linliu-code commented on code in PR #10137:
URL: https://github.com/apache/hudi/pull/10137#discussion_r1411397747
##########
hudi-client/hudi-spark-client/src/main/scala/org/apache/hudi/SparkFileFormatInternalRowReaderContext.scala:
##########
@@ -99,4 +104,49 @@ class
SparkFileFormatInternalRowReaderContext(baseFileReader: Option[Partitioned
})
deserializer.deserialize(avroRecord).get.asInstanceOf[InternalRow]
}
+
+ override def mergeBootstrapReaders(skeletonFileIterator:
ClosableIterator[InternalRow],
+ dataFileIterator:
ClosableIterator[InternalRow]): ClosableIterator[InternalRow] = {
+ doBootstrapMerge(skeletonFileIterator.asInstanceOf[ClosableIterator[Any]],
+ dataFileIterator.asInstanceOf[ClosableIterator[Any]])
+ }
+
+
+ protected def doBootstrapMerge(skeletonFileIterator: ClosableIterator[Any],
dataFileIterator: ClosableIterator[Any]): ClosableIterator[InternalRow] = {
+ new ClosableIterator[Any] {
+ val combinedRow = new JoinedRow()
+
+ override def hasNext: Boolean = {
+ //If the iterators are out of sync it is probably due to filter
pushdown
+ checkState(dataFileIterator.hasNext == skeletonFileIterator.hasNext,
+ "Bootstrap data-file iterator and skeleton-file iterator have to be
in-sync!")
+ dataFileIterator.hasNext && skeletonFileIterator.hasNext
+ }
+
+ override def next(): Any = {
Review Comment:
This reminds me: do we need to support vectorization for other query types
explicitly?
--
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.
To unsubscribe, e-mail: commits-unsubscr...@hudi.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
