Constant Folding(null propagation)

markhamstra · Apr 28, 2014 · 2645d4f · 2645d4f
1 parent 3d9fb09
commit 2645d4f
Show file tree

Hide file tree

Showing 2 changed files with 49 additions and 2 deletions.
diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/predicates.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/predicates.scala
@@ -65,8 +65,7 @@ abstract class BinaryPredicate extends BinaryExpression with Predicate {
   def nullable = left.nullable || right.nullable
 }
 
-case class Not(child: Expression) extends Predicate with trees.UnaryNode[Expression] {
-  def references = child.references
+case class Not(child: Expression) extends UnaryExpression with Predicate {
   override def foldable = child.foldable
   def nullable = child.nullable
   override def toString = s"NOT $child"

diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala
@@ -94,11 +94,59 @@ object ConstantFolding extends Rule[LogicalPlan] {
     case q: LogicalPlan => q transformExpressionsDown {
       // Skip redundant folding of literals.
       case l: Literal => l
+      case e @ If(Literal(v, _), trueValue, falseValue) => if(v == true) trueValue else falseValue
+      case e @ In(Literal(v, _), list) if(list.exists(c => c match {
+          case Literal(candidate, _) if(candidate == v) => true
+          case _ => false
+        })) => Literal(true, BooleanType)
       case e if e.foldable => Literal(e.eval(null), e.dataType)
     }
   }
 }
 
+/**
+ * The expression may be constant value, due to one or more of its children expressions is null or 
+ * not null constantly, replaces [[catalyst.expressions.Expression Expressions]] with equivalent 
+ * [[catalyst.expressions.Literal Literal]] values if possible caused by that. 
+ */
+object NullPropagation extends Rule[LogicalPlan] {
+  def apply(plan: LogicalPlan): LogicalPlan = plan transform {
+    case q: LogicalPlan => q transformExpressionsUp {
+      case l: Literal => l
+      case e @ IsNull(Literal(null, _)) => Literal(true, BooleanType)
+      case e @ IsNull(Literal(_, _)) => Literal(false, BooleanType)
+      case e @ IsNull(c @ Rand) => Literal(false, BooleanType)
+      case e @ IsNotNull(Literal(null, _)) => Literal(false, BooleanType)
+      case e @ IsNotNull(Literal(_, _)) => Literal(true, BooleanType)
+      case e @ IsNotNull(c @ Rand) => Literal(true, BooleanType)
+      case e @ GetItem(Literal(null, _), _) => Literal(null, e.dataType)
+      case e @ GetItem(_, Literal(null, _)) => Literal(null, e.dataType)
+      case e @ GetField(Literal(null, _), _) => Literal(null, e.dataType)
+      case e @ Coalesce(children) => {
+        val newChildren = children.filter(c => c match {
+          case Literal(null, _) => false
+          case _ => true
+        })
+        if(newChildren.length == null) {
+          Literal(null, e.dataType)
+        } else if(newChildren.length == children.length){
+          e
+        } else {
+          Coalesce(newChildren)
+        }
+      }
+      // TODO put exceptional cases(Unary & Binary Expression) before here.
+      case e: UnaryExpression => e.child match {
+        case Literal(null, _) => Literal(null, e.dataType)
+      }
+      case e: BinaryExpression => e.children match {
+        case Literal(null, _) :: right :: Nil => Literal(null, e.dataType)
+        case left :: Literal(null, _) :: Nil => Literal(null, e.dataType)
+      }
+    }
+  }
+}
+
 /**
  * Simplifies boolean expressions where the answer can be determined without evaluating both sides.
  * Note that this rule can eliminate expressions that might otherwise have been evaluated and thus