31.hbase和MapReduce整合

在这里我们仍然以wordcount为例，这里大数据的wordcount就和helloworld一样吧（笑）。还是逐步分析代码。
配置连接。

这里的修改hadoop源码是指修改org.apache.hadoop

 Configuration conf = new Configuration();
        conf.set("hbase.zookeeper.quorum", "node1,node2,node3");
        conf.set("fs.defaultFS", "hdfs://node1:8020");//写你active的namenode名称

创建job类

  Job job = Job.getInstance(conf);
job.setJarByClass(WCRunner.class);

设置mapreduce

//
        job.setMapperClass(WCMapper.class);
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);
// map设置完毕
        TableMapReduceUtil.initTableReducerJob("wc", WCReducer.class, job, null, null, null, null, false);
// 第一个参数是表名，往哪存数据，第二个class <? extend TableReducer>第三个job，后面全写空，最后一个必须写false
        FileInputFormat.addInputPath(job, new Path("/usr/wc"));//指定路径，从哪里读文件
        // reduce端输出的key和value的类型
        job.setOutputKeyClass(NullWritable.class);
        job.setOutputValueClass(Put.class);//hdfs的put
// job.setOutputFormatClass(cls);这注释的两句控制从哪个源读数据，向哪个源写数据
        // job.setInputFormatClass(cls);
       job.waitForCompletion(true);

TableMapReduceUtil.initTableReducerJob("wc", WCReducer.class, job, null, null, null, null, false);
https://blog.csdn.net/shudaqi2010/article/details/88653797

WCrunner代码

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.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;


public class WCRunner {

    public static void main(String[] args) throws Exception {
        // 配置文件设置
        Configuration conf = new Configuration();
        conf.set("hbase.zookeeper.quorum", "node1,node2,node3");
        conf.set("fs.defaultFS", "hdfs://node1:8020");

        Job job = Job.getInstance(conf);
        job.setJarByClass(WCRunner.class);

        job.setMapperClass(WCMapper.class);
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);
        TableMapReduceUtil.initTableReducerJob("wc", WCReducer.class, job, null, null, null, null, false);
        FileInputFormat.addInputPath(job, new Path("/usr/wc"));
        // reduce端输出的key和value的类型
        job.setOutputKeyClass(NullWritable.class);
        job.setOutputValueClass(Put.class);

        // job.setOutputFormatClass(cls);
        // job.setInputFormatClass(cls);

        job.waitForCompletion(true);

    }
}

WCMapper全部代码

import java.io.IOException;

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

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

    @Override
    protected void map(LongWritable key, Text value, Context context)
            throws IOException, InterruptedException {
        String[] splits = value.toString().split(" ");
//      new StringTokenizer(value.toString()," ");这两种方法都可以
        for (String string : splits) {
            context.write(new Text(string), new IntWritable(1));
        }
    }
}

reduce代码

import java.io.IOException;

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.IntWritable;
import org.apache.hadoop.io.Text;

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

    @Override
    protected void reduce(Text key, Iterable<IntWritable> iter,
            Context context)
            throws IOException, InterruptedException {
        int sum = 0;
        for (IntWritable intWritable : iter) {
            sum+=intWritable.get();
        }
        Put put = new Put(key.toString().getBytes());//rowkey
        put.add("cf".getBytes(), "cf".getBytes(), String.valueOf(sum).getBytes());
        context.write(null, put);
    }
}

建表

run后