HBase Java API 03:HBase与MapReduce整合

HBase版本:1.2.6

1. 案例说明

现有hbase表”student”,其中内容如下:

hbase(main):025:0> scan 'student'
ROW     COLUMN+CELL                                                                            
 0001   column=info:age, timestamp=1516139523768, value=15                                     
 0001   column=info:name, timestamp=1516139523388, value=Madeline                              
 0002   column=info:age, timestamp=1516139523820, value=16                                     
 0002   column=info:name, timestamp=1516139523469, value=Jed                                   
 0003   column=info:age, timestamp=1516139523862, value=17                                     
 0003   column=info:name, timestamp=1516139523607, value=Olivia                                
 0004   column=info:age, timestamp=1516139523908, value=18                                     
 0004   column=info:name, timestamp=1516139523680, value=Jed                                   
 0005   column=info:age, timestamp=1516139525527, value=19                                     
 0005   column=info:name, timestamp=1516139523725, value=Sarah

需求:

编写MapReduce程序,把”student”表中”info”列族下的”name”那一列抽取出来,存入新HBase表”student_extract”中,要求”student_extract”表中只有”info”这个列族,”info”这个列族下只有”name”这个列

2. 代码实现

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

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.hbase.Cell;
import org.apache.hadoop.hbase.CellUtil;
import org.apache.hadoop.hbase.HBaseConfiguration;
import org.apache.hadoop.hbase.HColumnDescriptor;
import org.apache.hadoop.hbase.HTableDescriptor;
import org.apache.hadoop.hbase.TableName;
import org.apache.hadoop.hbase.client.Admin;
import org.apache.hadoop.hbase.client.Connection;
import org.apache.hadoop.hbase.client.ConnectionFactory;
import org.apache.hadoop.hbase.client.Mutation;
import org.apache.hadoop.hbase.client.Put;
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.mapreduce.TableReducer;
import org.apache.hadoop.hbase.util.Bytes;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;

public class HBaseAndMapReduce {
    
    private static final String ZOOKEEPER_LIST = "repo:2181";
    private static final String INPUT_TABLE_NAME = "student";
    private static final String OUTPUT_TABLE_NAME = "student_extract";
    private static final byte[] FAMILY_NAME = "info".getBytes();
    private static final byte[] COLUMN_NAME = "name".getBytes();
    
    public static void main(String[] args) throws Exception {
        
        System.setProperty("HADOOP_USER_NAME", "root");
        Configuration conf = HBaseConfiguration.create();
        conf.set("hbase.zookeeper.quorum", ZOOKEEPER_LIST);
        
        // 创建需要添加数据的新表
        Connection conn = ConnectionFactory.createConnection(conf);
        Admin admin = conn.getAdmin();
        
        if(admin.tableExists(TableName.valueOf(OUTPUT_TABLE_NAME))) {
            admin.disableTable(TableName.valueOf(OUTPUT_TABLE_NAME));
            admin.deleteTable(TableName.valueOf(OUTPUT_TABLE_NAME));
        }
        
        HTableDescriptor tableDesc = new HTableDescriptor(TableName.valueOf(OUTPUT_TABLE_NAME));
        HColumnDescriptor columnDesc = new HColumnDescriptor(FAMILY_NAME);
        tableDesc.addFamily(columnDesc);
        admin.createTable(tableDesc);
        
        Job job = Job.getInstance(conf);
        
        // 初始化Job,设置Mapper和Reducer相关的参数
        Scan scan = new Scan();
        scan.addColumn(FAMILY_NAME, COLUMN_NAME);
        // 最后的参数代表是否添加依赖的jar包,本地模式设置为false
        TableMapReduceUtil.initTableMapperJob(INPUT_TABLE_NAME, scan, HBaseAndMapreduceMapper.class, Text.class, NullWritable.class, job, false);
        TableMapReduceUtil.initTableReducerJob(OUTPUT_TABLE_NAME, HBaseAndMapreduceReducer.class, job);
        
        /*
         * 上面两行代码中已经包含了下面的这5行代码
         * job.setMapperClass(HBaseAndMapreduceMapper.class);
         * job.setReducerClass(HBaseAndMapreduceReducer.class);
         * job.setMapOutputKeyClass(Text.class);
         * job.setMapOutputValueClass(NullWritable.class);
         * job.setOutputKeyClass(ImmutableBytesWritable.class);
         * job.setOutputValueClass(Mutation.class);
         */
        
        boolean successful = job.waitForCompletion(true);
        System.exit(successful ? 0 : -1);
        
    }
    
    // public abstract class TableMapper<KEYOUT, VALUEOUT> extends Mapper<ImmutableBytesWritable, Result, KEYOUT, VALUEOUT> {...}
    private static class HBaseAndMapreduceMapper extends TableMapper<Text, NullWritable> {

        @Override
        protected void map(ImmutableBytesWritable key, Result value, Context context)
                throws IOException, InterruptedException {
            
            String rowkey = Bytes.toString(key.copyBytes());
            List<Cell> cells = value.listCells();
            Text keyOut = new Text();
            StringBuilder sb = new StringBuilder();
            
            for(Cell cell : cells) {
                String family = new String(CellUtil.cloneFamily(cell));
                String qualifier = new String(CellUtil.cloneQualifier(cell));
                String rowValue = new String(CellUtil.cloneValue(cell));
                sb.append(rowkey + "\t" + family + "\t" + qualifier + "\t" + rowValue);
                keyOut.set(sb.toString());
                context.write(keyOut, NullWritable.get());
                
                sb = new StringBuilder();
            }
        }
        
    }
    
    // public abstract class TableReducer<KEYIN, VALUEIN, KEYOUT> extends Reducer<KEYIN, VALUEIN, KEYOUT, Mutation> {...}
    private static class HBaseAndMapreduceReducer extends TableReducer<Text, NullWritable, ImmutableBytesWritable> {

        @Override
        protected void reduce(Text key, Iterable<NullWritable> values, Context context) throws IOException, InterruptedException {
            
            byte[] rowkey = Bytes.toBytes(key.toString().split("\t")[0]);
            byte[] family = Bytes.toBytes(key.toString().split("\t")[1]);
            byte[] qualifier = Bytes.toBytes(key.toString().split("\t")[2]);
            byte[] rowValue = Bytes.toBytes(key.toString().split("\t")[3]);
            
            ImmutableBytesWritable newRowKey = new ImmutableBytesWritable(rowkey);
            Put put = new Put(rowkey);
            put.addImmutable(family, qualifier, rowValue);
            
            context.write(newRowKey, put);
        }
        
    }

}

# 程序运行结束后,"student_extract"表中数据为:

hbase(main):033:0> scan 'student_extract'
ROW     COLUMN+CELL                                                                            
 0001   column=info:name, timestamp=1516142234629, value=Madeline                              
 0002   column=info:name, timestamp=1516142234629, value=Jed                                   
 0003   column=info:name, timestamp=1516142234629, value=Olivia                                
 0004   column=info:name, timestamp=1516142234629, value=Jed                                   
 0005   column=info:name, timestamp=1516142234629, value=Sarah

    原文作者:CoderJed
    原文地址: https://www.jianshu.com/p/75e3465e7f64
    本文转自网络文章,转载此文章仅为分享知识,如有侵权,请联系博主进行删除。
点赞