一个简单的MR程序

一、pom.xml

    <dependency>
      <groupId>org.apache.hadoop</groupId>
      <artifactId>hadoop-client</artifactId>
      <version>2.5.0</version>
    </dependency>
    <dependency>
      <groupId>org.apache.hadoop</groupId>
      <artifactId>hadoop-common</artifactId>
      <version>2.5.0</version>
    </dependency>
    <dependency>
      <groupId>org.apache.hadoop</groupId>
      <artifactId>hadoop-hdfs</artifactId>
      <version>2.5.0</version>
    </dependency>

二、hadoop环境信息加入resources内

三、MR wordCount示例

package com.cys.mr;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
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;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;

import java.io.IOException;
import java.net.URI;

public class WordCountMapReducer extends Configured implements Tool {

	//Map类实现map方法，类型为map键值得输入输出类型<LongWritable, Text, Text, LongWritable>
    public static class WCMapper extends Mapper<LongWritable, Text, Text, LongWritable> {

		
        @Override
        protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {

            String line = value.toString();
            String[] words = line.split(" ");
            for(String word: words){

				//将map输出提交给context，context对象衔接map和reduce
                context.write(new Text(word),new LongWritable(1));
            }

        }
    }

    public static class WCReducer extends Reducer<Text, LongWritable, Text, LongWritable> {

        @Override
        protected void reduce(Text key, Iterable<LongWritable> values, Context context) throws IOException, InterruptedException {
            long sum = 0;
            for(LongWritable value: values){
                sum += value.get();
            }

            System.out.println("key: "+key+",value: "+sum);
            context.write(key, new LongWritable(sum));
        }
    }

    @Override
    public int run(String[] args) throws Exception {
        Configuration conf = new Configuration();
        //conf.addResource("core-site.xml");
        conf.set("mapreduce.app-submission.cross-platform","true");
        conf.set("fs.defaultFS", "hdfs://bigdata01:8020");// 指定namenode
        conf.set("mapreduce.framework.name", "yarn"); // 指定使用yarn框架
        conf.set("yarn.resourcemanager.address", "bigdata01:8032"); // 指定resourcemanager
        conf.set("yarn.resourcemanager.scheduler.address", "bigdata01:8030");// 指定资源分配器
        conf.set("mapreduce.jobhistory.address", "bigdata01:10020");


        Job job = Job.getInstance(conf,this.getClass().getSimpleName());


        Path pathIn = new Path(args[0]);
        Path pathOut = new Path(args[1]);
        FileSystem fs = FileSystem.get(URI.create(args[1]),conf);

        if(fs.exists(pathOut)){
            fs.delete(pathOut,true);
        }

        FileInputFormat.setInputPaths(job, pathIn);
        FileOutputFormat.setOutputPath(job, pathOut);

        job.setMapperClass(WCMapper.class);
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(LongWritable.class);

        job.setReducerClass(WCReducer.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(LongWritable.class);

        job.setJarByClass(WordCountMapReducer.class);
        //job.setJar("C:\\Users\\cys\\IdeaProjects\\MRTest\\out\\artifacts\\MRTest_jar\\MRTest.jar");


        boolean isSuccess = job.waitForCompletion(true);
        return isSuccess?1:-1;
    }

    public static void main(String[] args) throws Exception {
        args = new String[]{
                "/input/wordcount.txt",
                "/output"
        };

        ToolRunner.run(new WordCountMapReducer(), args);
    }
}

四、导出jar包提交到hadoop运行

$ bin/yarn jar mrtest.jar