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;
67 lines
1.6 KiB
Plaintext
67 lines
1.6 KiB
Plaintext
/*
|
|
* 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"
|
|
|
|
#include "subinclude.h"
|
|
|
|
HASINIT typedef struct {
|
|
HASINIT StopList stoplist;
|
|
HASINIT } DictExample;
|
|
|
|
|
|
HASINIT PG_FUNCTION_INFO_V1(dinit_CFG_MODNAME);
|
|
HASINIT Datum dinit_CFG_MODNAME(PG_FUNCTION_ARGS);
|
|
|
|
HASINIT Datum
|
|
HASINIT dinit_CFG_MODNAME(PG_FUNCTION_ARGS) {
|
|
HASINIT DictExample *d = (DictExample*)malloc( sizeof(DictExample) );
|
|
HASINIT
|
|
HASINIT if ( !d )
|
|
HASINIT ereport(ERROR,
|
|
HASINIT (errcode(ERRCODE_OUT_OF_MEMORY),
|
|
HASINIT errmsg("out of memory")));
|
|
HASINIT memset(d,0,sizeof(DictExample));
|
|
HASINIT
|
|
HASINIT d->stoplist.wordop=lowerstr;
|
|
HASINIT
|
|
HASINIT /* Your INIT code */
|
|
HASINIT
|
|
HASINIT if ( !PG_ARGISNULL(0) && PG_GETARG_POINTER(0)!=NULL ) {
|
|
HASINIT text *in = PG_GETARG_TEXT_P(0);
|
|
HASINIT readstoplist(in, &(d->stoplist));
|
|
HASINIT sortstoplist(&(d->stoplist));
|
|
HASINIT PG_FREE_IF_COPY(in, 0);
|
|
HASINIT }
|
|
HASINIT
|
|
HASINIT PG_RETURN_POINTER(d);
|
|
HASINIT }
|
|
|
|
PG_FUNCTION_INFO_V1(dlexize_CFG_MODNAME);
|
|
Datum dlexize_CFG_MODNAME(PG_FUNCTION_ARGS);
|
|
Datum
|
|
dlexize_CFG_MODNAME(PG_FUNCTION_ARGS) {
|
|
HASINIT 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);
|
|
|
|
/* Your LEXIZE dictionary code */
|
|
HASINIT if ( *txt=='\0' || searchstoplist(&(d->stoplist),txt) ) {
|
|
HASINIT pfree(txt);
|
|
HASINIT res[0].lexeme=NULL;
|
|
HASINIT } else
|
|
res[0].lexeme=txt;
|
|
res[1].lexeme=NULL;
|
|
|
|
PG_RETURN_POINTER(res);
|
|
}
|