find_bug.scala 2.85 KB
package com.gmei

import java.io.Serializable

import com.gmei.WeafareStat.{defaultParams, parser}
import org.apache.spark.sql.{SaveMode, TiContext}
import org.apache.log4j.{Level, Logger}
import scopt.OptionParser
import com.gmei.lib.AbstractParams

object find_bug {

  Logger.getLogger("org.apache.spark").setLevel(Level.WARN)
  Logger.getLogger("org.apache.eclipse.jetty.server").setLevel(Level.OFF)

  case class Params(env: String = "dev",
                    date: String = "2018-08-01"
                   ) extends AbstractParams[Params] with Serializable

  val defaultParams = Params()

  val parser = new OptionParser[Params]("Feed_EDA") {
    head("WeafareStat")
    opt[String]("env")
      .text(s"the databases environment you used")
      .action((x, c) => c.copy(env = x))
    opt[String] ("date")
      .text(s"the date you used")
      .action((x,c) => c.copy(date = x))
    note(
      """
        |For example, the following command runs this app on a tidb dataset:
        |
        | spark-submit --class com.gmei.WeafareStat ./target/scala-2.11/feededa-assembly-0.1.jar \
      """.stripMargin +
        s"|   --env ${defaultParams.env}"
    )
  }

  def main(args: Array[String]): Unit = {
    parser.parse(args, defaultParams).map { param =>
      GmeiConfig.setup(param.env)
      val spark_env = GmeiConfig.getSparkSession()
      val sc = spark_env._2

      val ti = new TiContext(sc)
      ti.tidbMapTable(dbName = "jerry_prod", tableName = "diary_video")
      ti.tidbMapTable(dbName = "jerry_prod", tableName = "data_feed_click")
      ti.tidbMapTable(dbName = "jerry_prod", tableName = "blacklist")
      ti.tidbMapTable(dbName = "jerry_test", tableName = "bl_device_list")
      ti.tidbMapTable(dbName = "jerry_prod", tableName = "data_feed_exposure")
      ti.tidbMapTable(dbName = "jerry_prod", tableName = "merge_queue_table")


//      val stat_date = GmeiConfig.getMinusNDate(1)
      val stat_date = param.date
      //println(param.date)
      val partition_date = stat_date.replace("-","")

      val clk_count_all = sc.sql(
        s"""
           |select '${stat_date}' as stat_date,count(cid_id) as clk_count_all
           |from data_feed_click
           |where  (cid_type = 'diary' or cid_type = 'diary_video')
           |and device_id not in (select device_id from blacklist)
           |and stat_date ='${stat_date}'
         """.stripMargin
      )

      val imp_count_all = sc.sql(
        s"""
           |select '${stat_date}' as stat_date,count(cid_id) as imp_count_all
           |from data_feed_exposure
           |where cid_type = 'diary'
           |and device_id not in (select device_id from blacklist)
           |and stat_date ='${stat_date}'
         """.stripMargin
      )


      val result1 = clk_count_all.join(imp_count_all,"stat_date")
      result1.show()

      GmeiConfig.writeToJDBCTable(result1, "find_bug", SaveMode.Append)


    }


  }

}