[SQL] Add toString to DataFrame/Column

Author: Michael Armbrust <michael@databricks.com>

Closes #4436 from marmbrus/dfToString and squashes the following commits:

8a3c35f [Michael Armbrust] Merge remote-tracking branch 'origin/master' into dfToString
b72a81b [Michael Armbrust] add toString

2 files changed, 32 insertions, 0 deletions

diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Expression.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Expression.scala
index cf14992ef8..c32a4b886e 100644
--- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Expression.scala
+++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Expression.scala
@@ -17,6 +17,7 @@
 
 package org.apache.spark.sql.catalyst.expressions
 
+import org.apache.spark.sql.catalyst.analysis.UnresolvedAttribute
 import org.apache.spark.sql.catalyst.errors.TreeNodeException
 import org.apache.spark.sql.catalyst.trees
 import org.apache.spark.sql.catalyst.trees.TreeNode
@@ -67,6 +68,17 @@ abstract class Expression extends TreeNode[Expression] {
   def childrenResolved = !children.exists(!_.resolved)
 
   /**
+   * Returns a string representation of this expression that does not have developer centric
+   * debugging information like the expression id.
+   */
+  def prettyString: String = {
+    transform {
+      case a: AttributeReference => PrettyAttribute(a.name)
+      case u: UnresolvedAttribute => PrettyAttribute(u.name)
+    }.toString
+  }
+
+  /**
    * A set of helper functions that return the correct descendant of `scala.math.Numeric[T]` type
    * and do any casting necessary of child evaluation.
    */
diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/namedExpressions.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/namedExpressions.scala
index e6ab1fd8d7..7f122e9d55 100644
--- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/namedExpressions.scala
+++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/namedExpressions.scala
@@ -190,6 +190,26 @@ case class AttributeReference(
   override def toString: String = s"$name#${exprId.id}$typeSuffix"
 }
 
+/**
+ * A place holder used when printing expressions without debugging information such as the
+ * expression id or the unresolved indicator.
+ */
+case class PrettyAttribute(name: String) extends Attribute with trees.LeafNode[Expression] {
+  type EvaluatedType = Any
+
+  override def toString = name
+
+  override def withNullability(newNullability: Boolean): Attribute = ???
+  override def newInstance(): Attribute = ???
+  override def withQualifiers(newQualifiers: Seq[String]): Attribute = ???
+  override def withName(newName: String): Attribute = ???
+  override def qualifiers: Seq[String] = ???
+  override def exprId: ExprId = ???
+  override def eval(input: Row): EvaluatedType = ???
+  override def nullable: Boolean = ???
+  override def dataType: DataType = ???
+}
+
 object VirtualColumn {
   val groupingIdName = "grouping__id"
   def newGroupingId = AttributeReference(groupingIdName, IntegerType, false)()