package com.zhangchao.mr;
import java.io.IOException;
import java.util.StringTokenizer;
import org.apache.hadoop.io.IntWritable;
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, IntWritable>
{
protected void map(LongWritable key, Text value,
Context context)
throws IOException, InterruptedException {
// TODO Auto-generated method stub
String line = value.toString();
StringTokenizer st = new StringTokenizer(line);
while(st.hasMoreTokens())
{
String word = st.nextToken();
context.write(new Text(word), new IntWritable(1));
}
}
}
## wordcount_mapper ##
## wordcount_reducer ##
package com.zhangchao.mr;
import java.io.IOException;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
public class WcReducer extends Reducer
package com.zhangchao.mr;
import java.io.IOException;
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;
public class JobRun
{
public static void main(String[] args) throws ClassNotFoundException, InterruptedException
{
Configuration conf = new Configuration();
conf.set("mapred.textoutputformat.separator", ",");
try {
Job job = new Job(conf);
job.setJarByClass(JobRun.class);
job.setMapperClass(WcMapper.class);
job.setReducerClass(WcReducer.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(IntWritable.class);
FileInputFormat.addInputPath(job, new Path("hdfs://192.168.1.128:9000/test/README.txt"));
FileOutputFormat.setOutputPath(job, new Path("hdfs://192.168.1.128:9000/test/output05"));
System.exit(job.waitForCompletion(true) ? 0:1);
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
}
}
“`## wordcount_jobrun ##