flink 透過繼承RichSinkFunction實現自定義sink,將資料錄入資料庫

hgs19921112發表於2019-02-19
//主類
package flink.streaming
import java.util.Properties
import org.apache.flink.streaming.api.scala._
import org.apache.flink.streaming.connectors.kafka.FlinkKafkaConsumer
import org.apache.flink.api.common.serialization.SimpleStringSchema
import org.apache.flink.streaming.api.windowing.time.Time
import org.apache.flink.streaming.api.TimeCharacteristic
import org.apache.flink.streaming.api.functions.sink.RichSinkFunction
import org.apache.flink.streaming.api.CheckpointingMode
object StreamingTest {
  def main(args: Array[String]): Unit = {
    val kafkaProps = new Properties()
    //kafka的一些屬性
    kafkaProps.setProperty("bootstrap.servers", "bigdata01:9092")
    //所在的消費組
    kafkaProps.setProperty("group.id", "group2")
    //獲取當前的執行環境
    val evn = StreamExecutionEnvironment.getExecutionEnvironment
    //evn.setStreamTimeCharacteristic(TimeCharacteristic.EventTime)
    //kafka的consumer,test1是要消費的topic
    val kafkaSource = new FlinkKafkaConsumer[String]("test1",new SimpleStringSchema,kafkaProps)
    //kafkaSource.assignTimestampsAndWatermarks(assigner)
    //設定從最新的offset開始消費
    //kafkaSource.setStartFromGroupOffsets()
    kafkaSource.setStartFromLatest()
    //自動提交offset
    kafkaSource.setCommitOffsetsOnCheckpoints(true)
    
    //flink的checkpoint的時間間隔
    //evn.enableCheckpointing(2000)
    //新增consumer
    val stream = evn.addSource(kafkaSource)
    evn.enableCheckpointing(2000, CheckpointingMode.EXACTLY_ONCE)
    //stream.setParallelism(3)
    val text = stream.flatMap{ _.toLowerCase().split(" ")filter { _.nonEmpty} }
          .map{(_,1)}
          .keyBy(0)
          .timeWindow(Time.seconds(5))
          .sum(1)
          .map(x=>{(x._1,(new Integer(x._2)))})
     //text.print()
     //啟動執行    
     
     text.addSink(new Ssinks())
     
    evn.execute("kafkawd")  
    
  }
}
//自定義sink
package flink.streaming
import java.sql.Connection
import java.sql.PreparedStatement
import java.sql.DriverManager
import org.apache.flink.streaming.api.functions.sink.RichSinkFunction
import org.apache.flink.configuration.Configuration
class Ssinks extends RichSinkFunction[(String,Integer)]{
  
      var conn:Connection=_;
      var pres:PreparedStatement = _;
      var username = "root";
      var password = "123456";
      var dburl = "jdbc:mysql://192.168.6.132:3306/hgs?useUnicode=true&characterEncoding=utf-8&useSSL=false";
      var sql = "insert into words(word,count) values(?,?)";
  override def invoke(value:(String, Integer) ) {
    
    pres.setString(1, value._1);
		pres.setInt(2,value._2);
		pres.executeUpdate();
		System.out.println("values :" +value._1+"--"+value._2);
  }
  
  override def open( parameters:Configuration) {
		Class.forName("com.mysql.jdbc.Driver");
		conn = DriverManager.getConnection(dburl, username, password);
		pres = conn.prepareStatement(sql);
		super.close()
	}
  
	override def close() {
	  pres.close();
	  conn.close();
	}
}


來自 “ ITPUB部落格 ” ,連結:http://blog.itpub.net/31506529/viewspace-2636334/,如需轉載,請註明出處,否則將追究法律責任。

相關文章