MapReduce之自定义分区器Partitioner

public class HashPartitioner<K,V> extends Partitioner<K,V>{
	public int getPartition(K key,V value, int numReduceTasks){
		return (key.hashCode() & Integer.MAX VALUE) & numReduceTasks;
	}
}

public class CustomPartitioner extends Partitioner<Text，FlowBea>{
	@Override 
	public int getPartition(Text key，FlowBean value，int numPartitions){
		//控制分区代码逻辑
		……
		return partition；
	}
}

job.setPartitionerClass(CustomPartitioner.class)

 job.setNumReduceTask(5);//假设需要分5个区

/*
 * KEY, VALUE: Mapper输出的Key-value类型
 */
public class MyPartitioner extends Partitioner<Text, FlowBean>{

	// 计算分区  numPartitions为总的分区数，reduceTask的数量
	// 分区号必须为int型的值，且必须符合 0<= partitionNum < numPartitions
	@Override
	public int getPartition(Text key, FlowBean value, int numPartitions) {
		
		String suffix = key.toString().substring(0, 3);//前开后闭，取手机号前三位数
		
		int partitionNum=0;//分区编号
		
		
		switch (suffix) {
		case "136":
			partitionNum=numPartitions-1;//由于分区编号不能大于分区总数，所以用这种方法比较好
			break;
		case "137":
			partitionNum=numPartitions-2;
			break;
		case "138":
			partitionNum=numPartitions-3;
			break;
		case "139":
			partitionNum=numPartitions-4;
			break;

		default:
			break;
		}

		return partitionNum;
	}

}

public class FlowBeanDriver {
	
	public static void main(String[] args) throws Exception {
		
		Path inputPath=new Path("e:/mrinput/flowbean");
		Path outputPath=new Path("e:/mroutput/partitionflowbean");
		
		//作为整个Job的配置
		Configuration conf = new Configuration();
		
		//保证输出目录不存在
		FileSystem fs=FileSystem.get(conf);
		
		if (fs.exists(outputPath)) {
			fs.delete(outputPath, true);
		}
		
		// ①创建Job
		Job job = Job.getInstance(conf);
		
		// ②设置Job
		// 设置Job运行的Mapper，Reducer类型，Mapper,Reducer输出的key-value类型
		job.setMapperClass(FlowBeanMapper.class);
		job.setReducerClass(FlowBeanReducer.class);
		
		// Job需要根据Mapper和Reducer输出的Key-value类型准备序列化器，通过序列化器对输出的key-value进行序列化和反序列化
		// 如果Mapper和Reducer输出的Key-value类型一致，直接设置Job最终的输出类型
		job.setOutputKeyClass(Text.class);
		job.setOutputValueClass(FlowBean.class);
		
		// 设置输入目录和输出目录
		FileInputFormat.setInputPaths(job, inputPath);
		FileOutputFormat.setOutputPath(job, outputPath);
		
		// 设置ReduceTask的数量为5
		job.setNumReduceTasks(5);
		
		// 设置使用自定义的分区器
		job.setPartitionerClass(MyPartitioner.class);
		
		// ③运行Job
		job.waitForCompletion(true);
		
	}
}

/*
 * 1. 统计手机号(String)的上行(long,int)，下行(long,int)，总流量(long,int)
 * 
 * 手机号为key,Bean{上行(long,int)，下行(long,int)，总流量(long,int)}为value
 * 		
 * 
 * 
 * 
 */
public class FlowBeanMapper extends Mapper<LongWritable, Text, Text, FlowBean>{
	
	private Text out_key=new Text();
	private FlowBean out_value=new FlowBean();
	
	// (0,1	13736230513	192.196.100.1	www.atguigu.com	2481	24681	200)
	@Override
	protected void map(LongWritable key, Text value, Mapper<LongWritable, Text, Text, FlowBean>.Context context)
			throws IOException, InterruptedException {
		
		String[] words = value.toString().split("t");
		
		//封装手机号
		out_key.set(words[1]);
		// 封装上行
		out_value.setUpFlow(Long.parseLong(words[words.length-3]));
		// 封装下行
		out_value.setDownFlow(Long.parseLong(words[words.length-2]));

		context.write(out_key, out_value);
	}
}

public class FlowBeanReducer extends Reducer<Text, FlowBean, Text, FlowBean>{
	
	private FlowBean out_value=new FlowBean();
	
	@Override
	protected void reduce(Text key, Iterable<FlowBean> values, Reducer<Text, FlowBean, Text, FlowBean>.Context context)
			throws IOException, InterruptedException {
		
		long sumUpFlow=0;
		long sumDownFlow=0;
		
		for (FlowBean flowBean : values) {
			
			sumUpFlow+=flowBean.getUpFlow();
			sumDownFlow+=flowBean.getDownFlow();
			
		}
		
		out_value.setUpFlow(sumUpFlow);
		out_value.setDownFlow(sumDownFlow);
		out_value.setSumFlow(sumDownFlow+sumUpFlow);
		
		context.write(key, out_value);
		
	}
}

public class FlowBean implements Writable{
	
	private long upFlow;
	private long downFlow;
	private long sumFlow;
	
	public FlowBean() {
		
	}

	public long getUpFlow() {
		return upFlow;
	}

	public void setUpFlow(long upFlow) {
		this.upFlow = upFlow;
	}

	public long getDownFlow() {
		return downFlow;
	}

	public void setDownFlow(long downFlow) {
		this.downFlow = downFlow;
	}

	public long getSumFlow() {
		return sumFlow;
	}

	public void setSumFlow(long sumFlow) {
		this.sumFlow = sumFlow;
	}

	// 序列化   在写出属性时，如果为引用数据类型，属性不能为null
	@Override
	public void write(DataOutput out) throws IOException {
		
		out.writeLong(upFlow);
		out.writeLong(downFlow);
		out.writeLong(sumFlow);
		
		
	}

	//反序列化   序列化和反序列化的顺序要一致
	@Override
	public void readFields(DataInput in) throws IOException {
		upFlow=in.readLong();
		downFlow=in.readLong();
		sumFlow=in.readLong();
		
	}

	@Override
	public String toString() {
		return  upFlow + "t" + downFlow + "t" + sumFlow;
	}
}