com.mb.saas.bi.job.WordCountJob.java Source code

Java tutorial

Introduction

Here is the source code for com.mb.saas.bi.job.WordCountJob.java

Source

package com.mb.saas.bi.job;

/**
 * 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.
 */

import java.io.File;
import java.io.IOException;
import java.util.StringTokenizer;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapred.JobConf;
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;

import com.mb.saas.bi.config.Constants;
import com.mb.saas.bi.util.UploadResource;

public class WordCountJob {

    public static class TokenizerMapper extends Mapper<Object, Text, Text, IntWritable> {

        private final static IntWritable one = new IntWritable(1);
        private Text word = new Text();

        public void map(Object key, Text value, Context context) throws IOException, InterruptedException {
            StringTokenizer itr = new StringTokenizer(value.toString());
            while (itr.hasMoreTokens()) {
                word.set(itr.nextToken());
                context.write(word, one);
            }
        }
    }

    public static class IntSumReducer extends Reducer<Text, IntWritable, Text, IntWritable> {
        private IntWritable result = new IntWritable();

        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);
        }
    }

    public static boolean runHadoopMapReduceJob() throws Exception {
        System.setProperty("HADOOP_USER_NAME", "hadoop");

        File jarFile = UploadResource.createTempJar("bin");
        ClassLoader classLoader = UploadResource.getClassLoader();
        Thread.currentThread().setContextClassLoader(classLoader);

        Configuration conf = new Configuration();

        conf.set("fs.defaultFS", "hdfs://mbcluster/");
        conf.set("dfs.nameservices", "mbcluster");
        conf.set("dfs.ha.namenodes.mbcluster", "ns1,ns2");
        conf.set("dfs.namenode.rpc-address.mbcluster.ns1", "master:4001");
        conf.set("dfs.namenode.rpc-address.mbcluster.ns2", "backup:4001");
        conf.set("dfs.client.failover.proxy.provider.mbcluster",
                "org.apache.hadoop.hdfs.server.namenode.ha.ConfiguredFailoverProxyProvider");

        Job job = new Job(conf, "word count");
        job.setJarByClass(WordCountJob.class);
        job.setMapperClass(TokenizerMapper.class);
        job.setCombinerClass(IntSumReducer.class);
        job.setReducerClass(IntSumReducer.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);

        if (jarFile != null)
            ((JobConf) job.getConfiguration()).setJar(jarFile.getAbsolutePath());

        boolean isMapReduceJarSetted = false;
        String hadoopMapReduceJar = "F:/henry_projects/mbHiveAnalyzer/t.jar";
        File file = new File(hadoopMapReduceJar);
        if (file.exists()) {
            ((JobConf) job.getConfiguration()).setJar(hadoopMapReduceJar);
            isMapReduceJarSetted = true;
        }

        if (!isMapReduceJarSetted && jarFile != null)
            ((JobConf) job.getConfiguration()).setJar(jarFile.getAbsolutePath());

        job.setNumReduceTasks(1);
        FileInputFormat.addInputPath(job, new Path("/input/wordcount.txt"));
        FileOutputFormat.setOutputPath(job, new Path("/output/001"));
        System.exit(job.waitForCompletion(true) ? 0 : 1);
        return true;
    }

    public static void main(String[] args) throws Exception {
        System.setProperty("HADOOP_USER_NAME", "hadoop");

        File jarFile = UploadResource.createTempJar("bin");
        System.setProperty("hadoop.home.dir", "F:/hadoop");
        ClassLoader classLoader = UploadResource.getClassLoader();
        Thread.currentThread().setContextClassLoader(classLoader);

        Configuration conf = new Configuration();
        //   conf.set("fs.defaultFS", "hdfs://slave1:4001");
        //   conf.set("mapreduce.framework.name", "yarn");
        //   conf.set("yarn.resourcemanager.address", "master:8032");
        //   conf.set("yarn.resourcemanager.scheduler.address", "master:8030");

        conf.set("fs.defaultFS", "hdfs://mbcluster/");
        conf.set("dfs.nameservices", "mbcluster");
        conf.set("dfs.ha.namenodes.mbcluster", "ns1,ns2");
        conf.set("dfs.namenode.rpc-address.mbcluster.ns1", "master:4001");
        conf.set("dfs.namenode.rpc-address.mbcluster.ns2", "backup:4001");
        conf.set("dfs.client.failover.proxy.provider.mbcluster",
                "org.apache.hadoop.hdfs.server.namenode.ha.ConfiguredFailoverProxyProvider");

        conf.set("mapred.remote.os", "Linux");
        System.out.println(conf.get("mapred.remote.os"));

        //   conf.set("mapreduce.job.reduces", "2");
        //   conf.set("mapreduce.tasktracker.map.tasks.maximum", "8");
        //   conf.set("mapreduce.input.fileinputformat.split.maxsize","123");

        Job job = new Job(conf, "word count");
        job.setJarByClass(WordCountJob.class);
        job.setMapperClass(TokenizerMapper.class);
        job.setCombinerClass(IntSumReducer.class);
        job.setReducerClass(IntSumReducer.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);

        if (jarFile != null)
            ((JobConf) job.getConfiguration()).setJar(jarFile.getAbsolutePath());

        //    job.setMaxMapAttempts(2);
        job.setNumReduceTasks(1);
        FileInputFormat.addInputPath(job, new Path("/input/wordcount2.txt"));
        //    FileInputFormat.addInputPath(job, new Path("/input/wordcount2.txt"));
        FileOutputFormat.setOutputPath(job, new Path("/output/001002"));
        System.exit(job.waitForCompletion(true) ? 0 : 1);
    }
}