Mapreduce的使用

创建三个类：

package com.example.mapreduce;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
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 WordCountDriver {public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {//设置用户名：System.setProperty("HADOOP_USER_NAME", "root");//1.获取job对象Configuration conf = new Configuration();conf.set("fs.defaultFS", "hdfs://hadoop100:8020");Job job = Job.getInstance(conf);//2.关联啊本地Driver类的jarjob.setJarByClass(WordCountDriver.class);//3.关联map和reducejob.setMapperClass(WordCountMapper.class);job.setReducerClass(WordCountReducer.class);//4.设置map的输出kv类型job.setMapOutputKeyClass(Text.class);job.setMapOutputValueClass(LongWritable.class);//5.设置map的输出kv类型job.setOutputKeyClass(Text.class);job.setOutputValueClass(LongWritable.class);//6.设置输入数据和输出结果的地址//FileInputFormat.setInputPaths(job, new Path("E\\cinput"));//FileOutputFormat.setOutputPath(job, new Path("E\\output10"));FileInputFormat.setInputPaths(job, new Path("/cinput"));FileOutputFormat.setOutputPath(job, new Path("/output10"));//7.提交jobSystem.exit(job.waitForCompletion(true) ? 0 : 1);}
}

package com.example.mapreduce;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.io.Text;import java.io.IOException;
//1.继承 hadoop的map重写
//2.重写map方法
public class WordCountMapper extends Mapper<LongWritable, Text, Text, LongWritable> {@Overrideprotected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {//每一行的文本内容，使用空格做拆分，得到一个列表String[] words = value.toString().split(" ");//对每一个单词，把它当做key,并设置value为1for (String word : words) {context.write(new Text(word), new LongWritable(1));}}
}

package com.example.mapreduce;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.io.Text;
import java.io.IOException;
//继承hadoop的reducer类
//重写reduce方法
public class WordCountReducer extends Reducer<Text, LongWritable, Text, LongWritable> {@Overrideprotected void reduce(Text key, Iterable<LongWritable> values, Context context) throws IOException, InterruptedException {//对value中的值做累加求和long sum = 0;for (LongWritable value : values) {sum += value.get();}//将结果输出context.write(key, new LongWritable(sum));}
}