Techwizz/kernel-fxtec-pro1x
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

[TEXTSEARCH]: Fix broken good shift array calculation in Boyer-Moore

Browse source 
The current logic does not calculate correctly the good shift array:
Let x be the pattern that is being searched. Let y be the block of data. 
The good shift array aligns the segment:

x[i+1 ... m-1] = y[i+j+1 ... j+m-1]

with its rightmost occurrence in x that fulfils x[i] neq y[i+j].

In previous version, the good shift array for the pattern ANPANMAN is:
[1, 8, 3, 8, 8, 8, 8, 8]
and should be:
[1, 8, 3, 6, 6, 6, 6, 6]

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
This commit is contained in:
Pablo Neira Ayuso 2006-02-02 17:15:41 -08:00 committed by David S. Miller
parent f00c401b9b
commit 3f330317ab
1 changed files with 25 additions and 15 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

40
lib/ts_bm.c
View file

@ -94,10 +94,28 @@ next: bs = bm->bad_shift[text[shift-i]];
return UINT_MAX; return UINT_MAX;
} }
static int subpattern(u8 *pattern, int i, int j, int g)
{
int x = i+g-1, y = j+g-1, ret = 0;
while(pattern[x--] == pattern[y--]) {
if (y < 0) {
ret = 1;
break;
}
if (--g == 0) {
ret = pattern[i-1] != pattern[j-1];
break;
}
}
return ret;
}
static void compute_prefix_tbl(struct ts_bm *bm, const u8 *pattern, static void compute_prefix_tbl(struct ts_bm *bm, const u8 *pattern,
unsigned int len) unsigned int len)
{ {
int i, j, ended, l[ASIZE]; int i, j, g;
for (i = 0; i < ASIZE; i++) for (i = 0; i < ASIZE; i++)
bm->bad_shift[i] = len; bm->bad_shift[i] = len;
@ -106,23 +124,15 @@ static void compute_prefix_tbl(struct ts_bm *bm, const u8 *pattern,
/* Compute the good shift array, used to match reocurrences /* Compute the good shift array, used to match reocurrences
* of a subpattern */ * of a subpattern */
for (i = 1; i < bm->patlen; i++) {
for (j = 0; j < bm->patlen && bm->pattern[bm->patlen - 1 - j]
== bm->pattern[bm->patlen - 1 - i - j]; j++);
l[i] = j;
}
bm->good_shift[0] = 1; bm->good_shift[0] = 1;
for (i = 1; i < bm->patlen; i++) for (i = 1; i < bm->patlen; i++)
bm->good_shift[i] = bm->patlen; bm->good_shift[i] = bm->patlen;
for (i = bm->patlen - 1; i > 0; i--) for (i = bm->patlen-1, g = 1; i > 0; g++, i--) {
bm->good_shift[l[i]] = i; for (j = i-1; j >= 1-g ; j--)
ended = 0; if (subpattern(bm->pattern, i, j, g)) {
for (i = 0; i < bm->patlen; i++) { bm->good_shift[g] = bm->patlen-j-g;
if (l[i] == bm->patlen - 1 - i) break;
ended = i; }
if (ended)
bm->good_shift[i] = ended;
} }
} }