util.c revision 332462
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: stable/11/usr.bin/locate/locate/util.c 332462 2018-04-13 02:40:10Z kevans $ 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 50char **colon(char **, char*, char*); 51char *patprep(char *); 52void print_matches(u_int); 53u_char *tolower_word(u_char *); 54int getwm(caddr_t); 55int getwf(FILE *); 56int 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 */ 62int 63check_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 */ 85char ** 86colon(char **dbv, char *path, char *dot) 87{ 88 int vlen, slen; 89 char *c, *ch, *p; 90 char **pv; 91 92 if (dbv == NULL) { 93 if ((dbv = malloc(sizeof(char *))) == NULL) 94 err(1, "malloc"); 95 *dbv = NULL; 96 } 97 98 /* empty string */ 99 if (*path == '\0') { 100 warnx("empty database name, ignored"); 101 return(dbv); 102 } 103 104 /* length of string vector */ 105 for(vlen = 0, pv = dbv; *pv != NULL; pv++, vlen++); 106 107 for (ch = c = path; ; ch++) { 108 if (*ch == ':' || 109 (!*ch && !(*(ch - 1) == ':' && ch == 1+ path))) { 110 /* single colon -> dot */ 111 if (ch == c) 112 p = dot; 113 else { 114 /* a string */ 115 slen = ch - c; 116 if ((p = malloc(sizeof(char) * (slen + 1))) 117 == NULL) 118 err(1, "malloc"); 119 bcopy(c, p, slen); 120 *(p + slen) = '\0'; 121 } 122 /* increase dbv with element p */ 123 if ((dbv = realloc(dbv, sizeof(char *) * (vlen + 2))) 124 == NULL) 125 err(1, "realloc"); 126 *(dbv + vlen) = p; 127 *(dbv + ++vlen) = NULL; 128 c = ch + 1; 129 } 130 if (*ch == '\0') 131 break; 132 } 133 return (dbv); 134} 135 136void 137print_matches(counter) 138 u_int counter; 139{ 140 (void)printf("%d\n", counter); 141} 142 143 144/* 145 * extract last glob-free subpattern in name for fast pre-match; prepend 146 * '\0' for backwards match; return end of new pattern 147 */ 148static char globfree[100]; 149 150char * 151patprep(name) 152 char *name; 153{ 154 register char *endmark, *p, *subp; 155 156 subp = globfree; 157 *subp++ = '\0'; /* set first element to '\0' */ 158 p = name + strlen(name) - 1; 159 160 /* skip trailing metacharacters */ 161 for (; p >= name; p--) 162 if (strchr(LOCATE_REG, *p) == NULL) 163 break; 164 165 /* 166 * check if maybe we are in a character class 167 * 168 * 'foo.[ch]' 169 * |----< p 170 */ 171 if (p >= name && 172 (strchr(p, '[') != NULL || strchr(p, ']') != NULL)) { 173 for (p = name; *p != '\0'; p++) 174 if (*p == ']' || *p == '[') 175 break; 176 p--; 177 178 /* 179 * cannot find a non-meta character, give up 180 * '*\*[a-z]' 181 * |-------< p 182 */ 183 if (p >= name && strchr(LOCATE_REG, *p) != NULL) 184 p = name - 1; 185 } 186 187 if (p < name) 188 /* only meta chars: "???", force '/' search */ 189 *subp++ = '/'; 190 191 else { 192 for (endmark = p; p >= name; p--) 193 if (strchr(LOCATE_REG, *p) != NULL) 194 break; 195 for (++p; 196 (p <= endmark) && subp < (globfree + sizeof(globfree));) 197 *subp++ = *p++; 198 } 199 *subp = '\0'; 200 return(--subp); 201} 202 203/* tolower word */ 204u_char * 205tolower_word(word) 206 u_char *word; 207{ 208 register u_char *p; 209 210 for(p = word; *p != '\0'; p++) 211 *p = TOLOWER(*p); 212 213 return(word); 214} 215 216 217/* 218 * Read integer from mmap pointer. 219 * Essentially a simple ``return *(int *)p'' but avoids sigbus 220 * for integer alignment (SunOS 4.x, 5.x). 221 * 222 * Convert network byte order to host byte order if necessary. 223 * So we can read a locate database on FreeBSD/i386 (little endian) 224 * which was built on SunOS/sparc (big endian). 225 */ 226 227int 228getwm(p) 229 caddr_t p; 230{ 231 union { 232 char buf[INTSIZE]; 233 int i; 234 } u; 235 register int i, hi; 236 237 for (i = 0; i < (int)INTSIZE; i++) 238 u.buf[i] = *p++; 239 240 i = u.i; 241 242 if (i > MAXPATHLEN || i < -(MAXPATHLEN)) { 243 hi = ntohl(i); 244 if (hi > MAXPATHLEN || hi < -(MAXPATHLEN)) 245 errx(1, "integer out of +-MAXPATHLEN (%d): %u", 246 MAXPATHLEN, abs(i) < abs(hi) ? i : hi); 247 return(hi); 248 } 249 return(i); 250} 251 252/* 253 * Read integer from stream. 254 * 255 * Convert network byte order to host byte order if necessary. 256 * So we can read on FreeBSD/i386 (little endian) a locate database 257 * which was built on SunOS/sparc (big endian). 258 */ 259 260int 261getwf(fp) 262 FILE *fp; 263{ 264 register int word, hword; 265 266 word = getw(fp); 267 268 if (word > MAXPATHLEN || word < -(MAXPATHLEN)) { 269 hword = ntohl(word); 270 if (hword > MAXPATHLEN || hword < -(MAXPATHLEN)) 271 errx(1, "integer out of +-MAXPATHLEN (%d): %u", 272 MAXPATHLEN, abs(word) < abs(hword) ? word : hword); 273 return(hword); 274 } 275 return(word); 276} 277