1 /* $NetBSD: bm.c,v 1.5 1997/07/13 20:24:13 christos 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 1.5 1997/07/13 20:24:13 christos Exp $"); 45 #endif 46 #endif /* LIBC_SCCS && not lint */ 47 48 #include <sys/types.h> 49 50 #include <bm.h> 51 #include <errno.h> 52 #include <stdlib.h> 53 #include <string.h> 54 55 /* 56 * XXX 57 * The default frequency table starts at 99 and counts down. The default 58 * table should probably be oriented toward text, and will necessarily be 59 * locale specific. This one is for English. It was derived from the 60 * OSF/1 and 4.4BSD formatted and unformatted manual pages, and about 100Mb 61 * of email and random text. Change it if you can find something better. 62 */ 63 static u_char const freq_def[256] = { 64 0, 0, 0, 0, 0, 0, 0, 0, 65 0, 77, 90, 0, 0, 0, 0, 0, 66 0, 0, 0, 0, 0, 0, 0, 0, 67 0, 0, 0, 0, 0, 0, 0, 0, 68 99, 28, 42, 27, 16, 14, 20, 51, 69 66, 65, 59, 24, 75, 76, 84, 56, 70 72, 74, 64, 55, 54, 47, 41, 37, 71 44, 61, 70, 43, 23, 53, 49, 22, 72 33, 58, 40, 46, 45, 57, 60, 26, 73 30, 63, 21, 12, 32, 50, 38, 39, 74 34, 11, 48, 67, 62, 35, 15, 29, 75 71, 18, 9, 17, 25, 13, 10, 52, 76 36, 95, 78, 86, 87, 98, 82, 80, 77 88, 94, 19, 68, 89, 83, 93, 96, 78 81, 7, 91, 92, 97, 85, 69, 73, 79 31, 79, 8, 5, 4, 6, 3, 0, 80 0, 0, 0, 0, 0, 0, 0, 0, 81 0, 0, 0, 0, 0, 0, 0, 0, 82 0, 0, 0, 0, 0, 0, 0, 0, 83 0, 0, 0, 0, 0, 0, 0, 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 }; 97 98 bm_pat * 99 bm_comp(pb, len, freq) 100 u_char const *pb; 101 size_t len; 102 u_char const *freq; 103 { 104 register u_char const *pe, *p; 105 register size_t *d, r; 106 register int j; 107 int sv_errno; 108 bm_pat *pat; 109 110 if (len == 0) { 111 errno = EINVAL; 112 return (NULL); 113 } 114 if ((pat = malloc(sizeof(*pat))) == NULL) 115 return (NULL); 116 pat->pat = NULL; 117 pat->delta = NULL; 118 119 pat->patlen = len; /* copy pattern */ 120 if ((pat->pat = malloc(pat->patlen)) == NULL) 121 goto mem; 122 memcpy(pat->pat, pb, pat->patlen); 123 /* get skip delta */ 124 if ((pat->delta = malloc(256 * sizeof(*d))) == NULL) 125 goto mem; 126 for (j = 0, d = pat->delta; j < 256; j++) 127 d[j] = pat->patlen; 128 for (pe = pb + pat->patlen - 1; pb <= pe; pb++) 129 d[*pb] = pe - pb; 130 131 if (freq == NULL) /* default freq table */ 132 freq = freq_def; 133 r = 0; /* get guard */ 134 for (pb = pat->pat, pe = pb + pat->patlen - 1; pb < pe; pb++) 135 if (freq[*pb] < freq[pat->pat[r]]) 136 r = pb - pat->pat; 137 pat->rarec = pat->pat[r]; 138 pat->rareoff = r - (pat->patlen - 1); 139 140 /* get md2 shift */ 141 for (pe = pat->pat + pat->patlen - 1, p = pe - 1; p >= pat->pat; p--) 142 if (*p == *pe) 143 break; 144 145 /* *p is first leftward reoccurrence of *pe */ 146 pat->md2 = pe - p; 147 return (pat); 148 149 mem: sv_errno = errno; 150 bm_free(pat); 151 errno = sv_errno; 152 return (NULL); 153 } 154 155 void 156 bm_free(pat) 157 bm_pat *pat; 158 { 159 if (pat->pat != NULL) 160 free(pat->pat); 161 if (pat->delta != NULL) 162 free(pat->delta); 163 free(pat); 164 } 165 166 u_char * 167 bm_exec(pat, base, n) 168 bm_pat *pat; 169 u_char *base; 170 size_t n; 171 { 172 register u_char *e, *ep, *p, *q, *s; 173 register size_t *d0, k, md2, n1, ro; 174 register int rc; 175 176 if (n == 0) 177 return (NULL); 178 179 d0 = pat->delta; 180 n1 = pat->patlen - 1; 181 md2 = pat->md2; 182 ro = pat->rareoff; 183 rc = pat->rarec; 184 ep = pat->pat + pat->patlen - 1; 185 s = base + (pat->patlen - 1); 186 187 /* fast loop up to n - 3 * patlen */ 188 e = base + n - 3 * pat->patlen; 189 while (s < e) { 190 k = d0[*s]; /* ufast skip loop */ 191 while (k) { 192 k = d0[*(s += k)]; 193 k = d0[*(s += k)]; 194 } 195 if (s >= e) 196 break; 197 if (s[ro] != rc) /* guard test */ 198 goto mismatch1; 199 /* fwd match */ 200 for (p = pat->pat, q = s - n1; p < ep;) 201 if (*q++ != *p++) 202 goto mismatch1; 203 return (s - n1); 204 205 mismatch1: s += md2; /* md2 shift */ 206 } 207 208 /* slow loop up to end */ 209 e = base + n; 210 while (s < e) { 211 s += d0[*s]; /* step */ 212 if (s >= e) 213 break; 214 if (s[ro] != rc) /* guard test */ 215 goto mismatch2; 216 /* fwd match */ 217 for (p = pat->pat, q = s - n1; p <= ep;) 218 if (*q++ != *p++) 219 goto mismatch2; 220 return (s - n1); 221 222 mismatch2: s += md2; /* md2 shift */ 223 } 224 225 return (NULL); 226 } 227