MapReduce实验——英语单词个数统计实验

MapReduce实验——英语单词个数统计实验

英语单词个数统计

Map类

package WordSum_02;import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;import java.io.IOException;public class MyMap extends Mapper<LongWritable,Text, NullWritable,LongWritable> {@Overrideprotected void map(LongWritable key,Text value,Context context) throws IOException, InterruptedException {//1 get values stringString valueString = String();//2 split stringString wArr[] = valueString.split(" ");//3 map out key/valuecontext.(),new LongWritable(wArr.length));}
}

Reduce类

package WordSum_02;import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.mapreduce.Reducer;import java.io.IOException;
import java.util.Iterator;public class MyReduce extends Reducer<NullWritable, LongWritable,NullWritable,LongWritable> {@Overrideprotected void reduce(NullWritable key,Iterable<LongWritable> valueIn,Context context) throws IOException, InterruptedException {Iterator<LongWritable> it = valueIn.iterator();//define sumlong sum = 0;//iterator count arrwhile(it.hasNext()){sum += it.next().get();}context.(),new LongWritable(sum));}
}

Job类

package WordSum_02;import org.f.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 TestJob {public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {Configuration conf = new Configuration();//1 get a jobJob job = Instance(conf);//2 set jar main classjob.setJarByClass(TestJob.class);//3 set map class and reducer classjob.setMapperClass(MyMap.class);job.setReducerClass(MyReduce.class);//4 set map reduce output typejob.setMapOutputKeyClass(Text.class);job.setMapOutputValueClass(LongWritable.class);job.setOutputKeyClass(Text.class);job.setOutputValueClass(LongWritable.class);//5 set key/value output file format and input/output pathFileInputFormat.setInputPaths(job,new Path("file:///"));FileOutputFormat.setOutputPath(job,new Path("file:///simple/result"));//6 commit jobjob.waitForCompletion(true);}
}