package mapreduce;
import java.io.IOException;
import java.util.StringTokenizer;
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.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 WordCount1{
public static void main(String[] args) throws IOException,ClassNotFoundException,InterruptedException {
Job job = Job.getInstance();
job.setJobName("WordCount1");
job.setJarByClass(WordCount1.class);
job.setMapperClass(doMapper.class);
job.setReducerClass(doReducer.class);
job.setoutputKeyClass(Text.class);
job.setoutputValueClass(IntWritable.class);
Path in = new Path("hdfs://localhost:9000/mymapreduce1/in/buyer_favorite1");
Path out = new Path("hdfs://localhost:9000/mymapreduce1/out");
FileInputFormat.addInputPath(job,in);
FileOutputFormat.setoutputPath(job,out);
System.exit(job.waitForCompletion(true)?0:1);
}
public static class doMapper extends Mapper<Object,Text,Text,IntWritable>{
public static final IntWritable one = new IntWritable(1);
public static Text word = new Text();
@Override
protected void map(Object key, Text value, Context context)
throws IOException,InterruptedException {
StringTokenizer tokenizer = new StringTokenizer(value.toString()," ");
word.set(tokenizer.nextToken());
context.write(word,one);
}
}
public static class doReducer extends Reducer<Text,IntWritable,Text,IntWritable>{
private IntWritable result = new IntWritable();
@Override
protected void reduce(Text key,Iterable<IntWritable> values,Context context)
throws IOException,InterruptedException{
int sum = 0;
for (IntWritable value : values){
sum += value.get();
}
result.set(sum);
context.write(key,result);
}
}
}
|
运行结果：
版权声明：本文内容由互联网用户自发贡献，该文观点与技术仅代表作者本人。本站仅提供信息存储空间服务，不拥有所有权，不承担相关法律责任。如发现本站有涉嫌侵权/违法违规的内容， 请发送邮件至 [email protected] 举报，一经查实，本站将立刻删除。
