Support XMLTABLE query expression

XMLTABLE is defined by the SQL/XML standard as a feature that allows
turning XML-formatted data into relational form, so that it can be used
as a <table primary> in the FROM clause of a query.

This new construct provides significant simplicity and performance
benefit for XML data processing; what in a client-side custom
implementation was reported to take 20 minutes can be executed in 400ms
using XMLTABLE.  (The same functionality was said to take 10 seconds
using nested PostgreSQL XPath function calls, and 5 seconds using
XMLReader under PL/Python).

The implemented syntax deviates slightly from what the standard
requires.  First, the standard indicates that the PASSING clause is
optional and that multiple XML input documents may be given to it; we
make it mandatory and accept a single document only.  Second, we don't
currently support a default namespace to be specified.

This implementation relies on a new executor node based on a hardcoded
method table.  (Because the grammar is fixed, there is no extensibility
in the current approach; further constructs can be implemented on top of
this such as JSON_TABLE, but they require changes to core code.)

Author: Pavel Stehule, Álvaro Herrera
Extensively reviewed by: Craig Ringer
Discussion: https://postgr.es/m/CAFj8pRAgfzMD-LoSmnMGybD0WsEznLHWap8DO79+-GTRAPR4qA@mail.gmail.com

1 files changed, 73 insertions, 0 deletions

diff --git a/src/backend/nodes/outfuncs.c b/src/backend/nodes/outfuncs.c
index b3802b4428f..d4297d11b18 100644
--- a/src/backend/nodes/outfuncs.c
+++ b/src/backend/nodes/outfuncs.c
@@ -566,6 +566,16 @@ _outFunctionScan(StringInfo str, const FunctionScan *node)
 }
 
 static void
+_outTableFuncScan(StringInfo str, const TableFuncScan *node)
+{
+	WRITE_NODE_TYPE("TABLEFUNCSCAN");
+
+	_outScanInfo(str, (const Scan *) node);
+
+	WRITE_NODE_FIELD(tablefunc);
+}
+
+static void
 _outValuesScan(StringInfo str, const ValuesScan *node)
 {
 	WRITE_NODE_TYPE("VALUESSCAN");
@@ -956,6 +966,26 @@ _outRangeVar(StringInfo str, const RangeVar *node)
 }
 
 static void
+_outTableFunc(StringInfo str, const TableFunc *node)
+{
+	WRITE_NODE_TYPE("TABLEFUNC");
+
+	WRITE_NODE_FIELD(ns_names);
+	WRITE_NODE_FIELD(ns_uris);
+	WRITE_NODE_FIELD(docexpr);
+	WRITE_NODE_FIELD(rowexpr);
+	WRITE_NODE_FIELD(colnames);
+	WRITE_NODE_FIELD(coltypes);
+	WRITE_NODE_FIELD(coltypmods);
+	WRITE_NODE_FIELD(colcollations);
+	WRITE_NODE_FIELD(colexprs);
+	WRITE_NODE_FIELD(coldefexprs);
+	WRITE_BITMAPSET_FIELD(notnulls);
+	WRITE_INT_FIELD(ordinalitycol);
+	WRITE_LOCATION_FIELD(location);
+}
+
+static void
 _outIntoClause(StringInfo str, const IntoClause *node)
 {
 	WRITE_NODE_TYPE("INTOCLAUSE");
@@ -2869,6 +2899,9 @@ _outRangeTblEntry(StringInfo str, const RangeTblEntry *node)
 			WRITE_NODE_FIELD(functions);
 			WRITE_BOOL_FIELD(funcordinality);
 			break;
+		case RTE_TABLEFUNC:
+			WRITE_NODE_FIELD(tablefunc);
+			break;
 		case RTE_VALUES:
 			WRITE_NODE_FIELD(values_lists);
 			WRITE_NODE_FIELD(coltypes);
@@ -3192,6 +3225,34 @@ _outRangeTableSample(StringInfo str, const RangeTableSample *node)
 }
 
 static void
+_outRangeTableFunc(StringInfo str, const RangeTableFunc *node)
+{
+	WRITE_NODE_TYPE("RANGETABLEFUNC");
+
+	WRITE_BOOL_FIELD(lateral);
+	WRITE_NODE_FIELD(docexpr);
+	WRITE_NODE_FIELD(rowexpr);
+	WRITE_NODE_FIELD(namespaces);
+	WRITE_NODE_FIELD(columns);
+	WRITE_NODE_FIELD(alias);
+	WRITE_LOCATION_FIELD(location);
+}
+
+static void
+_outRangeTableFuncCol(StringInfo str, const RangeTableFuncCol *node)
+{
+	WRITE_NODE_TYPE("RANGETABLEFUNCCOL");
+
+	WRITE_STRING_FIELD(colname);
+	WRITE_NODE_FIELD(typeName);
+	WRITE_BOOL_FIELD(for_ordinality);
+	WRITE_BOOL_FIELD(is_not_null);
+	WRITE_NODE_FIELD(colexpr);
+	WRITE_NODE_FIELD(coldefexpr);
+	WRITE_LOCATION_FIELD(location);
+}
+
+static void
 _outConstraint(StringInfo str, const Constraint *node)
 {
 	WRITE_NODE_TYPE("CONSTRAINT");
@@ -3440,6 +3501,9 @@ outNode(StringInfo str, const void *obj)
 			case T_FunctionScan:
 				_outFunctionScan(str, obj);
 				break;
+			case T_TableFuncScan:
+				_outTableFuncScan(str, obj);
+				break;
 			case T_ValuesScan:
 				_outValuesScan(str, obj);
 				break;
@@ -3512,6 +3576,9 @@ outNode(StringInfo str, const void *obj)
 			case T_RangeVar:
 				_outRangeVar(str, obj);
 				break;
+			case T_TableFunc:
+				_outTableFunc(str, obj);
+				break;
 			case T_IntoClause:
 				_outIntoClause(str, obj);
 				break;
@@ -3922,6 +3989,12 @@ outNode(StringInfo str, const void *obj)
 			case T_RangeTableSample:
 				_outRangeTableSample(str, obj);
 				break;
+			case T_RangeTableFunc:
+				_outRangeTableFunc(str, obj);
+				break;
+			case T_RangeTableFuncCol:
+				_outRangeTableFuncCol(str, obj);
+				break;
 			case T_Constraint:
 				_outConstraint(str, obj);
 				break;