06 MapReduce_取每人最高分

提示

在通过迭代器遍历values的时候，不要直接将value赋值给某个变量，因为这里是地址复制，后续value指向的值发生了变化，之前复制的那个变量的值收到影响

    protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
        IntWritable max = new IntWritable(0);
        // 在MapReduce为了节省内存空间，采取了地址复用机制
        // 在遍历迭代器的时候，迭代对象只创建一次
        // IntWritable val = new IntWritable();
        // val.set(312);
        // val.get() > max.get() -> 312 > 0 -> true
        // max = val; - val和max都是对象，所以赋值给的是地址 -> max和val的地址就一样了
        // val.set(684); - val和max的地址一样，那就意味着max中的值也变成了684
        // val.get() > max.get() -> 684 > 684 -> false
        // val.set(340); - max的值也跟着变成了340
        // 这么遍历下去，max的最终结果应该遍历的最后一个值
        for (IntWritable val : values) {
            if (val.get() > max.get())
                // max = val;
                "这里如果直接使用val复制，后续val的改变会影响到max，所以直接使用基本数据类型int进行赋值"
                max.set(val.get());
        }
        context.write(key, max);
    }

人名：分数1，分数2.分数3.分数4；
取最大值

package maxscore;

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

import java.io.IOException;

public class maxMapper extends Mapper<LongWritable,Text, Text, IntWritable> {
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        String[] s = value.toString().split(" ");
        context.write(new Text(s[0]),new IntWritable(Integer.valueOf(s[1])));
    }
}

package maxscore;

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

import java.io.IOException;

public class maxReducer extends Reducer<Text, IntWritable,Text,IntWritable> {
    @Override
    protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
        //找到values中的对大值
        int maxScore = 0;
        for(IntWritable i : values){
            if(i.get()>=maxScore)
                maxScore = i.get();
        }
        context.write(key,new IntWritable(maxScore));
    }
}

package maxscore;

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;

import java.io.IOException;

public class maxDriver {
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);
        job.setJarByClass(maxDriver.class);
        job.setMapperClass(maxMapper.class);
        job.setReducerClass(maxReducer.class);
        //设置mapper的输出类型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);
        //设置reducer的输出类型
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);
        //文件输入路径
        FileInputFormat.addInputPath(job,new Path("hdfs://hadoop01:9000/txt/score2.txt"));
        // 设置输出路径
        // 要求输出路径在HDFS上不存在
        FileOutputFormat.setOutputPath(job, new Path("hdfs://hadoop01:9000/result/score"));
        // 提交任务
        job.waitForCompletion(true);
    }
}