1 /*- 2 * Copyright (c) 1994 3 * The Regents of the University of California. All rights reserved. 4 * 5 * This code is derived from software contributed to Berkeley by 6 * Andrew Hume of AT&T Bell Laboratories. 7 * 8 * Redistribution and use in source and binary forms, with or without 9 * modification, are permitted provided that the following conditions 10 * are met: 11 * 1. Redistributions of source code must retain the above copyright 12 * notice, this list of conditions and the following disclaimer. 13 * 2. Redistributions in binary form must reproduce the above copyright 14 * notice, this list of conditions and the following disclaimer in the 15 * documentation and/or other materials provided with the distribution. 16 * 3. All advertising materials mentioning features or use of this software 17 * must display the following acknowledgement: 18 * This product includes software developed by the University of 19 * California, Berkeley and its contributors. 20 * 4. Neither the name of the University nor the names of its contributors 21 * may be used to endorse or promote products derived from this software 22 * without specific prior written permission. 23 * 24 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND 25 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE 26 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE 27 * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE 28 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL 29 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS 30 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) 31 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT 32 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY 33 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF 34 * SUCH DAMAGE. 35 */ 36 37 #ifndef lint 38 /* from: static char sccsid[] = "@(#)bm.c 8.7 (Berkeley) 6/21/94"; */ 39 static char *rcsid = "$Id: bm.c,v 1.3 1994/12/14 07:24:12 cgd Exp $"; 40 #endif /* not lint */ 41 42 #include <sys/types.h> 43 44 #include <bm.h> 45 #include <errno.h> 46 #include <stdlib.h> 47 #include <string.h> 48 49 /* 50 * XXX 51 * The default frequency table starts at 99 and counts down. The default 52 * table should probably be oriented toward text, and will necessarily be 53 * locale specific. This one is for English. It was derived from the 54 * OSF/1 and 4.4BSD formatted and unformatted manual pages, and about 100Mb 55 * of email and random text. Change it if you can find something better. 56 */ 57 static u_char const freq_def[256] = { 58 0, 0, 0, 0, 0, 0, 0, 0, 59 0, 77, 90, 0, 0, 0, 0, 0, 60 0, 0, 0, 0, 0, 0, 0, 0, 61 0, 0, 0, 0, 0, 0, 0, 0, 62 99, 28, 42, 27, 16, 14, 20, 51, 63 66, 65, 59, 24, 75, 76, 84, 56, 64 72, 74, 64, 55, 54, 47, 41, 37, 65 44, 61, 70, 43, 23, 53, 49, 22, 66 33, 58, 40, 46, 45, 57, 60, 26, 67 30, 63, 21, 12, 32, 50, 38, 39, 68 34, 11, 48, 67, 62, 35, 15, 29, 69 71, 18, 9, 17, 25, 13, 10, 52, 70 36, 95, 78, 86, 87, 98, 82, 80, 71 88, 94, 19, 68, 89, 83, 93, 96, 72 81, 7, 91, 92, 97, 85, 69, 73, 73 31, 79, 8, 5, 4, 6, 3, 0, 74 0, 0, 0, 0, 0, 0, 0, 0, 75 0, 0, 0, 0, 0, 0, 0, 0, 76 0, 0, 0, 0, 0, 0, 0, 0, 77 0, 0, 0, 0, 0, 0, 0, 0, 78 0, 0, 0, 0, 0, 0, 0, 0, 79 0, 0, 0, 0, 0, 0, 0, 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 }; 91 92 bm_pat * 93 bm_comp(pb, len, freq) 94 u_char const *pb; 95 size_t len; 96 u_char const *freq; 97 { 98 register u_char const *pe, *p; 99 register size_t *d, r; 100 register int j; 101 int sv_errno; 102 bm_pat *pat; 103 104 if (len == 0) { 105 errno = EINVAL; 106 return (NULL); 107 } 108 if ((pat = malloc(sizeof(*pat))) == NULL) 109 return (NULL); 110 pat->pat = NULL; 111 pat->delta = NULL; 112 113 pat->patlen = len; /* copy pattern */ 114 if ((pat->pat = malloc(pat->patlen)) == NULL) 115 goto mem; 116 memcpy(pat->pat, pb, pat->patlen); 117 /* get skip delta */ 118 if ((pat->delta = malloc(256 * sizeof(*d))) == NULL) 119 goto mem; 120 for (j = 0, d = pat->delta; j < 256; j++) 121 d[j] = pat->patlen; 122 for (pe = pb + pat->patlen - 1; pb <= pe; pb++) 123 d[*pb] = pe - pb; 124 125 if (freq == NULL) /* default freq table */ 126 freq = freq_def; 127 r = 0; /* get guard */ 128 for (pb = pat->pat, pe = pb + pat->patlen - 1; pb < pe; pb++) 129 if (freq[*pb] < freq[pat->pat[r]]) 130 r = pb - pat->pat; 131 pat->rarec = pat->pat[r]; 132 pat->rareoff = r - (pat->patlen - 1); 133 134 /* get md2 shift */ 135 for (pe = pat->pat + pat->patlen - 1, p = pe - 1; p >= pat->pat; p--) 136 if (*p == *pe) 137 break; 138 139 /* *p is first leftward reoccurrence of *pe */ 140 pat->md2 = pe - p; 141 return (pat); 142 143 mem: sv_errno = errno; 144 bm_free(pat); 145 errno = sv_errno; 146 return (NULL); 147 } 148 149 void 150 bm_free(pat) 151 bm_pat *pat; 152 { 153 if (pat->pat != NULL) 154 free(pat->pat); 155 if (pat->delta != NULL) 156 free(pat->delta); 157 free(pat); 158 } 159 160 u_char * 161 bm_exec(pat, base, n) 162 bm_pat *pat; 163 u_char *base; 164 size_t n; 165 { 166 register u_char *e, *ep, *p, *q, *s; 167 register size_t *d0, k, md2, n1, ro; 168 register int rc; 169 170 if (n == 0) 171 return (NULL); 172 173 d0 = pat->delta; 174 n1 = pat->patlen - 1; 175 md2 = pat->md2; 176 ro = pat->rareoff; 177 rc = pat->rarec; 178 ep = pat->pat + pat->patlen - 1; 179 s = base + (pat->patlen - 1); 180 181 /* fast loop up to n - 3 * patlen */ 182 e = base + n - 3 * pat->patlen; 183 while (s < e) { 184 k = d0[*s]; /* ufast skip loop */ 185 while (k) { 186 k = d0[*(s += k)]; 187 k = d0[*(s += k)]; 188 } 189 if (s >= e) 190 break; 191 if (s[ro] != rc) /* guard test */ 192 goto mismatch1; 193 /* fwd match */ 194 for (p = pat->pat, q = s - n1; p < ep;) 195 if (*q++ != *p++) 196 goto mismatch1; 197 return (s - n1); 198 199 mismatch1: s += md2; /* md2 shift */ 200 } 201 202 /* slow loop up to end */ 203 e = base + n; 204 while (s < e) { 205 s += d0[*s]; /* step */ 206 if (s >= e) 207 break; 208 if (s[ro] != rc) /* guard test */ 209 goto mismatch2; 210 /* fwd match */ 211 for (p = pat->pat, q = s - n1; p <= ep;) 212 if (*q++ != *p++) 213 goto mismatch2; 214 return (s - n1); 215 216 mismatch2: s += md2; /* md2 shift */ 217 } 218 219 return (NULL); 220 } 221