package com.bruce.mapreduce;
import java.io.IOException;
import java.util.StringTokenizer;
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.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
public class WordCount {
// step 1: Map Class
/**
* Mapper<KEYIN, VALUEIN, KEYOUT, VALUEOUT>
*
*/
public static class WordCountMapper extends
Mapper<LongWritable, Text, Text, IntWritable> {
private Text mapOutputKey = new Text();
private final static IntWritable mapOutputValue = new IntWritable(1);
@Override
protected void map(LongWritable key, Text value, Context context)
throws IOException, InterruptedException {
// TODO Auto-generated method stub
//line value
String lineValue = value.toString();
//split
StringTokenizer stringTokenizer = new StringTokenizer(lineValue);
//iterator
while(stringTokenizer.hasMoreElements()){
//get value
String wordValue = stringTokenizer.nextToken();
//set value
mapOutputKey.set(wordValue);
//output
context.write(mapOutputKey, mapOutputValue);
}
}
}
// step 2: Reduce Class
/**
* Reducer<KEYIN, VALUEIN, KEYOUT, VALUEOUT>
*
*/
public static class WordCountReducer extends
Reducer<Text, IntWritable, Text, IntWritable> {
private IntWritable outputValue = new IntWritable();
@Override
protected void reduce(Text key, Iterable<IntWritable> values,
Context context) throws IOException, InterruptedException {
// TODO Auto-generated method stub
//sum tmp
int sum = 0;
//iterator
for(IntWritable value: values){
//total
sum += value.get();
}
//set value
outputValue.set(sum);
//output
context.write(key, outputValue);
}
}
// step 3: Driver ,component job
public int run(String[] args) throws Exception {
// 1: get configration
Configuration configuration = new Configuration();
// 2: create Job
Job job = Job.getInstance(configuration, this.getClass()
.getSimpleName());
// run jar
job.setJarByClass(this.getClass());
// 3: set job
// input -> map -> reduce -> output
// 3.1 input
Path inPath = new Path(args[0]);
FileInputFormat.addInputPath(job, inPath);
// 3.2: map
job.setMapperClass(WordCountMapper.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(IntWritable.class);
// 3.3: reduce
job.setReducerClass(WordCountReducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
// 3.4: output
Path outPath = new Path(args[1]);
FileOutputFormat.setOutputPath(job, outPath);
// 4: submit job
boolean isSuccess = job.waitForCompletion(true);
return isSuccess ? 0 : 1;
}
//step 4: run program
public static void main(String[] args) throws Exception {
int status = new WordCount().run(args);
System.exit(status);
}
}
MapReduce自帶wordcount的實現
發表評論
所有評論
還沒有人評論,想成為第一個評論的人麼? 請在上方評論欄輸入並且點擊發布.