From 588cac414a9cf1e0f40a82cc6a78f77e26825f29 Mon Sep 17 00:00:00 2001
From: Andrew Or <andrew@databricks.com>
Date: Tue, 3 May 2016 13:47:58 -0700
Subject: [PATCH] [SPARK-15073][SQL] Hide SparkSession constructor from the
 public

## What changes were proposed in this pull request?

Users should use the builder pattern instead.

## How was this patch tested?

Jenks.

Author: Andrew Or <andrew@databricks.com>

Closes #12873 from andrewor14/spark-session-constructor.
---
 .../apache/spark/examples/sql/RDDRelation.scala    |  9 +++------
 .../scala/org/apache/spark/repl/SparkILoop.scala   |  4 ++--
 .../main/scala/org/apache/spark/repl/Main.scala    |  4 ++--
 .../scala/org/apache/spark/sql/SparkSession.scala  | 14 ++++++++++++--
 4 files changed, 19 insertions(+), 12 deletions(-)

diff --git a/examples/src/main/scala/org/apache/spark/examples/sql/RDDRelation.scala b/examples/src/main/scala/org/apache/spark/examples/sql/RDDRelation.scala
index 8ce4427c53..b4118b16e2 100644
--- a/examples/src/main/scala/org/apache/spark/examples/sql/RDDRelation.scala
+++ b/examples/src/main/scala/org/apache/spark/examples/sql/RDDRelation.scala
@@ -18,7 +18,6 @@
 // scalastyle:off println
 package org.apache.spark.examples.sql
 
-import org.apache.spark.{SparkConf, SparkContext}
 import org.apache.spark.sql.{SaveMode, SparkSession}
 
 // One method for defining the schema of an RDD is to make a case class with the desired column
@@ -27,14 +26,12 @@ case class Record(key: Int, value: String)
 
 object RDDRelation {
   def main(args: Array[String]) {
-    val sparkConf = new SparkConf().setAppName("RDDRelation")
-    val sc = new SparkContext(sparkConf)
-    val spark = new SparkSession(sc)
+    val spark = SparkSession.builder.appName("RDDRelation").getOrCreate()
 
     // Importing the SparkSession gives access to all the SQL functions and implicit conversions.
     import spark.implicits._
 
-    val df = sc.parallelize((1 to 100).map(i => Record(i, s"val_$i"))).toDF()
+    val df = spark.createDataFrame((1 to 100).map(i => Record(i, s"val_$i")))
     // Any RDD containing case classes can be registered as a table.  The schema of the table is
     // automatically inferred using scala reflection.
     df.registerTempTable("records")
@@ -70,7 +67,7 @@ object RDDRelation {
     parquetFile.registerTempTable("parquetFile")
     spark.sql("SELECT * FROM parquetFile").collect().foreach(println)
 
-    sc.stop()
+    spark.stop()
   }
 }
 // scalastyle:on println
diff --git a/repl/scala-2.10/src/main/scala/org/apache/spark/repl/SparkILoop.scala b/repl/scala-2.10/src/main/scala/org/apache/spark/repl/SparkILoop.scala
index 6a811adcf9..c4f64505a2 100644
--- a/repl/scala-2.10/src/main/scala/org/apache/spark/repl/SparkILoop.scala
+++ b/repl/scala-2.10/src/main/scala/org/apache/spark/repl/SparkILoop.scala
@@ -1030,10 +1030,10 @@ class SparkILoop(
   def createSparkSession(): SparkSession = {
     if (SparkSession.hiveClassesArePresent) {
       logInfo("Creating Spark session with Hive support")
-      SparkSession.withHiveSupport(sparkContext)
+      SparkSession.builder.enableHiveSupport().getOrCreate()
     } else {
       logInfo("Creating Spark session")
-      new SparkSession(sparkContext)
+      SparkSession.builder.getOrCreate()
     }
   }
 
diff --git a/repl/scala-2.11/src/main/scala/org/apache/spark/repl/Main.scala b/repl/scala-2.11/src/main/scala/org/apache/spark/repl/Main.scala
index 8e381ff6ae..a171759809 100644
--- a/repl/scala-2.11/src/main/scala/org/apache/spark/repl/Main.scala
+++ b/repl/scala-2.11/src/main/scala/org/apache/spark/repl/Main.scala
@@ -94,10 +94,10 @@ object Main extends Logging {
 
   def createSparkSession(): SparkSession = {
     if (SparkSession.hiveClassesArePresent) {
-      sparkSession = SparkSession.withHiveSupport(sparkContext)
+      sparkSession = SparkSession.builder.enableHiveSupport().getOrCreate()
       logInfo("Created Spark session with Hive support")
     } else {
-      sparkSession = new SparkSession(sparkContext)
+      sparkSession = SparkSession.builder.getOrCreate()
       logInfo("Created Spark session")
     }
     sparkSession
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/SparkSession.scala b/sql/core/src/main/scala/org/apache/spark/sql/SparkSession.scala
index 3836ce2daa..aa7c335c53 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/SparkSession.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/SparkSession.scala
@@ -54,6 +54,7 @@ import org.apache.spark.util.Utils
  * {{{
  *   SparkSession.builder()
  *     .master("local")
+ *     .appName("Word Count")
  *     .config("spark.some.config.option", "some-value").
  *     .getOrCreate()
  * }}}
@@ -63,7 +64,7 @@ class SparkSession private(
     @transient private val existingSharedState: Option[SharedState])
   extends Serializable with Logging { self =>
 
-  def this(sc: SparkContext) {
+  private[sql] def this(sc: SparkContext) {
     this(sc, None)
   }
 
@@ -573,7 +574,7 @@ class SparkSession private(
    * common Scala objects into [[DataFrame]]s.
    *
    * {{{
-   *   val sparkSession = new SparkSession(sc)
+   *   val sparkSession = SparkSession.builder.getOrCreate()
    *   import sparkSession.implicits._
    * }}}
    *
@@ -586,6 +587,15 @@ class SparkSession private(
   }
   // scalastyle:on
 
+  /**
+   * Stop the underlying [[SparkContext]].
+   *
+   * @since 2.0.0
+   */
+  def stop(): Unit = {
+    sparkContext.stop()
+  }
+
   protected[sql] def parseSql(sql: String): LogicalPlan = {
     sessionState.sqlParser.parsePlan(sql)
   }