Hadoop生态圈-HBase的HFile创建方式

　　　　　　　　　　　　　　　　　　　　　　Hadoop生态圈-HBase的HFile创建方式

　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　作者：尹正杰

版权声明：原创作品，谢绝转载！否则将追究法律责任。

　　废话不多说，直接上代码，想说的话都在代码的注释里面。

一.环境准备

list
create 'yinzhengjie:WordCount3','f1','f2'
list
desc 'yinzhengjie:WordCount3'
scan 'yinzhengjie:WordCount3'

二.编写HFile创建方式的代码

1>.编写Map端代码

/*
@author :yinzhengjie
Blog:http://www.cnblogs.com/yinzhengjie/tag/Hadoop%E7%94%9F%E6%80%81%E5%9C%88/
EMAIL:y1053419035@qq.com
*/
package cn.org.yinzhengjie.hbase.hfile;

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 HFileOutputMapper extends Mapper<LongWritable, Text, Text, IntWritable> {
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        //得到一行数据
        String line = value.toString();
        String[] arr = line.split(" ");
        //
        for (String word : arr){
            context.write(new Text(word),new IntWritable(1));
        }
    }
}

2>.编写Reducer端代码

/*
@author :yinzhengjie
Blog:http://www.cnblogs.com/yinzhengjie/tag/Hadoop%E7%94%9F%E6%80%81%E5%9C%88/
EMAIL:y1053419035@qq.com
*/
package cn.org.yinzhengjie.hbase.hfile;

import org.apache.hadoop.hbase.Cell;
import org.apache.hadoop.hbase.CellUtil;
import org.apache.hadoop.hbase.KeyValue;
import org.apache.hadoop.hbase.io.ImmutableBytesWritable;
import org.apache.hadoop.hbase.util.Bytes;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

import java.io.IOException;

public class HFileOutputReducer extends Reducer<Text,IntWritable,ImmutableBytesWritable,Cell> {
    @Override
    protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
        int sum = 0;
        for (IntWritable value : values) {
            sum += value.get();
        }
        if(key.toString().length() > 0){
            ImmutableBytesWritable outKey = new ImmutableBytesWritable(Bytes.toBytes(key.toString()));
            //创建cell
            Cell cell = CellUtil.createCell(Bytes.toBytes(key.toString()),
                    Bytes.toBytes("f1"), Bytes.toBytes("count"),System.currentTimeMillis(),
                    KeyValue.Type.Minimum,Bytes.toBytes(sum+""),null);
            context.write(outKey,cell);
        }
    }
}

3>.编写主程序代码

/*
@author :yinzhengjie
Blog:http://www.cnblogs.com/yinzhengjie/tag/Hadoop%E7%94%9F%E6%80%81%E5%9C%88/
EMAIL:y1053419035@qq.com
*/
package cn.org.yinzhengjie.hbase.hfile;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.hbase.Cell;
import org.apache.hadoop.hbase.HBaseConfiguration;
import org.apache.hadoop.hbase.HTableDescriptor;
import org.apache.hadoop.hbase.TableName;
import org.apache.hadoop.hbase.client.Connection;
import org.apache.hadoop.hbase.client.ConnectionFactory;
import org.apache.hadoop.hbase.io.ImmutableBytesWritable;
import org.apache.hadoop.hbase.mapreduce.HFileOutputFormat2;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

public class App {

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

        System.setProperty("HADOOP_USER_NAME", "yinzhengjie");
        Configuration conf = HBaseConfiguration.create();
        conf.set("fs.defaultFS","file:///");
        Connection conn = ConnectionFactory.createConnection(conf);
        Job job = Job.getInstance(conf);
        job.setJobName("HFile WordCount");
        job.setJarByClass(App.class);
        job.setMapperClass(HFileOutputMapper.class);
        job.setReducerClass(HFileOutputReducer.class);
        //设置输出格式
        job.setOutputFormatClass(HFileOutputFormat2.class);
        //设置路径
        FileInputFormat.addInputPath(job,new Path("file:///D:\BigData\yinzhengjieData\word.txt"));
        FileOutputFormat.setOutputPath(job,new Path("file:///D:\BigData\yinzhengjieData\hfile"));
        //设置输出k-v
        job.setOutputKeyClass(ImmutableBytesWritable.class);
        job.setOutputValueClass(Cell.class);
        //设置map端输出k-v
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);
        /**
         *      配置和"yinzhengjie:WordCount3"进行关联，也就是说"yinzhengjie:WordCount3"这个表必须在HBase数据库中存在，
         * 实际操作是以"yinzhengjie:WordCount3"为模板，便于生成HFile文件！
         */
        HFileOutputFormat2.configureIncrementalLoad(job, new HTableDescriptor(TableName.valueOf("yinzhengjie:WordCount3")),
                conn.getRegionLocator(TableName.valueOf("yinzhengjie:WordCount3")) );
        job.waitForCompletion(true);
    }
}

4>.查看测试结果