Java tutorial
/**************************************************************** * Licensed to the AOS Community (AOS) under one or more * * contributor license agreements. See the NOTICE file * * distributed with this work for additional information * * regarding copyright ownership. The AOS 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 io.aos.t4f.hadoop.mapreduce; import java.io.IOException; import java.util.HashMap; import java.util.Map; import java.util.StringTokenizer; import org.apache.hadoop.conf.Configuration; import org.apache.hadoop.filecache.DistributedCache; import org.apache.hadoop.fs.Path; import org.apache.hadoop.io.IntWritable; import org.apache.hadoop.io.LongWritable; import org.apache.hadoop.io.Text; import org.apache.hadoop.mapreduce.Job; import org.apache.hadoop.mapreduce.Mapper; import org.apache.hadoop.mapreduce.Reducer; import org.apache.hadoop.mapreduce.lib.input.FileInputFormat; import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat; public class WordCountMapReduceTest3 { private static Map<Text, IntWritable> map = new HashMap<Text, IntWritable>(); public void testMapReduce() throws Exception { String inputPath = "/docs/ChangesFancyStyle.css"; String outputPath = "/out"; Configuration configuration = new Configuration(); configuration.set("fs.default.name", "hdfs://ppc006:54310"); configuration.set("mapred.job.tracker", "ppc006:54311"); configuration.set("mapred.job.tracker", "local"); configuration.set("fs.default.name", "local"); DistributedCache.addArchiveToClassPath(new Path("/jar/t4f-nosql-hadoop-1.0-SNAPSHOT.jar"), configuration); Job job = new Job(configuration); // job.setJarByClass(Driver.class); job.setJobName("TestJob"); job.setMapperClass(MapClass.class); job.setReducerClass(ReduceClass.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(IntWritable.class); FileInputFormat.addInputPath(job, new Path(inputPath)); FileOutputFormat.setOutputPath(job, new Path(outputPath)); job.waitForCompletion(true); } public static class MapClass extends Mapper<LongWritable, Text, Text, IntWritable> { private final static IntWritable one = new IntWritable(1); private Text word = new Text(); @Override public void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException { String line = value.toString(); StringTokenizer itr = new StringTokenizer(line); while (itr.hasMoreTokens()) { word.set(itr.nextToken()); context.write(word, one); } } } /** * A reducer class that just emits the sum of the input values. */ public static class ReduceClass extends Reducer<Text, IntWritable, Text, IntWritable> { private IntWritable result = new IntWritable(); @Override public void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException { int sum = 0; for (IntWritable val : values) { sum += val.get(); } result.set(sum); context.write(key, result); map.put(key, result); System.out.println("===" + map.size()); } } }