mirror of
https://git.postgresql.org/git/postgresql.git
synced 2025-01-30 19:00:29 +08:00
d3aad4ac57
These do the same thing as the standard isdigit(), isspace(), and isprint() but with multibyte and encoding support. But all the callers are only interested in analyzing single-byte ASCII characters. So this extra layer is overkill and we can replace the uses with the standard functions. All the t_is*() functions in ts_locale.c are under scrutiny because they don't use the common locale provider framework but instead use the global libc locale settings. For the functions being touched by this patch, we don't need all that anyway, as mentioned above, so the simplest solution is to just remove them. The few remaining t_is*() functions will need a different treatment in a separate patch. pg_trgm has some compile-time options with macros such as KEEPONLYALNUM. These are not documented, and the non-default variant is not supported by any test cases. As part of this undertaking, I'm removing the non-default variant, as it is in the way of cleanup. So in this case, the not-KEEPONLYALNUM code path is gone. Reviewed-by: Jeff Davis <pgsql@j-davis.com> Discussion: https://www.postgresql.org/message-id/flat/653f3b84-fc87-45a7-9a0c-bfb4fcab3e7d%40eisentraut.org
135 lines
4.7 KiB
C
135 lines
4.7 KiB
C
/*
|
|
* contrib/pg_trgm/trgm.h
|
|
*/
|
|
#ifndef __TRGM_H__
|
|
#define __TRGM_H__
|
|
|
|
#include "access/gist.h"
|
|
#include "access/itup.h"
|
|
#include "access/stratnum.h"
|
|
#include "storage/bufpage.h"
|
|
|
|
/*
|
|
* Options ... but note that trgm_regexp.c effectively assumes these values
|
|
* of LPADDING and RPADDING.
|
|
*/
|
|
#define LPADDING 2
|
|
#define RPADDING 1
|
|
/*
|
|
* Caution: IGNORECASE macro means that trigrams are case-insensitive.
|
|
* If this macro is disabled, the ~* and ~~* operators 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 LikeStrategyNumber 3
|
|
#define ILikeStrategyNumber 4
|
|
#define RegExpStrategyNumber 5
|
|
#define RegExpICaseStrategyNumber 6
|
|
#define WordSimilarityStrategyNumber 7
|
|
#define WordDistanceStrategyNumber 8
|
|
#define StrictWordSimilarityStrategyNumber 9
|
|
#define StrictWordDistanceStrategyNumber 10
|
|
#define EqualStrategyNumber 11
|
|
|
|
typedef char trgm[3];
|
|
|
|
#define CMPCHAR(a,b) ( ((a)==(b)) ? 0 : ( ((a)<(b)) ? -1 : 1 ) )
|
|
#define CMPPCHAR(a,b,i) CMPCHAR( *(((const char*)(a))+i), *(((const char*)(b))+i) )
|
|
#define CMPTRGM(a,b) ( CMPPCHAR(a,b,0) ? CMPPCHAR(a,b,0) : ( CMPPCHAR(a,b,1) ? CMPPCHAR(a,b,1) : CMPPCHAR(a,b,2) ) )
|
|
|
|
#define CPTRGM(a,b) do { \
|
|
*(((char*)(a))+0) = *(((char*)(b))+0); \
|
|
*(((char*)(a))+1) = *(((char*)(b))+1); \
|
|
*(((char*)(a))+2) = *(((char*)(b))+2); \
|
|
} while(0)
|
|
|
|
#define ISWORDCHR(c) (t_isalnum(c))
|
|
#define ISPRINTABLECHAR(a) ( isascii( *(unsigned char*)(a) ) && (isalnum( *(unsigned char*)(a) ) || *(unsigned char*)(a)==' ') )
|
|
#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
|
|
{
|
|
int32 vl_len_; /* varlena header (do not touch directly!) */
|
|
uint8 flag;
|
|
char data[FLEXIBLE_ARRAY_MEMBER];
|
|
} TRGM;
|
|
|
|
#define TRGMHDRSIZE (VARHDRSZ + sizeof(uint8))
|
|
|
|
/* gist */
|
|
#define SIGLEN_DEFAULT (sizeof(int) * 3)
|
|
#define SIGLEN_MAX GISTMaxIndexKeySize
|
|
#define BITBYTE 8
|
|
|
|
#define SIGLENBIT(siglen) ((siglen) * BITBYTE - 1) /* see makesign */
|
|
|
|
typedef char *BITVECP;
|
|
|
|
#define LOOPBYTE(siglen) \
|
|
for (i = 0; i < (siglen); i++)
|
|
|
|
#define GETBYTE(x,i) ( *( (BITVECP)(x) + (int)( (i) / BITBYTE ) ) )
|
|
#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 )
|
|
|
|
#define HASHVAL(val, siglen) (((unsigned int)(val)) % SIGLENBIT(siglen))
|
|
#define HASH(sign, val, siglen) SETBIT((sign), HASHVAL(val, siglen))
|
|
|
|
#define ARRKEY 0x01
|
|
#define SIGNKEY 0x02
|
|
#define ALLISTRUE 0x04
|
|
|
|
#define ISARRKEY(x) ( ((TRGM*)x)->flag & ARRKEY )
|
|
#define ISSIGNKEY(x) ( ((TRGM*)x)->flag & SIGNKEY )
|
|
#define ISALLTRUE(x) ( ((TRGM*)x)->flag & ALLISTRUE )
|
|
|
|
#define CALCGTSIZE(flag, len) ( TRGMHDRSIZE + ( ( (flag) & ARRKEY ) ? ((len)*sizeof(trgm)) : (((flag) & ALLISTRUE) ? 0 : (len)) ) )
|
|
#define GETSIGN(x) ( (BITVECP)( (char*)x+TRGMHDRSIZE ) )
|
|
#define GETARR(x) ( (trgm*)( (char*)x+TRGMHDRSIZE ) )
|
|
#define ARRNELEM(x) ( ( VARSIZE(x) - TRGMHDRSIZE )/sizeof(trgm) )
|
|
|
|
/*
|
|
* If DIVUNION is defined then similarity formula is:
|
|
* count / (len1 + len2 - count)
|
|
* else if DIVUNION is not defined then similarity formula is:
|
|
* count / max(len1, len2)
|
|
*/
|
|
#ifdef DIVUNION
|
|
#define CALCSML(count, len1, len2) ((float4) (count)) / ((float4) ((len1) + (len2) - (count)))
|
|
#else
|
|
#define CALCSML(count, len1, len2) ((float4) (count)) / ((float4) (((len1) > (len2)) ? (len1) : (len2)))
|
|
#endif
|
|
|
|
typedef struct TrgmPackedGraph TrgmPackedGraph;
|
|
|
|
extern double similarity_threshold;
|
|
extern double word_similarity_threshold;
|
|
extern double strict_word_similarity_threshold;
|
|
|
|
extern double index_strategy_get_limit(StrategyNumber strategy);
|
|
extern uint32 trgm2int(trgm *ptr);
|
|
extern void compact_trigram(trgm *tptr, char *str, int bytelen);
|
|
extern TRGM *generate_trgm(char *str, int slen);
|
|
extern TRGM *generate_wildcard_trgm(const char *str, int slen);
|
|
extern float4 cnt_sml(TRGM *trg1, TRGM *trg2, bool inexact);
|
|
extern bool trgm_contained_by(TRGM *trg1, TRGM *trg2);
|
|
extern bool *trgm_presence_map(TRGM *query, TRGM *key);
|
|
extern TRGM *createTrgmNFA(text *text_re, Oid collation,
|
|
TrgmPackedGraph **graph, MemoryContext rcontext);
|
|
extern bool trigramsMatchGraph(TrgmPackedGraph *graph, bool *check);
|
|
|
|
#endif /* __TRGM_H__ */
|