Hadoop中如何从hbase到hdfs

import java.io.IOException;
import java.util.List;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.hbase.KeyValue;
import org.apache.hadoop.hbase.client.Result;
import org.apache.hadoop.hbase.client.Scan;
import org.apache.hadoop.hbase.io.ImmutableBytesWritable;
import org.apache.hadoop.hbase.mapreduce.TableMapReduceUtil;
import org.apache.hadoop.hbase.mapreduce.TableMapper;
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.output.FileOutputFormat;

public class HbaseToHdfs {
//maper阶段
static class MyMapper extends TableMapper<Text, IntWritable>{
Text k=new Text();
@Override
protected void map(ImmutableBytesWritable key, Result value,
Mapper<ImmutableBytesWritable, Result, Text, IntWritable>.Context context)
throws IOException, InterruptedException {
List list = value.list();
String sex = “”;
for(KeyValue kv : list){
String qualifier = new String(kv.getQualifier());
if(“sex”.equals(qualifier)){
sex = new String(kv.getValue());
}
}
if(!"".equals(sex)){
k.set(sex);
context.write(k, new IntWritable(1));
}
}
}
//reducer阶段
static class MyReducer extends Reducer<Text, IntWritable, Text, IntWritable>{
IntWritable v = new IntWritable();
@Override
protected void reduce(Text key, Iterable values,
Reducer<Text, IntWritable, Text, IntWritable>.Context context)
throws IOException, InterruptedException {
int count = 0;
for(IntWritable n : values){
count++;
}
v.set(count);
context.write(key, v);
}

}
public static void main(String[] args) {
	Configuration conf=new Configuration();
	conf.set("fs.defaultFS", "hdfs://bd1803");
	conf.set("hbase.zookeeper.quorum", "centos01:2181,centos02:2181,centos03:2181");
	System.setProperty("HADOOP_USER_NAME", "centos");
	try {
		FileSystem fs=FileSystem.get(conf);
		Job job=Job.getInstance(conf);
		job.setJarByClass(HbaseToHdfs.class);
		Scan scan=new Scan();
		TableMapReduceUtil.initTableMapperJob("mingxing", scan,
				MyMapper.class, 
				Text.class, 
				IntWritable.class, 
				job,false);	
		job.setReducerClass(MyReducer.class);
		job.setOutputKeyClass(Text.class);
		job.setOutputValueClass(IntWritable.class);	
		Path path=new Path("/hbase_hdfs121");
		if(fs.exists(path)) {
			fs.delete(path,true);
		}
		FileOutputFormat.setOutputPath(job, path);			
		job.waitForCompletion(true);		
	} catch (Exception e) {
		e.printStackTrace();
	}
}

}

猜你喜欢

转载自blog.csdn.net/zwmonk/article/details/82931973