Map Mapper1
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;
/**
* Created by 张倩 on 2017/3/18.
*/
public class WCMapMapper1 extends Mapper{
protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
Text keyOut = new Text();
IntWritable valueOut = new IntWritable();
String[] arr = value.toString().split(" ");
for(String s : arr){
keyOut.set(s);
valueOut.set(1);
context.write(keyOut,valueOut);
}
}
}
Mapper1是进行 单词分割 阶段
MapMapper2
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
import java.io.IOException;
/**
* Created by 张倩 on 2017/3/18.
*/
public class WCMapMapper2 extends Mapper {
protected void map(Text key, IntWritable value, Context context) throws IOException, InterruptedException {
if(!key.toString().equals("falungong")){
context.write(key,value);
}
}
}
Mapper2 阶段是过滤敏感词
Reduce
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
import java.io.IOException;
/**
* Created by 张倩 on 2017/3/18.
*/
public class WCReducer extends Reducer {
protected void reduce(Text key, Iterable values, Context context) throws IOException, InterruptedException {
int count = 0;
for(IntWritable iw : values){
count = count + iw.get();
}
context.write(key,new IntWritable(count));
}
}
Reduce阶段是对value进行迭代,算出总 的次数
Reducer Mapper
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
import java.io.IOException;
/**
* Created by 张倩 on 2017/3/18.
*/
public class WCReducerMapper1 extends Mapper{
protected void map(Text key, IntWritable value, Context context) throws IOException, InterruptedException {
if(value.get()>5){
context.write(key,value);
}
}
}
在Reduce端追加一个Mapper,过滤单词个数小于5的
ChainApp
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.chain.ChainMapper;
import org.apache.hadoop.mapreduce.lib.chain.ChainReducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
/**
* Created by 张倩 on 2017/3/18.
*/
public class WCChainApp {
public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
conf.set("fs.defaultFS","file:///");
Job job = Job.getInstance(conf);
//设置job的属性
job.setJobName("WCChainApp");
job.setJarByClass(WCChainApp.class);
job.setInputFormatClass(TextInputFormat.class);
//在Mapper链条上增加Mapper1
ChainMapper.addMapper(job,WCMapMapper1.class, LongWritable.class, Text.class,Text.class, IntWritable.class,conf);
//在Mapper链条上增加Mapper2
ChainMapper.addMapper(job,WCMapMapper2.class,Text.class,IntWritable.class,Text.class,IntWritable.class,conf);
//在Reducer链条上设置Reducer
ChainReducer.setReducer(job,WCReducer.class,Text.class,IntWritable.class,Text.class,IntWritable.class,conf);
//在reducer链条上增加Reducer端的Mapper
ChainReducer.addMapper(job,WCReducerMapper1.class,Text.class,IntWritable.class,Text.class,IntWritable.class,conf);
//设置文件输入输出路径
FileInputFormat.addInputPath(job,new Path("g:/comp/chain/"));
FileOutputFormat.setOutputPath(job,new Path("g:/comp/chain/out"));
//设置reducer任务个数
job.setNumReduceTasks(3);
job.waitForCompletion(true);
}
}
App端设置Mapper和Reducer的属性的时候,用的是ChainMapper和ChainReducer这两个类。好啦,链式编程已完成!