paimon icon indicating copy to clipboard operation
paimon copied to clipboard
verified publisher icon apache

[Bug][spark]java.lang.ArrayIndexOutOfBoundsException

Open melin opened this issue 8 months ago • 1 comments

Search before asking

  • [x] I searched in the issues and found nothing similar.

Paimon version

Image

3.5.2：
java.lang.ArrayIndexOutOfBoundsException: 1
        at org.apache.spark.sql.types.StructType.apply(StructType.scala:407)
        at org.apache.spark.sql.catalyst.expressions.GetStructField.toString(complexTypeExtractors.scala:118)
        at java.lang.String.valueOf(String.java:2994)
        at java.lang.StringBuilder.append(StringBuilder.java:131)
        at org.apache.spark.sql.catalyst.expressions.BinaryOperator.toString(Expression.scala:769)
        at java.lang.String.valueOf(String.java:2994)
        at java.lang.StringBuilder.append(StringBuilder.java:131)
        at org.apache.spark.sql.catalyst.expressions.BinaryOperator.toString(Expression.scala:769)
        at java.lang.String.valueOf(String.java:2994)
        at java.lang.StringBuilder.append(StringBuilder.java:131)
        at org.apache.spark.sql.execution.FilterExec.verboseStringWithOperatorId(basicPhysicalOperators.scala:295)
        at org.apache.spark.sql.execution.ExplainUtils$.$anonfun$processPlanSkippingSubqueries$2(ExplainUtils.scala:67)
        at org.apache.spark.sql.execution.ExplainUtils$.$anonfun$processPlanSkippingSubqueries$2$adapted(ExplainUtils.scala:67)
        at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
        at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
        at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
        at org.apache.spark.sql.execution.ExplainUtils$.processPlanSkippingSubqueries(ExplainUtils.scala:67)
        at org.apache.spark.sql.execution.ExplainUtils$.processPlan(ExplainUtils.scala:118)
        at org.apache.spark.sql.execution.QueryExecution.simpleString(QueryExecution.scala:238)
        at org.apache.spark.sql.execution.QueryExecution.org$apache$spark$sql$execution$QueryExecution$$explainString(QueryExecution.scala:284)
        at org.apache.spark.sql.execution.QueryExecution.explainString(QueryExecution.scala:252)
        at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:117)
        at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
        at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
        at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
        at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
        at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4322)
        at org.apache.spark.sql.Dataset.collect(Dataset.scala:3575)
        at org.apache.paimon.spark.commands.PaimonSparkWriter.write(PaimonSparkWriter.scala:235)
        at org.apache.paimon.spark.commands.WriteIntoPaimonTable.run(WriteIntoPaimonTable.scala:67)
        at org.apache.paimon.spark.commands.PaimonDynamicPartitionOverwriteCommand.run(PaimonDynamicPartitionOverwriteCommand.scala:69)
        at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:75)
        at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:73)
        at org.apache.spark.sql.execution.command.ExecutedCommandExec.executeCollect(commands.scala:84)
        at org.apache.spark.sql.execution.QueryExecution$$anonfun$eagerlyExecuteCommands$1.$anonfun$applyOrElse$1(QueryExecution.scala:107)
        at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
        at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
        at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
        at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
        at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
        at org.apache.spark.sql.execution.QueryExecution$$anonfun$eagerlyExecuteCommands$1.applyOrElse(QueryExecution.scala:107)
        at org.apache.spark.sql.execution.QueryExecution$$anonfun$eagerlyExecuteCommands$1.applyOrElse(QueryExecution.scala:98)
        at org.apache.spark.sql.catalyst.trees.TreeNode.$anonfun$transformDownWithPruning$1(TreeNode.scala:461)
        at org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(origin.scala:76)
        at org.apache.spark.sql.catalyst.trees.TreeNode.transformDownWithPruning(TreeNode.scala:461)
        at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.org$apache$spark$sql$catalyst$plans$logical$AnalysisHelper$$super$transformDownWithPruning(LogicalPlan.scala:32)
        at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.transformDownWithPruning(AnalysisHelper.scala:267)
        at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.transformDownWithPruning$(AnalysisHelper.scala:263)
        at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.transformDownWithPruning(LogicalPlan.scala:32)
        at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.transformDownWithPruning(LogicalPlan.scala:32)
        at org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:437)
        at org.apache.spark.sql.execution.QueryExecution.eagerlyExecuteCommands(QueryExecution.scala:98)
        at org.apache.spark.sql.execution.QueryExecution.commandExecuted$lzycompute(QueryExecution.scala:85)
        at org.apache.spark.sql.execution.QueryExecution.commandExecuted(QueryExecution.scala:83)
        at org.apache.spark.sql.Dataset.<init>(Dataset.scala:220)
        at org.apache.spark.sql.Dataset$.$anonfun$ofRows$2(Dataset.scala:100)
        at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
        at org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:97)
        at org.apache.spark.sql.SparkSession.$anonfun$sql$4(SparkSession.scala:691)
        at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
        at org.apache.spark.sql.SparkSession.sql(SparkSession.scala:682)
        at org.apache.spark.sql.SparkSession.sql(SparkSession.scala:713)
        at org.apache.spark.sql.SparkSession.sql(SparkSession.scala:744)
        at org.apache.spark.sql.SQLContext.sql(SQLContext.scala:651)
        at org.apache.spark.sql.hive.thriftserver.SparkSQLDriver.run(SparkSQLDriver.scala:68)
        at org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.processCmd(SparkSQLCLIDriver.scala:501)
        at org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.$anonfun$processLine$1(SparkSQLCLIDriver.scala:619)
        at org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.$anonfun$processLine$1$adapted(SparkSQLCLIDriver.scala:613)
        at scala.collection.Iterator.foreach(Iterator.scala:943)
        at scala.collection.Iterator.foreach$(Iterator.scala:943)
        at scala.collection.AbstractIterator.foreach(Iterator.scala:1431)
        at scala.collection.IterableLike.foreach(IterableLike.scala:74)
        at scala.collection.IterableLike.foreach$(IterableLike.scala:73)
        at scala.collection.AbstractIterable.foreach(Iterable.scala:56)
        at org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.processLine(SparkSQLCLIDriver.scala:613)
        at org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver$.main(SparkSQLCLIDriver.scala:310)
        at org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.main(SparkSQLCLIDriver.scala)
        at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
        at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
        at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
        at java.lang.reflect.Method.invoke(Method.java:498)
        at org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
        at org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1029)
        at org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:194)
        at org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:217)
        at org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
        at org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1120)
        at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1129)
        at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)

Compute Engine

Spark

Minimal reproduce step

null

What doesn't meet your expectations?

null

Anything else?

No response

Are you willing to submit a PR?

  • [ ] I'm willing to submit a PR!

melin avatar Apr 21 '25 06:04 melin

cc @YannByron

melin avatar Apr 21 '25 06:04 melin