You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@spark.apache.org by "Maxim Gekk (Jira)" <ji...@apache.org> on 2020/10/13 16:17:00 UTC
[jira] [Updated] (SPARK-33134) Incorrect nested complex JSON fields
raise an exception
[ https://issues.apache.org/jira/browse/SPARK-33134?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Maxim Gekk updated SPARK-33134:
-------------------------------
Description:
The code below:
{code:scala}
val pokerhand_raw = Seq("""[{"cards": [11], "playerId": 583651}]""").toDF("events")
val event = new StructType()
.add("playerId", LongType)
.add("cards", ArrayType(
new StructType()
.add("id", LongType)
.add("rank", StringType)))
val pokerhand_events = pokerhand_raw
.select(explode(from_json($"events", ArrayType(event))).as("event"))
pokerhand_events.show
{code}
throw the exception in the PERMISSIVE mode (default):
{code:java}
Caused by: java.lang.ClassCastException: java.lang.Long cannot be cast to org.apache.spark.sql.catalyst.util.ArrayData
at org.apache.spark.sql.catalyst.expressions.BaseGenericInternalRow.getArray(rows.scala:48)
at org.apache.spark.sql.catalyst.expressions.BaseGenericInternalRow.getArray$(rows.scala:48)
at org.apache.spark.sql.catalyst.expressions.GenericInternalRow.getArray(rows.scala:195)
at org.apache.spark.sql.catalyst.expressions.JsonToStructs.$anonfun$converter$2(jsonExpressions.scala:560)
at org.apache.spark.sql.catalyst.expressions.JsonToStructs.nullSafeEval(jsonExpressions.scala:597)
at org.apache.spark.sql.catalyst.expressions.UnaryExpression.eval(Expression.scala:461)
at org.apache.spark.sql.catalyst.expressions.ExplodeBase.eval(generators.scala:313)
at org.apache.spark.sql.execution.GenerateExec.$anonfun$doExecute$8(GenerateExec.scala:108)
{code}
The same works in Spark 2.4:
{code:scala}
Welcome to
____ __
/ __/__ ___ _____/ /__
_\ \/ _ \/ _ `/ __/ '_/
/___/ .__/\_,_/_/ /_/\_\ version 2.4.6
/_/
Using Scala version 2.11.12 (OpenJDK 64-Bit Server VM, Java 1.8.0_265)
...
scala> pokerhand_events.show()
+-----+
|event|
+-----+
+-----+
{code}
was:
The code below:
{code:scala}
val pokerhand_raw = Seq("""[{"cards": [11], "playerId": 583651}]""").toDF("events")
val event = new StructType()
.add("playerId", LongType)
.add("cards", ArrayType(
new StructType()
.add("id", LongType)
.add("rank", StringType)))
val pokerhand_events = pokerhand_raw
.select(explode(from_json($"events", ArrayType(event))).as("event"))
pokerhand_events.show
{code}
throw the exception in the PERMISSIVE mode (default):
{code:java}
Caused by: java.lang.ClassCastException: java.lang.Long cannot be cast to org.apache.spark.sql.catalyst.util.ArrayData
at org.apache.spark.sql.catalyst.expressions.BaseGenericInternalRow.getArray(rows.scala:48)
at org.apache.spark.sql.catalyst.expressions.BaseGenericInternalRow.getArray$(rows.scala:48)
at org.apache.spark.sql.catalyst.expressions.GenericInternalRow.getArray(rows.scala:195)
at org.apache.spark.sql.catalyst.expressions.JsonToStructs.$anonfun$converter$2(jsonExpressions.scala:560)
at org.apache.spark.sql.catalyst.expressions.JsonToStructs.nullSafeEval(jsonExpressions.scala:597)
at org.apache.spark.sql.catalyst.expressions.UnaryExpression.eval(Expression.scala:461)
at org.apache.spark.sql.catalyst.expressions.ExplodeBase.eval(generators.scala:313)
at org.apache.spark.sql.execution.GenerateExec.$anonfun$doExecute$8(GenerateExec.scala:108)
{code}
The same works in Spark 2.4:
{code:scala}
Welcome to
____ __
/ __/__ ___ _____/ /__
_\ \/ _ \/ _ `/ __/ '_/
/___/ .__/\_,_/_/ /_/\_\ version 2.4.6
/_/
Using Scala version 2.11.12 (OpenJDK 64-Bit Server VM, Java 1.8.0_265)
...
scala> pokerhand_events.show()
+-----+
|event|
+-----+
+-----+
{code}
> Incorrect nested complex JSON fields raise an exception
> -------------------------------------------------------
>
> Key: SPARK-33134
> URL: https://issues.apache.org/jira/browse/SPARK-33134
> Project: Spark
> Issue Type: Improvement
> Components: SQL
> Affects Versions: 3.0.2, 3.1.0
> Reporter: Maxim Gekk
> Priority: Major
>
> The code below:
> {code:scala}
> val pokerhand_raw = Seq("""[{"cards": [11], "playerId": 583651}]""").toDF("events")
> val event = new StructType()
> .add("playerId", LongType)
> .add("cards", ArrayType(
> new StructType()
> .add("id", LongType)
> .add("rank", StringType)))
> val pokerhand_events = pokerhand_raw
> .select(explode(from_json($"events", ArrayType(event))).as("event"))
> pokerhand_events.show
> {code}
> throw the exception in the PERMISSIVE mode (default):
> {code:java}
> Caused by: java.lang.ClassCastException: java.lang.Long cannot be cast to org.apache.spark.sql.catalyst.util.ArrayData
> at org.apache.spark.sql.catalyst.expressions.BaseGenericInternalRow.getArray(rows.scala:48)
> at org.apache.spark.sql.catalyst.expressions.BaseGenericInternalRow.getArray$(rows.scala:48)
> at org.apache.spark.sql.catalyst.expressions.GenericInternalRow.getArray(rows.scala:195)
> at org.apache.spark.sql.catalyst.expressions.JsonToStructs.$anonfun$converter$2(jsonExpressions.scala:560)
> at org.apache.spark.sql.catalyst.expressions.JsonToStructs.nullSafeEval(jsonExpressions.scala:597)
> at org.apache.spark.sql.catalyst.expressions.UnaryExpression.eval(Expression.scala:461)
> at org.apache.spark.sql.catalyst.expressions.ExplodeBase.eval(generators.scala:313)
> at org.apache.spark.sql.execution.GenerateExec.$anonfun$doExecute$8(GenerateExec.scala:108)
> {code}
> The same works in Spark 2.4:
> {code:scala}
> Welcome to
> ____ __
> / __/__ ___ _____/ /__
> _\ \/ _ \/ _ `/ __/ '_/
> /___/ .__/\_,_/_/ /_/\_\ version 2.4.6
> /_/
> Using Scala version 2.11.12 (OpenJDK 64-Bit Server VM, Java 1.8.0_265)
> ...
> scala> pokerhand_events.show()
> +-----+
> |event|
> +-----+
> +-----+
> {code}
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@spark.apache.org
For additional commands, e-mail: issues-help@spark.apache.org