[
https://issues.apache.org/jira/browse/SPARK-34594?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Zhang Jianguo updated SPARK-34594:
----------------------------------
Description:
RecordReaderInterator#hasNext doesn't handle exception thrown from
OrcColumnarBatchReader#nextKeyValue
{code:java}
// code placeholder
override def hasNext: Boolean = {
if (!finished && !havePair) {
finished = !rowReader.nextKeyValue // Exception thrown from here
if (finished) {
// Close and release the reader here; close() will also be called when
the task
// completes, but for tasks that read from many files, it helps to
release the
// resources early.
close()
}
havePair = !finished
}
!finished
}
{code}
[https://github.com/apache/spark/blob/96f51378b598501cc5dc5791f794c8586a48b355/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/RecordReaderIterator.scala#L37]
was:
RecordReaderInterator#hasNext doesn't handle exception thrown from
OrcColumnarBatchReader#nextKeyValue
```scala
override def hasNext: Boolean = {
if (!finished && !havePair) {
finished = !rowReader.nextKeyValue // Exception thrown from here
if (finished) {
// Close and release the reader here; close() will also be called when
the task
// completes, but for tasks that read from many files, it helps to
release the
// resources early.
close()
}
havePair = !finished
}
!finished
}
```
https://github.com/apache/spark/blob/96f51378b598501cc5dc5791f794c8586a48b355/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/RecordReaderIterator.scala#L37
> OrcColumnarBatchReader uncaught exception
> -----------------------------------------
>
> Key: SPARK-34594
> URL: https://issues.apache.org/jira/browse/SPARK-34594
> Project: Spark
> Issue Type: Bug
> Components: Spark Core
> Affects Versions: 2.4.5
> Reporter: Zhang Jianguo
> Priority: Major
>
> RecordReaderInterator#hasNext doesn't handle exception thrown from
> OrcColumnarBatchReader#nextKeyValue
> {code:java}
> // code placeholder
> override def hasNext: Boolean = {
> if (!finished && !havePair) {
> finished = !rowReader.nextKeyValue // Exception thrown from here
> if (finished) {
> // Close and release the reader here; close() will also be called when
> the task
> // completes, but for tasks that read from many files, it helps to
> release the
> // resources early.
> close()
> }
> havePair = !finished
> }
> !finished
> }
> {code}
>
> [https://github.com/apache/spark/blob/96f51378b598501cc5dc5791f794c8586a48b355/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/RecordReaderIterator.scala#L37]
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
