summaryrefslogtreecommitdiffstats
path: root/framework/src/suricata/src/util-spm-bm.c
blob: 7c5b8d2d4d656e2198df2394d80d5dbf9b92ac1d (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
/* Copyright (C) 2007-2014 Open Information Security Foundation
 *
 * You can copy, redistribute or modify this Program under the terms of
 * the GNU General Public License version 2 as published by the Free
 * Software Foundation.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * version 2 along with this program; if not, write to the Free Software
 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
 * 02110-1301, USA.
 */

/**
 * \file
 *
 * \author Pablo Rincon Crespo <pablo.rincon.crespo@gmail.com>
 *
 * Boyer Moore simple pattern matcher implementation
 *
 * Boyer Moore algorithm has a really good performance. It need two arrays
 * of context for each pattern that hold applicable shifts on the text
 * to seach in, based on characters not available in the pattern
 * and combinations of characters that start a sufix of the pattern.
 * If possible, we should store the context of patterns that we are going
 * to search for multiple times, so we don't spend time on rebuilding them.
 */

#include "suricata-common.h"
#include "suricata.h"

#include "util-spm-bm.h"
#include "util-debug.h"
#include "util-error.h"
#include "util-memcpy.h"

static int PreBmGs(const uint8_t *x, uint16_t m, uint16_t *bmGs);
static void PreBmBc(const uint8_t *x, uint16_t m, uint16_t *bmBc);
static void PreBmBcNocase(const uint8_t *x, uint16_t m, uint16_t *bmBc);
static void BoyerMooreSuffixesNocase(const uint8_t *x, uint16_t m, 
                                     uint16_t *suff);
static void PreBmGsNocase(const uint8_t *x, uint16_t m, uint16_t *bmGs);

/**
 * \brief Given a BmCtx structure, recreate the pre/suffixes for
 *        nocase
 *
 * \retval BmCtx pointer to the already created BmCtx (with BoyerMooreCtxInit())
 * \param str pointer to the pattern string
 * \param size length of the string
 */
void BoyerMooreCtxToNocase(BmCtx *bm_ctx, uint8_t *needle, uint16_t needle_len)
{
    /* Store the content as lower case to make searching faster */
    memcpy_tolower(needle, needle, needle_len);

    /* Prepare bad chars with nocase chars */
    PreBmBcNocase(needle, needle_len, bm_ctx->bmBc);

    /* Prepare good Suffixes with nocase chars */
    PreBmGsNocase(needle, needle_len, bm_ctx->bmGs);
}

/**
 * \brief Setup a Booyer Moore context.
 *
 * \param str pointer to the pattern string
 * \param size length of the string
 * \retval BmCtx pointer to the newly created Context for the pattern
 * \initonly BoyerMoore contexts should be created at init
 */
BmCtx *BoyerMooreCtxInit(uint8_t *needle, uint16_t needle_len)
{
    BmCtx *new = SCMalloc(sizeof(BmCtx));
    if (unlikely(new == NULL)) {
        SCLogError(SC_ERR_FATAL, "Fatal error encountered in BoyerMooreCtxInit. Exiting...");
        exit(EXIT_FAILURE);
    }

    /* Prepare bad chars */
    PreBmBc(needle, needle_len, new->bmBc);

    new->bmGs = SCMalloc(sizeof(uint16_t) * (needle_len + 1));
    if (new->bmGs == NULL) {
        exit(EXIT_FAILURE);
    }

    /* Prepare good Suffixes */
    if (PreBmGs(needle, needle_len, new->bmGs) == -1) {
        SCLogError(SC_ERR_FATAL, "Fatal error encountered in BooyerMooreCtxInit. Exiting...");
        exit(EXIT_FAILURE);
    }


    return new;
}

/**
 * \brief Setup a Booyer Moore context for nocase search
 *
 * \param str pointer to the pattern string
 * \param size length of the string
 * \retval BmCtx pointer to the newly created Context for the pattern
 * \initonly BoyerMoore contexts should be created at init
 */
BmCtx *BoyerMooreNocaseCtxInit(uint8_t *needle, uint16_t needle_len)
{
    BmCtx *bm_ctx = BoyerMooreCtxInit(needle, needle_len);

    BoyerMooreCtxToNocase(bm_ctx, needle, needle_len);

    return bm_ctx;
}

/**
 * \brief Free the memory allocated to Booyer Moore context.
 *
 * \param bmCtx pointer to the Context for the pattern
 */
void BoyerMooreCtxDeInit(BmCtx *bmctx)
{
    SCEnter();
    if (bmctx == NULL)
        SCReturn;

    if (bmctx->bmGs != NULL)
        SCFree(bmctx->bmGs);

    SCFree(bmctx);

    SCReturn;
}
/**
 * \brief Array setup function for bad characters that split the pattern
 *        Remember that the result array should be the length of ALPHABET_SIZE
 *
 * \param str pointer to the pattern string
 * \param size length of the string
 * \param result pointer to an empty array that will hold the badchars
 */
static void PreBmBc(const uint8_t *x, uint16_t m, uint16_t *bmBc)
{
    int32_t i;

    for (i = 0; i < 256; ++i) {
        bmBc[i] = m;
    }
    for (i = 0; i < m - 1; ++i) {
        bmBc[(unsigned char)x[i]] = m - i - 1;
    }
}

/**
 * \brief Array setup function for building prefixes (shift for valid prefixes) for boyermoore context
 *
 * \param x pointer to the pattern string
 * \param m length of the string
 * \param suff pointer to an empty array that will hold the prefixes (shifts)
 */
static void BoyerMooreSuffixes(const uint8_t *x, uint16_t m, uint16_t *suff)
{
    int32_t f = 0, g, i;
    suff[m - 1] = m;
    g = m - 1;
    for (i = m - 2; i >= 0; --i) {
        if (i > g && suff[i + m - 1 - f] < i - g)
            suff[i] = suff[i + m - 1 - f];
        else {
            if (i < g)
                g = i;
            f = i;
            while (g >= 0 && x[g] == x[g + m - 1 - f])
                --g;
            suff[i] = f - g;
        }
    }
}

/**
 * \brief Array setup function for building prefixes (shift for valid prefixes) for boyermoore context
 *
 * \param x pointer to the pattern string
 * \param m length of the string
 * \param bmGs pointer to an empty array that will hold the prefixes (shifts)
 * \retval 0 ok, -1 failed
 */
static int PreBmGs(const uint8_t *x, uint16_t m, uint16_t *bmGs)
{
    int32_t i, j;
    uint16_t suff[m + 1];

    BoyerMooreSuffixes(x, m, suff);

    for (i = 0; i < m; ++i)
        bmGs[i] = m;

    j = 0;

    for (i = m - 1; i >= -1; --i)
        if (i == -1 || suff[i] == i + 1)
            for (; j < m - 1 - i; ++j)
                if (bmGs[j] == m)
                    bmGs[j] = m - 1 - i;

    for (i = 0; i <= m - 2; ++i)
        bmGs[m - 1 - suff[i]] = m - 1 - i;
    return 0;
}

/**
 * \brief Array setup function for bad characters that split the pattern
 *        Remember that the result array should be the length of ALPHABET_SIZE
 *
 * \param str pointer to the pattern string
 * \param size length of the string
 * \param result pointer to an empty array that will hold the badchars
 */
static void PreBmBcNocase(const uint8_t *x, uint16_t m, uint16_t *bmBc)
{
    int32_t i;

    for (i = 0; i < 256; ++i) {
        bmBc[i] = m;
    }
    for (i = 0; i < m - 1; ++i) {
        bmBc[u8_tolower((unsigned char)x[i])] = m - 1 - i;
    }
}

static void BoyerMooreSuffixesNocase(const uint8_t *x, uint16_t m, 
                                     uint16_t *suff)
{
    int32_t f = 0, g, i;

    suff[m - 1] = m;
    g = m - 1;
    for (i = m - 2; i >= 0; --i) {
        if (i > g && suff[i + m - 1 - f] < i - g) {
            suff[i] = suff[i + m - 1 - f];
        } else {
            if (i < g) {
                g = i;
            }
            f = i;
            while (g >= 0 && u8_tolower(x[g]) == u8_tolower(x[g + m - 1 - f])) {
                --g;
            }
            suff[i] = f - g;
        }
    }
}

/**
 * \brief Array setup function for building prefixes (shift for valid prefixes)
 *        for boyermoore context case less
 *
 * \param x pointer to the pattern string
 * \param m length of the string
 * \param bmGs pointer to an empty array that will hold the prefixes (shifts)
 */
static void PreBmGsNocase(const uint8_t *x, uint16_t m, uint16_t *bmGs)
{
    int32_t i, j;
    uint16_t suff[m + 1];

    BoyerMooreSuffixesNocase(x, m, suff);

    for (i = 0; i < m; ++i) {
        bmGs[i] = m;
    }
    j = 0;
    for (i = m - 1; i >= 0; --i) {
        if (i == -1 || suff[i] == i + 1) {
            for (; j < m - 1 - i; ++j) {
                if (bmGs[j] == m) {
                    bmGs[j] = m - 1 - i;
                }
            }
        }
    }
    for (i = 0; i <= m - 2; ++i) {
        bmGs[m - 1 - suff[i]] = m - 1 - i;
    }
}

/**
 * \brief Boyer Moore search algorithm
 *        Is better as the pattern length increases and for big buffers to search in.
 *        The algorithm needs a context of two arrays already prepared
 *        by prep_bad_chars() and prep_good_suffix()
 *
 * \param y pointer to the buffer to search in
 * \param n length limit of the buffer
 * \param x pointer to the pattern we ar searching for
 * \param m length limit of the needle
 * \param bmBc pointer to an array of BoyerMooreSuffixes prepared by prep_good_suffix()
 * \param bmGs pointer to an array of bachars prepared by prep_bad_chars()
 *
 * \retval ptr to start of the match; NULL if no match
 */
uint8_t *BoyerMoore(uint8_t *x, uint16_t m, uint8_t *y, int32_t n, BmCtx *bm_ctx)
{
    uint16_t *bmGs = bm_ctx->bmGs;
    uint16_t *bmBc = bm_ctx->bmBc;

   int i, j, m1, m2;
#if 0
    printf("\nBad:\n");
    for (i=0;i<ALPHABET_SIZE;i++)
        printf("%c,%d ", i, bmBc[i]);

    printf("\ngood:\n");
    for (i=0;i<m;i++)
        printf("%c, %d ", x[i],bmBc[i]);
    printf("\n");
#endif
   j = 0;

   while (j <= n - m ) {
      for (i = m - 1; i >= 0 && x[i] == y[i + j]; --i);

      if (i < 0) {
         return y + j;
         //j += bmGs[0];
      } else {
 //        printf("%c", y[i+j]);
         j += (m1 = bmGs[i]) > (m2 = bmBc[y[i + j]] - m + 1 + i)? m1: m2;
//            printf("%d, %d\n", m1, m2);
      }
   }
   return NULL;
}


/**
 * \brief Boyer Moore search algorithm
 *        Is better as the pattern length increases and for big buffers to search in.
 *        The algorithm needs a context of two arrays already prepared
 *        by prep_bad_chars() and prep_good_suffix()
 *
 * \param y pointer to the buffer to search in
 * \param n length limit of the buffer
 * \param x pointer to the pattern we ar searching for
 * \param m length limit of the needle
 * \param bmBc pointer to an array of BoyerMooreSuffixes prepared by prep_good_suffix()
 * \param bmGs pointer to an array of bachars prepared by prep_bad_chars()
 *
 * \retval ptr to start of the match; NULL if no match
 */
uint8_t *BoyerMooreNocase(uint8_t *x, uint16_t m, uint8_t *y, int32_t n, BmCtx *bm_ctx)
{
    uint16_t *bmGs = bm_ctx->bmGs;
    uint16_t *bmBc = bm_ctx->bmBc;
    int i, j, m1, m2;
#if 0
    printf("\nBad:\n");
    for (i=0;i<ALPHABET_SIZE;i++)
        printf("%c,%d ", i, bmBc[i]);

    printf("\ngood:\n");
    for (i=0;i<m;i++)
        printf("%c, %d ", x[i],bmBc[i]);
    printf("\n");
#endif
    j = 0;
    while (j <= n - m ) {
        /* x is stored in lowercase. */
        for (i = m - 1; i >= 0 && x[i] == u8_tolower(y[i + j]); --i);

        if (i < 0) {
            return y + j;
        } else {
            j += (m1=bmGs[i]) > (m2=bmBc[u8_tolower(y[i + j])] - m + 1 + i)?m1:m2;
        }
   }
   return NULL;
}