[SPARK-13895][SQL] DataFrameReader.text should return Dataset[String]

## What changes were proposed in this pull request?
This patch changes DataFrameReader.text()'s return type from DataFrame to Dataset[String].

Closes #11731.

## How was this patch tested?
Updated existing integration tests to reflect the change.

Author: Reynold Xin <rxin@databricks.com>

Closes #11739 from rxin/SPARK-13895.

1 files changed, 8 insertions, 4 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
index 57c978bec8..ef85f1db89 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/DataFrameReader.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/DataFrameReader.scala
@@ -399,8 +399,10 @@ class DataFrameReader private[sql](sqlContext: SQLContext) extends Logging {
   }
 
   /**
-   * Loads a text file and returns a [[DataFrame]] with a single string column named "value".
-   * Each line in the text file is a new row in the resulting DataFrame. For example:
+   * Loads a text file and returns a [[Dataset]] of String. The underlying schema of the Dataset
+   * contains a single string column named "value".
+   *
+   * Each line in the text file is a new row in the resulting Dataset. For example:
    * {{{
    *   // Scala:
    *   sqlContext.read.text("/path/to/spark/README.md")
@@ -410,10 +412,12 @@ class DataFrameReader private[sql](sqlContext: SQLContext) extends Logging {
    * }}}
    *
    * @param paths input path
-   * @since 1.6.0
+   * @since 2.0.0
    */
   @scala.annotation.varargs
-  def text(paths: String*): DataFrame = format("text").load(paths : _*)
+  def text(paths: String*): Dataset[String] = {
+    format("text").load(paths : _*).as[String](sqlContext.implicits.newStringEncoder)
+  }
 
   ///////////////////////////////////////////////////////////////////////////////////////
   // Builder pattern config options