summaryrefslogtreecommitdiff
path: root/src/lib/libc/string/bm.c
diff options
context:
space:
mode:
Diffstat (limited to 'src/lib/libc/string/bm.c')
-rw-r--r--src/lib/libc/string/bm.c215
1 files changed, 215 insertions, 0 deletions
diff --git a/src/lib/libc/string/bm.c b/src/lib/libc/string/bm.c
new file mode 100644
index 0000000000..2c7f8fac32
--- /dev/null
+++ b/src/lib/libc/string/bm.c
@@ -0,0 +1,215 @@
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. Neither the name of the University nor the names of its contributors
17 * may be used to endorse or promote products derived from this software
18 * without specific prior written permission.
19 *
20 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
21 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
22 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
23 * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
24 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
25 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
26 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
27 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
28 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
29 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
30 * SUCH DAMAGE.
31 */
32
33#if defined(LIBC_SCCS) && !defined(lint)
34static char *rcsid = "$OpenBSD: bm.c,v 1.4 2003/06/02 20:18:38 millert Exp $";
35#endif /* LIBC_SCCS and not lint */
36
37#include <sys/types.h>
38
39#include <bm.h>
40#include <errno.h>
41#include <stdlib.h>
42#include <string.h>
43
44/*
45 * XXX
46 * The default frequency table starts at 99 and counts down. The default
47 * table should probably be oriented toward text, and will necessarily be
48 * locale specific. This one is for English. It was derived from the
49 * OSF/1 and 4.4BSD formatted and unformatted manual pages, and about 100Mb
50 * of email and random text. Change it if you can find something better.
51 */
52static u_char const freq_def[256] = {
53 0, 0, 0, 0, 0, 0, 0, 0,
54 0, 77, 90, 0, 0, 0, 0, 0,
55 0, 0, 0, 0, 0, 0, 0, 0,
56 0, 0, 0, 0, 0, 0, 0, 0,
57 99, 28, 42, 27, 16, 14, 20, 51,
58 66, 65, 59, 24, 75, 76, 84, 56,
59 72, 74, 64, 55, 54, 47, 41, 37,
60 44, 61, 70, 43, 23, 53, 49, 22,
61 33, 58, 40, 46, 45, 57, 60, 26,
62 30, 63, 21, 12, 32, 50, 38, 39,
63 34, 11, 48, 67, 62, 35, 15, 29,
64 71, 18, 9, 17, 25, 13, 10, 52,
65 36, 95, 78, 86, 87, 98, 82, 80,
66 88, 94, 19, 68, 89, 83, 93, 96,
67 81, 7, 91, 92, 97, 85, 69, 73,
68 31, 79, 8, 5, 4, 6, 3, 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 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};
86
87bm_pat *
88bm_comp(pb, len, freq)
89 u_char const *pb;
90 size_t len;
91 u_char const *freq;
92{
93 register u_char const *pe, *p;
94 register size_t *d, r;
95 register int j;
96 int sv_errno;
97 bm_pat *pat;
98
99 if (len == 0) {
100 errno = EINVAL;
101 return (NULL);
102 }
103 if ((pat = malloc(sizeof(*pat))) == NULL)
104 return (NULL);
105 pat->pat = NULL;
106 pat->delta = NULL;
107
108 pat->patlen = len; /* copy pattern */
109 if ((pat->pat = malloc(pat->patlen)) == NULL)
110 goto mem;
111 memcpy(pat->pat, pb, pat->patlen);
112 /* get skip delta */
113 if ((pat->delta = malloc(256 * sizeof(*d))) == NULL)
114 goto mem;
115 for (j = 0, d = pat->delta; j < 256; j++)
116 d[j] = pat->patlen;
117 for (pe = pb + pat->patlen - 1; pb <= pe; pb++)
118 d[*pb] = pe - pb;
119
120 if (freq == NULL) /* default freq table */
121 freq = freq_def;
122 r = 0; /* get guard */
123 for (pb = pat->pat, pe = pb + pat->patlen - 1; pb < pe; pb++)
124 if (freq[*pb] < freq[pat->pat[r]])
125 r = pb - pat->pat;
126 pat->rarec = pat->pat[r];
127 pat->rareoff = r - (pat->patlen - 1);
128
129 /* get md2 shift */
130 for (pe = pat->pat + pat->patlen - 1, p = pe - 1; p >= pat->pat; p--)
131 if (*p == *pe)
132 break;
133
134 /* *p is first leftward reoccurrence of *pe */
135 pat->md2 = pe - p;
136 return (pat);
137
138mem: sv_errno = errno;
139 bm_free(pat);
140 errno = sv_errno;
141 return (NULL);
142}
143
144void
145bm_free(pat)
146 bm_pat *pat;
147{
148 if (pat->pat != NULL)
149 free(pat->pat);
150 if (pat->delta != NULL)
151 free(pat->delta);
152 free(pat);
153}
154
155u_char *
156bm_exec(pat, base, n)
157 bm_pat *pat;
158 u_char *base;
159 size_t n;
160{
161 register u_char *e, *ep, *p, *q, *s;
162 register size_t *d0, k, md2, n1, ro;
163 register int rc;
164
165 if (n == 0)
166 return (NULL);
167
168 d0 = pat->delta;
169 n1 = pat->patlen - 1;
170 md2 = pat->md2;
171 ro = pat->rareoff;
172 rc = pat->rarec;
173 ep = pat->pat + pat->patlen - 1;
174 s = base + (pat->patlen - 1);
175
176 /* fast loop up to n - 3 * patlen */
177 e = base + n - 3 * pat->patlen;
178 while (s < e) {
179 k = d0[*s]; /* ufast skip loop */
180 while (k) {
181 k = d0[*(s += k)];
182 k = d0[*(s += k)];
183 }
184 if (s >= e)
185 break;
186 if (s[ro] != rc) /* guard test */
187 goto mismatch1;
188 /* fwd match */
189 for (p = pat->pat, q = s - n1; p < ep;)
190 if (*q++ != *p++)
191 goto mismatch1;
192 return (s - n1);
193
194mismatch1: s += md2; /* md2 shift */
195 }
196
197 /* slow loop up to end */
198 e = base + n;
199 while (s < e) {
200 s += d0[*s]; /* step */
201 if (s >= e)
202 break;
203 if (s[ro] != rc) /* guard test */
204 goto mismatch2;
205 /* fwd match */
206 for (p = pat->pat, q = s - n1; p <= ep;)
207 if (*q++ != *p++)
208 goto mismatch2;
209 return (s - n1);
210
211mismatch2: s += md2; /* md2 shift */
212 }
213
214 return (NULL);
215}
generated by cgit v1.2.3-55-g6feb (git 2.39.1) at 2025-04-27 02:47:15 +0000