From 998f4ff94df1d9db1c9e32c04091017c25cd4e81 Mon Sep 17 00:00:00 2001
From: Reynold Xin <rxin@databricks.com>
Date: Fri, 7 Aug 2015 19:09:28 -0700
Subject: [PATCH] [SPARK-9754][SQL] Remove TypeCheck in debug package.

TypeCheck no longer applies in the new "Tungsten" world.

Author: Reynold Xin <rxin@databricks.com>

Closes #8043 from rxin/SPARK-9754 and squashes the following commits:

4ec471e [Reynold Xin] [SPARK-9754][SQL] Remove TypeCheck in debug package.
---
 .../spark/sql/execution/debug/package.scala   | 104 +-----------------
 .../sql/execution/debug/DebuggingSuite.scala  |   4 -
 2 files changed, 4 insertions(+), 104 deletions(-)

diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/debug/package.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/debug/package.scala
index dd3858ea2b520..74892e4e13fa4 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/execution/debug/package.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/debug/package.scala
@@ -17,21 +17,16 @@
 
 package org.apache.spark.sql.execution
 
-import org.apache.spark.rdd.RDD
-import org.apache.spark.sql.catalyst.InternalRow
-import org.apache.spark.sql.catalyst.expressions.Attribute
-import org.apache.spark.unsafe.types.UTF8String
-
 import scala.collection.mutable.HashSet
 
-import org.apache.spark.{AccumulatorParam, Accumulator, Logging}
-import org.apache.spark.annotation.DeveloperApi
+import org.apache.spark.rdd.RDD
 import org.apache.spark.sql._
+import org.apache.spark.sql.catalyst.InternalRow
+import org.apache.spark.sql.catalyst.expressions.Attribute
 import org.apache.spark.sql.catalyst.trees.TreeNodeRef
-import org.apache.spark.sql.types._
+import org.apache.spark.{Accumulator, AccumulatorParam, Logging}
 
 /**
- * :: DeveloperApi ::
  * Contains methods for debugging query execution.
  *
  * Usage:
@@ -53,10 +48,8 @@ package object debug {
   }
 
   /**
-   * :: DeveloperApi ::
    * Augments [[DataFrame]]s with debug methods.
    */
-  @DeveloperApi
   implicit class DebugQuery(query: DataFrame) extends Logging {
     def debug(): Unit = {
       val plan = query.queryExecution.executedPlan
@@ -72,23 +65,6 @@ package object debug {
         case _ =>
       }
     }
-
-    def typeCheck(): Unit = {
-      val plan = query.queryExecution.executedPlan
-      val visited = new collection.mutable.HashSet[TreeNodeRef]()
-      val debugPlan = plan transform {
-        case s: SparkPlan if !visited.contains(new TreeNodeRef(s)) =>
-          visited += new TreeNodeRef(s)
-          TypeCheck(s)
-      }
-      try {
-        logDebug(s"Results returned: ${debugPlan.execute().count()}")
-      } catch {
-        case e: Exception =>
-          def unwrap(e: Throwable): Throwable = if (e.getCause == null) e else unwrap(e.getCause)
-          logDebug(s"Deepest Error: ${unwrap(e)}")
-      }
-    }
   }
 
   private[sql] case class DebugNode(child: SparkPlan) extends UnaryNode {
@@ -148,76 +124,4 @@ package object debug {
       }
     }
   }
-
-  /**
-   * Helper functions for checking that runtime types match a given schema.
-   */
-  private[sql] object TypeCheck {
-    def typeCheck(data: Any, schema: DataType): Unit = (data, schema) match {
-      case (null, _) =>
-
-      case (row: InternalRow, s: StructType) =>
-        row.toSeq(s).zip(s.map(_.dataType)).foreach { case(d, t) => typeCheck(d, t) }
-      case (a: ArrayData, ArrayType(elemType, _)) =>
-        a.foreach(elemType, (_, e) => {
-          typeCheck(e, elemType)
-        })
-      case (m: MapData, MapType(keyType, valueType, _)) =>
-        m.keyArray().foreach(keyType, (_, e) => {
-          typeCheck(e, keyType)
-        })
-        m.valueArray().foreach(valueType, (_, e) => {
-          typeCheck(e, valueType)
-        })
-
-      case (_: Long, LongType) =>
-      case (_: Int, IntegerType) =>
-      case (_: UTF8String, StringType) =>
-      case (_: Float, FloatType) =>
-      case (_: Byte, ByteType) =>
-      case (_: Short, ShortType) =>
-      case (_: Boolean, BooleanType) =>
-      case (_: Double, DoubleType) =>
-      case (_: Int, DateType) =>
-      case (_: Long, TimestampType) =>
-      case (v, udt: UserDefinedType[_]) => typeCheck(v, udt.sqlType)
-
-      case (d, t) => sys.error(s"Invalid data found: got $d (${d.getClass}) expected $t")
-    }
-  }
-
-  /**
-   * Augments [[DataFrame]]s with debug methods.
-   */
-  private[sql] case class TypeCheck(child: SparkPlan) extends SparkPlan {
-    import TypeCheck._
-
-    override def nodeName: String = ""
-
-    /* Only required when defining this class in a REPL.
-    override def makeCopy(args: Array[Object]): this.type =
-      TypeCheck(args(0).asInstanceOf[SparkPlan]).asInstanceOf[this.type]
-    */
-
-    def output: Seq[Attribute] = child.output
-
-    def children: List[SparkPlan] = child :: Nil
-
-    protected override def doExecute(): RDD[InternalRow] = {
-      child.execute().map { row =>
-        try typeCheck(row, child.schema) catch {
-          case e: Exception =>
-            sys.error(
-              s"""
-                  |ERROR WHEN TYPE CHECKING QUERY
-                  |==============================
-                  |$e
-                  |======== BAD TREE ============
-                  |$child
-             """.stripMargin)
-        }
-        row
-      }
-    }
-  }
 }
diff --git a/sql/core/src/test/scala/org/apache/spark/sql/execution/debug/DebuggingSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/execution/debug/DebuggingSuite.scala
index 8ec3985e00360..239deb7973845 100644
--- a/sql/core/src/test/scala/org/apache/spark/sql/execution/debug/DebuggingSuite.scala
+++ b/sql/core/src/test/scala/org/apache/spark/sql/execution/debug/DebuggingSuite.scala
@@ -25,8 +25,4 @@ class DebuggingSuite extends SparkFunSuite {
   test("DataFrame.debug()") {
     testData.debug()
   }
-
-  test("DataFrame.typeCheck()") {
-    testData.typeCheck()
-  }
 }