问具有周期性更新静态数据集的结构化流

EN

  // 1. Load the staticDataframe initially and keep as `var`
  var staticDf = spark.read.format("delta").load(deltaPath)
  staticDf.persist()

  //  2. Define a method that refreshes the static Dataframe
  def foreachBatchMethod[T](batchDf: Dataset[T], batchId: Long) = {
    staticDf.unpersist()
    staticDf = spark.read.format("delta").load(deltaPath)
    staticDf.persist()
    println(s"${Calendar.getInstance().getTime}: Refreshing static Dataframe from DeltaLake")
  }

  // 3. Use a "Rate" Stream that gets triggered at the required interval (e.g. 1 hour)
  val staticRefreshStream = spark.readStream
    .format("rate")
    .option("rowsPerSecond", 1)
    .option("numPartitions", 1)
    .load()
    .selectExpr("CAST(value as LONG) as trigger")
    .as[Long]

  // 4. Read actual streaming data and perform join operation with static Dataframe
  // As an example I used Kafka as a streaming source
  val streamingDf = spark.readStream
    .format("kafka")
    .option("kafka.bootstrap.servers", "localhost:9092")
    .option("subscribe", "test")
    .option("startingOffsets", "earliest")
    .option("failOnDataLoss", "false")
    .load()
    .selectExpr("CAST(value AS STRING) as id", "offset as streamingField")

  val joinDf = streamingDf.join(staticDf, "id")

  val query = joinDf.writeStream
    .format("console")
    .option("truncate", false)
    .option("checkpointLocation", "/path/to/sparkCheckpoint")
    .start()

  // 5. Within that Rate Stream have a `foreachBatch` sink that calls refresher method
  staticRefreshStream.writeStream
    .outputMode("append")
    .foreachBatch(foreachBatchMethod[Long] _)
    .queryName("RefreshStream")
    .trigger(Trigger.ProcessingTime("5 seconds"))
    .start()

  val deltaPath = "file:///tmp/delta/table"

  import spark.implicits._
  val df = Seq(
    (1L, "static1"),
    (2L, "static2")
  ).toDF("id", "deltaField")

  df.write
    .mode(SaveMode.Overwrite)
    .format("delta")
    .save(deltaPath)