Scala StreamSinkProvider类代码示例

OStack程序员社区-中国程序员成长平台 › 门户 › 编程› Scala›Scala教程

原作者: [db:作者] 来自: [db:来源] 收藏邀请

本文整理汇总了Scala中org.apache.spark.sql.sources.StreamSinkProvider类的典型用法代码示例。如果您正苦于以下问题：Scala StreamSinkProvider类的具体用法？Scala StreamSinkProvider怎么用？Scala StreamSinkProvider使用的例子？那么恭喜您, 这里精选的类代码示例或许可以为您提供帮助。

在下文中一共展示了StreamSinkProvider类的3个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于我们的系统推荐出更棒的Scala代码示例。

示例1: CustomSinkProvider

//设置package包名称以及导入依赖的类
package com.knockdata.spark.highcharts

import com.knockdata.spark.highcharts.model.Highcharts
import org.apache.spark.sql._
import org.apache.spark.sql.execution.streaming.Sink
import org.apache.spark.sql.sources.StreamSinkProvider
import org.apache.spark.sql.streaming.OutputMode

class CustomSinkProvider extends StreamSinkProvider {
  def createSink(
                  sqlContext: SQLContext,
                  parameters: Map[String, String],
                  partitionColumns: Seq[String],
                  outputMode: OutputMode): Sink = {
    new Sink {
      override def addBatch(batchId: Long, data: DataFrame): Unit = {

        val chartId = parameters("chartId")
        val chartParagraphId = parameters("chartParagraphId")

        println(s"batchId: $batchId, chartId: $chartId, chartParagraphId: $chartParagraphId")
//        data.show(3)

        val z = Registry.get(s"$chartId-z").asInstanceOf[ZeppelinContextHolder]
        val seriesHolder = Registry.get(s"$chartId-seriesHolder").asInstanceOf[SeriesHolder]
        val outputMode = Registry.get(s"$chartId-outputMode").asInstanceOf[CustomOutputMode]

        seriesHolder.dataFrame = data

        val result = seriesHolder.result
        val (normalSeriesList, drilldownSeriesList) = outputMode.result(result._1, result._2)

        val chart = new Highcharts(normalSeriesList, seriesHolder.chartId)
          .drilldown(drilldownSeriesList)

        val plotData = chart.plotData
//        val escaped = plotData.replace("%angular", "")
//        println(s" put $chartParagraphId $escaped")
        z.put(chartParagraphId, plotData)
        println(s"run $chartParagraphId")
        z.run(chartParagraphId)
      }
    }
  }
}

开发者ID:knockdata，项目名称:spark-highcharts，代码行数:46，代码来源:CustomSinkProvider.scala

示例2: CustomSinkProvider

//设置package包名称以及导入依赖的类
package com.rockiey.kafka

import org.apache.spark.sql._
import org.apache.spark.sql.execution.streaming.Sink
import org.apache.spark.sql.sources.StreamSinkProvider
import org.apache.spark.sql.streaming.OutputMode

class CustomSinkProvider extends StreamSinkProvider {
  def createSink(
                  sqlContext: SQLContext,
                  parameters: Map[String, String],
                  partitionColumns: Seq[String],
                  outputMode: OutputMode): Sink = {
    new Sink {
      override def addBatch(batchId: Long, data: DataFrame): Unit = {
        data.printSchema()

        data.show()
        println(s"count ${data.count()}")
      }
    }
  }
}

开发者ID:rockie-yang，项目名称:explore-spark-kafka，代码行数:24，代码来源:CustomSinkProvider.scala

示例3: ClickHouseSinkProvider

//设置package包名称以及导入依赖的类
package io.clickhouse.ext.spark.streaming

import io.clickhouse.ext.ClickHouseUtils
import org.apache.spark.internal.Logging
import org.apache.spark.sql.{Encoders, SQLContext}
import org.apache.spark.sql.sources.StreamSinkProvider
import org.apache.spark.sql.streaming.OutputMode
import scala.reflect.{ClassTag, classTag}
import scala.reflect.runtime.universe.TypeTag

abstract class ClickHouseSinkProvider[T <: Product: ClassTag](implicit tag: TypeTag[T]) extends StreamSinkProvider with Serializable with Logging {

  def clickHouseServers: Seq[(String, Int)]
  def dbName: String
  def tableName: Option[String] = None
  def eventDateColumnName: String
  def indexColumns: Seq[String]
  def partitionFunc: (org.apache.spark.sql.Row) => java.sql.Date

  override def createSink(
                           sqlContext: SQLContext,
                           parameters: Map[String, String],
                           partitionColumns: Seq[String],
                           outputMode: OutputMode): ClickHouseSink[T] = {

    val typeEncoder = Encoders.product[T]
    val schema = typeEncoder.schema
    val _tableName = tableName.get //tableName.getOrElse(classOf[T].getName)

    val createTableSql = ClickHouseUtils.createTableIfNotExistsSql(
      schema,
      dbName,
      _tableName,
      eventDateColumnName,
      indexColumns
    )
    log.info("create new table sql:")
    log.info(createTableSql)

    val connection = ClickHouseUtils.createConnection(getConnectionString())
    try{
      connection.createStatement().execute(createTableSql)
    }finally {
      connection.close()
      log.info(s"ClickHouse table ${dbName}.${_tableName} created")
    }

    log.info("Creating ClickHouse sink")
    new ClickHouseSink[T](dbName, _tableName, eventDateColumnName)(getConnectionString)(partitionFunc)
  }

  def getConnectionString(): (String, Int) = clickHouseServers.head

}

开发者ID:DmitryBe，项目名称:spark-streaming-clickhouse，代码行数:55，代码来源:ClickHouseSinkProvider.scala

注：本文中的org.apache.spark.sql.sources.StreamSinkProvider类示例整理自Github/MSDocs等源码及文档管理平台，相关代码片段筛选自各路编程大神贡献的开源项目，源码版权归原作者所有，传播和使用请参考对应项目的License；未经允许，请勿转载。