1 /* $OpenBSD: bm.c,v 1.6 2005/08/08 08:05:37 espie Exp $ */
2 /*-
3 * Copyright (c) 1994
4 * The Regents of the University of California. All rights reserved.
5 *
6 * This code is derived from software contributed to Berkeley by
7 * Andrew Hume of AT&T Bell Laboratories.
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. Neither the name of the University nor the names of its contributors
18 * may be used to endorse or promote products derived from this software
19 * without specific prior written permission.
20 *
21 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
22 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
23 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
24 * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
25 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
26 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
27 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
28 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
29 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
30 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
31 * SUCH DAMAGE.
32 */
33
34 #include <sys/types.h>
35
36 #include <bm.h>
37 #include <errno.h>
38 #include <stdlib.h>
39 #include <string.h>
40
41 /*
42 * XXX
43 * The default frequency table starts at 99 and counts down. The default
44 * table should probably be oriented toward text, and will necessarily be
45 * locale specific. This one is for English. It was derived from the
46 * OSF/1 and 4.4BSD formatted and unformatted manual pages, and about 100Mb
47 * of email and random text. Change it if you can find something better.
48 */
49 static u_char const freq_def[256] = {
50 0, 0, 0, 0, 0, 0, 0, 0,
51 0, 77, 90, 0, 0, 0, 0, 0,
52 0, 0, 0, 0, 0, 0, 0, 0,
53 0, 0, 0, 0, 0, 0, 0, 0,
54 99, 28, 42, 27, 16, 14, 20, 51,
55 66, 65, 59, 24, 75, 76, 84, 56,
56 72, 74, 64, 55, 54, 47, 41, 37,
57 44, 61, 70, 43, 23, 53, 49, 22,
58 33, 58, 40, 46, 45, 57, 60, 26,
59 30, 63, 21, 12, 32, 50, 38, 39,
60 34, 11, 48, 67, 62, 35, 15, 29,
61 71, 18, 9, 17, 25, 13, 10, 52,
62 36, 95, 78, 86, 87, 98, 82, 80,
63 88, 94, 19, 68, 89, 83, 93, 96,
64 81, 7, 91, 92, 97, 85, 69, 73,
65 31, 79, 8, 5, 4, 6, 3, 0,
66 0, 0, 0, 0, 0, 0, 0, 0,
67 0, 0, 0, 0, 0, 0, 0, 0,
68 0, 0, 0, 0, 0, 0, 0, 0,
69 0, 0, 0, 0, 0, 0, 0, 0,
70 0, 0, 0, 0, 0, 0, 0, 0,
71 0, 0, 0, 0, 0, 0, 0, 0,
72 0, 0, 0, 0, 0, 0, 0, 0,
73 0, 0, 0, 0, 0, 0, 0, 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 };
83
84 bm_pat *
bm_comp(u_char const * pb,size_t len,u_char const * freq)85 bm_comp(u_char const *pb, size_t len, u_char const *freq)
86 {
87 u_char const *pe, *p;
88 size_t *d, r;
89 int j;
90 int sv_errno;
91 bm_pat *pat;
92
93 if (len == 0) {
94 errno = EINVAL;
95 return (NULL);
96 }
97 if ((pat = malloc(sizeof(*pat))) == NULL)
98 return (NULL);
99 pat->pat = NULL;
100 pat->delta = NULL;
101
102 pat->patlen = len; /* copy pattern */
103 if ((pat->pat = malloc(pat->patlen)) == NULL)
104 goto mem;
105 memcpy(pat->pat, pb, pat->patlen);
106 /* get skip delta */
107 if ((pat->delta = malloc(256 * sizeof(*d))) == NULL)
108 goto mem;
109 for (j = 0, d = pat->delta; j < 256; j++)
110 d[j] = pat->patlen;
111 for (pe = pb + pat->patlen - 1; pb <= pe; pb++)
112 d[*pb] = pe - pb;
113
114 if (freq == NULL) /* default freq table */
115 freq = freq_def;
116 r = 0; /* get guard */
117 for (pb = pat->pat, pe = pb + pat->patlen - 1; pb < pe; pb++)
118 if (freq[*pb] < freq[pat->pat[r]])
119 r = pb - pat->pat;
120 pat->rarec = pat->pat[r];
121 pat->rareoff = r - (pat->patlen - 1);
122
123 /* get md2 shift */
124 for (pe = pat->pat + pat->patlen - 1, p = pe - 1; p >= pat->pat; p--)
125 if (*p == *pe)
126 break;
127
128 /* *p is first leftward reoccurrence of *pe */
129 pat->md2 = pe - p;
130 return (pat);
131
132 mem: sv_errno = errno;
133 bm_free(pat);
134 errno = sv_errno;
135 return (NULL);
136 }
137
138 void
bm_free(bm_pat * pat)139 bm_free(bm_pat *pat)
140 {
141 if (pat->pat != NULL)
142 free(pat->pat);
143 if (pat->delta != NULL)
144 free(pat->delta);
145 free(pat);
146 }
147
148 u_char *
bm_exec(bm_pat * pat,u_char * base,size_t n)149 bm_exec(bm_pat *pat, u_char *base, size_t n)
150 {
151 u_char *e, *ep, *p, *q, *s;
152 size_t *d0, k, md2, n1, ro;
153 int rc;
154
155 if (n == 0)
156 return (NULL);
157
158 d0 = pat->delta;
159 n1 = pat->patlen - 1;
160 md2 = pat->md2;
161 ro = pat->rareoff;
162 rc = pat->rarec;
163 ep = pat->pat + pat->patlen - 1;
164 s = base + (pat->patlen - 1);
165
166 /* fast loop up to n - 3 * patlen */
167 e = base + n - 3 * pat->patlen;
168 while (s < e) {
169 k = d0[*s]; /* ufast skip loop */
170 while (k) {
171 k = d0[*(s += k)];
172 k = d0[*(s += k)];
173 }
174 if (s >= e)
175 break;
176 if (s[ro] != rc) /* guard test */
177 goto mismatch1;
178 /* fwd match */
179 for (p = pat->pat, q = s - n1; p < ep;)
180 if (*q++ != *p++)
181 goto mismatch1;
182 return (s - n1);
183
184 mismatch1: s += md2; /* md2 shift */
185 }
186
187 /* slow loop up to end */
188 e = base + n;
189 while (s < e) {
190 s += d0[*s]; /* step */
191 if (s >= e)
192 break;
193 if (s[ro] != rc) /* guard test */
194 goto mismatch2;
195 /* fwd match */
196 for (p = pat->pat, q = s - n1; p <= ep;)
197 if (*q++ != *p++)
198 goto mismatch2;
199 return (s - n1);
200
201 mismatch2: s += md2; /* md2 shift */
202 }
203
204 return (NULL);
205 }
206