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.c219
1 files changed, 219 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..b191d340f6
--- /dev/null
+++ b/src/lib/libc/string/bm.c
@@ -0,0 +1,219 @@
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#if defined(LIBC_SCCS) && !defined(lint)
38static char *rcsid = "$OpenBSD: bm.c,v 1.3 1996/08/19 08:33:59 tholo Exp $";
39#endif /* LIBC_SCCS and not lint */
40
41#include <sys/types.h>
42
43#include <bm.h>
44#include <errno.h>
45#include <stdlib.h>
46#include <string.h>
47
48/*
49 * XXX
50 * The default frequency table starts at 99 and counts down. The default
51 * table should probably be oriented toward text, and will necessarily be
52 * locale specific. This one is for English. It was derived from the
53 * OSF/1 and 4.4BSD formatted and unformatted manual pages, and about 100Mb
54 * of email and random text. Change it if you can find something better.
55 */
56static u_char const freq_def[256] = {
57 0, 0, 0, 0, 0, 0, 0, 0,
58 0, 77, 90, 0, 0, 0, 0, 0,
59 0, 0, 0, 0, 0, 0, 0, 0,
60 0, 0, 0, 0, 0, 0, 0, 0,
61 99, 28, 42, 27, 16, 14, 20, 51,
62 66, 65, 59, 24, 75, 76, 84, 56,
63 72, 74, 64, 55, 54, 47, 41, 37,
64 44, 61, 70, 43, 23, 53, 49, 22,
65 33, 58, 40, 46, 45, 57, 60, 26,
66 30, 63, 21, 12, 32, 50, 38, 39,
67 34, 11, 48, 67, 62, 35, 15, 29,
68 71, 18, 9, 17, 25, 13, 10, 52,
69 36, 95, 78, 86, 87, 98, 82, 80,
70 88, 94, 19, 68, 89, 83, 93, 96,
71 81, 7, 91, 92, 97, 85, 69, 73,
72 31, 79, 8, 5, 4, 6, 3, 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 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};
90
91bm_pat *
92bm_comp(pb, len, freq)
93 u_char const *pb;
94 size_t len;
95 u_char const *freq;
96{
97 register u_char const *pe, *p;
98 register size_t *d, r;
99 register int j;
100 int sv_errno;
101 bm_pat *pat;
102
103 if (len == 0) {
104 errno = EINVAL;
105 return (NULL);
106 }
107 if ((pat = malloc(sizeof(*pat))) == NULL)
108 return (NULL);
109 pat->pat = NULL;
110 pat->delta = NULL;
111
112 pat->patlen = len; /* copy pattern */
113 if ((pat->pat = malloc(pat->patlen)) == NULL)
114 goto mem;
115 memcpy(pat->pat, pb, pat->patlen);
116 /* get skip delta */
117 if ((pat->delta = malloc(256 * sizeof(*d))) == NULL)
118 goto mem;
119 for (j = 0, d = pat->delta; j < 256; j++)
120 d[j] = pat->patlen;
121 for (pe = pb + pat->patlen - 1; pb <= pe; pb++)
122 d[*pb] = pe - pb;
123
124 if (freq == NULL) /* default freq table */
125 freq = freq_def;
126 r = 0; /* get guard */
127 for (pb = pat->pat, pe = pb + pat->patlen - 1; pb < pe; pb++)
128 if (freq[*pb] < freq[pat->pat[r]])
129 r = pb - pat->pat;
130 pat->rarec = pat->pat[r];
131 pat->rareoff = r - (pat->patlen - 1);
132
133 /* get md2 shift */
134 for (pe = pat->pat + pat->patlen - 1, p = pe - 1; p >= pat->pat; p--)
135 if (*p == *pe)
136 break;
137
138 /* *p is first leftward reoccurrence of *pe */
139 pat->md2 = pe - p;
140 return (pat);
141
142mem: sv_errno = errno;
143 bm_free(pat);
144 errno = sv_errno;
145 return (NULL);
146}
147
148void
149bm_free(pat)
150 bm_pat *pat;
151{
152 if (pat->pat != NULL)
153 free(pat->pat);
154 if (pat->delta != NULL)
155 free(pat->delta);
156 free(pat);
157}
158
159u_char *
160bm_exec(pat, base, n)
161 bm_pat *pat;
162 u_char *base;
163 size_t n;
164{
165 register u_char *e, *ep, *p, *q, *s;
166 register size_t *d0, k, md2, n1, ro;
167 register int rc;
168
169 if (n == 0)
170 return (NULL);
171
172 d0 = pat->delta;
173 n1 = pat->patlen - 1;
174 md2 = pat->md2;
175 ro = pat->rareoff;
176 rc = pat->rarec;
177 ep = pat->pat + pat->patlen - 1;
178 s = base + (pat->patlen - 1);
179
180 /* fast loop up to n - 3 * patlen */
181 e = base + n - 3 * pat->patlen;
182 while (s < e) {
183 k = d0[*s]; /* ufast skip loop */
184 while (k) {
185 k = d0[*(s += k)];
186 k = d0[*(s += k)];
187 }
188 if (s >= e)
189 break;
190 if (s[ro] != rc) /* guard test */
191 goto mismatch1;
192 /* fwd match */
193 for (p = pat->pat, q = s - n1; p < ep;)
194 if (*q++ != *p++)
195 goto mismatch1;
196 return (s - n1);
197
198mismatch1: s += md2; /* md2 shift */
199 }
200
201 /* slow loop up to end */
202 e = base + n;
203 while (s < e) {
204 s += d0[*s]; /* step */
205 if (s >= e)
206 break;
207 if (s[ro] != rc) /* guard test */
208 goto mismatch2;
209 /* fwd match */
210 for (p = pat->pat, q = s - n1; p <= ep;)
211 if (*q++ != *p++)
212 goto mismatch2;
213 return (s - n1);
214
215mismatch2: s += md2; /* md2 shift */
216 }
217
218 return (NULL);
219}
generated by cgit v1.2.3-55-g6feb (git 2.39.1) at 2025-04-27 08:56:16 +0000