Support ordered-set (WITHIN GROUP) aggregates.

This patch introduces generic support for ordered-set and hypothetical-set
aggregate functions, as well as implementations of the instances defined in
SQL:2008 (percentile_cont(), percentile_disc(), rank(), dense_rank(),
percent_rank(), cume_dist()).  We also added mode() though it is not in the
spec, as well as versions of percentile_cont() and percentile_disc() that
can compute multiple percentile values in one pass over the data.

Unlike the original submission, this patch puts full control of the sorting
process in the hands of the aggregate's support functions.  To allow the
support functions to find out how they're supposed to sort, a new API
function AggGetAggref() is added to nodeAgg.c.  This allows retrieval of
the aggregate call's Aggref node, which may have other uses beyond the
immediate need.  There is also support for ordered-set aggregates to
install cleanup callback functions, so that they can be sure that
infrastructure such as tuplesort objects gets cleaned up.

In passing, make some fixes in the recently-added support for variadic
aggregates, and make some editorial adjustments in the recent FILTER
additions for aggregates.  Also, simplify use of IsBinaryCoercible() by
allowing it to succeed whenever the target type is ANY or ANYELEMENT.
It was inconsistent that it dealt with other polymorphic target types
but not these.

Atri Sharma and Andrew Gierth; reviewed by Pavel Stehule and Vik Fearing,
and rather heavily editorialized upon by Tom Lane

1 files changed, 36 insertions, 1 deletions

diff --git a/src/backend/commands/aggregatecmds.c b/src/backend/commands/aggregatecmds.c
index 6fc3e045492..b570d3e5fa5 100644
--- a/src/backend/commands/aggregatecmds.c
+++ b/src/backend/commands/aggregatecmds.c
@@ -45,7 +45,10 @@
  *
  * "oldstyle" signals the old (pre-8.2) style where the aggregate input type
  * is specified by a BASETYPE element in the parameters.  Otherwise,
- * "args" is a list of FunctionParameter structs defining the agg's arguments.
+ * "args" is a pair, whose first element is a list of FunctionParameter structs
+ * defining the agg's arguments (both direct and aggregated), and whose second
+ * element is an Integer node with the number of direct args, or -1 if this
+ * isn't an ordered-set aggregate.
  * "parameters" is a list of DefElem representing the agg's definition clauses.
  */
 Oid
@@ -55,6 +58,7 @@ DefineAggregate(List *name, List *args, bool oldstyle, List *parameters,
 	char	   *aggName;
 	Oid			aggNamespace;
 	AclResult	aclresult;
+	char		aggKind = AGGKIND_NORMAL;
 	List	   *transfuncName = NIL;
 	List	   *finalfuncName = NIL;
 	List	   *sortoperatorName = NIL;
@@ -63,11 +67,13 @@ DefineAggregate(List *name, List *args, bool oldstyle, List *parameters,
 	int32		transSpace = 0;
 	char	   *initval = NULL;
 	int			numArgs;
+	int			numDirectArgs = 0;
 	oidvector  *parameterTypes;
 	ArrayType  *allParameterTypes;
 	ArrayType  *parameterModes;
 	ArrayType  *parameterNames;
 	List	   *parameterDefaults;
+	Oid			variadicArgType;
 	Oid			transTypeId;
 	char		transTypeType;
 	ListCell   *pl;
@@ -81,6 +87,19 @@ DefineAggregate(List *name, List *args, bool oldstyle, List *parameters,
 		aclcheck_error(aclresult, ACL_KIND_NAMESPACE,
 					   get_namespace_name(aggNamespace));
 
+	/* Deconstruct the output of the aggr_args grammar production */
+	if (!oldstyle)
+	{
+		Assert(list_length(args) == 2);
+		numDirectArgs = intVal(lsecond(args));
+		if (numDirectArgs >= 0)
+			aggKind = AGGKIND_ORDERED_SET;
+		else
+			numDirectArgs = 0;
+		args = (List *) linitial(args);
+	}
+
+	/* Examine aggregate's definition clauses */
 	foreach(pl, parameters)
 	{
 		DefElem    *defel = (DefElem *) lfirst(pl);
@@ -99,6 +118,17 @@ DefineAggregate(List *name, List *args, bool oldstyle, List *parameters,
 			sortoperatorName = defGetQualifiedName(defel);
 		else if (pg_strcasecmp(defel->defname, "basetype") == 0)
 			baseType = defGetTypeName(defel);
+		else if (pg_strcasecmp(defel->defname, "hypothetical") == 0)
+		{
+			if (defGetBoolean(defel))
+			{
+				if (aggKind == AGGKIND_NORMAL)
+					ereport(ERROR,
+							(errcode(ERRCODE_INVALID_FUNCTION_DEFINITION),
+							 errmsg("only ordered-set aggregates can be hypothetical")));
+				aggKind = AGGKIND_HYPOTHETICAL;
+			}
+		}
 		else if (pg_strcasecmp(defel->defname, "stype") == 0)
 			transType = defGetTypeName(defel);
 		else if (pg_strcasecmp(defel->defname, "stype1") == 0)
@@ -162,6 +192,7 @@ DefineAggregate(List *name, List *args, bool oldstyle, List *parameters,
 		parameterModes = NULL;
 		parameterNames = NULL;
 		parameterDefaults = NIL;
+		variadicArgType = InvalidOid;
 	}
 	else
 	{
@@ -186,6 +217,7 @@ DefineAggregate(List *name, List *args, bool oldstyle, List *parameters,
 										  &parameterModes,
 										  &parameterNames,
 										  &parameterDefaults,
+										  &variadicArgType,
 										  &requiredResultType);
 		/* Parameter defaults are not currently allowed by the grammar */
 		Assert(parameterDefaults == NIL);
@@ -241,12 +273,15 @@ DefineAggregate(List *name, List *args, bool oldstyle, List *parameters,
 	 */
 	return AggregateCreate(aggName,		/* aggregate name */
 						   aggNamespace,		/* namespace */
+						   aggKind,
 						   numArgs,
+						   numDirectArgs,
 						   parameterTypes,
 						   PointerGetDatum(allParameterTypes),
 						   PointerGetDatum(parameterModes),
 						   PointerGetDatum(parameterNames),
 						   parameterDefaults,
+						   variadicArgType,
 						   transfuncName,		/* step function name */
 						   finalfuncName,		/* final function name */
 						   sortoperatorName,	/* sort operator name */