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

1 files changed, 37 insertions, 0 deletions

diff --git a/src/include/nodes/parsenodes.h b/src/include/nodes/parsenodes.h
index 053f1b01213..6723f46f3f1 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):