You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@spark.apache.org by "Dongjoon Hyun (Jira)" <ji...@apache.org> on 2020/02/24 17:01:00 UTC
[jira] [Commented] (SPARK-30870) catalyst inception of lateral view
explode with struct raise a Catalyst error
[ https://issues.apache.org/jira/browse/SPARK-30870?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17043686#comment-17043686 ]
Dongjoon Hyun commented on SPARK-30870:
---------------------------------------
Thank you for reporting, [~tprelle-ubi].
> catalyst inception of lateral view explode with struct raise a Catalyst error
> -----------------------------------------------------------------------------
>
> Key: SPARK-30870
> URL: https://issues.apache.org/jira/browse/SPARK-30870
> Project: Spark
> Issue Type: Sub-task
> Components: Spark Core, SQL
> Affects Versions: 3.0.0
> Reporter: Thomas Prelle
> Priority: Major
>
> On spark 3.0.0.preview2 version I found a bug who are not in 3.0.0.preview version.
> With the table
> {code:java}
> spark.sql("select * from tmp").printSchema
> root
> |-- value: struct (nullable = true)
> | |-- array: array (nullable = true)
> | | |-- element: struct (containsNull = true)
> | | | |-- subarray: array (nullable = true)
> | | | | |-- element: struct (containsNull = true)
> | | | | | |-- key1: string (nullable = true)
> | | | | | |-- key2: string (nullable = true)
> {code}
> when you try a double lateral view explode
> {code:java}
> spark.sql("select subexplod.* from tmp lateral view explode(tmp.value.array) explod as array_explod lateral view explode(explod.array_explod.subarray) subexplod").show()
> {code}
> It's raising an error :
> {code:java}
> org.apache.spark.sql.catalyst.errors.package$TreeNodeException: Binding attribute, tree: _gen_alias_127#127
> at org.apache.spark.sql.catalyst.errors.package$.attachTree(package.scala:56)
> at org.apache.spark.sql.catalyst.expressions.BindReferences$$anonfun$bindReference$1.applyOrElse(BoundAttribute.scala:75)
> at org.apache.spark.sql.catalyst.expressions.BindReferences$$anonfun$bindReference$1.applyOrElse(BoundAttribute.scala:74)
> at org.apache.spark.sql.catalyst.trees.TreeNode.$anonfun$transformDown$1(TreeNode.scala:309)
> at org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:72)
> at org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:309)
> at org.apache.spark.sql.catalyst.trees.TreeNode.$anonfun$transformDown$3(TreeNode.scala:314)
> at org.apache.spark.sql.catalyst.trees.TreeNode.$anonfun$mapChildren$1(TreeNode.scala:399)
> at org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:237)
> at org.apache.spark.sql.catalyst.trees.TreeNode.mapChildren(TreeNode.scala:397)
> at org.apache.spark.sql.catalyst.trees.TreeNode.mapChildren(TreeNode.scala:350)
> at org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:314)
> at org.apache.spark.sql.catalyst.trees.TreeNode.transform(TreeNode.scala:298)
> at org.apache.spark.sql.catalyst.expressions.BindReferences$.bindReference(BoundAttribute.scala:74)
> at org.apache.spark.sql.catalyst.expressions.BindReferences$.$anonfun$bindReferences$1(BoundAttribute.scala:96)
> at scala.collection.TraversableLike.$anonfun$map$1(TraversableLike.scala:238)
> at scala.collection.immutable.List.foreach(List.scala:392)
> at scala.collection.TraversableLike.map(TraversableLike.scala:238)
> at scala.collection.TraversableLike.map$(TraversableLike.scala:231)
> at scala.collection.immutable.List.map(List.scala:298)
> at org.apache.spark.sql.catalyst.expressions.BindReferences$.bindReferences(BoundAttribute.scala:96)
> at org.apache.spark.sql.execution.ProjectExec.doConsume(basicPhysicalOperators.scala:65)
> at org.apache.spark.sql.execution.CodegenSupport.consume(WholeStageCodegenExec.scala:194)
> at org.apache.spark.sql.execution.CodegenSupport.consume$(WholeStageCodegenExec.scala:149)
> at org.apache.spark.sql.execution.InputAdapter.consume(WholeStageCodegenExec.scala:496)
> at org.apache.spark.sql.execution.InputRDDCodegen.doProduce(WholeStageCodegenExec.scala:483)
> at org.apache.spark.sql.execution.InputRDDCodegen.doProduce$(WholeStageCodegenExec.scala:456)
> at org.apache.spark.sql.execution.InputAdapter.doProduce(WholeStageCodegenExec.scala:496)
> at org.apache.spark.sql.execution.CodegenSupport.$anonfun$produce$1(WholeStageCodegenExec.scala:95)
> at org.apache.spark.sql.execution.SparkPlan.$anonfun$executeQuery$1(SparkPlan.scala:212)
> at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
> at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:209)
> at org.apache.spark.sql.execution.CodegenSupport.produce(WholeStageCodegenExec.scala:90)
> at org.apache.spark.sql.execution.CodegenSupport.produce$(WholeStageCodegenExec.scala:90)
> at org.apache.spark.sql.execution.InputAdapter.produce(WholeStageCodegenExec.scala:496)
> at org.apache.spark.sql.execution.ProjectExec.doProduce(basicPhysicalOperators.scala:51)
> at org.apache.spark.sql.execution.CodegenSupport.$anonfun$produce$1(WholeStageCodegenExec.scala:95)
> at org.apache.spark.sql.execution.SparkPlan.$anonfun$executeQuery$1(SparkPlan.scala:212)
> at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
> at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:209)
> at org.apache.spark.sql.execution.CodegenSupport.produce(WholeStageCodegenExec.scala:90)
> at org.apache.spark.sql.execution.CodegenSupport.produce$(WholeStageCodegenExec.scala:90)
> at org.apache.spark.sql.execution.ProjectExec.produce(basicPhysicalOperators.scala:41)
> at org.apache.spark.sql.execution.WholeStageCodegenExec.doCodeGen(WholeStageCodegenExec.scala:632)
> at org.apache.spark.sql.execution.WholeStageCodegenExec.doExecute(WholeStageCodegenExec.scala:692)
> at org.apache.spark.sql.execution.SparkPlan.$anonfun$execute$1(SparkPlan.scala:174)
> at org.apache.spark.sql.execution.SparkPlan.$anonfun$executeQuery$1(SparkPlan.scala:212)
> at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
> at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:209)
> at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:170)
> at org.apache.spark.sql.execution.GenerateExec.doExecute(GenerateExec.scala:80)
> at org.apache.spark.sql.execution.SparkPlan.$anonfun$execute$1(SparkPlan.scala:174)
> at org.apache.spark.sql.execution.SparkPlan.$anonfun$executeQuery$1(SparkPlan.scala:212)
> at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
> at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:209)
> at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:170)
> at org.apache.spark.sql.execution.InputAdapter.inputRDD(WholeStageCodegenExec.scala:525)
> at org.apache.spark.sql.execution.InputRDDCodegen.inputRDDs(WholeStageCodegenExec.scala:453)
> at org.apache.spark.sql.execution.InputRDDCodegen.inputRDDs$(WholeStageCodegenExec.scala:452)
> at org.apache.spark.sql.execution.InputAdapter.inputRDDs(WholeStageCodegenExec.scala:496)
> at org.apache.spark.sql.execution.ProjectExec.inputRDDs(basicPhysicalOperators.scala:47)
> at org.apache.spark.sql.execution.WholeStageCodegenExec.doExecute(WholeStageCodegenExec.scala:720)
> at org.apache.spark.sql.execution.SparkPlan.$anonfun$execute$1(SparkPlan.scala:174)
> at org.apache.spark.sql.execution.SparkPlan.$anonfun$executeQuery$1(SparkPlan.scala:212)
> at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
> at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:209)
> at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:170)
> at org.apache.spark.sql.execution.SparkPlan.getByteArrayRdd(SparkPlan.scala:315)
> at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:433)
> at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:419)
> at org.apache.spark.sql.execution.CollectLimitExec.executeCollect(limit.scala:47)
> at org.apache.spark.sql.Dataset.collectFromPlan(Dataset.scala:3537)
> at org.apache.spark.sql.Dataset.$anonfun$head$1(Dataset.scala:2590)
> at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:3527)
> at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$5(SQLExecution.scala:100)
> at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:160)
> at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:87)
> at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:762)
> at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:64)
> at org.apache.spark.sql.Dataset.withAction(Dataset.scala:3525)
> at org.apache.spark.sql.Dataset.head(Dataset.scala:2590)
> at org.apache.spark.sql.Dataset.take(Dataset.scala:2797)
> at org.apache.spark.sql.Dataset.getRows(Dataset.scala:297)
> at org.apache.spark.sql.Dataset.showString(Dataset.scala:334)
> at org.apache.spark.sql.Dataset.show(Dataset.scala:821)
> at org.apache.spark.sql.Dataset.show(Dataset.scala:780)
> at org.apache.spark.sql.Dataset.show(Dataset.scala:789)
> ... 47 elided
> Caused by: java.lang.RuntimeException: Couldn't find _gen_alias_127#127 in [array_explod#119]
> at scala.sys.package$.error(package.scala:30)
> at org.apache.spark.sql.catalyst.expressions.BindReferences$$anonfun$bindReference$1.$anonfun$applyOrElse$1(BoundAttribute.scala:81)
> at org.apache.spark.sql.catalyst.errors.package$.attachTree(package.scala:52)
> ... 133 more
> {code}
> To recreate the bug
> {code:java}
> import org.apache.spark.sql.Row
> import org.apache.spark.sql.types.{StringType, StructField, StructType, ArrayType}
> val structValue = StructType(StructField(name = "value", StringType, nullable = false) :: Nil)
> val struct : StructType = StructType(StructField("array", ArrayType(StructType(StructField("subarray", ArrayType(StructType(StructField("key1",StringType, true)::StructField("key2",StringType, true)::Nil)), nullable = false) :: Nil)), nullable = false) :: Nil)
> val value = "{\"array\": [{\"subarray\" : [{\"key1\":\"val1\",\"key2\":\"val2\"},{\"key1\":\"val11\",\"key2\":\"val12\"}]}]}"
> spark.createDataFrame(spark.sparkContext.parallelize(Seq(Row(value))),structValue).withColumn("value", from_json(col("value"),struct)).createOrReplaceTempView("tmp")
> spark.sql("select subexplod.* from tmp lateral view explode(tmp.value.array) explod as array_explod lateral view explode(explod.array_explod.subarray) subexplod").show()
> {code}
> If you just avec an Array of Array of String it's working
> {code:java}
> import org.apache.spark.sql.Row
> import org.apache.spark.sql.types.{StringType, StructField, StructType, ArrayType}
> val structValue = StructType(StructField(name = "value", StringType, nullable = false) :: Nil)
> val struct : StructType = StructType(StructField("array", ArrayType(StructType(StructField("subarray", ArrayType(StringType, true), nullable = false) :: Nil)), nullable = false) :: Nil)
> val value = "{\"array\": [{\"subarray\" : [\"val1\",\"val2\"]}]}"
> spark.createDataFrame(spark.sparkContext.parallelize(Seq(Row(value))),structValue).withColumn("value", from_json(col("value"),struct)).createOrReplaceTempView("tmp")
> spark.sql("select subexplod.* from tmp lateral view explode(tmp.value.array) explod as array_explod lateral view explode(explod.array_explod.subarray) subexplod").show()
> {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