Flink中将数据写入到文件和kafka(scala版)

1.将数输出到文件

package com.gqy.test

import org.apache.flink.api.common.serialization.SimpleStringEncoder
import org.apache.flink.core.fs.Path
import org.apache.flink.streaming.api.functions.sink.filesystem.StreamingFileSink
import org.apache.flink.streaming.api.scala._

/**
 * @author shkstart
 * @create 2021-08-05 14:15
 */
object ReduceTest {
  def main(args: Array[String]): Unit = {
    //创建环境
    val env = StreamExecutionEnvironment.getExecutionEnvironment
    env.setParallelism(1)

    //读取数据
    val path = getClass.getResource("/test").getPath
    val inputSream = env.readTextFile(path)

    inputSream.addSink(
     StreamingFileSink.forRowFormat(
       new Path("E:\\daima\\project\\UserBehaviorAnalysis\\OrderPayDetect\\src\\main\\resources\\output"),
       new SimpleStringEncoder[String]()
     ).build()
   )
    env.execute()
  }
}

结果：

2.将数据写道kafka中

依赖：这里的依赖要注意自己版本

<dependency>
    <groupId>org.apache.flink</groupId>
    <artifactId>flink-connector-kafka-0.11_2.12</artifactId>
    <version>1.10.1</version>
</dependency>

代码：

package com.gqy.test

import org.apache.flink.api.common.serialization.SimpleStringSchema
import org.apache.flink.streaming.api.scala._
import org.apache.flink.streaming.connectors.kafka.FlinkKafkaProducer

/**
 * @author shkstart
 * @create 2021-08-05 14:15
 */
object ReduceTest {
  def main(args: Array[String]): Unit = {
    //创建环境
    val env = StreamExecutionEnvironment.getExecutionEnvironment
    env.setParallelism(1)

    //读取数据
    val path = getClass.getResource("/test").getPath
    val inputSream = env.readTextFile(path)

    inputSream.addSink(
      new FlinkKafkaProducer[String]("hadoop101:9092","sinktest",new SimpleStringSchema())
    )

    env.execute()
  }
}

结果：