Fix WITH attached to a nested set operation (UNION/INTERSECT/EXCEPT).

Parse analysis neglected to cover the case of a WITH clause attached to an
intermediate-level set operation; it only handled WITH at the top level
or WITH attached to a leaf-level SELECT.  Per report from Adam Mackler.

In HEAD, I rearranged the order of SelectStmt's fields to put withClause
with the other fields that can appear on non-leaf SelectStmts.  In back
branches, leave it alone to avoid a possible ABI break for third-party
code.

Back-patch to 8.4 where WITH support was added.

src/backend/parser/analyze.c

@@ -1322,6 +1322,7 @@ transformSetOperationStmt(ParseState *pstate, SelectStmt *stmt)
 	Node	   *limitOffset;
 	Node	   *limitCount;
 	List	   *lockingClause;
+	WithClause *withClause;
 	Node	   *node;
 	ListCell   *left_tlist,
 			   *lct,
@@ -1338,14 +1339,6 @@ transformSetOperationStmt(ParseState *pstate, SelectStmt *stmt)
 
 	qry->commandType = CMD_SELECT;
 
-	/* process the WITH clause independently of all else */
-	if (stmt->withClause)
-	{
-		qry->hasRecursive = stmt->withClause->recursive;
-		qry->cteList = transformWithClause(pstate, stmt->withClause);
-		qry->hasModifyingCTE = pstate->p_hasModifyingCTE;
-	}
-
 	/*
 	 * Find leftmost leaf SelectStmt.  We currently only need to do this in
 	 * order to deliver a suitable error message if there's an INTO clause
@@ -1375,11 +1368,13 @@ transformSetOperationStmt(ParseState *pstate, SelectStmt *stmt)
 	limitOffset = stmt->limitOffset;
 	limitCount = stmt->limitCount;
 	lockingClause = stmt->lockingClause;
+	withClause = stmt->withClause;
 
 	stmt->sortClause = NIL;
 	stmt->limitOffset = NULL;
 	stmt->limitCount = NULL;
 	stmt->lockingClause = NIL;
+	stmt->withClause = NULL;
 
 	/* We don't support FOR UPDATE/SHARE with set ops at the moment. */
 	if (lockingClause)
@@ -1387,6 +1382,14 @@ transformSetOperationStmt(ParseState *pstate, SelectStmt *stmt)
 				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
 				 errmsg("SELECT FOR UPDATE/SHARE is not allowed with UNION/INTERSECT/EXCEPT")));
 
+	/* Process the WITH clause independently of all else */
+	if (withClause)
+	{
+		qry->hasRecursive = withClause->recursive;
+		qry->cteList = transformWithClause(pstate, withClause);
+		qry->hasModifyingCTE = pstate->p_hasModifyingCTE;
+	}
+
 	/*
 	 * Recursively transform the components of the tree.
 	 */
@@ -1572,10 +1575,10 @@ transformSetOperationTree(ParseState *pstate, SelectStmt *stmt,
 				 errmsg("SELECT FOR UPDATE/SHARE is not allowed with UNION/INTERSECT/EXCEPT")));
 
 	/*
-	 * If an internal node of a set-op tree has ORDER BY, LIMIT, or FOR UPDATE
+	 * If an internal node of a set-op tree has ORDER BY, LIMIT, FOR UPDATE,
-	 * clauses attached, we need to treat it like a leaf node to generate an
+	 * or WITH clauses attached, we need to treat it like a leaf node to
-	 * independent sub-Query tree.	Otherwise, it can be represented by a
+	 * generate an independent sub-Query tree.  Otherwise, it can be
-	 * SetOperationStmt node underneath the parent Query.
+	 * represented by a SetOperationStmt node underneath the parent Query.
 	 */
 	if (stmt->op == SETOP_NONE)
 	{
@@ -1586,7 +1589,7 @@ transformSetOperationTree(ParseState *pstate, SelectStmt *stmt,
 	{
 		Assert(stmt->larg != NULL && stmt->rarg != NULL);
 		if (stmt->sortClause || stmt->limitOffset || stmt->limitCount ||
-			stmt->lockingClause)
+			stmt->lockingClause || stmt->withClause)
 			isLeaf = true;
 		else
 			isLeaf = false;

src/backend/parser/parse_cte.c

@@ -678,6 +678,18 @@ checkWellFormedRecursion(CteState *cstate)
 		if (cstate->selfrefcount != 1)	/* shouldn't happen */
 			elog(ERROR, "missing recursive reference");
 
+		/* WITH mustn't contain self-reference, either */
+		if (stmt->withClause)
+		{
+			cstate->curitem = i;
+			cstate->innerwiths = NIL;
+			cstate->selfrefcount = 0;
+			cstate->context = RECURSION_SUBLINK;
+			checkWellFormedRecursionWalker((Node *) stmt->withClause->ctes,
+										   cstate);
+			Assert(cstate->innerwiths == NIL);
+		}
+
 		/*
 		 * Disallow ORDER BY and similar decoration atop the UNION. These
 		 * don't make sense because it's impossible to figure out what they
@@ -933,7 +945,7 @@ checkWellFormedSelectStmt(SelectStmt *stmt, CteState *cstate)
 											   cstate);
 				checkWellFormedRecursionWalker((Node *) stmt->lockingClause,
 											   cstate);
-				break;
+				/* stmt->withClause is intentionally ignored here */
 				break;
 			case SETOP_EXCEPT:
 				if (stmt->all)
@@ -952,6 +964,7 @@ checkWellFormedSelectStmt(SelectStmt *stmt, CteState *cstate)
 											   cstate);
 				checkWellFormedRecursionWalker((Node *) stmt->lockingClause,
 											   cstate);
+				/* stmt->withClause is intentionally ignored here */
 				break;
 			default:
 				elog(ERROR, "unrecognized set op: %d",

src/test/regress/expected/with.out

@@ -1160,6 +1160,57 @@ SELECT * FROM t;
  10
 (55 rows)
 
+--
+-- test WITH attached to intermediate-level set operation
+--
+WITH outermost(x) AS (
+  SELECT 1
+  UNION (WITH innermost as (SELECT 2)
+         SELECT * FROM innermost
+         UNION SELECT 3)
+)
+SELECT * FROM outermost;
+ x 
+---
+ 1
+ 2
+ 3
+(3 rows)
+
+WITH outermost(x) AS (
+  SELECT 1
+  UNION (WITH innermost as (SELECT 2)
+         SELECT * FROM outermost  -- fail
+         UNION SELECT * FROM innermost)
+)
+SELECT * FROM outermost;
+ERROR:  relation "outermost" does not exist
+LINE 4:          SELECT * FROM outermost  
+                               ^
+DETAIL:  There is a WITH item named "outermost", but it cannot be referenced from this part of the query.
+HINT:  Use WITH RECURSIVE, or re-order the WITH items to remove forward references.
+WITH RECURSIVE outermost(x) AS (
+  SELECT 1
+  UNION (WITH innermost as (SELECT 2)
+         SELECT * FROM outermost
+         UNION SELECT * FROM innermost)
+)
+SELECT * FROM outermost;
+ x 
+---
+ 1
+ 2
+(2 rows)
+
+WITH RECURSIVE outermost(x) AS (
+  WITH innermost as (SELECT 2 FROM outermost) -- fail
+    SELECT * FROM innermost
+    UNION SELECT * from outermost
+)
+SELECT * FROM outermost;
+ERROR:  recursive reference to query "outermost" must not appear within a subquery
+LINE 2:   WITH innermost as (SELECT 2 FROM outermost) 
+                                           ^
 --
 -- Data-modifying statements in WITH
 --

src/test/regress/sql/with.sql

@@ -539,6 +539,41 @@ WITH RECURSIVE t(j) AS (
 )
 SELECT * FROM t;
 
+--
+-- test WITH attached to intermediate-level set operation
+--
+
+WITH outermost(x) AS (
+  SELECT 1
+  UNION (WITH innermost as (SELECT 2)
+         SELECT * FROM innermost
+         UNION SELECT 3)
+)
+SELECT * FROM outermost;
+
+WITH outermost(x) AS (
+  SELECT 1
+  UNION (WITH innermost as (SELECT 2)
+         SELECT * FROM outermost  -- fail
+         UNION SELECT * FROM innermost)
+)
+SELECT * FROM outermost;
+
+WITH RECURSIVE outermost(x) AS (
+  SELECT 1
+  UNION (WITH innermost as (SELECT 2)
+         SELECT * FROM outermost
+         UNION SELECT * FROM innermost)
+)
+SELECT * FROM outermost;
+
+WITH RECURSIVE outermost(x) AS (
+  WITH innermost as (SELECT 2 FROM outermost) -- fail
+    SELECT * FROM innermost
+    UNION SELECT * from outermost
+)
+SELECT * FROM outermost;
+
 --
 -- Data-modifying statements in WITH
 --