[SPARK-13187][SQL] Add boolean/long/double options in DataFrameReader…

…/Writer This patch adds option function for boolean, long, and double types. This makes it slightly easier for Spark users to specify options without turning them into strings. Using the JSON data source as an example. Before this patch: ```scala sqlContext.read.option("primitivesAsString", "true").json("/path/to/json") ``` After this patch: Before this patch: ```scala sqlContext.read.option("primitivesAsString", true).json("/path/to/json") ``` Author: Reynold Xin <rxin@databricks.com> Closes apache#11072 from rxin/SPARK-13187.
anantmalhotra · Feb 5, 2016 · 82d84ff · 82d84ff
1 parent 352102e
commit 82d84ff
Show file tree

Hide file tree

Showing 3 changed files with 67 additions and 0 deletions.
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/DataFrameReader.scala b/sql/core/src/main/scala/org/apache/spark/sql/DataFrameReader.scala
@@ -78,6 +78,27 @@ class DataFrameReader private[sql](sqlContext: SQLContext) extends Logging {
     this
   }
 
+  /**
+   * Adds an input option for the underlying data source.
+   *
+   * @since 2.0.0
+   */
+  def option(key: String, value: Boolean): DataFrameReader = option(key, value.toString)
+
+  /**
+   * Adds an input option for the underlying data source.
+   *
+   * @since 2.0.0
+   */
+  def option(key: String, value: Long): DataFrameReader = option(key, value.toString)
+
+  /**
+   * Adds an input option for the underlying data source.
+   *
+   * @since 2.0.0
+   */
+  def option(key: String, value: Double): DataFrameReader = option(key, value.toString)
+
   /**
    * (Scala-specific) Adds input options for the underlying data source.
    *

diff --git a/sql/core/src/main/scala/org/apache/spark/sql/DataFrameWriter.scala b/sql/core/src/main/scala/org/apache/spark/sql/DataFrameWriter.scala
@@ -95,6 +95,27 @@ final class DataFrameWriter private[sql](df: DataFrame) {
     this
   }
 
+  /**
+   * Adds an output option for the underlying data source.
+   *
+   * @since 2.0.0
+   */
+  def option(key: String, value: Boolean): DataFrameWriter = option(key, value.toString)
+
+  /**
+   * Adds an output option for the underlying data source.
+   *
+   * @since 2.0.0
+   */
+  def option(key: String, value: Long): DataFrameWriter = option(key, value.toString)
+
+  /**
+   * Adds an output option for the underlying data source.
+   *
+   * @since 2.0.0
+   */
+  def option(key: String, value: Double): DataFrameWriter = option(key, value.toString)
+
   /**
    * (Scala-specific) Adds output options for the underlying data source.
    *

diff --git a/sql/core/src/test/scala/org/apache/spark/sql/streaming/DataStreamReaderSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/streaming/DataStreamReaderSuite.scala
@@ -162,4 +162,29 @@ class DataStreamReaderWriterSuite extends StreamTest with SharedSQLContext {
     assert(LastOptions.parameters("path") == "/test")
   }
 
+  test("test different data types for options") {
+    val df = sqlContext.read
+      .format("org.apache.spark.sql.streaming.test")
+      .option("intOpt", 56)
+      .option("boolOpt", false)
+      .option("doubleOpt", 6.7)
+      .stream("/test")
+
+    assert(LastOptions.parameters("intOpt") == "56")
+    assert(LastOptions.parameters("boolOpt") == "false")
+    assert(LastOptions.parameters("doubleOpt") == "6.7")
+
+    LastOptions.parameters = null
+    df.write
+      .format("org.apache.spark.sql.streaming.test")
+      .option("intOpt", 56)
+      .option("boolOpt", false)
+      .option("doubleOpt", 6.7)
+      .stream("/test")
+      .stop()
+
+    assert(LastOptions.parameters("intOpt") == "56")
+    assert(LastOptions.parameters("boolOpt") == "false")
+    assert(LastOptions.parameters("doubleOpt") == "6.7")
+  }
 }