database/postgres
1
0
Fork 0
mirror of https://github.com/postgres/postgres.git synced 2025-07-31 22:04:40 +03:00
Code Activity

Support LIKE and ILIKE index searches via contrib/pg_trgm indexes.

Browse Source 
Unlike Btree-based LIKE optimization, this works for non-left-anchored
search patterns.  The effectiveness of the search depends on how many
trigrams can be extracted from the pattern.  (The worst case, with no
trigrams, degrades to a full-table scan, so this isn't a panacea.  But
it can be very useful.)

Alexander Korotkov, reviewed by Jan Urbanski
This commit is contained in:
Tom Lane
2011-01-31 21:33:55 -05:00
parent 6238473adb
commit 6e2f3ae884
9 changed files with 639 additions and 49 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
contrib/pg_trgm/trgm.h
View File

@ -13,12 +13,21 @@
#define LPADDING 2
#define RPADDING 1
#define KEEPONLYALNUM
/*
* Caution: IGNORECASE macro means that trigrams are case-insensitive.
* If this macro is disabled, the ~~* operator must be removed from the
* operator classes, because we can't handle case-insensitive wildcard search
* with case-sensitive trigrams. Failure to do this will result in "cannot
* handle ~~* with case-sensitive trigrams" errors.
*/
#define IGNORECASE
#define DIVUNION
/* operator strategy numbers */
#define SimilarityStrategyNumber 1
#define DistanceStrategyNumber 2
#define SimilarityStrategyNumber 1
#define DistanceStrategyNumber 2
#define LikeStrategyNumber 3
#define ILikeStrategyNumber 4
typedef char trgm[3];
@ -40,7 +49,10 @@ uint32 trgm2int(trgm *ptr);
#else
#define ISPRINTABLECHAR(a) ( isascii( *(unsigned char*)(a) ) && isprint( *(unsigned char*)(a) ) )
#endif
#define ISPRINTABLETRGM(t) ( ISPRINTABLECHAR( ((char*)t) ) && ISPRINTABLECHAR( ((char*)t)+1 ) && ISPRINTABLECHAR( ((char*)t)+2 ) )
#define ISPRINTABLETRGM(t) ( ISPRINTABLECHAR( ((char*)(t)) ) && ISPRINTABLECHAR( ((char*)(t))+1 ) && ISPRINTABLECHAR( ((char*)(t))+2 ) )
#define ISESCAPECHAR(x) (*(x) == '\\') /* Wildcard escape character */
#define ISWILDCARDCHAR(x) (*(x) == '_' || *(x) == '%') /* Wildcard meta-character */
typedef struct
{
@ -65,7 +77,7 @@ typedef char *BITVECP;
for(i=0;i<SIGLEN;i++)
#define GETBYTE(x,i) ( *( (BITVECP)(x) + (int)( (i) / BITBYTE ) ) )
#define GETBITBYTE(x,i) ( ((char)(x)) >> i & 0x01 )
#define GETBITBYTE(x,i) ( (((char)(x)) >> (i)) & 0x01 )
#define CLRBIT(x,i) GETBYTE(x,i) &= ~( 0x01 << ( (i) % BITBYTE ) )
#define SETBIT(x,i) GETBYTE(x,i) |= ( 0x01 << ( (i) % BITBYTE ) )
#define GETBIT(x,i) ( (GETBYTE(x,i) >> ( (i) % BITBYTE )) & 0x01 )
@ -89,6 +101,8 @@ typedef char *BITVECP;
extern float4 trgm_limit;
TRGM *generate_trgm(char *str, int slen);
TRGM *generate_wildcard_trgm(const char *str, int slen);
float4 cnt_sml(TRGM *trg1, TRGM *trg2);
bool trgm_contained_by(TRGM *trg1, TRGM *trg2);
#endif /* __TRGM_H__ */