实时 Spark Streaming 消费示例

示例代码

## StructuredLoghubWordCount.Scala

object StructuredLoghubSample {
  def main(args: Array[String]) {
    if (args.length < 7) {
      System.err.println("Usage: StructuredLoghubSample <logService-project> " +
        "<logService-store> <access-key-id> <access-key-secret> <endpoint> " +
        "<starting-offsets> <max-offsets-per-trigger> [<checkpoint-location>]")
      System.exit(1)
    }

    val Array(project, logStore, accessKeyId, accessKeySecret, endpoint, startingOffsets, maxOffsetsPerTrigger, outputPath, _*) = args
    val checkpointLocation =
      if (args.length > 8) args(8) else "/tmp/temporary-" + UUID.randomUUID.toString

    val spark = SparkSession
      .builder
      .appName("StructuredLoghubSample")
      .master("local[5]")
      .getOrCreate()

    import spark.implicits._

    // Create DataSet representing the stream of input lines from loghub
    val lines = spark
      .readStream
      .format("loghub")
      .option("sls.project", project)
      .option("sls.store", logStore)
      .option("access.key.id", accessKeyId)
      .option("access.key.secret", accessKeySecret)
      .option("endpoint", endpoint)
      .option("startingoffsets", startingOffsets)
      .option("zookeeper.connect.address", "localhost:2181")
      .option("maxOffsetsPerTrigger", maxOffsetsPerTrigger)
      .load()
      .selectExpr("CAST(content AS STRING)")
      .as[String]

    val query = lines.writeStream
      .format("parquet")
      .option("checkpointLocation", checkpointLocation)
      .option("path", outputPath)
      .outputMode("append")
      .trigger(Trigger.ProcessingTime(30000))
      .start()

    query.awaitTermination()
  }
}

编译运行

## 编译命令
mvn clean package -DskipTests

## 编译完后，作业jar包位于target/shaded/下

## 提交执行

spark-submit --master yarn-cluster --executor-cores 2 --executor-memory 1g --driver-memory 1g 
--num-executors 2--class x.x.x.StructuredLoghubSample xxx.jar <logService-project> 
<logService-store> <access-key-id> <access-key-secret> <endpoint> <starting-offsets> 
<max-offsets-per-trigger> <zookeeper-connect-address> <output-path> <checkpoint-location>

注意事项