zhztheplayer commented on code in PR #12198:
URL: https://github.com/apache/gluten/pull/12198#discussion_r3357092159
##########
backends-velox/src/main/scala/org/apache/gluten/backendsapi/velox/VeloxIteratorApi.scala:
##########
@@ -179,6 +214,93 @@ class VeloxIteratorApi extends IteratorApi with Logging {
NativePlanEvaluator.injectWriteFilesTempPath(path, fileName)
}
+ private def normalizeDeltaSplitMetadata(
+ partitionColumnCount: Int,
+ partitionFiles: Seq[PartitionedFile]):
Option[NormalizedDeltaSplitMetadata] = {
+ try {
+ // scalastyle:off classforname
+ val moduleClass = Class.forName(deltaScanInfoClassName)
+ // scalastyle:on classforname
+ val module = moduleClass.getField("MODULE$").get(null)
+ val extractAllMethod = moduleClass.getMethod(
+ "extractAllFromJava",
+ classOf[SparkSession],
+ classOf[Int],
+ classOf[java.util.List[_]])
+ val scanInfos = extractAllMethod
+ .invoke(module, activeSparkSession, Int.box(partitionColumnCount),
partitionFiles.asJava)
+ .asInstanceOf[java.util.List[_]]
+ .asScala
+ .toSeq
+ val splitMetadata = scanInfos.map(toDeltaSplitMetadata)
+ if (splitMetadata.exists(_._2.hasDeletionVector())) {
+ Some((splitMetadata.map(_._1), splitMetadata.map(_._2)))
+ } else {
+ None
+ }
+ } catch {
+ case _: ClassNotFoundException | _: NoSuchMethodException =>
+ None
+ }
+ }
+
+ private def toDeltaSplitMetadata(
+ scanInfo: Any): (java.util.Map[String, Object], DeltaFileReadOptions) = {
+ val metadata = scanInfo
+ .getClass
+ .getMethod("normalizedOtherMetadataColumns")
+ .invoke(scanInfo)
+ .asInstanceOf[scala.collection.Map[String, Object]]
+ .asJava
+ val deletionVectorInfo =
scanInfo.getClass.getMethod("deletionVectorInfo").invoke(scanInfo)
+ val rowIndexFilterType = deletionVectorInfo
+ .getClass
+ .getMethod("rowIndexFilterType")
+ .invoke(deletionVectorInfo)
+ .toString
+ val hasDeletionVector = deletionVectorInfo
+ .getClass
+ .getMethod("hasDeletionVector")
+ .invoke(deletionVectorInfo)
+ .asInstanceOf[Boolean]
+ val cardinality = deletionVectorInfo
+ .getClass
+ .getMethod("cardinality")
+ .invoke(deletionVectorInfo)
+ .asInstanceOf[JLong]
+ .longValue()
+ val serializedDeletionVector = deletionVectorInfo
+ .getClass
+ .getMethod("serializedDeletionVector")
+ .invoke(deletionVectorInfo)
+ .asInstanceOf[Array[Byte]]
+
+ (
+ metadata,
+ new DeltaFileReadOptions(
+ toDeltaRowIndexFilterType(rowIndexFilterType),
+ hasDeletionVector,
+ cardinality,
+ serializedDeletionVector))
+ }
Review Comment:
If reflection is inevitable, can we encapsulate the reflection code in a
utility class?
##########
backends-velox/src-delta/main/scala/org/apache/gluten/component/VeloxDeltaComponent.scala:
##########
@@ -46,4 +53,22 @@ class VeloxDeltaComponent extends Component {
}
DeltaPostTransformRules.rules.foreach(r => legacy.injectPostTransform(_ =>
r))
}
+
+ private def deltaDvPreprocessRule(spark: SparkSession): Rule[LogicalPlan] = {
+ if (!SparkReflectionUtil.isClassPresent(deltaDvPreprocessRuleClassName)) {
+ return VeloxDeltaComponent.IdentityRule
+ }
+
+ Class
+ .forName(deltaDvPreprocessRuleClassName)
+ .getConstructor(classOf[SparkSession])
+ .newInstance(spark)
+ .asInstanceOf[Rule[LogicalPlan]]
Review Comment:
Is there any particular reason for using reflection here? Given it's against
Gluten's own class?
--
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: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
