nsivabalan commented on code in PR #9066: URL: https://github.com/apache/hudi/pull/9066#discussion_r1256254717
########## hudi-hadoop-mr/src/main/java/org/apache/hudi/hadoop/realtime/HoodieMergeOnReadSnapshotReader.java: ########## @@ -0,0 +1,216 @@ +/* + * 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.hadoop.realtime; + +import org.apache.hudi.common.fs.FSUtils; +import org.apache.hudi.common.model.HoodieAvroIndexedRecord; +import org.apache.hudi.common.model.HoodieLogFile; +import org.apache.hudi.common.model.HoodieRecord; +import org.apache.hudi.common.table.log.HoodieMergedLogRecordScanner; +import org.apache.hudi.common.util.DefaultSizeEstimator; +import org.apache.hudi.common.util.HoodieRecordSizeEstimator; +import org.apache.hudi.common.util.HoodieTimer; +import org.apache.hudi.common.util.Option; +import org.apache.hudi.common.util.collection.ClosableIterator; +import org.apache.hudi.common.util.collection.ExternalSpillableMap; +import org.apache.hudi.hadoop.utils.HoodieInputFormatUtils; +import org.apache.hudi.io.storage.HoodieFileReader; + +import org.apache.avro.Schema; +import org.apache.hadoop.fs.Path; +import org.apache.hadoop.mapred.JobConf; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +import java.io.IOException; +import java.util.HashSet; +import java.util.Iterator; +import java.util.List; +import java.util.Map; +import java.util.Set; +import java.util.stream.Collectors; + +import static org.apache.hudi.common.config.HoodieCommonConfig.DISK_MAP_BITCASK_COMPRESSION_ENABLED; +import static org.apache.hudi.common.config.HoodieCommonConfig.SPILLABLE_DISK_MAP_TYPE; +import static org.apache.hudi.hadoop.config.HoodieRealtimeConfig.COMPACTION_LAZY_BLOCK_READ_ENABLED_PROP; +import static org.apache.hudi.hadoop.config.HoodieRealtimeConfig.DEFAULT_COMPACTION_LAZY_BLOCK_READ_ENABLED; +import static org.apache.hudi.hadoop.config.HoodieRealtimeConfig.DEFAULT_MAX_DFS_STREAM_BUFFER_SIZE; +import static org.apache.hudi.hadoop.config.HoodieRealtimeConfig.DEFAULT_SPILLABLE_MAP_BASE_PATH; +import static org.apache.hudi.hadoop.config.HoodieRealtimeConfig.ENABLE_OPTIMIZED_LOG_BLOCKS_SCAN; +import static org.apache.hudi.hadoop.config.HoodieRealtimeConfig.MAX_DFS_STREAM_BUFFER_SIZE_PROP; +import static org.apache.hudi.hadoop.config.HoodieRealtimeConfig.SPILLABLE_MAP_BASE_PATH_PROP; +import static org.apache.hudi.hadoop.utils.HoodieRealtimeRecordReaderUtils.getBaseFileReader; +import static org.apache.hudi.hadoop.utils.HoodieRealtimeRecordReaderUtils.getMaxCompactionMemoryInBytes; +import static org.apache.hudi.internal.schema.InternalSchema.getEmptyInternalSchema; + +/** + * An implementation of {@link AbstractRealtimeRecordReader} that reads from base parquet files and log files, + * and merges the records on the fly. It differs from {@link HoodieRealtimeRecordReader} in that it does not + * implement Hadoop's RecordReader interface, and instead implements Iterator interface that returns an iterator + * of {@link HoodieRecord}s which are {@link HoodieAvroIndexedRecord}s. This can be used by query engines like + * Trino that do not use Hadoop's RecordReader interface. However, the engine must support reading from iterators + * and also support Avro (de)serialization. + */ +public class HoodieMergeOnReadSnapshotReader extends AbstractRealtimeRecordReader implements Iterator<HoodieRecord>, AutoCloseable { + + private static final Logger LOG = LoggerFactory.getLogger(HoodieMergeOnReadSnapshotReader.class); + + private final String tableBasePath; + private final List<HoodieLogFile> logFilePaths; + private final String latestInstantTime; + private final Schema readerSchema; + private final JobConf jobConf; + private final HoodieMergedLogRecordScanner logRecordScanner; + private final HoodieFileReader baseFileReader; + private final Map<String, HoodieRecord> logRecordsByKey; + private final Iterator<HoodieRecord> recordsIterator; + private final ExternalSpillableMap<String, HoodieRecord> mergedRecordsByKey; + + /** + * In order to instantiate this record reader, one needs to provide following parameters. + * An example usage is demonstrated in TestHoodieMergeOnReadSnapshotReader. + * + * @param tableBasePath Base path of the Hudi table + * @param baseFilePath Path of the base file as of the latest instant time for the split being processed + * @param logFilePaths Paths of the log files as of the latest file slices pertaining to file group id of the base file + * @param latestInstantTime Latest instant time + * @param readerSchema Schema of the reader + * @param jobConf Any job configuration + * @param start Start offset + * @param length Length of the split + */ + public HoodieMergeOnReadSnapshotReader(String tableBasePath, Review Comment: oh man. another record reader impl? Did we take a look at [HoodieMergedReadHandle](https://github.com/apache/hudi/blob/0ca0999420ca36b777b23fc9cf3998ce8f31481f/hudi-client/hudi-client-common/src/main/java/org/apache/hudi/io/HoodieMergedReadHandle.java) ? -- 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]
