Add inputSet, references to QueryPlan. Improve tree string with a prefix to denote invalid or unresolved nodes.

Author: marmbrus

sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/QueryPlan.scala

@@ -31,6 +31,25 @@ abstract class QueryPlan[PlanType <: TreeNode[PlanType]] extends TreeNode[PlanTy
    */
   def outputSet: AttributeSet = AttributeSet(output)
 
+  /**
+   * All Attributes that appear in expressions from this operator.  Note that this set does not
+   * include attributes that are implicitly referenced by being passed through to the output tuple.
+   */
+  def references: AttributeSet = AttributeSet(expressions.flatMap(_.references))
+
+  /**
+   * The set of all attributes that are input to this operator by its children.
+   */
+  def inputSet: AttributeSet =
+    AttributeSet(children.flatMap(_.asInstanceOf[QueryPlan[PlanType]].output))
+
+  /**
+   * Attributes that are referenced by expressions but not provided by this nodes children.
+   * Subclasses should override this method if they produce attributes internally as it is used by
+   * assertions designed to prevent the construction of invalid plans.
+   */
+  def missingInput: AttributeSet = references -- inputSet
+
   /**
    * Runs [[transform]] with `rule` on all expressions present in this query operator.
    * Users should not expect a specific directionality. If a specific directionality is needed,
@@ -132,4 +151,8 @@ abstract class QueryPlan[PlanType <: TreeNode[PlanType]] extends TreeNode[PlanTy
 
   /** Prints out the schema in the tree format */
   def printSchema(): Unit = println(schemaString)
+
+  protected def statePrefix = if (missingInput.nonEmpty && children.nonEmpty) "!" else ""
+
+  override def simpleString = statePrefix + super.simpleString
 }

sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/LogicalPlan.scala

@@ -53,12 +53,6 @@ abstract class LogicalPlan extends QueryPlan[LogicalPlan] with Logging {
       sizeInBytes = children.map(_.statistics).map(_.sizeInBytes).product)
   }
 
-  /**
-   * Returns the set of attributes that this node takes as
-   * input from its children.
-   */
-  lazy val inputSet: AttributeSet = AttributeSet(children.flatMap(_.output))
-
   /**
    * Returns true if this expression and all its children have been resolved to a specific schema
    * and false if it still contains any unresolved placeholders. Implementations of LogicalPlan
@@ -68,6 +62,8 @@ abstract class LogicalPlan extends QueryPlan[LogicalPlan] with Logging {
    */
   lazy val resolved: Boolean = !expressions.exists(!_.resolved) && childrenResolved
 
+  override protected def statePrefix = if (!resolved) "'" else super.statePrefix
+
   /**
    * Returns true if all its children of this query plan have been resolved.
    */

sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/basicOperators.scala

@@ -138,11 +138,6 @@ case class Aggregate(
     child: LogicalPlan)
   extends UnaryNode {
 
-  /** The set of all AttributeReferences required for this aggregation. */
-  def references =
-    AttributeSet(
-      groupingExpressions.flatMap(_.references) ++ aggregateExpressions.flatMap(_.references))
-
   override def output = aggregateExpressions.map(_.toAttribute)
 }