flink读取数据源的四种方式

最新推荐文章于 2025-09-18 21:19:38 发布

原创

最新推荐文章于 2025-09-18 21:19:38 发布 · 3.2k 阅读

6 ·

CC 4.0 BY-SA版权

object SourceDemo {
  def main(args: Array[String]): Unit = {
    val env = StreamExecutionEnvironment.getExecutionEnvironment

    //数据来源
    //1.从文件读取
    val inpath="D:\\programs\\sparkPrograms\\FlinkProgarm\\src\\main\\resources\\hello.txt"
    val stream1 =  env.readTextFile(inpath)

    //2.从socket流中读取
    val stream2 =env.socketTextStream("hadoop01",7777)

    //3.从kafka中读取
    val properties=new Properties()
    properties.setProperty("bootstrap.servers","hadoop01:9092")
    properties.setProperty("group.id","cosumer-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 stream3 = env.addSource(new FlinkKafkaConsumer011[String]("sensor", new
        SimpleStringSchema(), properties))
    //    stream3.print("stream3")
    
    //4.