maomaodev commented on code in PR #7476: URL: https://github.com/apache/kyuubi/pull/7476#discussion_r3788116241
########## extensions/spark/kyuubi-spark-connector-hive/src/main/scala/org/apache/kyuubi/spark/connector/hive/read/KyuubiParquetScanBuilder.scala: ########## @@ -0,0 +1,120 @@ +/* + * 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 scala.collection.JavaConverters._ + +import org.apache.hadoop.conf.Configuration +import org.apache.spark.sql.SparkSession +import org.apache.spark.sql.catalyst.catalog.CatalogTable +import org.apache.spark.sql.connector.expressions.aggregate.Aggregation +import org.apache.spark.sql.connector.read.SupportsPushDownAggregates +import org.apache.spark.sql.execution.datasources.{AggregatePushDownUtils, PartitioningAwareFileIndex} +import org.apache.spark.sql.execution.datasources.v2.FileScanBuilder +import org.apache.spark.sql.hive.kyuubi.connector.HiveBridgeHelper +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.spark.connector.hive.HiveTableCatalog + +/** + * A ScanBuilder that mirrors Spark's built-in [[ParquetScanBuilder]] but builds + * [[KyuubiParquetScan]] instances, which additionally implement + * `SupportsRuntimeFiltering` so that Dynamic Partition Pruning works when + * a Hive Parquet table goes through Spark's vectorized Parquet reader path. + * + * Kept semantically equivalent to [[ParquetScanBuilder]] - filter, aggregate and + * column pushdown behaviour is identical. + */ +class KyuubiParquetScanBuilder( + sparkSession: SparkSession, + fileIndex: PartitioningAwareFileIndex, + schema: StructType, + dataSchema: StructType, + options: CaseInsensitiveStringMap, + catalogTable: CatalogTable, + hiveTableCatalog: HiveTableCatalog) + extends FileScanBuilder(sparkSession, fileIndex, dataSchema) + with SupportsPushDownAggregates { + + lazy val hadoopConf: Configuration = { + // Start from the catalog-level hadoopConf so that per-catalog Hadoop + // configurations are honored. Clone it to avoid polluting the shared + // instance held by HiveTableCatalog. + val conf = new Configuration(hiveTableCatalog.hadoopConfiguration()) Review Comment: Kept the catalog-snapshot direction. Added: - A note in `KyuubiParquetScanBuilder.hadoopConf` / `KyuubiOrcScanBuilder.hadoopConf` scaladoc. - A guard test in `HiveCatalogSuite`, asserting `fieldId.read.enabled` / `ignoreMissing` SET mid-session do **not** reach the resulting `hadoopConf`. -- 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]
