spark streaming:从kafka读取CSV字符串，写入拼接

import org.apache.spark.streaming._
import org.apache.spark.streaming.kafka010._

val sparkConf = new SparkConf().setAppName("SparkStreamingExample")
val ssc = new StreamingContext(sparkConf, Seconds(1))

val kafkaParams = Map[String, Object](
  "bootstrap.servers" -> "kafka-server:9092",
  "key.deserializer" -> classOf[StringDeserializer],
  "value.deserializer" -> classOf[StringDeserializer],
  "group.id" -> "spark-streaming-consumer",
  "auto.offset.reset" -> "latest",
  "enable.auto.commit" -> (false: java.lang.Boolean)
)

val topics = Array("topic1")
val stream = KafkaUtils.createDirectStream[String, String](
  ssc,
  PreferConsistent,
  Subscribe[String, String](topics, kafkaParams)
)

import org.apache.spark.sql._
import org.apache.spark.sql.functions._

stream.foreachRDD { rdd =>
  val spark = SparkSession.builder.config(rdd.sparkContext.getConf).getOrCreate()
  import spark.implicits._

  val df = spark.read.csv(rdd.map(_.value))
  val concatenatedDF = df.withColumn("concatenated", concat($"_c0", $"_c1"))

  concatenatedDF.show()
}