jenniferdai commented on a change in pull request #4253: Add segment pre-processing Hadoop job URL: https://github.com/apache/incubator-pinot/pull/4253#discussion_r290839617
########## File path: pinot-hadoop/src/main/java/org/apache/pinot/hadoop/job/reducer/SegmentPreprocessingReducer.java ########## @@ -0,0 +1,84 @@ +/** + * 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.pinot.hadoop.job.reducer; + +import java.io.IOException; +import java.util.concurrent.atomic.AtomicInteger; +import org.apache.avro.generic.GenericRecord; +import org.apache.avro.mapred.AvroKey; +import org.apache.avro.mapred.AvroValue; +import org.apache.avro.mapreduce.AvroMultipleOutputs; +import org.apache.commons.lang3.RandomStringUtils; +import org.apache.hadoop.conf.Configuration; +import org.apache.hadoop.io.NullWritable; +import org.apache.hadoop.mapreduce.Reducer; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +import static org.apache.pinot.hadoop.job.JobConfigConstants.*; + + +public class SegmentPreprocessingReducer<T> + extends Reducer<T, AvroValue<GenericRecord>, AvroKey<GenericRecord>, NullWritable> { + private static final Logger LOGGER = LoggerFactory.getLogger(SegmentPreprocessingReducer.class); + + private AvroMultipleOutputs _multipleOutputs; + private AtomicInteger _counter; + private int _maxNumberOfRecords; + private String _filePrefix; + + @Override + public void setup(Context context) { + LOGGER.info("Using multiple outputs strategy."); + Configuration configuration = context.getConfiguration(); + _multipleOutputs = new AvroMultipleOutputs(context); + _counter = new AtomicInteger(); + _maxNumberOfRecords = configuration.getInt(MAXIMUM_NUMBER_OF_RECORDS, 0); + LOGGER.info("Maximum number of records per file: {}", _maxNumberOfRecords); + _filePrefix = RandomStringUtils.randomAlphanumeric(4); Review comment: interesting, so each reducer no longer just generates one file, how do we determine that? ---------------------------------------------------------------- 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 --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
