第一个mapreduce

wordcount

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 WordCount {
    public static void main(String[] args) throws Exception {
        //定义配置变量
        Configuration conf=new Configuration();
        //定义一个工作任务对象
        Job job=Job.getInstance(conf);
        //获取map的一个对象
        job.setMapperClass(WordCountMap.class);
        //指定map阶段的一个输出key
        job.setMapOutputKeyClass(Text.class);
        //指定map阶段输出的values类型
        job.setMapOutputValueClass(IntWritable.class);
        //map阶段的输入文件
        FileInputFormat.setInputPaths(job,new Path("C:/Users/hasee/Desktop/藏宝库.txt"));

        //指定Reduce的类
        job.setReducerClass(WordCountReduce.class);
        //指定reduce阶段的一个输出key'
        job.setOutputKeyClass(Text.class);
        //指定reduce阶段输出的values类型
        job.setOutputValueClass(IntWritable.class);
        //指定reduce阶段的输出文件
        FileOutputFormat.setOutputPath(job,new Path("C:/Users/hasee/Desktop/12.txt"));
        job.waitForCompletion(true);
    }
}

wordcountmap

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 WordCountMap extends Mapper<LongWritable,Text, Text, IntWritable> {
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        //读取每行文本
        String line =value.toString();
        //splite拆分每行
        String[] words =line.split("/t");
        //取出每个单词
        for(String word : words){
            //将单词转变为Text类型
            Text wordText = new Text(word);
            //将1转变为IntWritable
            IntWritable outValue = new IntWritable(1);
            //写出单词跟对应1
            context.write(wordText,outValue);
        }
    }
}

wordcountreduce

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

import java.io.IOException;

//Text 输入的字符串类型，序列化
//IntWritable 输入一串1，序列化
//Text 输出的字符串类型，序列化
//IntWritable 输出的求和数组，序列化
public class WordCountReduce extends Reducer<Text, IntWritable,Text, IntWritable> {
//    key 输入单词名字
//    values 输入一串1
//    context 输出的工具
    @Override
    protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
        int sum=0;
        for(IntWritable number:values){
            sum += number.get();
        }
        context.write(key,new IntWritable(sum));
    }
}