1 /* $NetBSD: bm.c,v 1.11 2003/08/07 16:43:47 agc Exp $ */ 2 3 /*- 4 * Copyright (c) 1994 5 * The Regents of the University of California. All rights reserved. 6 * 7 * This code is derived from software contributed to Berkeley by 8 * Andrew Hume of AT&T Bell Laboratories. 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 35 #include <sys/cdefs.h> 36 #if defined(LIBC_SCCS) && !defined(lint) 37 #if 0 38 static char sccsid[] = "@(#)bm.c 8.7 (Berkeley) 6/21/94"; 39 #else 40 __RCSID("$NetBSD: bm.c,v 1.11 2003/08/07 16:43:47 agc Exp $"); 41 #endif 42 #endif /* LIBC_SCCS && not lint */ 43 44 #include "namespace.h" 45 #include <sys/types.h> 46 47 #include <assert.h> 48 #include <bm.h> 49 #include <errno.h> 50 #include <stdlib.h> 51 #include <string.h> 52 53 #ifdef __weak_alias 54 __weak_alias(bm_comp,_bm_comp) 55 __weak_alias(bm_exec,_bm_exec) 56 __weak_alias(bm_free,_bm_free) 57 #endif 58 59 /* 60 * XXX 61 * The default frequency table starts at 99 and counts down. The default 62 * table should probably be oriented toward text, and will necessarily be 63 * locale specific. This one is for English. It was derived from the 64 * OSF/1 and 4.4BSD formatted and unformatted manual pages, and about 100Mb 65 * of email and random text. Change it if you can find something better. 66 */ 67 static u_char const freq_def[256] = { 68 0, 0, 0, 0, 0, 0, 0, 0, 69 0, 77, 90, 0, 0, 0, 0, 0, 70 0, 0, 0, 0, 0, 0, 0, 0, 71 0, 0, 0, 0, 0, 0, 0, 0, 72 99, 28, 42, 27, 16, 14, 20, 51, 73 66, 65, 59, 24, 75, 76, 84, 56, 74 72, 74, 64, 55, 54, 47, 41, 37, 75 44, 61, 70, 43, 23, 53, 49, 22, 76 33, 58, 40, 46, 45, 57, 60, 26, 77 30, 63, 21, 12, 32, 50, 38, 39, 78 34, 11, 48, 67, 62, 35, 15, 29, 79 71, 18, 9, 17, 25, 13, 10, 52, 80 36, 95, 78, 86, 87, 98, 82, 80, 81 88, 94, 19, 68, 89, 83, 93, 96, 82 81, 7, 91, 92, 97, 85, 69, 73, 83 31, 79, 8, 5, 4, 6, 3, 0, 84 0, 0, 0, 0, 0, 0, 0, 0, 85 0, 0, 0, 0, 0, 0, 0, 0, 86 0, 0, 0, 0, 0, 0, 0, 0, 87 0, 0, 0, 0, 0, 0, 0, 0, 88 0, 0, 0, 0, 0, 0, 0, 0, 89 0, 0, 0, 0, 0, 0, 0, 0, 90 0, 0, 0, 0, 0, 0, 0, 0, 91 0, 0, 0, 0, 0, 0, 0, 0, 92 0, 0, 0, 0, 0, 0, 0, 0, 93 0, 0, 0, 0, 0, 0, 0, 0, 94 0, 0, 0, 0, 0, 0, 0, 0, 95 0, 0, 0, 0, 0, 0, 0, 0, 96 0, 0, 0, 0, 0, 0, 0, 0, 97 0, 0, 0, 0, 0, 0, 0, 0, 98 0, 0, 0, 0, 0, 0, 0, 0, 99 0, 0, 0, 0, 0, 0, 0, 0, 100 }; 101 102 bm_pat * 103 bm_comp(pb, len, freq) 104 u_char const *pb; 105 size_t len; 106 u_char const *freq; 107 { 108 u_char const *pe, *p; 109 size_t *d, r; 110 int j; 111 int sv_errno; 112 bm_pat *pat; 113 114 _DIAGASSERT(pb != NULL); 115 /* freq may be NULL */ 116 117 if (len == 0) { 118 errno = EINVAL; 119 return (NULL); 120 } 121 if ((pat = malloc(sizeof(*pat))) == NULL) 122 return (NULL); 123 pat->pat = NULL; 124 pat->delta = NULL; 125 126 pat->patlen = len; /* copy pattern */ 127 if ((pat->pat = malloc(pat->patlen)) == NULL) 128 goto mem; 129 memcpy(pat->pat, pb, pat->patlen); 130 /* get skip delta */ 131 if ((pat->delta = malloc(256 * sizeof(*d))) == NULL) 132 goto mem; 133 for (j = 0, d = pat->delta; j < 256; j++) 134 d[j] = pat->patlen; 135 for (pe = pb + pat->patlen - 1; pb <= pe; pb++) 136 d[*pb] = pe - pb; 137 138 if (freq == NULL) /* default freq table */ 139 freq = freq_def; 140 r = 0; /* get guard */ 141 for (pb = pat->pat, pe = pb + pat->patlen - 1; pb < pe; pb++) 142 if (freq[*pb] < freq[pat->pat[r]]) 143 r = pb - pat->pat; 144 pat->rarec = pat->pat[r]; 145 pat->rareoff = r - (pat->patlen - 1); 146 147 /* get md2 shift */ 148 for (pe = pat->pat + pat->patlen - 1, p = pe - 1; p >= pat->pat; p--) 149 if (*p == *pe) 150 break; 151 152 /* *p is first leftward reoccurrence of *pe */ 153 pat->md2 = pe - p; 154 return (pat); 155 156 mem: sv_errno = errno; 157 bm_free(pat); 158 errno = sv_errno; 159 return (NULL); 160 } 161 162 void 163 bm_free(pat) 164 bm_pat *pat; 165 { 166 167 _DIAGASSERT(pat != NULL); 168 169 if (pat->pat != NULL) 170 free(pat->pat); 171 if (pat->delta != NULL) 172 free(pat->delta); 173 free(pat); 174 } 175 176 u_char * 177 bm_exec(pat, base, n) 178 bm_pat *pat; 179 u_char *base; 180 size_t n; 181 { 182 u_char *e, *ep, *p, *q, *s; 183 size_t *d0, k, md2, n1, ro; 184 int rc; 185 186 _DIAGASSERT(pat != NULL); 187 _DIAGASSERT(base != NULL); 188 189 if (n == 0) 190 return (NULL); 191 192 d0 = pat->delta; 193 n1 = pat->patlen - 1; 194 md2 = pat->md2; 195 ro = pat->rareoff; 196 rc = pat->rarec; 197 ep = pat->pat + pat->patlen - 1; 198 s = base + (pat->patlen - 1); 199 200 /* fast loop up to n - 3 * patlen */ 201 e = base + n - 3 * pat->patlen; 202 while (s < e) { 203 k = d0[*s]; /* ufast skip loop */ 204 while (k) { 205 k = d0[*(s += k)]; 206 k = d0[*(s += k)]; 207 } 208 if (s >= e) 209 break; 210 if (s[ro] != rc) /* guard test */ 211 goto mismatch1; 212 /* fwd match */ 213 for (p = pat->pat, q = s - n1; p < ep;) 214 if (*q++ != *p++) 215 goto mismatch1; 216 return (s - n1); 217 218 mismatch1: s += md2; /* md2 shift */ 219 } 220 221 /* slow loop up to end */ 222 e = base + n; 223 while (s < e) { 224 s += d0[*s]; /* step */ 225 if (s >= e) 226 break; 227 if (s[ro] != rc) /* guard test */ 228 goto mismatch2; 229 /* fwd match */ 230 for (p = pat->pat, q = s - n1; p <= ep;) 231 if (*q++ != *p++) 232 goto mismatch2; 233 return (s - n1); 234 235 mismatch2: s += md2; /* md2 shift */ 236 } 237 238 return (NULL); 239 } 240