1 /*
2 * lib/ts_kmp.c Knuth-Morris-Pratt text search implementation
3 *
4 * This program is free software; you can redistribute it and/or
5 * modify it under the terms of the GNU General Public License
6 * as published by the Free Software Foundation; either version
7 * 2 of the License, or (at your option) any later version.
8 *
9 * Authors: Thomas Graf <tgraf@suug.ch>
10 *
11 * ==========================================================================
12 *
13 * Implements a linear-time string-matching algorithm due to Knuth,
14 * Morris, and Pratt [1]. Their algorithm avoids the explicit
15 * computation of the transition function DELTA altogether. Its
16 * matching time is O(n), for n being length(text), using just an
17 * auxiliary function PI[1..m], for m being length(pattern),
18 * precomputed from the pattern in time O(m). The array PI allows
19 * the transition function DELTA to be computed efficiently
20 * "on the fly" as needed. Roughly speaking, for any state
21 * "q" = 0,1,...,m and any character "a" in SIGMA, the value
22 * PI["q"] contains the information that is independent of "a" and
23 * is needed to compute DELTA("q", "a") [2]. Since the array PI
24 * has only m entries, whereas DELTA has O(m|SIGMA|) entries, we
25 * save a factor of |SIGMA| in the preprocessing time by computing
26 * PI rather than DELTA.
27 *
28 * [1] Cormen, Leiserson, Rivest, Stein
29 * Introdcution to Algorithms, 2nd Edition, MIT Press
30 * [2] See finite automation theory
31 */
32
33 #include <linux/module.h>
34 #include <linux/types.h>
35 #include <linux/string.h>
36 #include <linux/ctype.h>
37 #include <linux/textsearch.h>
38
39 struct ts_kmp
40 {
41 u8 * pattern;
42 unsigned int pattern_len;
43 unsigned int prefix_tbl[0];
44 };
45
kmp_find(struct ts_config * conf,struct ts_state * state)46 static unsigned int kmp_find(struct ts_config *conf, struct ts_state *state)
47 {
48 struct ts_kmp *kmp = ts_config_priv(conf);
49 unsigned int i, q = 0, text_len, consumed = state->offset;
50 const u8 *text;
51 const int icase = conf->flags & TS_IGNORECASE;
52
53 for (;;) {
54 text_len = conf->get_next_block(consumed, &text, conf, state);
55
56 if (unlikely(text_len == 0))
57 break;
58
59 for (i = 0; i < text_len; i++) {
60 while (q > 0 && kmp->pattern[q]
61 != (icase ? toupper(text[i]) : text[i]))
62 q = kmp->prefix_tbl[q - 1];
63 if (kmp->pattern[q]
64 == (icase ? toupper(text[i]) : text[i]))
65 q++;
66 if (unlikely(q == kmp->pattern_len)) {
67 state->offset = consumed + i + 1;
68 return state->offset - kmp->pattern_len;
69 }
70 }
71
72 consumed += text_len;
73 }
74
75 return UINT_MAX;
76 }
77
compute_prefix_tbl(const u8 * pattern,unsigned int len,unsigned int * prefix_tbl,int flags)78 static inline void compute_prefix_tbl(const u8 *pattern, unsigned int len,
79 unsigned int *prefix_tbl, int flags)
80 {
81 unsigned int k, q;
82 const u8 icase = flags & TS_IGNORECASE;
83
84 for (k = 0, q = 1; q < len; q++) {
85 while (k > 0 && (icase ? toupper(pattern[k]) : pattern[k])
86 != (icase ? toupper(pattern[q]) : pattern[q]))
87 k = prefix_tbl[k-1];
88 if ((icase ? toupper(pattern[k]) : pattern[k])
89 == (icase ? toupper(pattern[q]) : pattern[q]))
90 k++;
91 prefix_tbl[q] = k;
92 }
93 }
94
kmp_init(const void * pattern,unsigned int len,gfp_t gfp_mask,int flags)95 static struct ts_config *kmp_init(const void *pattern, unsigned int len,
96 gfp_t gfp_mask, int flags)
97 {
98 struct ts_config *conf;
99 struct ts_kmp *kmp;
100 int i;
101 unsigned int prefix_tbl_len = len * sizeof(unsigned int);
102 size_t priv_size = sizeof(*kmp) + len + prefix_tbl_len;
103
104 conf = alloc_ts_config(priv_size, gfp_mask);
105 if (IS_ERR(conf))
106 return conf;
107
108 conf->flags = flags;
109 kmp = ts_config_priv(conf);
110 kmp->pattern_len = len;
111 compute_prefix_tbl(pattern, len, kmp->prefix_tbl, flags);
112 kmp->pattern = (u8 *) kmp->prefix_tbl + prefix_tbl_len;
113 if (flags & TS_IGNORECASE)
114 for (i = 0; i < len; i++)
115 kmp->pattern[i] = toupper(((u8 *)pattern)[i]);
116 else
117 memcpy(kmp->pattern, pattern, len);
118
119 return conf;
120 }
121
kmp_get_pattern(struct ts_config * conf)122 static void *kmp_get_pattern(struct ts_config *conf)
123 {
124 struct ts_kmp *kmp = ts_config_priv(conf);
125 return kmp->pattern;
126 }
127
kmp_get_pattern_len(struct ts_config * conf)128 static unsigned int kmp_get_pattern_len(struct ts_config *conf)
129 {
130 struct ts_kmp *kmp = ts_config_priv(conf);
131 return kmp->pattern_len;
132 }
133
134 static struct ts_ops kmp_ops = {
135 .name = "kmp",
136 .find = kmp_find,
137 .init = kmp_init,
138 .get_pattern = kmp_get_pattern,
139 .get_pattern_len = kmp_get_pattern_len,
140 .owner = THIS_MODULE,
141 .list = LIST_HEAD_INIT(kmp_ops.list)
142 };
143
init_kmp(void)144 static int __init init_kmp(void)
145 {
146 return textsearch_register(&kmp_ops);
147 }
148
exit_kmp(void)149 static void __exit exit_kmp(void)
150 {
151 textsearch_unregister(&kmp_ops);
152 }
153
154 MODULE_LICENSE("GPL");
155
156 module_init(init_kmp);
157 module_exit(exit_kmp);
158