org.apache.hadoop.examples.Join Maven / Gradle / Ivy
/**
* 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.examples;
import java.io.IOException;
import java.util.ArrayList;
import java.util.Date;
import java.util.List;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.BytesWritable;
import org.apache.hadoop.io.Writable;
import org.apache.hadoop.io.WritableComparable;
import org.apache.hadoop.mapred.ClusterStatus;
import org.apache.hadoop.mapred.JobClient;
import org.apache.hadoop.mapreduce.InputFormat;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.OutputFormat;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.SequenceFileInputFormat;
import org.apache.hadoop.mapreduce.lib.join.CompositeInputFormat;
import org.apache.hadoop.mapreduce.lib.join.TupleWritable;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.SequenceFileOutputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;
/**
* Given a set of sorted datasets keyed with the same class and yielding
* equal partitions, it is possible to effect a join of those datasets
* prior to the map. The example facilitates the same.
*
* To run: bin/hadoop jar build/hadoop-examples.jar join
* [-r reduces]
* [-inFormat input format class]
* [-outFormat output format class]
* [-outKey output key class]
* [-outValue output value class]
* [-joinOp <inner|outer|override>]
* [in-dir]* in-dir out-dir
*/
public class Join extends Configured implements Tool {
public static final String REDUCES_PER_HOST = "mapreduce.join.reduces_per_host";
static int printUsage() {
System.out.println("join [-r ] " +
"[-inFormat ] " +
"[-outFormat