1 /* 2 * Copyright (c) 1989, 1993 3 * The Regents of the University of California. All rights reserved. 4 * 5 * This code is derived from software contributed to Berkeley by 6 * James A. Woods. 7 * 8 * Redistribution and use in source and binary forms, with or without 9 * modification, are permitted provided that the following conditions 10 * are met: 11 * 1. Redistributions of source code must retain the above copyright 12 * notice, this list of conditions and the following disclaimer. 13 * 2. Redistributions in binary form must reproduce the above copyright 14 * notice, this list of conditions and the following disclaimer in the 15 * documentation and/or other materials provided with the distribution. 16 * 3. All advertising materials mentioning features or use of this software 17 * must display the following acknowledgement: 18 * This product includes software developed by the University of 19 * California, Berkeley and its contributors. 20 * 4. Neither the name of the University nor the names of its contributors 21 * may be used to endorse or promote products derived from this software 22 * without specific prior written permission. 23 * 24 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND 25 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE 26 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE 27 * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE 28 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL 29 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS 30 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) 31 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT 32 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY 33 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF 34 * SUCH DAMAGE. 35 */ 36 37 #ifndef lint 38 static char copyright[] = 39 "@(#) Copyright (c) 1989, 1993\n\ 40 The Regents of the University of California. All rights reserved.\n"; 41 #endif /* not lint */ 42 43 #ifndef lint 44 static char sccsid[] = "@(#)locate.code.c 8.1 (Berkeley) 6/6/93"; 45 #endif /* not lint */ 46 47 /* 48 * PURPOSE: sorted list compressor (works with a modified 'find' 49 * to encode/decode a filename database) 50 * 51 * USAGE: bigram < list > bigrams 52 * process bigrams (see updatedb) > common_bigrams 53 * code common_bigrams < list > squozen_list 54 * 55 * METHOD: Uses 'front compression' (see ";login:", Volume 8, Number 1 56 * February/March 1983, p. 8). Output format is, per line, an 57 * offset differential count byte followed by a partially bigram- 58 * encoded ascii residue. A bigram is a two-character sequence, 59 * the first 128 most common of which are encoded in one byte. 60 * 61 * EXAMPLE: For simple front compression with no bigram encoding, 62 * if the input is... then the output is... 63 * 64 * /usr/src 0 /usr/src 65 * /usr/src/cmd/aardvark.c 8 /cmd/aardvark.c 66 * /usr/src/cmd/armadillo.c 14 armadillo.c 67 * /usr/tmp/zoo 5 tmp/zoo 68 * 69 * The codes are: 70 * 71 * 0-28 likeliest differential counts + offset to make nonnegative 72 * 30 switch code for out-of-range count to follow in next word 73 * 128-255 bigram codes (128 most common, as determined by 'updatedb') 74 * 32-127 single character (printable) ascii residue (ie, literal) 75 * 76 * SEE ALSO: updatedb.csh, bigram.c 77 * 78 * AUTHOR: James A. Woods, Informatics General Corp., 79 * NASA Ames Research Center, 10/82 80 */ 81 82 #include <sys/param.h> 83 #include <err.h> 84 #include <errno.h> 85 #include <stdlib.h> 86 #include <string.h> 87 #include <stdio.h> 88 #include "locate.h" 89 90 #define BGBUFSIZE (NBG * 2) /* size of bigram buffer */ 91 92 char buf1[MAXPATHLEN + 1] = " "; 93 char buf2[MAXPATHLEN + 1]; 94 char bigrams[BGBUFSIZE + 1] = { 0 }; 95 96 int bgindex __P((char *)); 97 void usage __P((void)); 98 99 int 100 main(argc, argv) 101 int argc; 102 char *argv[]; 103 { 104 register char *cp, *oldpath, *path; 105 int ch, code, count, diffcount, oldcount; 106 FILE *fp; 107 108 while ((ch = getopt(argc, argv, "")) != EOF) 109 switch(ch) { 110 case '?': 111 default: 112 usage(); 113 } 114 argc -= optind; 115 argv += optind; 116 117 if (argc != 1) 118 usage(); 119 120 if ((fp = fopen(argv[0], "r")) == NULL) 121 err(1, "%s", argv[0]); 122 123 /* First copy bigram array to stdout. */ 124 (void)fgets(bigrams, BGBUFSIZE + 1, fp); 125 if (fwrite(bigrams, 1, BGBUFSIZE, stdout) != BGBUFSIZE) 126 err(1, "stdout"); 127 (void)fclose(fp); 128 129 oldpath = buf1; 130 path = buf2; 131 oldcount = 0; 132 while (fgets(path, sizeof(buf2) - 1, stdin) != NULL) { 133 /* Truncate newline. */ 134 cp = path + strlen(path) - 1; 135 if (cp > path && *cp == '\n') 136 *cp = '\0'; 137 138 /* Squelch characters that would botch the decoding. */ 139 for (cp = path; *cp != NULL; cp++) { 140 if ((u_char)*cp >= PARITY) 141 *cp &= PARITY-1; 142 if (*cp <= SWITCH) 143 *cp = '?'; 144 } 145 146 /* Skip longest common prefix. */ 147 for (cp = path; *cp == *oldpath; cp++, oldpath++) 148 if (*oldpath == NULL) 149 break; 150 count = cp - path; 151 diffcount = count - oldcount + OFFSET; 152 oldcount = count; 153 if (diffcount < 0 || diffcount > 2 * OFFSET) { 154 if (putchar(SWITCH) == EOF || 155 putw(diffcount, stdout) == EOF) 156 err(1, "stdout"); 157 } else 158 if (putchar(diffcount) == EOF) 159 err(1, "stdout"); 160 161 while (*cp != NULL) { 162 if (*(cp + 1) == NULL) { 163 if (putchar(*cp) == EOF) 164 err(1, "stdout"); 165 break; 166 } 167 if ((code = bgindex(cp)) < 0) { 168 if (putchar(*cp++) == EOF || 169 putchar(*cp++) == EOF) 170 err(1, "stdout"); 171 } else { 172 /* Found, so mark byte with parity bit. */ 173 if (putchar((code / 2) | PARITY) == EOF) 174 err(1, "stdout"); 175 cp += 2; 176 } 177 } 178 if (path == buf1) { /* swap pointers */ 179 path = buf2; 180 oldpath = buf1; 181 } else { 182 path = buf1; 183 oldpath = buf2; 184 } 185 } 186 /* Non-zero status if there were errors */ 187 if (fflush(stdout) != 0 || ferror(stdout)) 188 exit(1); 189 exit(0); 190 } 191 192 int 193 bgindex(bg) /* Return location of bg in bigrams or -1. */ 194 char *bg; 195 { 196 register char bg0, bg1, *p; 197 198 bg0 = bg[0]; 199 bg1 = bg[1]; 200 for (p = bigrams; *p != NULL; p++) 201 if (*p++ == bg0 && *p == bg1) 202 break; 203 return (*p == NULL ? -1 : --p - bigrams); 204 } 205 206 void 207 usage() 208 { 209 (void)fprintf(stderr, 210 "usage: locate.code common_bigrams < list > squozen_list\n"); 211 exit(1); 212 } 213