Updated on 2022-09-14 GMT+08:00

Scala Sample Code

Function

In Spark applications, use StructuredStreaming to invoke Kafka interface to obtain word records. Collect the statistics of records for each word.

Code Sample

The following code is an example. For details, see com.huawei.bigdata.spark.examples.SecurityKafkaWordCount.

When new data is available in Streaming DataFrame/Dataset, outputMode is used for configuring data written to the Streaming receiver.

object SecurityKafkaWordCount {
  def main(args: Array[String]): Unit = {
    if (args.length < 6) {
      System.err.println("Usage: SecurityKafkaWordCount <bootstrap-servers> " +
        "<subscribe-type> <topics> <protocol> <service> <domain>")
      System.exit(1)
    }

    val Array(bootstrapServers, subscribeType, topics, protocol, service, domain) = args

    val spark = SparkSession
      .builder
      .appName("SecurityKafkaWordCount")
      .getOrCreate()

    import spark.implicits._

    // Create DataSet representing the stream of input lines from kafka
    val lines = spark
      .readStream
      .format("kafka")
      .option("kafka.bootstrap.servers", bootstrapServers)
      .option(subscribeType, topics)
      .option("kafka.security.protocol", protocol)
      .option("kafka.sasl.kerberos.service.name", service)
      .option("kafka.kerberos.domain.name", domain)
      .load()
      .selectExpr("CAST(value AS STRING)")
      .as[String]

    // Generate running word count
    val wordCounts = lines.flatMap(_.split(" ")).groupBy("value").count()

    // Start running the query that prints the running counts to the console
    val query = wordCounts.writeStream
      .outputMode("complete")
      .format("console")
      .start()

    query.awaitTermination()
  }
}