maomaodev commented on code in PR #7476: URL: https://github.com/apache/kyuubi/pull/7476#discussion_r3788127620
########## extensions/spark/kyuubi-spark-connector-hive/src/main/scala/org/apache/kyuubi/spark/connector/hive/read/KyuubiParquetScan.scala: ########## @@ -0,0 +1,229 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.kyuubi.spark.connector.hive.read + +import org.apache.hadoop.conf.Configuration +import org.apache.hadoop.fs.Path +import org.apache.spark.sql.SparkSession +import org.apache.spark.sql.catalyst.catalog.CatalogTable +import org.apache.spark.sql.catalyst.expressions.Expression +import org.apache.spark.sql.connector.expressions.NamedReference +import org.apache.spark.sql.connector.expressions.aggregate.Aggregation +import org.apache.spark.sql.connector.read.{InputPartition, PartitionReaderFactory, SupportsRuntimeFiltering} +import org.apache.spark.sql.execution.datasources.PartitioningAwareFileIndex +import org.apache.spark.sql.execution.datasources.v2.FileScan +import org.apache.spark.sql.execution.datasources.v2.parquet.ParquetScan +import org.apache.spark.sql.sources.Filter +import org.apache.spark.sql.types.StructType +import org.apache.spark.sql.util.CaseInsensitiveStringMap + +import org.apache.kyuubi.util.reflect.{DynClasses, DynConstructors} + +/** + * A DPP-aware wrapper around Spark's built-in [[ParquetScan]] that adds + * [[SupportsRuntimeFiltering]] so Dynamic Partition Pruning can push runtime + * IN predicates down to the Hive partitioned scan. + * + * Implementation notes: + * 1. Only DPP-specific methods ([[filter]] / [[filterAttributes]] / + * [[planInputPartitions]]) contain custom logic, all other methods + * delegate to the wrapped [[ParquetScan]]. + * 2. [[equals]] / [[hashCode]] are overridden to key on `getClass`, so a + * `KyuubiParquetScan` is never reused in place of a plain [[ParquetScan]] + * during exchange/subquery reuse. + */ +class KyuubiParquetScan( + val sparkSession: SparkSession, + val hadoopConf: Configuration, + val fileIndex: PartitioningAwareFileIndex, + val dataSchema: StructType, + val readDataSchema: StructType, + val readPartitionSchema: StructType, + val pushedFilters: Array[Filter], + val options: CaseInsensitiveStringMap, + val pushedAggregate: Option[Aggregation], + val partitionFilters: Seq[Expression], + val dataFilters: Seq[Expression], + val catalogTable: CatalogTable) + extends FileScan + with SupportsRuntimeFiltering + with KyuubiParquetColumnarMixin { + + private[hive] val inner: ParquetScan = KyuubiParquetScan.newParquetScan( + sparkSession, + hadoopConf, + fileIndex, + dataSchema, + readDataSchema, + readPartitionSchema, + pushedFilters, + options, + pushedAggregate, + partitionFilters, + dataFilters) + + private var runtimeFilters: Seq[Expression] = Seq.empty + + private val isCaseSensitive = sparkSession.sessionState.conf.caseSensitiveAnalysis + + override def filterAttributes(): Array[NamedReference] = { Review Comment: Fixed in both `KyuubiParquetScan.filterAttributes` and `KyuubiOrcScan.filterAttributes`. -- 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]
