CTTY commented on code in PR #5943:
URL: https://github.com/apache/hudi/pull/5943#discussion_r925176816
##########
hudi-spark-datasource/hudi-spark3/src/main/scala/org/apache/hudi/Spark33HoodieFileScanRDD.scala:
##########
@@ -20,14 +20,15 @@ package org.apache.hudi
import org.apache.spark.sql.SparkSession
import org.apache.spark.sql.catalyst.InternalRow
+import org.apache.spark.sql.catalyst.expressions.AttributeReference
import org.apache.spark.sql.execution.datasources.{FilePartition, FileScanRDD,
PartitionedFile}
+import org.apache.spark.sql.types.StructType
-case class HoodieBaseFileSplit(filePartition: FilePartition) extends
HoodieFileSplit
-
-class HoodieFileScanRDD(@transient private val sparkSession: SparkSession,
+class Spark33HoodieFileScanRDD(@transient private val sparkSession:
SparkSession,
readFunction: PartitionedFile => Iterator[InternalRow],
- @transient fileSplits: Seq[HoodieBaseFileSplit])
- extends FileScanRDD(sparkSession, readFunction,
fileSplits.map(_.filePartition))
+ @transient filePartitions: Seq[FilePartition],
+ readDataSchema: StructType, metadataColumns:
Seq[AttributeReference] = Seq.empty)
+ extends FileScanRDD(sparkSession, readFunction, filePartitions,
readDataSchema, metadataColumns)
Review Comment:
FileScanRDD constructor changed in spark3.3
--
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]
