor the names of its contributors 20 * may be used to endorse or promote products derived from this software 21 * without specific prior written permission. 22 * 23 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND 24 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE 25 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE 26 * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE 27 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL 28 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS 29 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) 30 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT 31 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY 32 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF 33 * SUCH DAMAGE. 34 * 35 * $FreeBSD$ 36 */ 37 38 #if 0 39 #ifndef lint 40 static char copyright[] = 41 "@(#) 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 static char sccsid[] = "@(#)locate.code.c 8.1 (Berkeley) 6/6/93"; 47 #endif /* not lint */ 48 #endif 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 <unistd.h> 101 #include "locate.h" 102 103 #define BGBUFSIZE (NBG * 2) /* size of bigram buffer */ 104 105 u_char buf1[LOCATE_PATH_MAX] = " "; 106 u_char buf2[LOCATE_PATH_MAX]; 107 u_char bigrams[BGBUFSIZE + 1] = { 0 }; 108 109 /* use a lookup array instead a function, 3x faster than linear search */ 110 int big [UCHAR_MAX + 1][UCHAR_MAX + 1]; 111 #define BGINDEX(x) (big[(u_char)*x][(u_char)*(x + 1)]) 112 113 void usage(void); 114 115 int 116 main(int argc, char *argv[]) 117 { 118 u_char *cp, *oldpath, *path; 119 int ch, code, count, diffcount, oldcount; 120 u_int i, j; 121 FILE *fp; 122 123 while ((ch = getopt(argc, argv, "")) != -1) 124 switch(ch) { 125 default: 126 usage(); 127 } 128 argc -= optind; 129 argv += optind; 130 131 if (argc != 1) 132 usage(); 133 134 if ((fp = fopen(argv[0], "r")) == NULL) 135 err(1, "%s", argv[0]); 136 137 /* First copy bigram array to stdout. */ 138 if (fgets(bigrams, BGBUFSIZE + 1, fp) == NULL) { 139 if (!feof(fp) || ferror(fp)) 140 err(1, "get bigram array"); 141 } 142 143 if (fwrite(bigrams, 1, BGBUFSIZE, stdout) != BGBUFSIZE) 144 err(1, "stdout"); 145 (void)fclose(fp); 146 147 /* init lookup table */ 148 for (i = 0; i < UCHAR_MAX + 1; i++) 149 for (j = 0; j < UCHAR_MAX + 1; j++) 150 big[i][j] = -1; 151 152 for (cp = bigrams, i = 0; *cp != '\0'; i += 2, cp += 2) 153 big[(u_char)*cp][(u_char)*(cp + 1)] = i; 154 155 oldpath = buf1; 156 path = buf2; 157 oldcount = 0; 158 159 while (fgets(path, sizeof(buf2), stdin) != NULL) { 160 161 /* skip empty lines */ 162 if (*path == '\n') 163 continue; 164 165 /* remove newline */ 166 for (cp = path; *cp != '\0'; cp++) { 167 /* chop newline */ 168 if (*cp == '\n') 169 *cp = '\0'; 170 } 171 172 /* Skip longest common prefix. */ 173 for (cp = path; *cp == *oldpath; cp++, oldpath++) 174 if (*cp == '\0') 175 break; 176 177 count = cp - path; 178 diffcount = count - oldcount + OFFSET; 179 oldcount = count; 180 if (diffcount < 0 || diffcount > 2 * OFFSET) { 181 if (putchar(SWITCH) == EOF || 182 putw(diffcount, stdout) == EOF) 183 err(1, "stdout"); 184 } else 185 if (putchar(diffcount) == EOF) 186 err(1, "stdout"); 187 188 while (*cp != '\0') { 189 /* print *two* characters */ 190 191 if ((code = BGINDEX(cp)) != -1) { 192 /* 193 * print *one* as bigram 194 * Found, so mark byte with 195 * parity bit. 196 */ 197 if (putchar((code / 2) | PARITY) == EOF) 198 err(1, "stdout"); 199 cp += 2; 200 } 201 202 else { 203 for (i = 0; i < 2; i++) { 204 if (*cp == '\0') 205 break; 206 207 /* print umlauts in file names */ 208 if (*cp < ASCII_MIN || 209 *cp > ASCII_MAX) { 210 if (putchar(UMLAUT) == EOF || 211 putchar(*cp++) == EOF) 212 err(1, "stdout"); 213 } 214 215 else { 216 /* normal character */ 217 if(putchar(*cp++) == EOF) 218 err(1, "stdout"); 219 } 220 } 221 222 } 223 } 224 225 if (path == buf1) { /* swap pointers */ 226 path = buf2; 227 oldpath = buf1; 228 } else { 229 path = buf1; 230 oldpath = buf2; 231 } 232 } 233 234 /* Non-zero status if there were errors */ 235 if (fflush(stdout) != 0 || ferror(stdout)) 236 errx(1, "stdout"); 237 238 exit(0); 239 } 240 241 void 242 usage(void) 243 { 244 (void)fprintf(stderr, 245 "usage: locate.code common_bigrams < list > squozen_list\n"); 246 exit(1); 247 } 248