1 /* $OpenBSD: util.c,v 1.14 2016/09/01 09:48:20 tedu Exp $ 2 * 3 * Copyright (c) 1995 Wolfram Schneider <wosch@FreeBSD.org>. Berlin. 4 * Copyright (c) 1989, 1993 5 * The Regents of the University of California. All rights reserved. 6 * 7 * This code is derived from software contributed to Berkeley by 8 * James A. Woods. 9 * 10 * Redistribution and use in source and binary forms, with or without 11 * modification, are permitted provided that the following conditions 12 * are met: 13 * 1. Redistributions of source code must retain the above copyright 14 * notice, this list of conditions and the following disclaimer. 15 * 2. Redistributions in binary form must reproduce the above copyright 16 * notice, this list of conditions and the following disclaimer in the 17 * documentation and/or other materials provided with the distribution. 18 * 3. Neither the name of the University nor the names of its contributors 19 * may be used to endorse or promote products derived from this software 20 * without specific prior written permission. 21 * 22 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND 23 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE 24 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE 25 * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE 26 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL 27 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS 28 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) 29 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT 30 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY 31 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF 32 * SUCH DAMAGE. 33 * 34 * $Id: util.c,v 1.14 2016/09/01 09:48:20 tedu Exp $ 35 */ 36 37 38 #include <stdlib.h> 39 #include <string.h> 40 #include <err.h> 41 #include <stdio.h> 42 #include <limits.h> 43 44 #include "locate.h" 45 46 char **colon(char **, char*, char*); 47 char *patprep(char *); 48 void print_matches(u_int); 49 u_char *tolower_word(u_char *); 50 int getwm(caddr_t); 51 int getwf(FILE *); 52 int check_bigram_char(int); 53 54 /* 55 * Validate bigram chars. If the test failed the database is corrupt 56 * or the database is obviously not a locate database. 57 */ 58 int 59 check_bigram_char(ch) 60 int ch; 61 { 62 /* legal bigram: 0, ASCII_MIN ... ASCII_MAX */ 63 if (ch == 0 || 64 (ch >= ASCII_MIN && ch <= ASCII_MAX)) 65 return(ch); 66 67 (void)fprintf(stderr, "locate database header corrupt, bigram "); 68 (void)fprintf(stderr, "char outside 0, %d-%d: %d\n", 69 ASCII_MIN, ASCII_MAX, ch); 70 exit(1); 71 } 72 73 /* split a colon separated string into a char vector 74 * 75 * "bla:foo" -> {"bla", "foo"} 76 * "bla:" -> {"bla", dot} 77 * "bla" -> {"bla"} 78 * "" -> do nothing 79 * 80 */ 81 char ** 82 colon(dbv, path, dot) 83 char **dbv; 84 char *path; 85 char *dot; /* default for single ':' */ 86 { 87 int vlen, slen; 88 char *c, *ch, *p; 89 char **pv; 90 91 if (dbv == NULL) { 92 if ((dbv = malloc(sizeof(*dbv))) == NULL) 93 err(1, "malloc"); 94 *dbv = NULL; 95 } 96 97 /* empty string */ 98 if (*path == '\0') { 99 (void)fprintf(stderr, "empty database name, ignored\n"); 100 return(dbv); 101 } 102 103 /* length of string vector */ 104 for (vlen = 0, pv = dbv; *pv != NULL; pv++, vlen++) 105 ; 106 107 for (ch = c = path; ; ch++) { 108 if (*ch == ':' || 109 (!*ch && !(*(ch - 1) == ':' && ch == 1+ path))) { 110 char **newdbv; 111 112 /* single colon -> dot */ 113 if (ch == c) 114 p = dot; 115 else { 116 /* a string */ 117 slen = ch - c; 118 if ((p = calloc(sizeof(char), slen + 1)) 119 == NULL) 120 err(1, "malloc"); 121 bcopy(c, p, slen); 122 *(p + slen) = '\0'; 123 } 124 /* increase dbv with element p */ 125 if ((newdbv = reallocarray(dbv, vlen + 2, 126 sizeof(*newdbv))) == NULL) 127 err(1, "realloc"); 128 dbv = newdbv; 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 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 (strchr(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 (strchr(p, '[') != NULL || strchr(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 && strchr(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 (strchr(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 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. 224 * 225 * Convert network byte order to host byte order if necessary. 226 */ 227 228 int 229 getwm(p) 230 caddr_t p; 231 { 232 union { 233 char buf[INTSIZE]; 234 int i; 235 } u; 236 int i; 237 238 for (i = 0; i < INTSIZE; i++) 239 u.buf[i] = *p++; 240 241 i = u.i; 242 243 if (i > PATH_MAX || i < -(PATH_MAX)) { 244 i = ntohl(i); 245 if (i > PATH_MAX || i < -(PATH_MAX)) { 246 (void)fprintf(stderr, 247 "integer out of +-PATH_MAX (%d): %d\n", 248 PATH_MAX, i); 249 exit(1); 250 } 251 } 252 return(i); 253 } 254 255 /* 256 * Read integer from stream. 257 * 258 * Convert network byte order to host byte order if necessary. 259 * So we can read on FreeBSD/i386 (little endian) a locate database 260 * which was built on SunOS/sparc (big endian). 261 */ 262 263 int 264 getwf(fp) 265 FILE *fp; 266 { 267 int word; 268 269 word = getw(fp); 270 271 if (word > PATH_MAX || word < -(PATH_MAX)) { 272 word = ntohl(word); 273 if (word > PATH_MAX || word < -(PATH_MAX)) { 274 (void)fprintf(stderr, 275 "integer out of +-PATH_MAX (%d): %d\n", 276 PATH_MAX, word); 277 exit(1); 278 } 279 } 280 return(word); 281 } 282