从hdfs读数据到hbase

package com.bigdata.hbase.hdfstohbase;

import org.apache.hadoop.hbase.client.Put;
import org.apache.hadoop.hbase.io.ImmutableBytesWritable;
import org.apache.hadoop.hbase.util.Bytes;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

import java.io.IOException;

/**
 * 构建ReadCityFromHDFSMapper于读取HDFS中的文件数据
 */
public class ReadCityFromHDFSMapper extends Mapper<LongWritable, Text, ImmutableBytesWritable, Put> {
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        //从hdfs中读数据
        String lineValue=value.toString();
        //\t切分数据
        String[] splits=lineValue.split("\t");
        //读取数据中的数据
        String rowkey=splits[0];
        String name=splits[1];
        String country=splits[2];

        //初始化rowKey
        ImmutableBytesWritable rowkeywriteable=new ImmutableBytesWritable(Bytes.toBytes(rowkey));
        //初始化put对象
        Put put=new Put(Bytes.toBytes(rowkey));
        //参数分别:列族、列、值
        put.addColumn(Bytes.toBytes("info"),Bytes.toBytes("name"),Bytes.toBytes(name));
        put.addColumn(Bytes.toBytes("info"),Bytes.toBytes("country"),Bytes.toBytes(country));
        context.write(rowkeywriteable,put);

    }
}

package com.bigdata.hbase.hdfstohbase;

import org.apache.hadoop.hbase.client.Put;
import org.apache.hadoop.hbase.io.ImmutableBytesWritable;
import org.apache.hadoop.hbase.mapreduce.TableReducer;
import org.apache.hadoop.io.NullWritable;


import java.io.IOException;
/**
*运行reduce类
*/
public class WriteCityMRFromTxtReduce extends TableReducer<ImmutableBytesWritable, Put, NullWritable> {
    @Override
    protected void reduce(ImmutableBytesWritable key, Iterable<Put> values, Context context) throws IOException, InterruptedException {
        //读出来的每一行数据写入到city表中
        for(Put put: values){
            context.write(NullWritable.get(), put);
        }

    }

}

package com.bigdata.hbase.hdfstohbase;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.Path;

import org.apache.hadoop.hbase.HBaseConfiguration;
import org.apache.hadoop.hbase.client.Put;
import org.apache.hadoop.hbase.io.ImmutableBytesWritable;
import org.apache.hadoop.hbase.mapreduce.TableMapReduceUtil;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;

/**
 * 运行读hdfs数据到hbase
 */
public class HDFSToHbaseRunner  extends Configured implements Tool {
    @Override
    public int run(String[] strings) throws Exception {
        //得到Configuration
        Configuration conf = this.getConf();
        //创建Job任务
        Job job = Job.getInstance(conf, this.getClass().getSimpleName());
        job.setJarByClass(HDFSToHbaseRunner.class);
        Path inPath = new Path("hdfs://bigdata112:9000//hbase_mr_test/city.tsv");
        FileInputFormat.addInputPath(job, inPath);

        //设置Mapper
        job.setMapperClass(ReadCityFromHDFSMapper.class);
        job.setMapOutputKeyClass(ImmutableBytesWritable.class);
        job.setMapOutputValueClass(Put.class);

        //设置Reducer
        TableMapReduceUtil.initTableReducerJob("city", WriteCityMRFromTxtReduce.class, job);
        //设置Reduce数量，最少1个
        job.setNumReduceTasks(1);
        boolean isSuccess = job.waitForCompletion(true);
        return isSuccess ? 1 : 0;
    }

    public static void main(String[] args) throws Exception {
        Configuration conf = HBaseConfiguration.create();
        int status = ToolRunner.run(conf, new HDFSToHbaseRunner(), args);
        System.exit(status);


    }
}

运行前效果。空city表

运行后效果。