Kafka---将kafka中的数据导入HBase
Posted Shall潇
tags:
篇首语:本文由小常识网(cha138.com)小编为大家整理,主要介绍了Kafka---将kafka中的数据导入HBase相关的知识,希望对你有一定的参考价值。
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.hbase.HBaseConfiguration;
import org.apache.hadoop.hbase.HConstants;
import org.apache.hadoop.hbase.TableName;
import org.apache.hadoop.hbase.client.*;
import org.apache.hadoop.hbase.util.Bytes;
import org.apache.kafka.clients.consumer.ConsumerConfig;
import org.apache.kafka.clients.consumer.ConsumerRecord;
import org.apache.kafka.clients.consumer.ConsumerRecords;
import org.apache.kafka.clients.consumer.KafkaConsumer;
import org.apache.kafka.common.serialization.StringDeserializer;
import java.io.IOException;
import java.util.ArrayList;
import java.util.Collections;
import java.util.List;
import java.util.Properties;
/**
* @Author shall潇
* @Date 2021/5/31
* @Description 将 kafka topic数据导入 hbase
*/
public class UserFriendToHB {
static int num = 0;
public static void main(String[] args) {
//1.kafka 消费端属性配置
Properties properties = new Properties();
properties.put(ConsumerConfig.BOOTSTRAP_SERVERS_CONFIG,"192.168.159.100:9092");
properties.put(ConsumerConfig.KEY_DESERIALIZER_CLASS_CONFIG, StringDeserializer.class);
properties.put(ConsumerConfig.VALUE_DESERIALIZER_CLASS_CONFIG, StringDeserializer.class);
properties.put(ConsumerConfig.SESSION_TIMEOUT_MS_CONFIG,"30000");
//是否自动提交,获取数据的状态 false 是手动提交,true是自动提交,时间间隔1000
properties.put(ConsumerConfig.ENABLE_AUTO_COMMIT_CONFIG,"false");
properties.put(ConsumerConfig.AUTO_COMMIT_INTERVAL_MS_CONFIG,"1000");
properties.put(ConsumerConfig.AUTO_OFFSET_RESET_CONFIG,"earliest");
properties.put(ConsumerConfig.GROUP_ID_CONFIG,"user_friend_group");
//订阅对应主题的消息
KafkaConsumer<String, String> consumer = new KafkaConsumer<>(properties);
consumer.subscribe(Collections.singleton("user_friends"));
//2.HBase 配置
Configuration conf = HBaseConfiguration.create();
conf.set(HConstants.HBASE_DIR,"hdfs://192.168.159.100:9000/hbase");
conf.set("hbase.zookeeper.quorum","192.168.159.100");
conf.set("hbase.zookeeper.property.clientPort","2181");
Connection connection = null;
try {
connection = ConnectionFactory.createConnection(conf);
Admin admin = connection.getAdmin();
Table table = connection.getTable(TableName.valueOf("event_db:user_friend"));
while (true){
//3.处理读到的record,并且put到HBase中的表中
ConsumerRecords<String, String> records = consumer.poll(100);
List<Put> datas = new ArrayList<>();
for (ConsumerRecord<String, String> record : records) {
System.out.println(record.value());
String[] split = record.value().split(",");
Put put = new Put(Bytes.toBytes((split[0] + split[1]).hashCode()));
put.addColumn("uf".getBytes(),"userid".getBytes(),split[0].getBytes());
put.addColumn("uf".getBytes(),"friendid".getBytes(),split[1].getBytes());
datas.add(put);
}
num+=datas.size();
System.out.println(num+"行");
table.put(datas);
}
} catch (IOException e) {
e.printStackTrace();
}
}
}
以上是关于Kafka---将kafka中的数据导入HBase的主要内容,如果未能解决你的问题,请参考以下文章
新闻网大数据实时分析可视化系统项目——9Flume+HBase+Kafka集成与开发