adulau/aha
1
0
Fork 0
mirror of https://github.com/adulau/aha.git synced 2024-12-27 19:26:25 +00:00
Code Issues Projects Releases Packages Wiki Activity

textsearch: ts_bm: support case insensitive searching in Boyer-Moore algorithm

Browse source 
Add support for case insensitive search to Boyer-Moore algorithm.

Signed-off-by: Joonwoo Park <joonwpark81@gmail.com>
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
This commit is contained in:
Joonwoo Park 2008-07-08 02:37:54 -07:00 committed by David S. Miller
parent b9c7967831
commit 3b76d08190
1 changed files with 20 additions and 6 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

24
lib/ts_bm.c
View file

@ -39,6 +39,7 @@
#include <linux/module.h> #include <linux/module.h>
#include <linux/types.h> #include <linux/types.h>
#include <linux/string.h> #include <linux/string.h>
#include <linux/ctype.h>
#include <linux/textsearch.h> #include <linux/textsearch.h>
/* Alphabet size, use ASCII */ /* Alphabet size, use ASCII */
@ -64,6 +65,7 @@ static unsigned int bm_find(struct ts_config *conf, struct ts_state *state)
unsigned int i, text_len, consumed = state->offset; unsigned int i, text_len, consumed = state->offset;
const u8 *text; const u8 *text;
int shift = bm->patlen - 1, bs; int shift = bm->patlen - 1, bs;
const u8 icase = conf->flags & TS_IGNORECASE;
for (;;) { for (;;) {
text_len = conf->get_next_block(consumed, &text, conf, state); text_len = conf->get_next_block(consumed, &text, conf, state);
@ -75,7 +77,9 @@ static unsigned int bm_find(struct ts_config *conf, struct ts_state *state)
DEBUGP("Searching in position %d (%c)\n", DEBUGP("Searching in position %d (%c)\n",
shift, text[shift]); shift, text[shift]);
for (i = 0; i < bm->patlen; i++) for (i = 0; i < bm->patlen; i++)
if (text[shift-i] != bm->pattern[bm->patlen-1-i]) if ((icase ? toupper(text[shift-i])
: text[shift-i])
!= bm->pattern[bm->patlen-1-i])
goto next; goto next;
/* London calling... */ /* London calling... */
@ -111,14 +115,18 @@ static int subpattern(u8 *pattern, int i, int j, int g)
return ret; return ret;
} }
static void compute_prefix_tbl(struct ts_bm *bm) static void compute_prefix_tbl(struct ts_bm *bm, int flags)
{ {
int i, j, g; int i, j, g;
for (i = 0; i < ASIZE; i++) for (i = 0; i < ASIZE; i++)
bm->bad_shift[i] = bm->patlen; bm->bad_shift[i] = bm->patlen;
for (i = 0; i < bm->patlen - 1; i++) for (i = 0; i < bm->patlen - 1; i++) {
bm->bad_shift[bm->pattern[i]] = bm->patlen - 1 - i; bm->bad_shift[bm->pattern[i]] = bm->patlen - 1 - i;
if (flags & TS_IGNORECASE)
bm->bad_shift[tolower(bm->pattern[i])]
= bm->patlen - 1 - i;
}
/* Compute the good shift array, used to match reocurrences /* Compute the good shift array, used to match reocurrences
* of a subpattern */ * of a subpattern */
@ -135,10 +143,11 @@ static void compute_prefix_tbl(struct ts_bm *bm)
} }
static struct ts_config *bm_init(const void *pattern, unsigned int len, static struct ts_config *bm_init(const void *pattern, unsigned int len,
gfp_t gfp_mask) gfp_t gfp_mask, int flags)
{ {
struct ts_config *conf; struct ts_config *conf;
struct ts_bm *bm; struct ts_bm *bm;
int i;
unsigned int prefix_tbl_len = len * sizeof(unsigned int); unsigned int prefix_tbl_len = len * sizeof(unsigned int);
size_t priv_size = sizeof(*bm) + len + prefix_tbl_len; size_t priv_size = sizeof(*bm) + len + prefix_tbl_len;
@ -146,11 +155,16 @@ static struct ts_config *bm_init(const void *pattern, unsigned int len,
if (IS_ERR(conf)) if (IS_ERR(conf))
return conf; return conf;
conf->flags = flags;
bm = ts_config_priv(conf); bm = ts_config_priv(conf);
bm->patlen = len; bm->patlen = len;
bm->pattern = (u8 *) bm->good_shift + prefix_tbl_len; bm->pattern = (u8 *) bm->good_shift + prefix_tbl_len;
if (flags & TS_IGNORECASE)
for (i = 0; i < len; i++)
bm->pattern[i] = toupper(((u8 *)pattern)[i]);
else
memcpy(bm->pattern, pattern, len); memcpy(bm->pattern, pattern, len);
compute_prefix_tbl(bm); compute_prefix_tbl(bm, flags);
return conf; return conf;
} }