postgresql/contrib/tsearch2/ts_cfg.h
Teodor Sigaev 324300bc7c improve support of agglutinative languages (query with compound words).
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;
2005-01-25 15:24:38 +00:00

79 lines
1.1 KiB
C

#ifndef __TS_CFG_H__
#define __TS_CFG_H__
#include "postgres.h"
#include "query.h"
typedef struct
{
int len;
Datum *dict_id;
} ListDictionary;
typedef struct
{
Oid id;
Oid prs_id;
int len;
ListDictionary *map;
} TSCfgInfo;
Oid name2id_cfg(text *name);
TSCfgInfo *findcfg(Oid id);
void init_cfg(Oid id, TSCfgInfo * cfg);
void reset_cfg(void);
typedef struct
{
uint16 len;
uint16 nvariant;
union
{
uint16 pos;
uint16 *apos;
} pos;
char *word;
uint32 alen;
} TSWORD;
typedef struct
{
TSWORD *words;
int4 lenwords;
int4 curwords;
int4 pos;
} PRSTEXT;
typedef struct
{
uint32 selected:1,
in:1,
replace:1,
repeated:1,
unused:4,
type:8,
len:16;
char *word;
ITEM *item;
} HLWORD;
typedef struct
{
HLWORD *words;
int4 lenwords;
int4 curwords;
char *startsel;
char *stopsel;
int2 startsellen;
int2 stopsellen;
} HLPRSTEXT;
void hlparsetext(TSCfgInfo * cfg, HLPRSTEXT * prs, QUERYTYPE * query, char *buf, int4 buflen);
text *genhl(HLPRSTEXT * prs);
void parsetext_v2(TSCfgInfo * cfg, PRSTEXT * prs, char *buf, int4 buflen);
int get_currcfg(void);
#endif