Hbase与wordcount的结合使用

最新推荐文章于 2021-02-25 10:25:33 发布

小江_xiaojiang

最新推荐文章于 2021-02-25 10:25:33 发布

阅读量842

点赞数

分类专栏： MapReduce

本文链接：https://blog.csdn.net/jiangsanfeng1111/article/details/45787613

版权

MapReduce 专栏收录该内容

14 篇文章 1 订阅

订阅专栏

文章来源：hadoop实战2

程序首先从文件中收集数据，在shuffle完成之后进行统计并计算，最后将计算结果存储到hbase中。

输入样例：

hello hadoop

hello world

bye hadoop

bye world

输出样例：

scan 'wordcount'

ROW COLUMN+CELL

bye column=content:count ,timestamp=1297571391451,value=2

hadoop column=content:count ,timestamp=1297571391452,value=2

hello column=content:count ,timestamp=1297571391452,value=2

world column=content:count ,timestamp=1297571391452,value=2

package hbase;

import java.io.IOException;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.hbase.HBaseConfiguration;
import org.apache.hadoop.hbase.HColumnDescriptor;
import org.apache.hadoop.hbase.HTableDescriptor;
import org.apache.hadoop.hbase.client.HBaseAdmin;
import org.apache.hadoop.hbase.client.Put;
import org.apache.hadoop.hbase.mapreduce.TableOutputFormat;
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.LongWritable;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;

public class WordCountHBase {

	public static class Map extends Mapper<LongWritable, Text, Text, IntWritable>{

		@Override
		protected void map(LongWritable key, Text value, Context context)
				throws IOException, InterruptedException {
			String s[] = value.toString().trim().split(" ");
			for(String m :s){
				context.write(new Text(m), new IntWritable(1));
			}
		}
	}
	
	public static class Reduce extends TableReducer<Text, IntWritable, NullWritable>{

		protected void reduce(Text key, Iterable<IntWritable> values,Context context)
				throws IOException, InterruptedException {
			int sum=0;
			for(IntWritable i: values){
				sum+=i.get();
			}
			//Put实例化，每一个词存一行 rowkey
			Put put = new Put(Bytes.toBytes(key.toString()));
			//列族为content，列修饰符为count，列值为数目
			put.add(Bytes.toBytes("content"), Bytes.toBytes("count"), Bytes.toBytes(String.valueOf(sum)));
			context.write(NullWritable.get(), put);
		}
	}
	
	public static void createHBaseTable(String tablename) throws Exception{
		HTableDescriptor htd = new HTableDescriptor(tablename);
		HColumnDescriptor col = new HColumnDescriptor("content:");
		htd.addFamily(col);
		HBaseConfiguration config = new HBaseConfiguration();
		HBaseAdmin admin = new HBaseAdmin(config);
		if(admin.tableExists(tablename)){
			System.out.println("table exists,trying recreate table !");
			admin.disableTable(tablename);
			admin.deleteTable(tablename);
		}
		System.out.println("Create new table: "+ tablename);
		admin.createTable(htd);
	}
	
	public static void main(String[] args) throws Exception {
		String tablename = "wordcount";
		Configuration conf = new Configuration();
		conf.set(TableOutputFormat.OUTPUT_TABLE, tablename);
		createHBaseTable(tablename);
		String input = args[0];
		Job job = new Job(conf,"WordCount table with"+input);
		job.setJarByClass(WordCountHBase.class);
		job.setNumReduceTasks(3);
		job.setMapperClass(Map.class);
		job.setReducerClass(Reduce.class);
		job.setMapOutputKeyClass(Text.class);
		job.setMapOutputValueClass(IntWritable.class);
		job.setInputFormatClass(TextInputFormat.class);
		job.setOutputFormatClass(TableOutputFormat.class);
		FileInputFormat.addInputPath(job, new Path(input));
		System.exit(job.waitForCompletion(true)?0:1);
	}
	
	
}