【Hadoop学习项目】4. 求最大最小值

0. 项目结构

1. MaxDriver

package hadoop_test.min_max_demo_04;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;



public class MaxDriver {
/* 数据内容
假设我们需要处理一批有关天气的数据，其格式如下：
按照ASCII码存储，每行一条记录。每行共24个字符（包含符号在内）
第9、10、11、12字符为年份，第19、20、21、22字符代表温度，求每年的最高和最低温度

2329999919500515070000
9909999919500515120022
9909999919500515180011
9509999919490324120111
6509999919490324180078
9909999919370515070001
9909999919370515120002
9909999919450515180001
6509999919450324120002
8509999919450324180078
 */
	public static void main(String[] args) throws Exception {

		System.setProperty("HADOOP_USER_NAME", "root");

		Configuration conf=new Configuration();
		Job job=Job.getInstance(conf);

		job.setJarByClass(MaxDriver.class);

		job.setMapperClass(MaxMapper.class);
		job.setReducerClass(MaxReducer.class);

		job.setMapOutputKeyClass(Text.class);
		job.setMapOutputValueClass(IntWritable.class);
		job.setOutputKeyClass(Text.class);
		job.setOutputValueClass(IntWritable.class);

		FileInputFormat.setInputPaths(job,new Path("/hadoop_test/min_max/min_max.data"));
		FileOutputFormat.setOutputPath(job,new Path("/hadoop_test/min_max/result"));
		
		job.waitForCompletion(true);

	}

}

2. MaxMapper

package hadoop_test.min_max_demo_04;

import java.io.IOException;

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

public class MaxMapper extends Mapper<LongWritable, Text, Text, IntWritable>{
	@Override
	protected void map(LongWritable key, Text value, Context context)
			throws IOException, InterruptedException {
		String line=value.toString();
//		拿出年份
		String year=line.substring(8,12);
//      拿出温度
		int temp=Integer.parseInt(line.substring(18));
		context.write(new Text(year), new IntWritable(temp));
	}

}

3. MaxReducer

package hadoop_test.min_max_demo_04;

import java.io.IOException;

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

public class MaxReducer extends Reducer<Text, IntWritable, Text, Text> {
	
	@Override
	protected void reduce(Text key, Iterable<IntWritable> values,
			Context context) throws IOException, InterruptedException {

		int max=0;						// 找最大的所以从0开始
		int min=Integer.MAX_VALUE;		// 找最小的所以从最大整数开始
		for(IntWritable value:values){
			if(max<value.get()){
				max=value.get();
			}
			if(min>value.get()){
				min=value.get();
			}
		}
		context.write(key, new Text(String.valueOf(max)+":"+String.valueOf(min)));
	}

}