Repository: spark Updated Branches: refs/heads/master fd6c3a0b1 -> d5593f7f5
[SPARK-19543] from_json fails when the input row is empty ## 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 <brk...@gmail.com> Closes #16881 from brkyvz/json-fix. Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/d5593f7f Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/d5593f7f Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/d5593f7f Branch: refs/heads/master Commit: d5593f7f5794bd0343e783ac4957864fed9d1b38 Parents: fd6c3a0 Author: Burak Yavuz <brk...@gmail.com> Authored: Fri Feb 10 12:55:06 2017 +0100 Committer: Herman van Hovell <hvanhov...@databricks.com> Committed: Fri Feb 10 12:55:06 2017 +0100 ---------------------------------------------------------------------- .../spark/sql/catalyst/expressions/jsonExpressions.scala | 2 +- .../sql/catalyst/expressions/JsonExpressionsSuite.scala | 8 ++++++++ 2 files changed, 9 insertions(+), 1 deletion(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/spark/blob/d5593f7f/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/jsonExpressions.scala ---------------------------------------------------------------------- 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 index d55f85d..c410e79 100644 --- 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 } } http://git-wip-us.apache.org/repos/asf/spark/blob/d5593f7f/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/JsonExpressionsSuite.scala ---------------------------------------------------------------------- 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 index 618b8b2..8e20bd1 100644 --- 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) --------------------------------------------------------------------- To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org For additional commands, e-mail: commits-h...@spark.apache.org