[SPARK-19543] from_json fails when the input row is empty

brkyvz · hvanhovell · commit d5593f7f5794 · 2017-02-10T12:55:06.000+01:00
## What changes were proposed in this pull request? Using from_json on a column with an empty string results in: java.util.NoSuchElementException: head of empty list. This is because `parser.parse(input)` may return `Nil` when `input.trim.isEmpty` ## How was this patch tested? Regression test in `JsonExpressionsSuite` Author: Burak Yavuz <brkyvz@gmail.com> Closes #16881 from brkyvz/json-fix.
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
@@ -496,7 +496,7 @@ case class JsonToStruct(schema: StructType, options: Map[String, String], child:
   override def dataType: DataType = schema
 
   override def nullSafeEval(json: Any): Any = {
-    try parser.parse(json.toString).head catch {
+    try parser.parse(json.toString).headOption.orNull catch {
       case _: SparkSQLJsonProcessingException => null
     }
   }
diff --git a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/JsonExpressionsSuite.scala b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/JsonExpressionsSuite.scala
@@ -376,6 +376,14 @@ class JsonExpressionsSuite extends SparkFunSuite with ExpressionEvalHelper {
     )
   }
 
+  test("SPARK-19543: from_json empty input column") {
+    val schema = StructType(StructField("a", IntegerType) :: Nil)
+    checkEvaluation(
+      JsonToStruct(schema, Map.empty, Literal.create(" ", StringType)),
+      null
+    )
+  }
+
   test("to_json") {
     val schema = StructType(StructField("a", IntegerType) :: Nil)
     val struct = Literal.create(create_row(1), schema)

Original file line number	Diff line number	Diff line change
`@@ -496,7 +496,7 @@ case class JsonToStruct(schema: StructType, options: Map[String, String], child:`
`496`	`496`	`override def dataType: DataType = schema`
`497`	`497`
`498`	`498`	`override def nullSafeEval(json: Any): Any = {`
`499`		`- try parser.parse(json.toString).head catch {`
	`499`	`+ try parser.parse(json.toString).headOption.orNull catch {`
`500`	`500`	`case _: SparkSQLJsonProcessingException => null`
`501`	`501`	`}`
`502`	`502`	`}`
Original file line number	Diff line number	Diff line change
`@@ -376,6 +376,14 @@ class JsonExpressionsSuite extends SparkFunSuite with ExpressionEvalHelper {`
`376`	`376`	`)`
`377`	`377`	`}`
`378`	`378`
	`379`	`+ test("SPARK-19543: from_json empty input column") {`
	`380`	`+ val schema = StructType(StructField("a", IntegerType) :: Nil)`
	`381`	`+ checkEvaluation(`
	`382`	`+ JsonToStruct(schema, Map.empty, Literal.create(" ", StringType)),`
	`383`	`+ null`
	`384`	`+ )`
	`385`	`+ }`
	`386`	`+`
`379`	`387`	`test("to_json") {`
`380`	`388`	`val schema = StructType(StructField("a", IntegerType) :: Nil)`
`381`	`389`	`val struct = Literal.create(create_row(1), schema)`