org.apache.hadoop.mapred.MapRunner.java Source code

Introduction

Here is the source code for org.apache.hadoop.mapred.MapRunner.java

Source

/**
 * 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.hadoop.mapred;

import java.io.IOException;

import org.apache.hadoop.classification.InterfaceAudience;
import org.apache.hadoop.classification.InterfaceStability;
import org.apache.hadoop.util.ReflectionUtils;

/** Default {@link MapRunnable} implementation.*/
@InterfaceAudience.Public
@InterfaceStability.Stable
public class MapRunner<K1, V1, K2, V2> implements MapRunnable<K1, V1, K2, V2> {

    private Mapper<K1, V1, K2, V2> mapper;
    private boolean incrProcCount;

    @SuppressWarnings("unchecked")
    public void configure(JobConf job) {
        this.mapper = ReflectionUtils.newInstance(job.getMapperClass(), job);
        //increment processed counter only if skipping feature is enabled
        this.incrProcCount = SkipBadRecords.getMapperMaxSkipRecords(job) > 0
                && SkipBadRecords.getAutoIncrMapperProcCount(job);
    }

    public void run(RecordReader<K1, V1> input, OutputCollector<K2, V2> output, Reporter reporter)
            throws IOException {
        try {
            // allocate key & value instances that are re-used for all entries
            K1 key = input.createKey();
            V1 value = input.createValue();

            while (input.next(key, value)) {
                // map pair to output
                mapper.map(key, value, output, reporter);
                if (incrProcCount) {
                    reporter.incrCounter(SkipBadRecords.COUNTER_GROUP, SkipBadRecords.COUNTER_MAP_PROCESSED_RECORDS,
                            1);
                }
            }
        } finally {
            mapper.close();
        }
    }

    protected Mapper<K1, V1, K2, V2> getMapper() {
        return mapper;
    }
}