java MapReduce步骤

1、Eclipse简历Maven工程，由Maven管理jar，打开pom.xml——>添加

<build>  
        <plugins>  
            <plugin>  
            <artifactId>maven-assembly-plugin</artifactId>  <span style="white-space:pre">			</span><!--maven一个插件，具体查看另一博客-->
            <version>2.4.1</version>
                <configuration>  
                    <archive>  
                        <manifest>  
                            <mainClass>hadooptest.TestStart</mainClass>         <!--执行主函数-->
                        </manifest>  
                    </archive>  
                    <descriptorRefs>  
                        <descriptorRef>jar-with-dependencies</descriptorRef>  <span style="white-space:pre">	</span><!--打包时把依赖jar包打入包中-->
                    </descriptorRefs>  
                </configuration>  
            </plugin>  
        </plugins>  
    </build>  
	<dependencies>
		<dependency>
			<groupId>org.apache.hadoop</groupId><span style="white-space:pre">			</span><!--maven管理依赖-->
			<artifactId>hadoop-core</artifactId>
			<version>1.2.1</version>
		</dependency>
	</dependencies>

2、新建mapper处理，代码如下

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

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapred.MapReduceBase;
import org.apache.hadoop.mapred.Mapper;
import org.apache.hadoop.mapred.OutputCollector;
import org.apache.hadoop.mapred.Reporter;

public class TestMapper extends MapReduceBase implements Mapper<LongWritable, Text, Text, IntWritable> {
	private final static IntWritable one = new IntWritable(1);
	private final Text word = new Text();
	public void map(LongWritable key, Text value,
			OutputCollector<Text, IntWritable> output, Reporter reporter)
			throws IOException {
		String line = value.toString();
		StringTokenizer tokenizer = new StringTokenizer(line);
		while (tokenizer.hasMoreTokens()) {
			word.set(tokenizer.nextToken());
			output.collect(word, one);
		}
	}

}

3、新建Reduce处理，代码如下：

import java.io.IOException;
import java.util.Iterator;

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapred.MapReduceBase;
import org.apache.hadoop.mapred.OutputCollector;
import org.apache.hadoop.mapred.Reducer;
import org.apache.hadoop.mapred.Reporter;

public class TestReduce extends MapReduceBase implements
		Reducer<Text, IntWritable, Text, IntWritable> {

	public void reduce(Text key, Iterator<IntWritable> value,
			OutputCollector<Text, IntWritable> output, Reporter reporter)
			throws IOException {
		int sum = 0;
		while (value.hasNext()) {
			sum += value.next().get();
		}
		output.collect(key, new IntWritable(sum));
	}

}

4、新建main方法，代码如下

import java.io.IOException;
import java.util.Iterator;

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapred.MapReduceBase;
import org.apache.hadoop.mapred.OutputCollector;
import org.apache.hadoop.mapred.Reducer;
import org.apache.hadoop.mapred.Reporter;

public class TestReduce extends MapReduceBase implements
		Reducer<Text, IntWritable, Text, IntWritable> {

	public void reduce(Text key, Iterator<IntWritable> value,
			OutputCollector<Text, IntWritable> output, Reporter reporter)
			throws IOException {
		int sum = 0;
		while (value.hasNext()) {
			sum += value.next().get();
		}
		output.collect(key, new IntWritable(sum));
	}

}

5、所有ok后，在当前工程下，执行命令mvn assembly:assembly。在target下面找到jar包

6、拷贝生成的jar到，运行的hadoop服务器下。启动hadoop

执行java -jar XXX.jar  本地输入文件   本地输出文件