1 /* $NetBSD: bm.c,v 1.6 1997/07/21 14:09:07 jtc 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. All advertising materials mentioning features or use of this software 19 * must display the following acknowledgement: 20 * This product includes software developed by the University of 21 * California, Berkeley and its contributors. 22 * 4. Neither the name of the University nor the names of its contributors 23 * may be used to endorse or promote products derived from this software 24 * without specific prior written permission. 25 * 26 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND 27 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE 28 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE 29 * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE 30 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL 31 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS 32 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) 33 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT 34 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY 35 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF 36 * SUCH DAMAGE. 37 */ 38 39 #include <sys/cdefs.h> 40 #if defined(LIBC_SCCS) && !defined(lint) 41 #if 0 42 static char sccsid[] = "@(#)bm.c 8.7 (Berkeley) 6/21/94"; 43 #else 44 __RCSID("$NetBSD: bm.c,v 1.6 1997/07/21 14:09:07 jtc Exp $"); 45 #endif 46 #endif /* LIBC_SCCS && not lint */ 47 48 #include "namespace.h" 49 #include <sys/types.h> 50 51 #include <bm.h> 52 #include <errno.h> 53 #include <stdlib.h> 54 #include <string.h> 55 56 #ifdef __weak_alias 57 __weak_alias(bm_comp,_bm_comp); 58 __weak_alias(bm_exec,_bm_exec); 59 __weak_alias(bm_free,_bm_free); 60 #endif 61 62 /* 63 * XXX 64 * The default frequency table starts at 99 and counts down. The default 65 * table should probably be oriented toward text, and will necessarily be 66 * locale specific. This one is for English. It was derived from the 67 * OSF/1 and 4.4BSD formatted and unformatted manual pages, and about 100Mb 68 * of email and random text. Change it if you can find something better. 69 */ 70 static u_char const freq_def[256] = { 71 0, 0, 0, 0, 0, 0, 0, 0, 72 0, 77, 90, 0, 0, 0, 0, 0, 73 0, 0, 0, 0, 0, 0, 0, 0, 74 0, 0, 0, 0, 0, 0, 0, 0, 75 99, 28, 42, 27, 16, 14, 20, 51, 76 66, 65, 59, 24, 75, 76, 84, 56, 77 72, 74, 64, 55, 54, 47, 41, 37, 78 44, 61, 70, 43, 23, 53, 49, 22, 79 33, 58, 40, 46, 45, 57, 60, 26, 80 30, 63, 21, 12, 32, 50, 38, 39, 81 34, 11, 48, 67, 62, 35, 15, 29, 82 71, 18, 9, 17, 25, 13, 10, 52, 83 36, 95, 78, 86, 87, 98, 82, 80, 84 88, 94, 19, 68, 89, 83, 93, 96, 85 81, 7, 91, 92, 97, 85, 69, 73, 86 31, 79, 8, 5, 4, 6, 3, 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 0, 0, 0, 0, 0, 0, 0, 0, 101 0, 0, 0, 0, 0, 0, 0, 0, 102 0, 0, 0, 0, 0, 0, 0, 0, 103 }; 104 105 bm_pat * 106 bm_comp(pb, len, freq) 107 u_char const *pb; 108 size_t len; 109 u_char const *freq; 110 { 111 register u_char const *pe, *p; 112 register size_t *d, r; 113 register int j; 114 int sv_errno; 115 bm_pat *pat; 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 if (pat->pat != NULL) 167 free(pat->pat); 168 if (pat->delta != NULL) 169 free(pat->delta); 170 free(pat); 171 } 172 173 u_char * 174 bm_exec(pat, base, n) 175 bm_pat *pat; 176 u_char *base; 177 size_t n; 178 { 179 register u_char *e, *ep, *p, *q, *s; 180 register size_t *d0, k, md2, n1, ro; 181 register int rc; 182 183 if (n == 0) 184 return (NULL); 185 186 d0 = pat->delta; 187 n1 = pat->patlen - 1; 188 md2 = pat->md2; 189 ro = pat->rareoff; 190 rc = pat->rarec; 191 ep = pat->pat + pat->patlen - 1; 192 s = base + (pat->patlen - 1); 193 194 /* fast loop up to n - 3 * patlen */ 195 e = base + n - 3 * pat->patlen; 196 while (s < e) { 197 k = d0[*s]; /* ufast skip loop */ 198 while (k) { 199 k = d0[*(s += k)]; 200 k = d0[*(s += k)]; 201 } 202 if (s >= e) 203 break; 204 if (s[ro] != rc) /* guard test */ 205 goto mismatch1; 206 /* fwd match */ 207 for (p = pat->pat, q = s - n1; p < ep;) 208 if (*q++ != *p++) 209 goto mismatch1; 210 return (s - n1); 211 212 mismatch1: s += md2; /* md2 shift */ 213 } 214 215 /* slow loop up to end */ 216 e = base + n; 217 while (s < e) { 218 s += d0[*s]; /* step */ 219 if (s >= e) 220 break; 221 if (s[ro] != rc) /* guard test */ 222 goto mismatch2; 223 /* fwd match */ 224 for (p = pat->pat, q = s - n1; p <= ep;) 225 if (*q++ != *p++) 226 goto mismatch2; 227 return (s - n1); 228 229 mismatch2: s += md2; /* md2 shift */ 230 } 231 232 return (NULL); 233 } 234