locate/locate/util.c

   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  * $FreeBSD: src/usr.bin/locate/locate/util.c,v 1.10 2002/06/24 12:40:11 naddy Exp $
  38  */
  39
  40
  41 #include <stdlib.h>
  42 #include <string.h>
  43 #include <err.h>
  44 #include <sys/param.h>
  45 #include <arpa/inet.h>
  46 #include <stdio.h>
  47
  48 #include "locate.h"
  49
  50 char    **colon(char **, char*, char*);
  51 char    *patprep(char *);
  52 void print_matches(u_int);
  53 u_char  *tolower_word(u_char *);
  54 int     getwm(caddr_t);
  55 int     getwf(FILE *);
  56 int     check_bigram_char(int);
  57
  58 /*
  59  * Validate bigram chars. If the test failed the database is corrupt
  60  * or the database is obviously not a locate database.
  61  */
  62 int
  63 check_bigram_char(ch)
  64         int ch;
  65 {
  66         /* legal bigram: 0, ASCII_MIN ... ASCII_MAX */
  67         if (ch == 0 ||
  68             (ch >= ASCII_MIN && ch <= ASCII_MAX))
  69                 return(ch);
  70
  71         errx(1,
  72                 "locate database header corrupt, bigram char outside 0, %d-%d: %d",
  73                 ASCII_MIN, ASCII_MAX, ch);
  74         exit(1);
  75 }
  76
  77 /* split a colon separated string into a char vector
  78  *
  79  * "bla:foo" -> {"foo", "bla"}
  80  * "bla:"    -> {"foo", dot}
  81  * "bla"     -> {"bla"}
  82  * ""        -> do nothing
  83  *
  84  */
  85 char **
  86 colon(dbv, path, dot)
  87         char **dbv;
  88         char *path;
  89         char *dot; /* default for single ':' */
  90 {
  91         int vlen, slen;
  92         char *c, *ch, *p;
  93         char **pv;
  94
  95         if (dbv == NULL) {
  96                 if ((dbv = malloc(sizeof(char **))) == NULL)
  97                         err(1, "malloc");
  98                 *dbv = NULL;
  99         }
 100
 101         /* empty string */
 102         if (*path == '\0') {
 103                 warnx("empty database name, ignored");
 104                 return(dbv);
 105         }
 106
 107         /* length of string vector */
 108         for(vlen = 0, pv = dbv; *pv != NULL; pv++, vlen++);
 109
 110         for (ch = c = path; ; ch++) {
 111                 if (*ch == ':' ||
 112                     (!*ch && !(*(ch - 1) == ':' && ch == 1+ path))) {
 113                         /* single colon -> dot */
 114                         if (ch == c)
 115                                 p = dot;
 116                         else {
 117                                 /* a string */
 118                                 slen = ch - c;
 119                                 if ((p = malloc(sizeof(char) * (slen + 1)))
 120                                     == NULL)
 121                                         err(1, "malloc");
 122                                 bcopy(c, p, slen);
 123                                 *(p + slen) = '\0';
 124                         }
 125                         /* increase dbv with element p */
 126                         if ((dbv = realloc(dbv, sizeof(char **) * (vlen + 2)))
 127                             == NULL)
 128                                 err(1, "realloc");
 129                         *(dbv + vlen) = p;
 130                         *(dbv + ++vlen) = NULL;
 131                         c = ch + 1;
 132                 }
 133                 if (*ch == '\0')
 134                         break;
 135         }
 136         return (dbv);
 137 }
 138
 139 void
 140 print_matches(counter)
 141         u_int counter;
 142 {
 143         (void)printf("%d\n", counter);
 144 }
 145
 146
 147 /*
 148  * extract last glob-free subpattern in name for fast pre-match; prepend
 149  * '\0' for backwards match; return end of new pattern
 150  */
 151 static char globfree[100];
 152
 153 char *
 154 patprep(name)
 155         char *name;
 156 {
 157         register char *endmark, *p, *subp;
 158
 159         subp = globfree;
 160         *subp++ = '\0';   /* set first element to '\0' */
 161         p = name + strlen(name) - 1;
 162
 163         /* skip trailing metacharacters */
 164         for (; p >= name; p--)
 165                 if (index(LOCATE_REG, *p) == NULL)
 166                         break;
 167
 168         /*
 169          * check if maybe we are in a character class
 170          *
 171          * 'foo.[ch]'
 172          *        |----< p
 173          */
 174         if (p >= name &&
 175             (index(p, '[') != NULL || index(p, ']') != NULL)) {
 176                 for (p = name; *p != '\0'; p++)
 177                         if (*p == ']' || *p == '[')
 178                                 break;
 179                 p--;
 180
 181                 /*
 182                  * cannot find a non-meta character, give up
 183                  * '*\*[a-z]'
 184                  *    |-------< p
 185                  */
 186                 if (p >= name && index(LOCATE_REG, *p) != NULL)
 187                         p = name - 1;
 188         }
 189
 190         if (p < name)
 191                 /* only meta chars: "???", force '/' search */
 192                 *subp++ = '/';
 193
 194         else {
 195                 for (endmark = p; p >= name; p--)
 196                         if (index(LOCATE_REG, *p) != NULL)
 197                                 break;
 198                 for (++p;
 199                     (p <= endmark) && subp < (globfree + sizeof(globfree));)
 200                         *subp++ = *p++;
 201         }
 202         *subp = '\0';
 203         return(--subp);
 204 }
 205
 206 /* tolower word */
 207 u_char *
 208 tolower_word(word)
 209         u_char *word;
 210 {
 211         register u_char *p;
 212
 213         for(p = word; *p != '\0'; p++)
 214                 *p = TOLOWER(*p);
 215
 216         return(word);
 217 }
 218
 219
 220 /*
 221  * Read integer from mmap pointer.
 222  * Essential a simple  ``return *(int *)p'' but avoid sigbus
 223  * for integer alignment (SunOS 4.x, 5.x).
 224  *
 225  * Convert network byte order to host byte order if neccessary.
 226  * So we can read on FreeBSD/i386 (little endian) a locate database
 227  * which was built on SunOS/sparc (big endian).
 228  */
 229
 230 int
 231 getwm(p)
 232         caddr_t p;
 233 {
 234         union {
 235                 char buf[INTSIZE];
 236                 int i;
 237         } u;
 238         register int i;
 239
 240         for (i = 0; i < INTSIZE; i++)
 241                 u.buf[i] = *p++;
 242
 243         i = u.i;
 244
 245         if (i > MAXPATHLEN || i < -(MAXPATHLEN)) {
 246                 i = ntohl(i);
 247                 if (i > MAXPATHLEN || i < -(MAXPATHLEN))
 248                         errx(1, "integer out of +-MAXPATHLEN (%d): %d",
 249                             MAXPATHLEN, abs(i) < abs(htonl(i)) ? i : htonl(i));
 250         }
 251         return(i);
 252 }
 253
 254 /*
 255  * Read integer from stream.
 256  *
 257  * Convert network byte order to host byte order if neccessary.
 258  * So we can read on FreeBSD/i386 (little endian) a locate database
 259  * which was built on SunOS/sparc (big endian).
 260  */
 261
 262 int
 263 getwf(fp)
 264         FILE *fp;
 265 {
 266         register int word;
 267
 268         word = getw(fp);
 269
 270         if (word > MAXPATHLEN || word < -(MAXPATHLEN)) {
 271                 word = ntohl(word);
 272                 if (word > MAXPATHLEN || word < -(MAXPATHLEN))
 273                         errx(1, "integer out of +-MAXPATHLEN (%d): %d",
 274                             MAXPATHLEN, abs(word) < abs(htonl(word)) ? word :
 275                                 htonl(word));
 276         }
 277         return(word);
 278 }