1
0
mirror of https://github.com/postgres/postgres.git synced 2025-06-29 10:41:53 +03:00

TABLESAMPLE, SQL Standard and extensible

Add a TABLESAMPLE clause to SELECT statements that allows
user to specify random BERNOULLI sampling or block level
SYSTEM sampling. Implementation allows for extensible
sampling functions to be written, using a standard API.
Basic version follows SQLStandard exactly. Usable
concrete use cases for the sampling API follow in later
commits.

Petr Jelinek

Reviewed by Michael Paquier and Simon Riggs
This commit is contained in:
Simon Riggs
2015-05-15 14:37:10 -04:00
parent 11a83bbedd
commit f6d208d6e5
66 changed files with 2756 additions and 40 deletions

View File

@ -17,6 +17,7 @@
#include "access/heapam.h"
#include "catalog/catalog.h"
#include "access/htup_details.h"
#include "catalog/heap.h"
#include "catalog/pg_constraint.h"
#include "catalog/pg_type.h"
@ -31,6 +32,7 @@
#include "parser/parse_coerce.h"
#include "parser/parse_collate.h"
#include "parser/parse_expr.h"
#include "parser/parse_func.h"
#include "parser/parse_oper.h"
#include "parser/parse_relation.h"
#include "parser/parse_target.h"
@ -39,6 +41,7 @@
#include "utils/guc.h"
#include "utils/lsyscache.h"
#include "utils/rel.h"
#include "utils/syscache.h"
/* Convenience macro for the most common makeNamespaceItem() case */
@ -419,6 +422,39 @@ transformJoinOnClause(ParseState *pstate, JoinExpr *j, List *namespace)
return result;
}
static RangeTblEntry *
transformTableSampleEntry(ParseState *pstate, RangeTableSample *rv)
{
RangeTblEntry *rte = NULL;
CommonTableExpr *cte = NULL;
TableSampleClause *tablesample = NULL;
/* if relation has an unqualified name, it might be a CTE reference */
if (!rv->relation->schemaname)
{
Index levelsup;
cte = scanNameSpaceForCTE(pstate, rv->relation->relname, &levelsup);
}
/* We first need to build a range table entry */
if (!cte)
rte = transformTableEntry(pstate, rv->relation);
if (!rte ||
(rte->relkind != RELKIND_RELATION &&
rte->relkind != RELKIND_MATVIEW))
ereport(ERROR,
(errcode(ERRCODE_SYNTAX_ERROR),
errmsg("TABLESAMPLE clause can only be used on tables and materialized views"),
parser_errposition(pstate, rv->relation->location)));
tablesample = ParseTableSample(pstate, rv->method, rv->repeatable,
rv->args, rv->relation->location);
rte->tablesample = tablesample;
return rte;
}
/*
* transformTableEntry --- transform a RangeVar (simple relation reference)
*/
@ -1127,6 +1163,26 @@ transformFromClauseItem(ParseState *pstate, Node *n,
return (Node *) j;
}
else if (IsA(n, RangeTableSample))
{
/* Tablesample reference */
RangeTableSample *rv = (RangeTableSample *) n;
RangeTblRef *rtr;
RangeTblEntry *rte = NULL;
int rtindex;
rte = transformTableSampleEntry(pstate, rv);
/* assume new rte is at end */
rtindex = list_length(pstate->p_rtable);
Assert(rte == rt_fetch(rtindex, pstate->p_rtable));
*top_rte = rte;
*top_rti = rtindex;
*namespace = list_make1(makeDefaultNSItem(rte));
rtr = makeNode(RangeTblRef);
rtr->rtindex = rtindex;
return (Node *) rtr;
}
else
elog(ERROR, "unrecognized node type: %d", (int) nodeTag(n));
return NULL; /* can't get here, keep compiler quiet */