hadoop算法(100万个数字取最大值)

Map

import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;


public class MyMapper extends Mapper<LongWritable, Text, LongWritable, NullWritable> {
	long max = Long.MIN_VALUE;

	protected void map(LongWritable key, Text value,Context context)
			throws java.io.IOException, InterruptedException {
		Long current = Long.parseLong(value.toString());
		if (current > max) {
			max = current;
		}
	};
	//当mapper结束的时候执行的,因为每一行都执行一次map函数,所以不能在map函数里写context.write
	protected void cleanup(
			org.apache.hadoop.mapreduce.Mapper<LongWritable, Text, LongWritable, NullWritable>.Context context)
			throws java.io.IOException, InterruptedException {
		context.write(new LongWritable(max), NullWritable.get());
	};
}

需要注意的是map和reduce类中都有个cleanup方法,也就是当map和reduce执行完任务后会去执行cleanup方法。

Reduce

import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.mapreduce.Reducer;

/**
 * 因为reduce接收的是从多个map任务输出的结果,所以在reduce中还要进行一个比较大小的操作
 * 
 */
public class MyReduce extends Reducer<LongWritable, NullWritable, LongWritable, NullWritable> {
	long max = Long.MIN_VALUE;

	protected void reduce(LongWritable key2, java.lang.Iterable<NullWritable> values2,
			org.apache.hadoop.mapreduce.Reducer<LongWritable, NullWritable, LongWritable, NullWritable>.Context context)
			throws java.io.IOException, InterruptedException {
		long current = key2.get();
		if (current > max) {
			max = current;
		}
	};

	// 由于一个mapper输出执行一次reduce,所以只有在reduce全部执行完毕后才晓得最大值
	protected void cleanup(
			org.apache.hadoop.mapreduce.Reducer<LongWritable, NullWritable, LongWritable, NullWritable>.Context context)
			throws java.io.IOException, InterruptedException {
		context.write(new LongWritable(max), NullWritable.get());
	};
}

测试类

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

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
import org.apache.hadoop.mapreduce.lib.partition.HashPartitioner;

public class TestMaxNum {
	private static final String INPUT_PATH = "hdfs://xxc:9000/input";
	private static final String OUT_PATH = "hdfs://xxc:9000/out";

	public static void main(String[] args) throws IOException, InterruptedException, ClassNotFoundException, URISyntaxException {
		Configuration conf = new Configuration();
		
		FileSystem fileSystem = FileSystem.get(new URI(INPUT_PATH), conf);
		Path outPath = new Path(OUT_PATH);
		if(fileSystem.exists(outPath)){
			fileSystem.delete(outPath, true);
		}
		
		Job job = new Job(conf,TestMaxNum.class.getSimpleName());
		
		//1.1 指定读取的文件路径
		FileInputFormat.setInputPaths(job, INPUT_PATH);
		//指定如何对输入文件进行格式化,把输入文件每一行解析成键值对
		job.setInputFormatClass(TextInputFormat.class);

		//1.2 指定自定义的map类
		job.setMapperClass(MyMapper.class);
		//指定map输出的<k,v>类型.如果<k3,v3>的类型和<k2,v2>类型一致,则可以省略
		job.setMapOutputKeyClass(LongWritable.class);
		job.setMapOutputValueClass(NullWritable.class);
		
		//1.3 分区
		job.setPartitionerClass(HashPartitioner.class);
		//有一个reduce任务运行
		job.setNumReduceTasks(1);
		
		//1.4 TODO 排序、分组
		
		//1.5  规约 
		job.setCombinerClass(MyReduce.class);
		
		
		//2.2  指定自定义reduce类
		job.setReducerClass(MyReduce.class);
		//指定reduce的输出类型
		job.setOutputKeyClass(LongWritable.class);
		job.setOutputValueClass(NullWritable.class);
		
		//2.3 指定输出到哪个路径
		FileOutputFormat.setOutputPath(job, new Path(OUT_PATH));
		job.setOutputFormatClass(TextOutputFormat.class);
		//把job提交给JobTracker运行
		job.waitForCompletion(true);
		
	}
}