mapreduce读取hbase数据输出到文件中

爱被打了一巴掌 2022-06-13 06:56 262阅读 0赞

package hadoop;
    
    import java.io.IOException;
    import java.util.ArrayList;
    import java.util.List;
    
    import org.apache.hadoop.conf.Configuration;
    import org.apache.hadoop.fs.Path;
    import org.apache.hadoop.hbase.Cell;
    import org.apache.hadoop.hbase.CellUtil;
    import org.apache.hadoop.hbase.HBaseConfiguration;
    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.hbase.util.Bytes;
    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;
    import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
    import org.apache.thrift.transport.TFileTransport.truncableBufferedInputStream;
    import org.joni.exception.JOniException;
    
    public class HbaseMapreduce {
    	
    	static class HbaseMapper extends TableMapper<ImmutableBytesWritable, Text>{
    
    		@Override
    		protected void map(ImmutableBytesWritable key, Result value,Context context)
    				throws IOException, InterruptedException {
    			for(Cell cell :value.rawCells()){
    				context.write(new ImmutableBytesWritable("test".getBytes()),new Text(Bytes.toString(CellUtil.cloneQualifier(cell))+","+Bytes.toString(CellUtil.cloneValue(cell))));
    			}
    		}
    		
    	}
    	static class HbaseReduce extends Reducer<ImmutableBytesWritable, Text, Text, Text>{
    
    		@Override
    		protected void reduce(ImmutableBytesWritable key, Iterable<Text> values,
    				Context context)
    				throws IOException, InterruptedException {
    			for(Text text:values){
    				context.write(new Text("test"), text);
    			}
    		}
    		
    		
    	}
    	
    	public static void main(String[] args) throws Exception {
    		Configuration conf = HBaseConfiguration.create();
    		conf.set("hbase.zookeeper.quorum", "192.168.10.250");
    		conf.set("hbase.zookeeper.property.clientPort", "2181");
    		Job job = Job.getInstance(conf,"hbasedemo");
    		job.setJarByClass(HbaseMapreduce.class);
    		
    		List<Scan> list = new ArrayList<Scan>();
    		Scan scan = new Scan();
    		scan.setCaching(200);
    		scan.setCacheBlocks(false);
    		scan.setStartRow("row1".getBytes());
    		scan.setStopRow("row5".getBytes());
    		scan.setAttribute(Scan.SCAN_ATTRIBUTES_TABLE_NAME, "mapreduce".getBytes());
    		list.add(scan);
    		
    		TableMapReduceUtil.initTableMapperJob(list, HbaseMapper.class, ImmutableBytesWritable.class,Text.class, job);
    		job.setMapOutputKeyClass(ImmutableBytesWritable.class);
    		job.setMapOutputValueClass(Text.class);
    		job.setReducerClass(HbaseReduce.class);
    		job.setOutputKeyClass(Text.class);
    		job.setOutputValueClass(Text.class);
    		FileOutputFormat.setOutputPath(job, new Path("/test/output"));
    			
    		System.exit(job.waitForCompletion(true)==true?0:1);
    		
    		
    		
    	}
    	
    	
    }