1 /*	$OpenBSD: memmem.c,v 1.5 2020/04/16 12:39:28 claudio Exp $ */
2 
3 /*
4  * Copyright (c) 2005-2020 Rich Felker, et al.
5  *
6  * Permission is hereby granted, free of charge, to any person obtaining
7  * a copy of this software and associated documentation files (the
8  * "Software"), to deal in the Software without restriction, including
9  * without limitation the rights to use, copy, modify, merge, publish,
10  * distribute, sublicense, and/or sell copies of the Software, and to
11  * permit persons to whom the Software is furnished to do so, subject to
12  * the following conditions:
13  *
14  * The above copyright notice and this permission notice shall be
15  * included in all copies or substantial portions of the Software.
16  *
17  * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
18  * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
19  * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
20  * IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY
21  * CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
22  * TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
23  * SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
24  */
25 
26 #include <string.h>
27 #include <stdint.h>
28 
29 static char *
30 twobyte_memmem(const unsigned char *h, size_t k, const unsigned char *n)
31 {
32 	uint16_t nw = n[0]<<8 | n[1], hw = h[0]<<8 | h[1];
33 	for (h+=2, k-=2; k; k--, hw = hw<<8 | *h++)
34 		if (hw == nw) return (char *)h-2;
35 	return hw == nw ? (char *)h-2 : 0;
36 }
37 
38 static char *
39 threebyte_memmem(const unsigned char *h, size_t k, const unsigned char *n)
40 {
41 	uint32_t nw = n[0]<<24 | n[1]<<16 | n[2]<<8;
42 	uint32_t hw = h[0]<<24 | h[1]<<16 | h[2]<<8;
43 	for (h+=3, k-=3; k; k--, hw = (hw|*h++)<<8)
44 		if (hw == nw) return (char *)h-3;
45 	return hw == nw ? (char *)h-3 : 0;
46 }
47 
48 static char *
49 fourbyte_memmem(const unsigned char *h, size_t k, const unsigned char *n)
50 {
51 	uint32_t nw = n[0]<<24 | n[1]<<16 | n[2]<<8 | n[3];
52 	uint32_t hw = h[0]<<24 | h[1]<<16 | h[2]<<8 | h[3];
53 	for (h+=4, k-=4; k; k--, hw = hw<<8 | *h++)
54 		if (hw == nw) return (char *)h-4;
55 	return hw == nw ? (char *)h-4 : 0;
56 }
57 
58 #define MAX(a,b) ((a)>(b)?(a):(b))
59 #define MIN(a,b) ((a)<(b)?(a):(b))
60 
61 #define BITOP(a,b,op) \
62  ((a)[(size_t)(b)/(8*sizeof *(a))] op (size_t)1<<((size_t)(b)%(8*sizeof *(a))))
63 
64 /*
65  * Maxime Crochemore and Dominique Perrin, Two-way string-matching,
66  * Journal of the ACM, 38(3):651-675, July 1991.
67  */
68 static char *
69 twoway_memmem(const unsigned char *h, const unsigned char *z,
70     const unsigned char *n, size_t l)
71 {
72 	size_t i, ip, jp, k, p, ms, p0, mem, mem0;
73 	size_t byteset[32 / sizeof(size_t)] = { 0 };
74 	size_t shift[256];
75 
76 	/* Computing length of needle and fill shift table */
77 	for (i=0; i<l; i++)
78 		BITOP(byteset, n[i], |=), shift[n[i]] = i+1;
79 
80 	/* Compute maximal suffix */
81 	ip = -1; jp = 0; k = p = 1;
82 	while (jp+k<l) {
83 		if (n[ip+k] == n[jp+k]) {
84 			if (k == p) {
85 				jp += p;
86 				k = 1;
87 			} else k++;
88 		} else if (n[ip+k] > n[jp+k]) {
89 			jp += k;
90 			k = 1;
91 			p = jp - ip;
92 		} else {
93 			ip = jp++;
94 			k = p = 1;
95 		}
96 	}
97 	ms = ip;
98 	p0 = p;
99 
100 	/* And with the opposite comparison */
101 	ip = -1; jp = 0; k = p = 1;
102 	while (jp+k<l) {
103 		if (n[ip+k] == n[jp+k]) {
104 			if (k == p) {
105 				jp += p;
106 				k = 1;
107 			} else k++;
108 		} else if (n[ip+k] < n[jp+k]) {
109 			jp += k;
110 			k = 1;
111 			p = jp - ip;
112 		} else {
113 			ip = jp++;
114 			k = p = 1;
115 		}
116 	}
117 	if (ip+1 > ms+1) ms = ip;
118 	else p = p0;
119 
120 	/* Periodic needle? */
121 	if (memcmp(n, n+p, ms+1)) {
122 		mem0 = 0;
123 		p = MAX(ms, l-ms-1) + 1;
124 	} else mem0 = l-p;
125 	mem = 0;
126 
127 	/* Search loop */
128 	for (;;) {
129 		/* If remainder of haystack is shorter than needle, done */
130 		if (z-h < l) return 0;
131 
132 		/* Check last byte first; advance by shift on mismatch */
133 		if (BITOP(byteset, h[l-1], &)) {
134 			k = l-shift[h[l-1]];
135 			if (k) {
136 				if (k < mem) k = mem;
137 				h += k;
138 				mem = 0;
139 				continue;
140 			}
141 		} else {
142 			h += l;
143 			mem = 0;
144 			continue;
145 		}
146 
147 		/* Compare right half */
148 		for (k=MAX(ms+1,mem); k<l && n[k] == h[k]; k++);
149 		if (k < l) {
150 			h += k-ms;
151 			mem = 0;
152 			continue;
153 		}
154 		/* Compare left half */
155 		for (k=ms+1; k>mem && n[k-1] == h[k-1]; k--);
156 		if (k <= mem) return (char *)h;
157 		h += p;
158 		mem = mem0;
159 	}
160 }
161 
162 void *
163 memmem(const void *h0, size_t k, const void *n0, size_t l)
164 {
165 	const unsigned char *h = h0, *n = n0;
166 
167 	/* Return immediately on empty needle */
168 	if (!l) return (void *)h;
169 
170 	/* Return immediately when needle is longer than haystack */
171 	if (k<l) return 0;
172 
173 	/* Use faster algorithms for short needles */
174 	h = memchr(h0, *n, k);
175 	if (!h || l==1) return (void *)h;
176 	k -= h - (const unsigned char *)h0;
177 	if (k<l) return 0;
178 	if (l==2) return twobyte_memmem(h, k, n);
179 	if (l==3) return threebyte_memmem(h, k, n);
180 	if (l==4) return fourbyte_memmem(h, k, n);
181 
182 	return twoway_memmem(h, h+k, n, l);
183 }