Avoid recursion when processing simple lists of AND'ed or OR'ed clauses.

Since most of the system thinks AND and OR are N-argument expressions
anyway, let's have the grammar generate a representation of that form when
dealing with input like "x AND y AND z AND ...", rather than generating
a deeply-nested binary tree that just has to be flattened later by the
planner.  This avoids stack overflow in parse analysis when dealing with
queries having more than a few thousand such clauses; and in any case it
removes some rather unsightly inconsistencies, since some parts of parse
analysis were generating N-argument ANDs/ORs already.

It's still possible to get a stack overflow with weirdly parenthesized
input, such as "x AND (y AND (z AND ( ... )))", but such cases are not
mainstream usage.  The maximum depth of parenthesization is already
limited by Bison's stack in such cases, anyway, so that the limit is
probably fairly platform-independent.

Patch originally by Gurjeet Singh, heavily revised by me

3 files changed, 126 insertions, 103 deletions

diff --git a/src/backend/parser/gram.y b/src/backend/parser/gram.y
index 7b9895d61ec..dd04b1a88ab 100644
--- a/src/backend/parser/gram.y
+++ b/src/backend/parser/gram.y
@@ -151,6 +151,9 @@ static void insertSelectOptions(SelectStmt *stmt,
 static Node *makeSetOp(SetOperation op, bool all, Node *larg, Node *rarg);
 static Node *doNegate(Node *n, int location);
 static void doNegateFloat(Value *v);
+static Node *makeAndExpr(Node *lexpr, Node *rexpr, int location);
+static Node *makeOrExpr(Node *lexpr, Node *rexpr, int location);
+static Node *makeNotExpr(Node *expr, int location);
 static Node *makeAArrayExpr(List *elements, int location);
 static Node *makeXmlExpr(XmlExprOp op, char *name, List *named_args,
 						 List *args, int location);
@@ -10849,11 +10852,11 @@ a_expr:		c_expr									{ $$ = $1; }
 				{ $$ = (Node *) makeA_Expr(AEXPR_OP, $2, $1, NULL, @2); }
 
 			| a_expr AND a_expr
-				{ $$ = (Node *) makeA_Expr(AEXPR_AND, NIL, $1, $3, @2); }
+				{ $$ = makeAndExpr($1, $3, @2); }
 			| a_expr OR a_expr
-				{ $$ = (Node *) makeA_Expr(AEXPR_OR, NIL, $1, $3, @2); }
+				{ $$ = makeOrExpr($1, $3, @2); }
 			| NOT a_expr
-				{ $$ = (Node *) makeA_Expr(AEXPR_NOT, NIL, NULL, $2, @1); }
+				{ $$ = makeNotExpr($2, @1); }
 
 			| a_expr LIKE a_expr
 				{ $$ = (Node *) makeSimpleA_Expr(AEXPR_OP, "~~", $1, $3, @2); }
@@ -11022,11 +11025,9 @@ a_expr:		c_expr									{ $$ = $1; }
 				}
 			| a_expr IS NOT DISTINCT FROM a_expr		%prec IS
 				{
-					$$ = (Node *) makeA_Expr(AEXPR_NOT, NIL, NULL,
-									(Node *) makeSimpleA_Expr(AEXPR_DISTINCT,
-															  "=", $1, $6, @2),
-											 @2);
-
+					$$ = makeNotExpr((Node *) makeSimpleA_Expr(AEXPR_DISTINCT,
+															   "=", $1, $6, @2),
+									 @2);
 				}
 			| a_expr IS OF '(' type_list ')'			%prec IS
 				{
@@ -11044,43 +11045,43 @@ a_expr:		c_expr									{ $$ = $1; }
 			 */
 			| a_expr BETWEEN opt_asymmetric b_expr AND b_expr		%prec BETWEEN
 				{
-					$$ = (Node *) makeA_Expr(AEXPR_AND, NIL,
+					$$ = makeAndExpr(
 						(Node *) makeSimpleA_Expr(AEXPR_OP, ">=", $1, $4, @2),
 						(Node *) makeSimpleA_Expr(AEXPR_OP, "<=", $1, $6, @2),
-											 @2);
+									 @2);
 				}
 			| a_expr NOT BETWEEN opt_asymmetric b_expr AND b_expr	%prec BETWEEN
 				{
-					$$ = (Node *) makeA_Expr(AEXPR_OR, NIL,
+					$$ = makeOrExpr(
 						(Node *) makeSimpleA_Expr(AEXPR_OP, "<", $1, $5, @2),
 						(Node *) makeSimpleA_Expr(AEXPR_OP, ">", $1, $7, @2),
-											 @2);
+									@2);
 				}
 			| a_expr BETWEEN SYMMETRIC b_expr AND b_expr			%prec BETWEEN
 				{
-					$$ = (Node *) makeA_Expr(AEXPR_OR, NIL,
-						(Node *) makeA_Expr(AEXPR_AND, NIL,
+					$$ = makeOrExpr(
+						  makeAndExpr(
 							(Node *) makeSimpleA_Expr(AEXPR_OP, ">=", $1, $4, @2),
 							(Node *) makeSimpleA_Expr(AEXPR_OP, "<=", $1, $6, @2),
-											@2),
-						(Node *) makeA_Expr(AEXPR_AND, NIL,
+									  @2),
+						  makeAndExpr(
 							(Node *) makeSimpleA_Expr(AEXPR_OP, ">=", $1, $6, @2),
 							(Node *) makeSimpleA_Expr(AEXPR_OP, "<=", $1, $4, @2),
-											@2),
-											 @2);
+									  @2),
+									@2);
 				}
 			| a_expr NOT BETWEEN SYMMETRIC b_expr AND b_expr		%prec BETWEEN
 				{
-					$$ = (Node *) makeA_Expr(AEXPR_AND, NIL,
-						(Node *) makeA_Expr(AEXPR_OR, NIL,
+					$$ = makeAndExpr(
+						   makeOrExpr(
 							(Node *) makeSimpleA_Expr(AEXPR_OP, "<", $1, $5, @2),
 							(Node *) makeSimpleA_Expr(AEXPR_OP, ">", $1, $7, @2),
-											@2),
-						(Node *) makeA_Expr(AEXPR_OR, NIL,
+									  @2),
+						   makeOrExpr(
 							(Node *) makeSimpleA_Expr(AEXPR_OP, "<", $1, $7, @2),
 							(Node *) makeSimpleA_Expr(AEXPR_OP, ">", $1, $5, @2),
-											@2),
-											 @2);
+									  @2),
+									 @2);
 				}
 			| a_expr IN_P in_expr
 				{
@@ -11114,7 +11115,7 @@ a_expr:		c_expr									{ $$ = $1; }
 						n->operName = list_make1(makeString("="));
 						n->location = @3;
 						/* Stick a NOT on top */
-						$$ = (Node *) makeA_Expr(AEXPR_NOT, NIL, NULL, (Node *) n, @2);
+						$$ = makeNotExpr((Node *) n, @2);
 					}
 					else
 					{
@@ -11162,10 +11163,9 @@ a_expr:		c_expr									{ $$ = $1; }
 				}
 			| a_expr IS NOT DOCUMENT_P				%prec IS
 				{
-					$$ = (Node *) makeA_Expr(AEXPR_NOT, NIL, NULL,
-											 makeXmlExpr(IS_DOCUMENT, NULL, NIL,
-														 list_make1($1), @2),
-											 @2);
+					$$ = makeNotExpr(makeXmlExpr(IS_DOCUMENT, NULL, NIL,
+												 list_make1($1), @2),
+									 @2);
 				}
 		;
 
@@ -11216,8 +11216,9 @@ b_expr:		c_expr
 				}
 			| b_expr IS NOT DISTINCT FROM b_expr	%prec IS
 				{
-					$$ = (Node *) makeA_Expr(AEXPR_NOT, NIL,
-						NULL, (Node *) makeSimpleA_Expr(AEXPR_DISTINCT, "=", $1, $6, @2), @2);
+					$$ = makeNotExpr((Node *) makeSimpleA_Expr(AEXPR_DISTINCT,
+															   "=", $1, $6, @2),
+									 @2);
 				}
 			| b_expr IS OF '(' type_list ')'		%prec IS
 				{
@@ -11234,10 +11235,9 @@ b_expr:		c_expr
 				}
 			| b_expr IS NOT DOCUMENT_P				%prec IS
 				{
-					$$ = (Node *) makeA_Expr(AEXPR_NOT, NIL, NULL,
-											 makeXmlExpr(IS_DOCUMENT, NULL, NIL,
-														 list_make1($1), @2),
-											 @2);
+					$$ = makeNotExpr(makeXmlExpr(IS_DOCUMENT, NULL, NIL,
+												 list_make1($1), @2),
+									 @2);
 				}
 		;
 
@@ -13693,6 +13693,46 @@ doNegateFloat(Value *v)
 }
 
 static Node *
+makeAndExpr(Node *lexpr, Node *rexpr, int location)
+{
+	/* Flatten "a AND b AND c ..." to a single BoolExpr on sight */
+	if (IsA(lexpr, BoolExpr))
+	{
+		BoolExpr *blexpr = (BoolExpr *) lexpr;
+
+		if (blexpr->boolop == AND_EXPR)
+		{
+			blexpr->args = lappend(blexpr->args, rexpr);
+			return (Node *) blexpr;
+		}
+	}
+	return (Node *) makeBoolExpr(AND_EXPR, list_make2(lexpr, rexpr), location);
+}
+
+static Node *
+makeOrExpr(Node *lexpr, Node *rexpr, int location)
+{
+	/* Flatten "a OR b OR c ..." to a single BoolExpr on sight */
+	if (IsA(lexpr, BoolExpr))
+	{
+		BoolExpr *blexpr = (BoolExpr *) lexpr;
+
+		if (blexpr->boolop == OR_EXPR)
+		{
+			blexpr->args = lappend(blexpr->args, rexpr);
+			return (Node *) blexpr;
+		}
+	}
+	return (Node *) makeBoolExpr(OR_EXPR, list_make2(lexpr, rexpr), location);
+}
+
+static Node *
+makeNotExpr(Node *expr, int location)
+{
+	return (Node *) makeBoolExpr(NOT_EXPR, list_make1(expr), location);
+}
+
+static Node *
 makeAArrayExpr(List *elements, int location)
 {
 	A_ArrayExpr *n = makeNode(A_ArrayExpr);
diff --git a/src/backend/parser/parse_clause.c b/src/backend/parser/parse_clause.c
index fcee1379c0c..4931dcad3b6 100644
--- a/src/backend/parser/parse_clause.c
+++ b/src/backend/parser/parse_clause.c
@@ -332,7 +332,8 @@ transformJoinUsingClause(ParseState *pstate,
 						 RangeTblEntry *leftRTE, RangeTblEntry *rightRTE,
 						 List *leftVars, List *rightVars)
 {
-	Node	   *result = NULL;
+	Node	   *result;
+	List	   *andargs = NIL;
 	ListCell   *lvars,
 			   *rvars;
 
@@ -358,18 +359,16 @@ transformJoinUsingClause(ParseState *pstate,
 							 copyObject(lvar), copyObject(rvar),
 							 -1);
 
-		/* And combine into an AND clause, if multiple join columns */
-		if (result == NULL)
-			result = (Node *) e;
-		else
-		{
-			A_Expr	   *a;
-
-			a = makeA_Expr(AEXPR_AND, NIL, result, (Node *) e, -1);
-			result = (Node *) a;
-		}
+		/* Prepare to combine into an AND clause, if multiple join columns */
+		andargs = lappend(andargs, e);
 	}
 
+	/* Only need an AND if there's more than one join column */
+	if (list_length(andargs) == 1)
+		result = (Node *) linitial(andargs);
+	else
+		result = (Node *) makeBoolExpr(AND_EXPR, andargs, -1);
+
 	/*
 	 * Since the references are already Vars, and are certainly from the input
 	 * relations, we don't have to go through the same pushups that
diff --git a/src/backend/parser/parse_expr.c b/src/backend/parser/parse_expr.c
index 088224573f3..83e20db2768 100644
--- a/src/backend/parser/parse_expr.c
+++ b/src/backend/parser/parse_expr.c
@@ -41,15 +41,13 @@ bool		Transform_null_equals = false;
 static Node *transformExprRecurse(ParseState *pstate, Node *expr);
 static Node *transformParamRef(ParseState *pstate, ParamRef *pref);
 static Node *transformAExprOp(ParseState *pstate, A_Expr *a);
-static Node *transformAExprAnd(ParseState *pstate, A_Expr *a);
-static Node *transformAExprOr(ParseState *pstate, A_Expr *a);
-static Node *transformAExprNot(ParseState *pstate, A_Expr *a);
 static Node *transformAExprOpAny(ParseState *pstate, A_Expr *a);
 static Node *transformAExprOpAll(ParseState *pstate, A_Expr *a);
 static Node *transformAExprDistinct(ParseState *pstate, A_Expr *a);
 static Node *transformAExprNullIf(ParseState *pstate, A_Expr *a);
 static Node *transformAExprOf(ParseState *pstate, A_Expr *a);
 static Node *transformAExprIn(ParseState *pstate, A_Expr *a);
+static Node *transformBoolExpr(ParseState *pstate, BoolExpr *a);
 static Node *transformFuncCall(ParseState *pstate, FuncCall *fn);
 static Node *transformCaseExpr(ParseState *pstate, CaseExpr *c);
 static Node *transformSubLink(ParseState *pstate, SubLink *sublink);
@@ -223,15 +221,6 @@ transformExprRecurse(ParseState *pstate, Node *expr)
 					case AEXPR_OP:
 						result = transformAExprOp(pstate, a);
 						break;
-					case AEXPR_AND:
-						result = transformAExprAnd(pstate, a);
-						break;
-					case AEXPR_OR:
-						result = transformAExprOr(pstate, a);
-						break;
-					case AEXPR_NOT:
-						result = transformAExprNot(pstate, a);
-						break;
 					case AEXPR_OP_ANY:
 						result = transformAExprOpAny(pstate, a);
 						break;
@@ -258,6 +247,10 @@ transformExprRecurse(ParseState *pstate, Node *expr)
 				break;
 			}
 
+		case T_BoolExpr:
+			result = transformBoolExpr(pstate, (BoolExpr *) expr);
+			break;
+
 		case T_FuncCall:
 			result = transformFuncCall(pstate, (FuncCall *) expr);
 			break;
@@ -337,7 +330,6 @@ transformExprRecurse(ParseState *pstate, Node *expr)
 		case T_DistinctExpr:
 		case T_NullIfExpr:
 		case T_ScalarArrayOpExpr:
-		case T_BoolExpr:
 		case T_FieldSelect:
 		case T_FieldStore:
 		case T_RelabelType:
@@ -919,46 +911,6 @@ transformAExprOp(ParseState *pstate, A_Expr *a)
 }
 
 static Node *
-transformAExprAnd(ParseState *pstate, A_Expr *a)
-{
-	Node	   *lexpr = transformExprRecurse(pstate, a->lexpr);
-	Node	   *rexpr = transformExprRecurse(pstate, a->rexpr);
-
-	lexpr = coerce_to_boolean(pstate, lexpr, "AND");
-	rexpr = coerce_to_boolean(pstate, rexpr, "AND");
-
-	return (Node *) makeBoolExpr(AND_EXPR,
-								 list_make2(lexpr, rexpr),
-								 a->location);
-}
-
-static Node *
-transformAExprOr(ParseState *pstate, A_Expr *a)
-{
-	Node	   *lexpr = transformExprRecurse(pstate, a->lexpr);
-	Node	   *rexpr = transformExprRecurse(pstate, a->rexpr);
-
-	lexpr = coerce_to_boolean(pstate, lexpr, "OR");
-	rexpr = coerce_to_boolean(pstate, rexpr, "OR");
-
-	return (Node *) makeBoolExpr(OR_EXPR,
-								 list_make2(lexpr, rexpr),
-								 a->location);
-}
-
-static Node *
-transformAExprNot(ParseState *pstate, A_Expr *a)
-{
-	Node	   *rexpr = transformExprRecurse(pstate, a->rexpr);
-
-	rexpr = coerce_to_boolean(pstate, rexpr, "NOT");
-
-	return (Node *) makeBoolExpr(NOT_EXPR,
-								 list_make1(rexpr),
-								 a->location);
-}
-
-static Node *
 transformAExprOpAny(ParseState *pstate, A_Expr *a)
 {
 	Node	   *lexpr = transformExprRecurse(pstate, a->lexpr);
@@ -1238,6 +1190,42 @@ transformAExprIn(ParseState *pstate, A_Expr *a)
 }
 
 static Node *
+transformBoolExpr(ParseState *pstate, BoolExpr *a)
+{
+	List	   *args = NIL;
+	const char *opname;
+	ListCell   *lc;
+
+	switch (a->boolop)
+	{
+		case AND_EXPR:
+			opname = "AND";
+			break;
+		case OR_EXPR:
+			opname = "OR";
+			break;
+		case NOT_EXPR:
+			opname = "NOT";
+			break;
+		default:
+			elog(ERROR, "unrecognized boolop: %d", (int) a->boolop);
+			opname = NULL;		/* keep compiler quiet */
+			break;
+	}
+
+	foreach(lc, a->args)
+	{
+		Node	   *arg = (Node *) lfirst(lc);
+
+		arg = transformExprRecurse(pstate, arg);
+		arg = coerce_to_boolean(pstate, arg, opname);
+		args = lappend(args, arg);
+	}
+
+	return (Node *) makeBoolExpr(a->boolop, args, a->location);
+}
+
+static Node *
 transformFuncCall(ParseState *pstate, FuncCall *fn)
 {
 	List	   *targs;
@@ -2428,10 +2416,6 @@ make_row_comparison_op(ParseState *pstate, List *opname,
 	/*
 	 * For = and <> cases, we just combine the pairwise operators with AND or
 	 * OR respectively.
-	 *
-	 * Note: this is presently the only place where the parser generates
-	 * BoolExpr with more than two arguments.  Should be OK since the rest of
-	 * the system thinks BoolExpr is N-argument anyway.
 	 */
 	if (rctype == ROWCOMPARE_EQ)
 		return (Node *) makeBoolExpr(AND_EXPR, opexprs, location);