[SPARK-18260] Make from_json null safe

## What changes were proposed in this pull request? `from_json` is currently not safe against `null` rows. This PR adds a fix and a regression test for it. ## How was this patch tested? Regression test Author: Burak Yavuz <[email protected]> Closes apache#15771 from brkyvz/json_fix.
DoufuX · Nov 5, 2016 · 6e27018 · 6e27018
1 parent 8a9ca19
commit 6e27018
Show file tree

Hide file tree

Showing 2 changed files with 11 additions and 1 deletion.
diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/jsonExpressions.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/jsonExpressions.scala
@@ -498,7 +498,9 @@ case class JsonToStruct(schema: StructType, options: Map[String, String], child:
   override def children: Seq[Expression] = child :: Nil
 
   override def eval(input: InternalRow): Any = {
-    try parser.parse(child.eval(input).toString).head catch {
+    val json = child.eval(input)
+    if (json == null) return null
+    try parser.parse(json.toString).head catch {
       case _: SparkSQLJsonProcessingException => null
     }
   }

diff --git a/...alyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/JsonExpressionsSuite.scala b/...alyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/JsonExpressionsSuite.scala
@@ -344,6 +344,14 @@ class JsonExpressionsSuite extends SparkFunSuite with ExpressionEvalHelper {
     )
   }
 
+  test("from_json null input column") {
+    val schema = StructType(StructField("a", IntegerType) :: Nil)
+    checkEvaluation(
+      JsonToStruct(schema, Map.empty, Literal(null)),
+      null
+    )
+  }
+
   test("to_json") {
     val schema = StructType(StructField("a", IntegerType) :: Nil)
     val struct = Literal.create(create_row(1), schema)