[SPARK-8686] [SQL] DataFrame should support `where` with expression represented by String

DataFrame supports `filter` function with two types of argument, `Column` and `String`. But `where` doesn't.

Author: Kousuke Saruta <sarutak@oss.nttdata.co.jp>

Closes #7063 from sarutak/SPARK-8686 and squashes the following commits:

180f9a4 [Kousuke Saruta] Added test
d61aec4 [Kousuke Saruta] Add "where" method with String argument to DataFrame

2 files changed, 18 insertions, 0 deletions

diff --git a/sql/core/src/main/scala/org/apache/spark/sql/DataFrame.scala b/sql/core/src/main/scala/org/apache/spark/sql/DataFrame.scala
index 0db4df34f9..d75d883075 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/DataFrame.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/DataFrame.scala
@@ -715,6 +715,18 @@ class DataFrame private[sql](
   def where(condition: Column): DataFrame = filter(condition)
 
   /**
+   * Filters rows using the given SQL expression.
+   * {{{
+   *   peopleDf.where("age > 15")
+   * }}}
+   * @group dfops
+   * @since 1.5.0
+   */
+  def where(conditionExpr: String): DataFrame = {
+    filter(Column(new SqlParser().parseExpression(conditionExpr)))
+  }
+
+  /**
    * Groups the [[DataFrame]] using the specified columns, so we can run aggregation on them.
    * See [[GroupedData]] for all the available aggregate functions.
    *
diff --git a/sql/core/src/test/scala/org/apache/spark/sql/DataFrameSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/DataFrameSuite.scala
index 47443a917b..d06b9c5785 100644
--- a/sql/core/src/test/scala/org/apache/spark/sql/DataFrameSuite.scala
+++ b/sql/core/src/test/scala/org/apache/spark/sql/DataFrameSuite.scala
@@ -160,6 +160,12 @@ class DataFrameSuite extends QueryTest {
       testData.collect().filter(_.getInt(0) > 90).toSeq)
   }
 
+  test("filterExpr using where") {
+    checkAnswer(
+      testData.where("key > 50"),
+      testData.collect().filter(_.getInt(0) > 50).toSeq)
+  }
+
   test("repartition") {
     checkAnswer(
       testData.select('key).repartition(10).select('key),