Flink-Environment的三种方式和Source的四种读取方式-从集合中、从kafka中、从文件中、自定义

Environment

getExecutionEnvironment:创建一个执行环境，表示当前执行程序的上下文。 如果程序是独立调用的，则此方法返回本地执行环境；如果从命令行客户端调用程序以提交到集群，则此方法返回此集群的执行环境，也就是说，getExecutionEnvironment会根据查询运行的方式决定返回什么样的运行环境，是最常用的一种创建执行环境的方式。如果没有设置并行度，会以flink-conf.yaml中的配置为准，默认是1。

// 批处理
val env: ExecutionEnvironment = ExecutionEnvironment.getExecutionEnvironment
// 流处理
val env = StreamExecutionEnvironment.getExecutionEnvironment

createLocalEnvironment：返回本地执行环境，需要在调用时指定默认的并行度

val env = StreamExecutionEnvironment.createLocalEnvironment(1)

createRemoteEnvironment：返回集群执行环境，将Jar提交到远程服务器。需要在调用时指定JobManager的IP和端口号，并指定要在集群中运行的Jar包。

val env = ExecutionEnvironment.createRemoteEnvironment("jobmanage-hostname", 6123,"YOURPATH//wordcount.jar")

Source之从集合中读取数据

SensorReading.scala

// 定义样例类，传感器id，时间戳，温度
case class SensorReading(id: String, timestamp: Long, temperature: Double)

SourceForCollection.scala

// 隐式转换很重要
import org.apache.flink.streaming.api.scala._

/**
 * 从集合中获取数据
 */
object SourceForCollection {
  def main(args: Array[String]): Unit = {

    // 创建执行环境
    val env = StreamExecutionEnvironment.getExecutionEnvironment

    // 从集合中读取数据
    val listDstream : DataStream[SensorReading] = env.fromCollection(List(
      SensorReading("sensor_1", 1547718199, 35.8),
      SensorReading("sensor_6", 1547718201, 15.4),
      SensorReading("sensor_7", 1547718202, 6.7),
      SensorReading("sensor_10", 1547718205, 38.1)
    ))

    listDstream.print("stream for list").setParallelism(1)

    // 执行job
    env.execute("source test job")
  }
}

Source之从文件中读取数据

SensorReading.txt

sensor_1,1547718199,35.8
sensor_6,1547718201,15.4
sensor_7,1547718202,6.7
sensor_10,1547718205,38.1

SourceForFile.scala

import org.apache.flink.streaming.api.scala._

/**
 * Source从文件中读取
 */
object SourceForFile {
  def main(args: Array[String]): Unit = {

    // 创建执行环境
    val env = StreamExecutionEnvironment.getExecutionEnvironment

    val fileDstream: DataStream[String] =
      env.readTextFile("D:\\MyWork\\WorkSpaceIDEA\\flink-tutorial\\src\\main\\resources\\SensorReading.txt")

    fileDstream.print("source for file")

    // 执行job
    env.execute("source test job")
  }
}

Source之从Kafka消息队列的数据作为来源

pom.xml

<dependency>
    <groupId>org.apache.flink</groupId>
    <artifactId>flink-connector-kafka-0.11_2.11</artifactId>
    <version>1.10.0</version>
</dependency>

SourceForKafka.scala

import java.util.Properties


import org.apache.flink.api.common.serialization.SimpleStringSchema
import org.apache.flink.streaming.api.scala._
import org.apache.flink.streaming.connectors.kafka.FlinkKafkaConsumer011


/**
 * 以kafka消息队列的数据作为来源
 */
object SourceForKafka {
  def main(args: Array[String]): Unit = {

    val env: StreamExecutionEnvironment = StreamExecutionEnvironment.getExecutionEnvironment

    // 先创建kafka的相关配置
    val properties: Properties = new Properties()
    properties.setProperty("bootstrap.servers", "hadoop102:9092")
    properties.setProperty("group.id", "consumer-group")
    properties.setProperty("key.deserializer", "org.apache.kafka.common.serialization.StringDeserializer")
    properties.setProperty("value.deserializer", "org.apache.kafka.common.serialization.StringDeserializer")
    properties.setProperty("auto.offset.reset", "latest")

    val kafkaDstream:DataStream[String] = env.addSource( new FlinkKafkaConsumer011[String]("sensor", new SimpleStringSchema(), properties))

    kafkaDstream.print("source for kafka")

    env.execute("source test job")
  }
}

开启kafka生产者

// kafka数据生产者
./bin/kafka-console-producer.sh --broker-list hadoop102:9092 --topic sensor

自定义Source

SourceForCustom.scala

import com.atguigu.bean.SensorReading
import org.apache.flink.streaming.api.functions.source.SourceFunction
import org.apache.flink.streaming.api.scala._

import scala.collection.immutable
import scala.util.Random

/**
 * 自定义一个Source
 */
object SourceForCustom {

  def main(args: Array[String]): Unit = {

    // 创建执行环境
    val env = StreamExecutionEnvironment.getExecutionEnvironment

    val customDstream: DataStream[SensorReading] = env.addSource( MySensorSource())

    customDstream.print("source for custom").setParallelism(4)

    env.execute("source test job")
  }
}


// 自定义生成测试数据源的SourceFunction
case class MySensorSource() extends SourceFunction[SensorReading]{

  // 定义一个标识位，用来表示数据源是否正常运行
  var running: Boolean = true

  override def cancel(): Unit = {
    running = false
  }

  // 随机生成10个传感器的温度数据
  override def run(sourceContext: SourceFunction.SourceContext[SensorReading]): Unit = {

    // 初始化一个随机数生成器
    val random = new Random()

    // 初始化10个传感器的温度值，随机生成，包装成二元组（id, temperature）
    var createTemperature: immutable.IndexedSeq[(String, Double)] = 1.to(10).map(
      i => ("sensor_" + i, 60 + random.nextGaussian() * 20)
    )

    // 无限循环生成数据，如果cancel的话就停止
    while (running) {
      // 更新当前温度值，再之前温度上增加微小扰动(上下浮动的数)
      createTemperature = createTemperature.map(
        data => (data._1, data._2 + random.nextGaussian())
      )

      // 获取当前时间戳，包装样例类
      val timestamp: Long = System.currentTimeMillis()
      createTemperature.foreach(
        data => sourceContext.collect( SensorReading(data._1, timestamp, data._2))
      )

      // 间隔200ms
      Thread.sleep(200)
    }
  }
}