import org.apache.spark.SparkConf
import org.apache.spark.rdd.RDD
import org.apache.spark.sql.SparkSession
import org.apache.spark.streaming.{Seconds, StreamingContext, Time}
/**
* Spark Streaming整合Spark SQL完成词频统计操作
*/
object SqlNetworkWordCount {
def main(args: Array[String]): Unit = {
val sparkConf = new SparkConf().setAppName("ForeachRDDApp").setMaster("local[2]")
val ssc = new StreamingContext(sparkConf, Seconds(5))
val lines = ssc.socketTextStream("localhost", 9999)
val words = lines.flatMap(_.split(" "))
// Convert RDDs of the words DStream to DataFrame and run SQL query
words.foreachRDD { (rdd: RDD[String], time: Time) =>
val spark = SparkSessionSingleton.getInstance(rdd.sparkContext.getConf)
import spark.implicits._
// Convert RDD[String] to RDD[case class] to DataFrame
val wordsDataFrame = rdd.map(w => Record(w)).toDF()
// Creates a temporary view using the DataFrame
wordsDataFrame.createOrReplaceTempView("words")
// Do word count on table using SQL and print it
val wordCountsDataFrame =
spark.sql("select word, count(*) as total from words group by word")
println(s"========= $time =========")
wordCountsDataFrame.show()
}
ssc.start()
ssc.awaitTermination()
}
/** Case class for converting RDD to DataFrame */
case class Record(word: String)
/** Lazily instantiated singleton instance of SparkSession */
object SparkSessionSingleton {
@transient private var instance: SparkSession = _
def getInstance(sparkConf: SparkConf): SparkSession = {
if (instance == null) {
instance = SparkSession
.builder
.config(sparkConf)
.getOrCreate()
}
instance
}
}
}
[Spark][spark_streaming]#5_spark_streaming&spark_sql
最新推荐文章于 2024-09-14 21:13:40 发布