Hadoop之MapReduces统计单词个数

    
        org.apache.hadoop
        hadoop-client
        3.1.4
    
    
        junit
        junit
        4.12
    
    
        org.slf4j
        slf4j-log4j12
        1.7.30
    

重新载入

log4j.rootLogger=INFO, stdout  
log4j.appender.stdout=org.apache.log4j.ConsoleAppender  
log4j.appender.stdout.layout=org.apache.log4j.PatternLayout  
log4j.appender.stdout.layout.ConversionPattern=%d %p [%c] - %m%n  
log4j.appender.logfile=org.apache.log4j.FileAppender  
log4j.appender.logfile.File=target/spring.log  
log4j.appender.logfile.layout=org.apache.log4j.PatternLayout  
log4j.appender.logfile.layout.ConversionPattern=%d %p [%c] - %m%n

package com.haoedu.wordcount;

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 WordCountMapper extends Mapper {
    private Text outkey= new Text();
    private IntWritable outvalue = new IntWritable(1);

    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        //获取一行
        String line = value.toString();
        String[] words = line.split(",");
        for (String word : words) {
            outkey.set(word);
            context.write(outkey, outvalue);
        }
    }
}

package com.haoedu.wordcount;


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

import java.io.IOException;


public class WordCountReducer extends Reducer {
    private IntWritable outvalue = new IntWritable();
    @Override
    protected void reduce(Text key, Iterable values, Context context) throws IOException, InterruptedException {
        int sum = 0;
        for (IntWritable value : values) {
            sum += value.get();
        }
        outvalue.set(sum);

        context.write(key,outvalue);
    }
}

package com.haoedu.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;

import java.io.IOException;

public class WordCountDriver {

    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {

        // 1 获取job
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);

        // 2 设置jar包路径
        job.setJarByClass(WordCountDriver.class);

        // 3 关联mapper和reducer
        job.setMapperClass(WordCountMapper.class);
        job.setReducerClass(WordCountReducer.class);

        // 4 设置map输出的kv类型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);

        // 5 设置最终输出的kV类型
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);

        // 6 设置输入路径和输出路径
        FileInputFormat.setInputPaths(job, new Path("D:\大数据全集资料\Hadoop3.x\11_input\inputword"));
        FileOutputFormat.setOutputPath(job, new Path("D:\大数据全集资料\Hadoop3.x\output888"));

        // 7 提交job
        boolean result = job.waitForCompletion(true);

        System.exit(result ? 0 : 1);





    }
}

结果如下

注入依赖

    
        
            maven-compiler-plugin
            3.6.1
            
                1.8
                1.8
            
        
        
            maven-assembly-plugin
            
                
                    jar-with-dependencies
                
            
            
                
                    make-assembly
                    package
                    
                        single
                    
                
            
        
    

在集群上运行的时候需要动态输入,输入输出改成

args[0],args[1]