vinothchandar commented on a change in pull request #1402: [WIP][HUDI-407] Adding Simple Index URL: https://github.com/apache/incubator-hudi/pull/1402#discussion_r400425128
########## File path: hudi-client/src/main/java/org/apache/hudi/index/bloom/HoodieSimpleIndex.java ########## @@ -0,0 +1,244 @@ +/* + * 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.hudi.index.bloom; + +import org.apache.hudi.WriteStatus; +import org.apache.hudi.common.model.HoodieDataFile; +import org.apache.hudi.common.model.HoodieKey; +import org.apache.hudi.common.model.HoodieRecord; +import org.apache.hudi.common.model.HoodieRecordLocation; +import org.apache.hudi.common.model.HoodieRecordPayload; +import org.apache.hudi.common.table.timeline.HoodieInstant; +import org.apache.hudi.common.util.Option; +import org.apache.hudi.common.util.ParquetUtils; +import org.apache.hudi.common.util.collection.Pair; +import org.apache.hudi.config.HoodieWriteConfig; +import org.apache.hudi.table.HoodieTable; + +import com.clearspring.analytics.util.Lists; +import com.google.common.annotations.VisibleForTesting; +import org.apache.hadoop.fs.Path; +import org.apache.log4j.LogManager; +import org.apache.log4j.Logger; +import org.apache.spark.api.java.JavaPairRDD; +import org.apache.spark.api.java.JavaRDD; +import org.apache.spark.api.java.JavaSparkContext; +import org.apache.spark.api.java.Optional; +import org.apache.spark.api.java.function.Function; +import org.apache.spark.api.java.function.PairFunction; +import org.apache.spark.storage.StorageLevel; + +import java.util.ArrayList; +import java.util.Arrays; +import java.util.List; +import java.util.Map; +import java.util.stream.Collectors; + +import scala.Tuple2; + +import static java.util.stream.Collectors.toList; + +/** + * A simple index which reads interested fields from parquet and joins with incoming records to find the tagged location + * + * @param <T> + */ +public class HoodieSimpleIndex<T extends HoodieRecordPayload> extends HoodieBloomIndex<T> { Review comment: Will do.. We should really create a new abstract class `AbstactFileLevelIndex` which can be extended by the BloomIndex and SimpleIndex classes.. HoodieIndex should be left alone, since stuff the HBaseIndex does not really work this way.. ---------------------------------------------------------------- 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: [email protected] With regards, Apache Git Services
