HDFS文件内容写入HBase

创建三个文件

1. XJTRunner

2. XJTReducer

3. XJTMapper

resource目录引入HDFS连接文件:

具体代码

XJTRunner类

package com.ke.xjt;


import org.apache.hadoop.conf.Configuration;

import org.apache.hadoop.fs.Path;
import org.apache.hadoop.hbase.client.Put;
import org.apache.hadoop.hbase.mapreduce.TableMapReduceUtil;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.Job;

public class XJTRunner {

    public static void main(String[] args) throws Exception{

        Configuration conf = new Configuration(true);
        // 使用hbase,需要加载zookeeper配置
        conf.set("hbase.zookeeper.quorum","node04,node02,node03");
        //让框架知道是windows异构平台运行
        conf.set("mapreduce.app-submission.cross-platform","true");
        conf.set("mapreduce.framework.name","local");

        //创建job对象
        Job job = Job.getInstance(conf);
        job.setJarByClass(XJTRunner.class);

        //设置mapper类
        job.setMapperClass(XJTMapper.class);
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);

        //设置reduce类
        //wordcount是hbase表
        TableMapReduceUtil.initTableReducerJob("wordcount",XJTReducer.class,job,null,null,null,null,false);

        job.setOutputKeyClass(NullWritable.class);
        job.setOutputValueClass(Put.class);


        //指定hdfs存储数据的目录
        FileInputFormat.addInputPath(job, new Path("/data/godno"));
        job.waitForCompletion(true);
    }

}

XJTMapper类

package com.ke.xjt;

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

import java.io.IOException;

public class XJTMapper extends Mapper<LongWritable, Text, Text, IntWritable> {

    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        System.out.println("key - - -" + key);
        System.out.println("value - - -" + value);
        System.out.println("context - - -" + context);
        String[] split = value.toString().split("	");
        for (String s : split) {
            context.write(new Text(s), new IntWritable(1));
        }
    }
}

XJTReducer类

package com.ke.xjt;

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.hbase.util.Bytes;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;

import java.io.IOException;

public class XJTReducer extends TableReducer<Text, IntWritable, ImmutableBytesWritable> {

    @Override
    protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {

        System.out.println("XJTReducer-key - - -" + key);
        System.out.println("XJTReducer-value - - -" + values);
        System.out.println("XJTReducer-context - - -" + context);

        int num = 0;
        for (IntWritable value : values) {
            num = value.get();
        }
        Put put = new Put(Bytes.toBytes(key.toString()));
        put.addColumn(Bytes.toBytes("cf"), Bytes.toBytes("ct"), Bytes.toBytes(num));
        context.write(null, put);

    }
}

注意: 一定要先在HBase先创建对应的表 wordcount

代码：https://gitee.com/Xiaokeworksveryhard/big-data.git