| Commit | Line | Data |
|---|---|---|
| 984263bc MD |
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 1.6.2.1 2001/12/20 04:21:48 mikeh Exp $ | |
| 38 | */ | |
| 39 | ||
| 40 | ||
| 41 | #include <stdlib.h> | |
| 42 | #include <string.h> | |
| 43 | #include <err.h> | |
| 44 | #include <sys/param.h> | |
| 45 | #include <stdio.h> | |
| 46 | ||
| 47 | #include "locate.h" | |
| 48 | ||
| 2d8a3be7 EN |
49 | char **colon(char **, char*, char*); |
| 50 | char *patprep(char *); | |
| 51 | void print_matches(u_int); | |
| 52 | u_char *tolower_word(u_char *); | |
| 53 | int getwm(caddr_t); | |
| 54 | int getwf(FILE *); | |
| 55 | int check_bigram_char(int); | |
| 984263bc MD |
56 | |
| 57 | /* | |
| 58 | * Validate bigram chars. If the test failed the database is corrupt | |
| 59 | * or the database is obviously not a locate database. | |
| 60 | */ | |
| 61 | int | |
| 89a89091 | 62 | check_bigram_char(int ch) |
| 984263bc MD |
63 | { |
| 64 | /* legal bigram: 0, ASCII_MIN ... ASCII_MAX */ | |
| 65 | if (ch == 0 || | |
| 66 | (ch >= ASCII_MIN && ch <= ASCII_MAX)) | |
| 67 | return(ch); | |
| 68 | ||
| 69 | errx(1, | |
| 70 | "locate database header corrupt, bigram char outside 0, %d-%d: %d", | |
| 71 | ASCII_MIN, ASCII_MAX, ch); | |
| 72 | exit(1); | |
| 73 | } | |
| 74 | ||
| 75 | /* split a colon separated string into a char vector | |
| 76 | * | |
| 77 | * "bla:foo" -> {"foo", "bla"} | |
| 78 | * "bla:" -> {"foo", dot} | |
| 79 | * "bla" -> {"bla"} | |
| 80 | * "" -> do nothing | |
| 81 | * | |
| 82 | */ | |
| 83 | char ** | |
| 89a89091 | 84 | colon(char **dbv, char *path, char *dot) |
| 984263bc MD |
85 | { |
| 86 | int vlen, slen; | |
| 87 | char *c, *ch, *p; | |
| 88 | char **pv; | |
| 89 | ||
| 90 | if (dbv == NULL) { | |
| 91 | if ((dbv = malloc(sizeof(char **))) == NULL) | |
| 92 | err(1, "malloc"); | |
| 93 | *dbv = NULL; | |
| 94 | } | |
| 95 | ||
| 96 | /* empty string */ | |
| 97 | if (*path == '\0') { | |
| 98 | warnx("empty database name, ignored"); | |
| 99 | return(dbv); | |
| 100 | } | |
| 101 | ||
| 102 | /* length of string vector */ | |
| 103 | for(vlen = 0, pv = dbv; *pv != NULL; pv++, vlen++); | |
| 104 | ||
| 105 | for (ch = c = path; ; ch++) { | |
| 106 | if (*ch == ':' || | |
| 107 | (!*ch && !(*(ch - 1) == ':' && ch == 1+ path))) { | |
| 108 | /* single colon -> dot */ | |
| 109 | if (ch == c) | |
| 110 | p = dot; | |
| 111 | else { | |
| 112 | /* a string */ | |
| 113 | slen = ch - c; | |
| 114 | if ((p = malloc(sizeof(char) * (slen + 1))) | |
| 115 | == NULL) | |
| 116 | err(1, "malloc"); | |
| 117 | bcopy(c, p, slen); | |
| 118 | *(p + slen) = '\0'; | |
| 119 | } | |
| 120 | /* increase dbv with element p */ | |
| 121 | if ((dbv = realloc(dbv, sizeof(char **) * (vlen + 2))) | |
| 122 | == NULL) | |
| 123 | err(1, "realloc"); | |
| 124 | *(dbv + vlen) = p; | |
| 125 | *(dbv + ++vlen) = NULL; | |
| 126 | c = ch + 1; | |
| 127 | } | |
| 128 | if (*ch == '\0') | |
| 129 | break; | |
| 130 | } | |
| 131 | return (dbv); | |
| 132 | } | |
| 133 | ||
| 134 | void | |
| 89a89091 | 135 | print_matches(u_int counter) |
| 984263bc MD |
136 | { |
| 137 | (void)printf("%d\n", counter); | |
| 138 | } | |
| 139 | ||
| 140 | ||
| 141 | /* | |
| 142 | * extract last glob-free subpattern in name for fast pre-match; prepend | |
| 143 | * '\0' for backwards match; return end of new pattern | |
| 144 | */ | |
| 145 | static char globfree[100]; | |
| 146 | ||
| 147 | char * | |
| 89a89091 | 148 | patprep(char *name) |
| 984263bc | 149 | { |
| 6bd457ed | 150 | char *endmark, *p, *subp; |
| 984263bc MD |
151 | |
| 152 | subp = globfree; | |
| 153 | *subp++ = '\0'; /* set first element to '\0' */ | |
| 154 | p = name + strlen(name) - 1; | |
| 155 | ||
| 156 | /* skip trailing metacharacters */ | |
| 157 | for (; p >= name; p--) | |
| 158 | if (index(LOCATE_REG, *p) == NULL) | |
| 159 | break; | |
| 160 | ||
| 161 | /* | |
| 162 | * check if maybe we are in a character class | |
| 163 | * | |
| 164 | * 'foo.[ch]' | |
| 165 | * |----< p | |
| 166 | */ | |
| 167 | if (p >= name && | |
| 168 | (index(p, '[') != NULL || index(p, ']') != NULL)) { | |
| 169 | for (p = name; *p != '\0'; p++) | |
| 170 | if (*p == ']' || *p == '[') | |
| 171 | break; | |
| 172 | p--; | |
| 173 | ||
| 174 | /* | |
| 175 | * cannot find a non-meta character, give up | |
| 176 | * '*\*[a-z]' | |
| 177 | * |-------< p | |
| 178 | */ | |
| 179 | if (p >= name && index(LOCATE_REG, *p) != NULL) | |
| 180 | p = name - 1; | |
| 181 | } | |
| 182 | ||
| 183 | if (p < name) | |
| 184 | /* only meta chars: "???", force '/' search */ | |
| 185 | *subp++ = '/'; | |
| 186 | ||
| 187 | else { | |
| 188 | for (endmark = p; p >= name; p--) | |
| 189 | if (index(LOCATE_REG, *p) != NULL) | |
| 190 | break; | |
| 191 | for (++p; | |
| 192 | (p <= endmark) && subp < (globfree + sizeof(globfree));) | |
| 193 | *subp++ = *p++; | |
| 194 | } | |
| 195 | *subp = '\0'; | |
| 196 | return(--subp); | |
| 197 | } | |
| 198 | ||
| 199 | /* tolower word */ | |
| 200 | u_char * | |
| 89a89091 | 201 | tolower_word(u_char *word) |
| 984263bc | 202 | { |
| 6bd457ed | 203 | u_char *p; |
| 984263bc MD |
204 | |
| 205 | for(p = word; *p != '\0'; p++) | |
| 206 | *p = TOLOWER(*p); | |
| 207 | ||
| 208 | return(word); | |
| 209 | } | |
| 210 | ||
| 211 | ||
| 212 | /* | |
| 213 | * Read integer from mmap pointer. | |
| 214 | * Essential a simple ``return *(int *)p'' but avoid sigbus | |
| 215 | * for integer alignment (SunOS 4.x, 5.x). | |
| 216 | * | |
| 217 | * Convert network byte order to host byte order if neccessary. | |
| 218 | * So we can read on FreeBSD/i386 (little endian) a locate database | |
| 219 | * which was built on SunOS/sparc (big endian). | |
| 220 | */ | |
| 221 | ||
| 222 | int | |
| 89a89091 | 223 | getwm(caddr_t p) |
| 984263bc MD |
224 | { |
| 225 | static char buf[INTSIZE]; | |
| 6bd457ed | 226 | int i; |
| 984263bc MD |
227 | |
| 228 | for (i = 0; i < INTSIZE; i++) | |
| 229 | buf[i] = *p++; | |
| 230 | ||
| 231 | i = *(int *)buf; | |
| 232 | ||
| 233 | if (i > MAXPATHLEN || i < -(MAXPATHLEN)) { | |
| 234 | i = ntohl(i); | |
| 235 | if (i > MAXPATHLEN || i < -(MAXPATHLEN)) | |
| 236 | errx(1, "integer out of +-MAXPATHLEN (%d): %d", | |
| 237 | MAXPATHLEN, abs(i) < abs(htonl(i)) ? i : htonl(i)); | |
| 238 | } | |
| 239 | return(i); | |
| 240 | } | |
| 241 | ||
| 242 | /* | |
| 243 | * Read integer from stream. | |
| 244 | * | |
| 245 | * Convert network byte order to host byte order if neccessary. | |
| 246 | * So we can read on FreeBSD/i386 (little endian) a locate database | |
| 247 | * which was built on SunOS/sparc (big endian). | |
| 248 | */ | |
| 249 | ||
| 250 | int | |
| 89a89091 | 251 | getwf(FILE *fp) |
| 984263bc | 252 | { |
| 6bd457ed | 253 | int word; |
| 984263bc MD |
254 | |
| 255 | word = getw(fp); | |
| 256 | ||
| 257 | if (word > MAXPATHLEN || word < -(MAXPATHLEN)) { | |
| 258 | word = ntohl(word); | |
| 259 | if (word > MAXPATHLEN || word < -(MAXPATHLEN)) | |
| 260 | errx(1, "integer out of +-MAXPATHLEN (%d): %d", | |
| 261 | MAXPATHLEN, abs(word) < abs(htonl(word)) ? word : | |
| 262 | htonl(word)); | |
| 263 | } | |
| 264 | return(word); | |
| 265 | } |