jackylk commented on a change in pull request #3540:
[CARBONDATA-3639][CARBONDATA-3638] Fix global sort exception in load from CSV
flow with binary non-sort columns
URL: https://github.com/apache/carbondata/pull/3540#discussion_r361846507
##########
File path:
integration/spark-common/src/main/scala/org/apache/carbondata/spark/load/DataLoadProcessorStepOnSpark.scala
##########
@@ -97,6 +97,36 @@ object DataLoadProcessorStepOnSpark {
}
}
+ def inputFuncForCsvRows(
+ rows: Iterator[StringArrayRow],
+ index: Int,
+ modelBroadcast: Broadcast[CarbonLoadModel],
+ rowCounter: Accumulator[Int]): Iterator[CarbonRow] = {
+ val model: CarbonLoadModel =
modelBroadcast.value.getCopyWithTaskNo(index.toString)
+ val conf = DataLoadProcessBuilder.createConfiguration(model)
+ val rowParser = new RowParserImpl(conf.getDataFields, conf)
+ val isRawDataRequired = CarbonDataProcessorUtil.isRawDataRequired(conf)
+ TaskContext.get().addTaskFailureListener { (t: TaskContext, e: Throwable)
=>
+ wrapException(e, model)
+ }
+
+ new Iterator[CarbonRow] {
+ override def hasNext: Boolean = rows.hasNext
+
+ override def next(): CarbonRow = {
+ var row : CarbonRow = null
+ val rawRow = rows.next().values.asInstanceOf[Array[Object]]
+ if(isRawDataRequired) {
Review comment:
```suggestion
val row = if (isRawDataRequired) {
```
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
With regards,
Apache Git Services
