324300bc7c
regression=# select to_tsquery( '\'fotballklubber\'');
to_tsquery
------------------------------------------------
'fotball' & 'klubb' | 'fot' & 'ball' & 'klubb'
(1 row)
So, changed interface to dictionaries, lexize method of dictionary shoud return
pointer to aray of TSLexeme structs instead of char**. Last element should
have TSLexeme->lexeme == NULL.
typedef struct {
/* number of variant of split word , for example
Word 'fotballklubber' (norwegian) has two varian to split:
( fotball, klubb ) and ( fot, ball, klubb ). So, dictionary
should return:
nvariant lexeme
1 fotball
1 klubb
2 fot
2 ball
2 klubb
*/
uint16 nvariant;
/* currently unused */
uint16 flags;
/* C-string */
char *lexeme;
} TSLexeme;
70 lines
1.2 KiB
C
70 lines
1.2 KiB
C
/*
|
|
* example of dictionary
|
|
* Teodor Sigaev <teodor@sigaev.ru>
|
|
*/
|
|
#include <errno.h>
|
|
#include <stdlib.h>
|
|
#include <string.h>
|
|
|
|
#include "postgres.h"
|
|
|
|
#include "dict.h"
|
|
#include "common.h"
|
|
|
|
typedef struct
|
|
{
|
|
StopList stoplist;
|
|
} DictExample;
|
|
|
|
|
|
PG_FUNCTION_INFO_V1(dex_init);
|
|
Datum dex_init(PG_FUNCTION_ARGS);
|
|
|
|
PG_FUNCTION_INFO_V1(dex_lexize);
|
|
Datum dex_lexize(PG_FUNCTION_ARGS);
|
|
|
|
Datum
|
|
dex_init(PG_FUNCTION_ARGS)
|
|
{
|
|
DictExample *d = (DictExample *) malloc(sizeof(DictExample));
|
|
|
|
if (!d)
|
|
ereport(ERROR,
|
|
(errcode(ERRCODE_OUT_OF_MEMORY),
|
|
errmsg("out of memory")));
|
|
memset(d, 0, sizeof(DictExample));
|
|
|
|
d->stoplist.wordop = lowerstr;
|
|
|
|
if (!PG_ARGISNULL(0) && PG_GETARG_POINTER(0) != NULL)
|
|
{
|
|
text *in = PG_GETARG_TEXT_P(0);
|
|
|
|
readstoplist(in, &(d->stoplist));
|
|
sortstoplist(&(d->stoplist));
|
|
PG_FREE_IF_COPY(in, 0);
|
|
}
|
|
|
|
PG_RETURN_POINTER(d);
|
|
}
|
|
|
|
Datum
|
|
dex_lexize(PG_FUNCTION_ARGS)
|
|
{
|
|
DictExample *d = (DictExample *) PG_GETARG_POINTER(0);
|
|
char *in = (char *) PG_GETARG_POINTER(1);
|
|
char *txt = pnstrdup(in, PG_GETARG_INT32(2));
|
|
TSLexeme *res = palloc(sizeof(TSLexeme) * 2);
|
|
|
|
memset(res,0,sizeof(TSLexeme) * 2);
|
|
|
|
if (*txt == '\0' || searchstoplist(&(d->stoplist), txt))
|
|
{
|
|
pfree(txt);
|
|
}
|
|
else
|
|
res[0].lexeme = txt;
|
|
|
|
PG_RETURN_POINTER(res);
|
|
}
|