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.
6 * This code is derived from software contributed to Berkeley by
9 * Redistribution and use in source and binary forms, with or without
10 * modification, are permitted provided that the following conditions
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.
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
39 static const char copyright[] =
40 "@(#) Copyright (c) 1995-1996 Wolfram Schneider, Berlin.\n\
41 @(#) Copyright (c) 1989, 1993\n\
42 The Regents of the University of California. All rights reserved.\n";
47 static char sccsid[] = "@(#)locate.c 8.1 (Berkeley) 6/6/93";
49 static const char rcsid[] =
54 * Ref: Usenix ;login:, Vol 8, No 1, February/March, 1983, p. 8.
56 * Locate scans a file list for the full pathname of a file given only part
57 * of the name. The list has been processed with with "front-compression"
58 * and bigram coding. Front compression reduces space by a factor of 4-5,
59 * bigram coding by a further 20-25%.
63 * 0-28 likeliest differential counts + offset to make nonnegative
64 * 30 switch code for out-of-range count to follow in next word
65 * 31 an 8 bit char followed
66 * 128-255 bigram codes (128 most common, as determined by 'updatedb')
67 * 32-127 single character (printable) ascii residue (ie, literal)
69 * A novel two-tiered string search technique is employed:
71 * First, a metacharacter-free subpattern and partial pathname is matched
72 * BACKWARDS to avoid full expansion of the pathname list. The time savings
73 * is 40-50% over forward matching, which cannot efficiently handle
74 * overlapped search patterns and compressed path residue.
76 * Then, the actual shell glob-style regular expression (if in this form) is
77 * matched against the candidate pathnames using the slower routines provided
78 * in the standard 'find'.
81 #include <sys/param.h>
92 # include <sys/types.h>
93 # include <sys/stat.h>
94 # include <sys/mman.h>
100 #include <netinet/in.h> /* SunOS byteorder(3) htohl(3) */
107 #include "pathnames.h"
110 # include <sys/time.h>
111 # include <sys/types.h>
112 # include <sys/resource.h>
115 char *path_fcodes; /* locate database */
116 int f_mmap; /* use mmap */
117 int f_icase; /* ignore case */
118 int f_stdin; /* read database from stdin */
119 int f_statistic; /* print statistic */
120 int f_silent; /* suppress output, show only count of matches */
121 int f_limit; /* limit number of output lines, 0 == infinite */
122 u_int counter; /* counter for matches [-c] */
125 void usage __P((void));
126 void statistic __P((FILE *, char *));
127 void fastfind __P((FILE *, char *, char *));
128 void fastfind_icase __P((FILE *, char *, char *));
129 void fastfind_mmap __P((char *, caddr_t, int, char *));
130 void fastfind_mmap_icase __P((char *, caddr_t, int, char *));
131 void search_mmap __P((char *, char **));
132 void search_fopen __P((char *, char **));
133 unsigned long cputime __P((void));
135 extern char **colon __P((char **, char*, char*));
136 extern void print_matches __P((u_int));
137 extern int getwm __P((caddr_t));
138 extern int getwf __P((FILE *));
139 extern u_char *tolower_word __P((u_char *));
140 extern int check_bigram_char __P((int));
141 extern char *patprep __P((char *));
155 f_mmap = 1; /* mmap is default */
157 (void) setlocale(LC_ALL, "");
159 while ((ch = getopt(argc, argv, "Scd:il:ms")) != -1)
161 case 'S': /* statistic lines */
164 case 'l': /* limit number of output lines, 0 == infinite */
165 f_limit = atoi(optarg);
167 case 'd': /* database */
168 dbv = colon(dbv, optarg, _PATH_FCODES);
170 case 'i': /* ignore case */
177 warnx("mmap(2) not implemented");
180 case 's': /* stdio lib */
183 case 'c': /* suppress output, show only count of matches */
192 /* to few arguments */
193 if (argc < 1 && !(f_statistic))
196 /* no (valid) database as argument */
197 if (dbv == NULL || *dbv == NULL) {
198 /* try to read database from enviroment */
199 if ((path_fcodes = getenv("LOCATE_PATH")) == NULL ||
200 *path_fcodes == '\0')
201 /* use default database */
202 dbv = colon(dbv, _PATH_FCODES, _PATH_FCODES);
203 else /* $LOCATE_PATH */
204 dbv = colon(dbv, path_fcodes, _PATH_FCODES);
207 if (f_icase && UCHAR_MAX < 4096) /* init tolower lookup table */
208 for (ch = 0; ch < UCHAR_MAX + 1; ch++)
209 myctype[ch] = tolower(ch);
211 /* foreach database ... */
212 while((path_fcodes = *dbv) != NULL) {
215 if (!strcmp(path_fcodes, "-"))
221 f_mmap = 0; /* be paranoid */
223 if (!f_mmap || f_stdin || f_statistic)
224 search_fopen(path_fcodes, argv);
226 search_mmap(path_fcodes, argv);
230 print_matches(counter);
237 char *db; /* database */
238 char **s; /* search strings */
245 /* can only read stdin once */
248 if (*(s+1) != NULL) {
249 warnx("read database from stdin, use only `%s' as pattern", *s);
253 else if ((fp = fopen(path_fcodes, "r")) == NULL)
254 err(1, "`%s'", path_fcodes);
256 /* count only chars or lines */
258 statistic(fp, path_fcodes);
263 /* foreach search string ... */
269 fseek(fp, (long)0, SEEK_SET) == -1)
270 err(1, "fseek to begin of ``%s''\n", path_fcodes);
273 fastfind_icase(fp, *s, path_fcodes);
275 fastfind(fp, *s, path_fcodes);
277 warnx("fastfind %ld ms", cputime () - t0);
287 char *db; /* database */
288 char **s; /* search strings */
297 if ((fd = open(path_fcodes, O_RDONLY)) == -1 ||
298 fstat(fd, &sb) == -1)
299 err(1, "`%s'", path_fcodes);
302 if ((p = mmap((caddr_t)0, (size_t)len,
303 PROT_READ, MAP_SHARED,
304 fd, (off_t)0)) == MAP_FAILED)
305 err(1, "mmap ``%s''", path_fcodes);
307 /* foreach search string ... */
313 fastfind_mmap_icase(*s, p, (int)len, path_fcodes);
315 fastfind_mmap(*s, p, (int)len, path_fcodes);
317 warnx("fastfind %ld ms", cputime () - t0);
322 if (munmap(p, (size_t)len) == -1)
323 warn("munmap %s\n", path_fcodes);
336 return(rus.ru_utime.tv_sec * 1000 + rus.ru_utime.tv_usec / 1000);
343 (void)fprintf(stderr,
344 "usage: locate [-Scims] [-l limit] [-d database] pattern ...\n\n");
345 (void)fprintf(stderr,
346 "default database: `%s' or $LOCATE_PATH\n", _PATH_FCODES);
351 /* load fastfind functions */
354 /* fastfind_mmap, fastfind_mmap_icase */
360 #include "fastfind.c"
362 #include "fastfind.c"
366 /* fastfind, fastfind_icase */
369 #include "fastfind.c"
371 #include "fastfind.c"