//设置package包名称以及导入依赖的类
package com.jjzhk.sparkexamples.streaming

import java.sql.Timestamp

import org.apache.spark.sql.SparkSession
import org.apache.spark.sql.functions.window



object OnlineHotestItems {
  def main(args: Array[String]): Unit = {
    val spark = SparkSession.builder().master("spark://Master:7077").appName("OnlineHotestItems").getOrCreate()

    val lines = spark.readStream.format("socket").option("host", "Master").option("port", 9999)
      .option("includeTimestamp", true).load()
    import spark.implicits._
    val words = lines.as[(String, Timestamp)].flatMap(line =>
      line._1.split(" ").map(word => (word, line._2))
    ).toDF("word", "timestamp")
    import spark.implicits._
    val windowedCounts = words.groupBy(
      window($"timestamp", "", ""), $"word"
    ).count().orderBy("window")

    // Start running the query that prints the windowed word counts to the console
    val query = windowedCounts.writeStream
      .outputMode("complete")
      .format("console")
      .option("truncate", "false")
      .start()
  }
}