Strom+Hbase

最新推荐文章于 2024-01-28 14:32:40 发布

ZJ18712852367

最新推荐文章于 2024-01-28 14:32:40 发布

阅读量232

点赞数 1

本文链接：https://blog.csdn.net/ZJ18712852367/article/details/82810193

版权

0、Hbase中创建表‘ns1：wordcount’

$hbase shell>create 'ns1:wordcount' , 'f1'

表结构为：

rowkey就是word

f1列族下有：word列和count列

1 、引入依赖

<?xml version="1.0" encoding="UTF-8"?>
		<project xmlns="http://maven.apache.org/POM/4.0.0"
				 xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
				 xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
			<modelVersion>4.0.0</modelVersion>

			<groupId>com.XXXX</groupId>
			<artifactId>StormDemo</artifactId>
			<version>1.0-SNAPSHOT</version>

			<dependencies>
				<dependency>
					<groupId>org.apache.storm</groupId>
					<artifactId>storm-core</artifactId>
					<version>1.0.3</version>
				</dependency>
				<dependency>
					<groupId>junit</groupId>
					<artifactId>junit</artifactId>
					<version>4.11</version>
				</dependency>
				<dependency>
					<groupId>org.apache.storm</groupId>
					<artifactId>storm-kafka</artifactId>
					<version>1.0.2</version>
				</dependency>
				<dependency>
					<groupId>log4j</groupId>
					<artifactId>log4j</artifactId>
					<version>1.2.17</version>
				</dependency>
				<dependency>
					<groupId>org.apache.kafka</groupId>
					<artifactId>kafka_2.10</artifactId>
					<version>0.8.1.1</version>
					<exclusions>
						<exclusion>
							<groupId>org.apache.zookeeper</groupId>
							<artifactId>zookeeper</artifactId>
						</exclusion>
						<exclusion>
							<groupId>log4j</groupId>
							<artifactId>log4j</artifactId>
						</exclusion>
					</exclusions>
				</dependency>
				<dependency>
					<groupId>org.apache.storm</groupId>
					<artifactId>storm-hbase</artifactId>
					<version>1.0.3</version>
				</dependency>
				<dependency>
					<groupId>org.apache.hbase</groupId>
					<artifactId>hbase-client</artifactId>
					<version>1.2.3</version>
				</dependency>
				<dependency>
					<groupId>org.apache.hadoop</groupId>
					<artifactId>hadoop-common</artifactId>
					<version>2.7.3</version>
				</dependency>
			</dependencies>

		</project>

2、HbaseBolt

package com.XXX.stormdemo.hbase;

		import org.apache.hadoop.conf.Configuration;
		import org.apache.hadoop.hbase.HBaseConfiguration;
		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.client.Table;
		import org.apache.hadoop.hbase.util.Bytes;
		import org.apache.storm.shade.org.apache.http.conn.HttpConnectionFactory;
		import org.apache.storm.task.OutputCollector;
		import org.apache.storm.task.TopologyContext;
		import org.apache.storm.topology.IRichBolt;
		import org.apache.storm.topology.OutputFieldsDeclarer;
		import org.apache.storm.tuple.Tuple;

		import java.io.IOException;
		import java.util.Map;

		/**
		 * HbaseBolt,写入数据到hbase库中。
		 */
		public class HbaseBolot implements IRichBolt {

			private Table t ;
			public void prepare(Map stormConf, TopologyContext context, OutputCollector collector) {
				try {
					Configuration conf = HBaseConfiguration.create();
					Connection conn = ConnectionFactory.createConnection(conf);
					TableName tname = TableName.valueOf("ns1:wordcount");
					t = conn.getTable(tname);
				} catch (IOException e) {
					e.printStackTrace();
				}

			}

			public void execute(Tuple tuple) {
				String word = tuple.getString(0);
				Integer count = tuple.getInteger(1);
				//使用hbase的increment机制进行wordcount
				byte[] rowkey = Bytes.toBytes(word);
				byte[] f = Bytes.toBytes("f1");
				byte[] c = Bytes.toBytes("count");
				try {
					t.incrementColumnValue(rowkey,f,c,count);
				} catch (IOException e) {
				}
			}

			public void cleanup() {
			}

			public void declareOutputFields(OutputFieldsDeclarer declarer) {
			}

			public Map<String, Object> getComponentConfiguration() {
				return null;
			}
		}

3、把配置文件复制到sources文件夹下

[resources]
hbase-site.xml
hdfs-site.xml

4、查看Hbase中提前创建好的表‘ns1：wordcount’

scan ‘ns1：wordcount’