mapreduce实现与流程解析—Hadoop2.6.0

package wc;

import java.io.IOException;

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 wc.WCMapper;
import wc.WCReducer;

public class WordCount {

public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
Configuration conf = new Configuration();

Job job = Job.getInstance(conf);
//设置jar
job.setJarByClass(WordCount.class);

//设置Mapper属性  具体含义函数名
job.setMapperClass(WCMapper.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(LongWritable.class);
FileInputFormat.setInputPaths(job, new Path("hdfs://hadoop1:9000/inputfile/words"));//也可以从本地读取数据

//设置Reducer属性
job.setReducerClass(WCReducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(LongWritable.class);
FileOutputFormat.setOutputPath(job, new Path("D:/wordCountResult"));//结果放在本地的文件夹

//job.setCombinerClass(WCReducer.class);

job.waitForCompletion(true);
}

}

package wc;

import java.io.IOException;

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

public class WCMapper extends Mapper<LongWritable, Text, Text, LongWritable> {

@Override
protected void map(LongWritable key, Text value, Context context)
throws IOException, InterruptedException {
//输入：行索引为key,行内容为value 形成一个<key,value>对.每一个<key,value>都map会一次.本例中也就是每一行都执行一次map.
//输出为：对value内容解析,新形成的key,value.
String line = value.toString();
String[] words = line.split(" ");
for(String w : words){

context.write(new Text(w), new LongWritable(1));
}
}

}

package wc;

import java.io.IOException;

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

public class WCReducer extends Reducer<Text, LongWritable, Text, LongWritable> {

@Override
//map与reuce之间有一个非常重要的过程shuffle.默认情况下shuffle会将map输出的具有相同key的结果聚集在一起
//使得reduce的输入为<key,list(value1,value2)>  reduce输出的value
protected void reduce(Text key, Iterable<LongWritable> v2s, Context context)
throws IOException, InterruptedException {
long sum = 0;
for(LongWritable lw : v2s){
sum += lw.get();
}
//输出
context.write(key, new LongWritable(sum));
}

}