gengliangwang commented on a change in pull request #24327: [SPARK-27418][SQL] Migrate Parquet to File Data Source V2 URL: https://github.com/apache/spark/pull/24327#discussion_r293878249
########## File path: sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/parquet/ParquetScanBuilder.scala ########## @@ -0,0 +1,75 @@ +/* + * 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.spark.sql.execution.datasources.v2.parquet + +import scala.collection.JavaConverters._ + +import org.apache.spark.sql.SparkSession +import org.apache.spark.sql.execution.datasources.PartitioningAwareFileIndex +import org.apache.spark.sql.execution.datasources.parquet.{ParquetFilters, SparkToParquetSchemaConverter} +import org.apache.spark.sql.execution.datasources.v2.FileScanBuilder +import org.apache.spark.sql.sources.Filter +import org.apache.spark.sql.sources.v2.reader.{Scan, SupportsPushDownFilters} +import org.apache.spark.sql.types.StructType +import org.apache.spark.sql.util.CaseInsensitiveStringMap + +case class ParquetScanBuilder( + sparkSession: SparkSession, + fileIndex: PartitioningAwareFileIndex, + schema: StructType, + dataSchema: StructType, + options: CaseInsensitiveStringMap) + extends FileScanBuilder(sparkSession, fileIndex, dataSchema) with SupportsPushDownFilters { + lazy val hadoopConf = { + val caseSensitiveMap = options.asCaseSensitiveMap.asScala.toMap + // Hadoop Configurations are case sensitive. + sparkSession.sessionState.newHadoopConfWithOptions(caseSensitiveMap) + } + + lazy val _pushedFilters = { + val sqlConf = sparkSession.sessionState.conf + val pushDownDate = sqlConf.parquetFilterPushDownDate + val pushDownTimestamp = sqlConf.parquetFilterPushDownTimestamp + val pushDownDecimal = sqlConf.parquetFilterPushDownDecimal + val pushDownStringStartWith = sqlConf.parquetFilterPushDownStringStartWith + val pushDownInFilterThreshold = sqlConf.parquetFilterPushDownInFilterThreshold + val isCaseSensitive = sqlConf.caseSensitiveAnalysis + val parquetSchema = + new SparkToParquetSchemaConverter(sparkSession.sessionState.conf).convert(schema) + val parquetFilters = new ParquetFilters(parquetSchema, pushDownDate, pushDownTimestamp, + pushDownDecimal, pushDownStringStartWith, pushDownInFilterThreshold, isCaseSensitive) + parquetFilters.convertibleFilters(this.filters).toArray Review comment: `ParquetFilters.convertibleFilters` returns `Seq[org.apache.spark.sql.sources.Filter] ` `ParquetFilters.createFilters` returns `org.apache.parquet.filter2.predicate.FilterPredicate` The overlap of the two methods is only on the `And`/`Or`/`Not` operator. ---------------------------------------------------------------- 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. For queries about this service, please contact Infrastructure at: us...@infra.apache.org With regards, Apache Git Services --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
