【Hadoop2.x】Eclipse 提交MR Job

1、建立Maven Project

hello-hadoop

bash-3.2$ /usr/local/bin/tree -L 4
.
├── pom.xml
└── src
    ├── main
    │   ├── java
    │   │   └── com
    │   └── resources
    │       ├── core-site.xml            ==>從Hadoop機器上下載配置文件
    │       ├── hdfs-site.xml
    │       ├── log4j.properties         ==>調整日誌級別
    │       ├── mapred-site.xml
    │       └── yarn-site.xml
    └── test

6 directories, 6 files

2、添加Hadoop依賴

cat pom.xml

....
<dependency>
    <groupId>org.apache.hadoop</groupId>
    <artifactId>hadoop-common</artifactId>
    <version>2.7.1</version>
</dependency>
<dependency>
    <groupId>org.apache.hadoop</groupId>
    <artifactId>hadoop-hdfs</artifactId>
    <version>2.7.1</version>
</dependency>
<dependency>
    <groupId>org.apache.hadoop</groupId>
    <artifactId>hadoop-mapreduce-client-jobclient</artifactId>
    <version>2.7.1</version>
</dependency>
...

3、編寫MR

package com.harry.examples;

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.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 WordCount {

	public static class TokenizerMapper extends Mapper<LongWritable, Text, Text, IntWritable> {
		private final static IntWritable one = new IntWritable(1);
		private Text word = new Text();

		@Override
		protected void map(LongWritable key, Text value, Mapper<LongWritable, Text, Text, IntWritable>.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();

		@Override
		protected void reduce(Text key, Iterable<IntWritable> values,
				Reducer<Text, IntWritable, Text, IntWritable>.Context context)
				throws IOException, InterruptedException {
			int sum = 0;

			for (IntWritable value : values) {
				sum += value.get();
			}

			result.set(sum);

			context.write(key, result);
		}
	}

	public static void main(String[] args) throws Exception {
		Configuration configuration = new Configuration();
		// configuration.set("mapreduce.framework.name", "yarn");
		// configuration.addResource("classpath:/hadoop/core-site.xml");
		// configuration.addResource("classpath:/hadoop/hdfs-site.xml");
		// configuration.addResource("classpath:/hadoop/mapred-site.xml");
		// configuration.addResource("classpath:/hadoop/yarn-site.xml");

		Job job = Job.getInstance(configuration, "WordCount");
		job.setJarByClass(WordCount.class);
		job.setMapperClass(TokenizerMapper.class);
		job.setCombinerClass(IntSumReducer.class);
		job.setReducerClass(IntSumReducer.class);

		job.setOutputKeyClass(Text.class);
		job.setOutputValueClass(IntWritable.class);
                //添加mr job的jar，使用mvn clean package 打jar，填寫絕對路徑
		job.setJar("hello-hadoop-0.0.1-SNAPSHOT.jar");

                //hdfs路徑
		FileInputFormat.addInputPath(job, new Path("hdfs://master:9000/tmp/README.md"));
		FileOutputFormat.setOutputPath(job, new Path("hdfs://master:9000/tmp/wc"));

		System.exit(job.waitForCompletion(true) ? 0 : 1);

	}
}

4、run

-> Run As -> Java Application

能夠調整log4j.properties的日誌級別。能夠在console中看到日誌