postgresql/src/include/access/spgist.h
Alexander Korotkov 911e702077 Implement operator class parameters
PostgreSQL provides set of template index access methods, where opclasses have
much freedom in the semantics of indexing.  These index AMs are GiST, GIN,
SP-GiST and BRIN.  There opclasses define representation of keys, operations on
them and supported search strategies.  So, it's natural that opclasses may be
faced some tradeoffs, which require user-side decision.  This commit implements
opclass parameters allowing users to set some values, which tell opclass how to
index the particular dataset.

This commit doesn't introduce new storage in system catalog.  Instead it uses
pg_attribute.attoptions, which is used for table column storage options but
unused for index attributes.

In order to evade changing signature of each opclass support function, we
implement unified way to pass options to opclass support functions.  Options
are set to fn_expr as the constant bytea expression.  It's possible due to the
fact that opclass support functions are executed outside of expressions, so
fn_expr is unused for them.

This commit comes with some examples of opclass options usage.  We parametrize
signature length in GiST.  That applies to multiple opclasses: tsvector_ops,
gist__intbig_ops, gist_ltree_ops, gist__ltree_ops, gist_trgm_ops and
gist_hstore_ops.  Also we parametrize maximum number of integer ranges for
gist__int_ops.  However, the main future usage of this feature is expected
to be json, where users would be able to specify which way to index particular
json parts.

Catversion is bumped.

Discussion: https://postgr.es/m/d22c3a18-31c7-1879-fc11-4c1ce2f5e5af%40postgrespro.ru
Author: Nikita Glukhov, revised by me
Reviwed-by: Nikolay Shaplov, Robert Haas, Tom Lane, Tomas Vondra, Alvaro Herrera
2020-03-30 19:17:23 +03:00

225 lines
7.5 KiB
C

/*-------------------------------------------------------------------------
*
* spgist.h
* Public header file for SP-GiST access method.
*
*
* Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group
* Portions Copyright (c) 1994, Regents of the University of California
*
* src/include/access/spgist.h
*
*-------------------------------------------------------------------------
*/
#ifndef SPGIST_H
#define SPGIST_H
#include "access/amapi.h"
#include "access/xlogreader.h"
#include "lib/stringinfo.h"
/* SPGiST opclass support function numbers */
#define SPGIST_CONFIG_PROC 1
#define SPGIST_CHOOSE_PROC 2
#define SPGIST_PICKSPLIT_PROC 3
#define SPGIST_INNER_CONSISTENT_PROC 4
#define SPGIST_LEAF_CONSISTENT_PROC 5
#define SPGIST_COMPRESS_PROC 6
#define SPGIST_OPTIONS_PROC 7
#define SPGISTNRequiredProc 5
#define SPGISTNProc 7
/*
* Argument structs for spg_config method
*/
typedef struct spgConfigIn
{
Oid attType; /* Data type to be indexed */
} spgConfigIn;
typedef struct spgConfigOut
{
Oid prefixType; /* Data type of inner-tuple prefixes */
Oid labelType; /* Data type of inner-tuple node labels */
Oid leafType; /* Data type of leaf-tuple values */
bool canReturnData; /* Opclass can reconstruct original data */
bool longValuesOK; /* Opclass can cope with values > 1 page */
} spgConfigOut;
/*
* Argument structs for spg_choose method
*/
typedef struct spgChooseIn
{
Datum datum; /* original datum to be indexed */
Datum leafDatum; /* current datum to be stored at leaf */
int level; /* current level (counting from zero) */
/* Data from current inner tuple */
bool allTheSame; /* tuple is marked all-the-same? */
bool hasPrefix; /* tuple has a prefix? */
Datum prefixDatum; /* if so, the prefix value */
int nNodes; /* number of nodes in the inner tuple */
Datum *nodeLabels; /* node label values (NULL if none) */
} spgChooseIn;
typedef enum spgChooseResultType
{
spgMatchNode = 1, /* descend into existing node */
spgAddNode, /* add a node to the inner tuple */
spgSplitTuple /* split inner tuple (change its prefix) */
} spgChooseResultType;
typedef struct spgChooseOut
{
spgChooseResultType resultType; /* action code, see above */
union
{
struct /* results for spgMatchNode */
{
int nodeN; /* descend to this node (index from 0) */
int levelAdd; /* increment level by this much */
Datum restDatum; /* new leaf datum */
} matchNode;
struct /* results for spgAddNode */
{
Datum nodeLabel; /* new node's label */
int nodeN; /* where to insert it (index from 0) */
} addNode;
struct /* results for spgSplitTuple */
{
/* Info to form new upper-level inner tuple with one child tuple */
bool prefixHasPrefix; /* tuple should have a prefix? */
Datum prefixPrefixDatum; /* if so, its value */
int prefixNNodes; /* number of nodes */
Datum *prefixNodeLabels; /* their labels (or NULL for no
* labels) */
int childNodeN; /* which node gets child tuple */
/* Info to form new lower-level inner tuple with all old nodes */
bool postfixHasPrefix; /* tuple should have a prefix? */
Datum postfixPrefixDatum; /* if so, its value */
} splitTuple;
} result;
} spgChooseOut;
/*
* Argument structs for spg_picksplit method
*/
typedef struct spgPickSplitIn
{
int nTuples; /* number of leaf tuples */
Datum *datums; /* their datums (array of length nTuples) */
int level; /* current level (counting from zero) */
} spgPickSplitIn;
typedef struct spgPickSplitOut
{
bool hasPrefix; /* new inner tuple should have a prefix? */
Datum prefixDatum; /* if so, its value */
int nNodes; /* number of nodes for new inner tuple */
Datum *nodeLabels; /* their labels (or NULL for no labels) */
int *mapTuplesToNodes; /* node index for each leaf tuple */
Datum *leafTupleDatums; /* datum to store in each new leaf tuple */
} spgPickSplitOut;
/*
* Argument structs for spg_inner_consistent method
*/
typedef struct spgInnerConsistentIn
{
ScanKey scankeys; /* array of operators and comparison values */
ScanKey orderbys; /* array of ordering operators and comparison
* values */
int nkeys; /* length of scankeys array */
int norderbys; /* length of orderbys array */
Datum reconstructedValue; /* value reconstructed at parent */
void *traversalValue; /* opclass-specific traverse value */
MemoryContext traversalMemoryContext; /* put new traverse values here */
int level; /* current level (counting from zero) */
bool returnData; /* original data must be returned? */
/* Data from current inner tuple */
bool allTheSame; /* tuple is marked all-the-same? */
bool hasPrefix; /* tuple has a prefix? */
Datum prefixDatum; /* if so, the prefix value */
int nNodes; /* number of nodes in the inner tuple */
Datum *nodeLabels; /* node label values (NULL if none) */
} spgInnerConsistentIn;
typedef struct spgInnerConsistentOut
{
int nNodes; /* number of child nodes to be visited */
int *nodeNumbers; /* their indexes in the node array */
int *levelAdds; /* increment level by this much for each */
Datum *reconstructedValues; /* associated reconstructed values */
void **traversalValues; /* opclass-specific traverse values */
double **distances; /* associated distances */
} spgInnerConsistentOut;
/*
* Argument structs for spg_leaf_consistent method
*/
typedef struct spgLeafConsistentIn
{
ScanKey scankeys; /* array of operators and comparison values */
ScanKey orderbys; /* array of ordering operators and comparison
* values */
int nkeys; /* length of scankeys array */
int norderbys; /* length of orderbys array */
Datum reconstructedValue; /* value reconstructed at parent */
void *traversalValue; /* opclass-specific traverse value */
int level; /* current level (counting from zero) */
bool returnData; /* original data must be returned? */
Datum leafDatum; /* datum in leaf tuple */
} spgLeafConsistentIn;
typedef struct spgLeafConsistentOut
{
Datum leafValue; /* reconstructed original data, if any */
bool recheck; /* set true if operator must be rechecked */
bool recheckDistances; /* set true if distances must be rechecked */
double *distances; /* associated distances */
} spgLeafConsistentOut;
/* spgutils.c */
extern bytea *spgoptions(Datum reloptions, bool validate);
/* spginsert.c */
extern IndexBuildResult *spgbuild(Relation heap, Relation index,
struct IndexInfo *indexInfo);
extern void spgbuildempty(Relation index);
extern bool spginsert(Relation index, Datum *values, bool *isnull,
ItemPointer ht_ctid, Relation heapRel,
IndexUniqueCheck checkUnique,
struct IndexInfo *indexInfo);
/* spgscan.c */
extern IndexScanDesc spgbeginscan(Relation rel, int keysz, int orderbysz);
extern void spgendscan(IndexScanDesc scan);
extern void spgrescan(IndexScanDesc scan, ScanKey scankey, int nscankeys,
ScanKey orderbys, int norderbys);
extern int64 spggetbitmap(IndexScanDesc scan, TIDBitmap *tbm);
extern bool spggettuple(IndexScanDesc scan, ScanDirection dir);
extern bool spgcanreturn(Relation index, int attno);
/* spgvacuum.c */
extern IndexBulkDeleteResult *spgbulkdelete(IndexVacuumInfo *info,
IndexBulkDeleteResult *stats,
IndexBulkDeleteCallback callback,
void *callback_state);
extern IndexBulkDeleteResult *spgvacuumcleanup(IndexVacuumInfo *info,
IndexBulkDeleteResult *stats);
/* spgvalidate.c */
extern bool spgvalidate(Oid opclassoid);
#endif /* SPGIST_H */