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

4 files changed, 56 insertions, 0 deletions

diff --git a/src/include/nodes/execnodes.h b/src/include/nodes/execnodes.h
index fcfe1107f9..972368019a 100644
--- a/src/include/nodes/execnodes.h
+++ b/src/include/nodes/execnodes.h
@@ -1238,6 +1238,15 @@ typedef struct ScanState
 typedef ScanState SeqScanState;
 
 /*
+ * SampleScan
+ */
+typedef struct SampleScanState
+{
+	ScanState	ss;
+	struct TableSampleDesc *tsdesc;
+} SampleScanState;
+
+/*
  * These structs store information about index quals that don't have simple
  * constant right-hand sides.  See comments for ExecIndexBuildScanKeys()
  * for discussion.
diff --git a/src/include/nodes/nodes.h b/src/include/nodes/nodes.h
index 768f413a45..8b275f6e26 100644
--- a/src/include/nodes/nodes.h
+++ b/src/include/nodes/nodes.h
@@ -61,6 +61,7 @@ typedef enum NodeTag
 	T_ValuesScan,
 	T_CteScan,
 	T_WorkTableScan,
+	T_SampleScan,
 	T_ForeignScan,
 	T_CustomScan,
 	T_Join,
@@ -97,6 +98,7 @@ typedef enum NodeTag
 	T_BitmapOrState,
 	T_ScanState,
 	T_SeqScanState,
+	T_SampleScanState,
 	T_IndexScanState,
 	T_IndexOnlyScanState,
 	T_BitmapIndexScanState,
@@ -419,6 +421,8 @@ typedef enum NodeTag
 	T_OnConflictClause,
 	T_CommonTableExpr,
 	T_RoleSpec,
+	T_RangeTableSample,
+	T_TableSampleClause,
 
 	/*
 	 * TAGS FOR REPLICATION GRAMMAR PARSE NODES (replnodes.h)
diff --git a/src/include/nodes/parsenodes.h b/src/include/nodes/parsenodes.h
index 053f1b0121..6723f46f3f 100644
--- a/src/include/nodes/parsenodes.h
+++ b/src/include/nodes/parsenodes.h
@@ -336,6 +336,26 @@ typedef struct FuncCall
 } FuncCall;
 
 /*
+ * TableSampleClause - a sampling method information
+ */
+typedef struct TableSampleClause
+{
+	NodeTag		type;
+	Oid			tsmid;
+	bool		tsmseqscan;
+	bool		tsmpagemode;
+	Oid			tsminit;
+	Oid			tsmnextblock;
+	Oid			tsmnexttuple;
+	Oid			tsmexaminetuple;
+	Oid			tsmend;
+	Oid			tsmreset;
+	Oid			tsmcost;
+	Node	   *repeatable;
+	List	   *args;
+} TableSampleClause;
+
+/*
  * A_Star - '*' representing all columns of a table or compound field
  *
  * This can appear within ColumnRef.fields, A_Indirection.indirection, and
@@ -536,6 +556,22 @@ typedef struct RangeFunction
 } RangeFunction;
 
 /*
+ * RangeTableSample - represents <table> TABLESAMPLE <method> (<params>) REPEATABLE (<num>)
+ *
+ * SQL Standard specifies only one parameter which is percentage. But we allow
+ * custom tablesample methods which may need different input arguments so we
+ * accept list of arguments.
+ */
+typedef struct RangeTableSample
+{
+	NodeTag		type;
+	RangeVar   *relation;
+	char	   *method;		/* sampling method */
+	Node	   *repeatable;
+	List	   *args;		/* arguments for sampling method */
+} RangeTableSample;
+
+/*
  * ColumnDef - column definition (used in various creates)
  *
  * If the column has a default value, we may have the value expression
@@ -772,6 +808,7 @@ typedef struct RangeTblEntry
 	 */
 	Oid			relid;			/* OID of the relation */
 	char		relkind;		/* relation kind (see pg_class.relkind) */
+	TableSampleClause	*tablesample;	/* sampling method and parameters */
 
 	/*
 	 * Fields valid for a subquery RTE (else NULL):
diff --git a/src/include/nodes/plannodes.h b/src/include/nodes/plannodes.h
index 65f71d8170..4e655b0e6c 100644
--- a/src/include/nodes/plannodes.h
+++ b/src/include/nodes/plannodes.h
@@ -287,6 +287,12 @@ typedef struct Scan
 typedef Scan SeqScan;
 
 /* ----------------
+ *		table sample scan node
+ * ----------------
+ */
+typedef Scan SampleScan;
+
+/* ----------------
  *		index scan node
  *
  * indexqualorig is an implicitly-ANDed list of index qual expressions, each