org.apache.spark.sql.catalyst.plans.QueryPlan Scala Examples

The following examples show how to use org.apache.spark.sql.catalyst.plans.QueryPlan. You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example.
Example 1
Source File: cache.scala    From sparkoscope   with Apache License 2.0 5 votes vote down vote up 
package org.apache.spark.sql.execution.command

import org.apache.spark.sql.{Dataset, Row, SparkSession}
import org.apache.spark.sql.catalyst.TableIdentifier
import org.apache.spark.sql.catalyst.analysis.NoSuchTableException
import org.apache.spark.sql.catalyst.plans.QueryPlan
import org.apache.spark.sql.catalyst.plans.logical.LogicalPlan

case class CacheTableCommand(
    tableIdent: TableIdentifier,
    plan: Option[LogicalPlan],
    isLazy: Boolean) extends RunnableCommand {
  require(plan.isEmpty || tableIdent.database.isEmpty,
    "Database name is not allowed in CACHE TABLE AS SELECT")

  override protected def innerChildren: Seq[QueryPlan[_]] = {
    plan.toSeq
  }

  override def run(sparkSession: SparkSession): Seq[Row] = {
    plan.foreach { logicalPlan =>
      Dataset.ofRows(sparkSession, logicalPlan).createTempView(tableIdent.quotedString)
    }
    sparkSession.catalog.cacheTable(tableIdent.quotedString)

    if (!isLazy) {
      // Performs eager caching
      sparkSession.table(tableIdent).count()
    }

    Seq.empty[Row]
  }
}


case class UncacheTableCommand(
    tableIdent: TableIdentifier,
    ifExists: Boolean) extends RunnableCommand {

  override def run(sparkSession: SparkSession): Seq[Row] = {
    val tableId = tableIdent.quotedString
    try {
      sparkSession.catalog.uncacheTable(tableId)
    } catch {
      case _: NoSuchTableException if ifExists => // don't throw
    }
    Seq.empty[Row]
  }
}


case object ClearCacheCommand extends RunnableCommand {

  override def run(sparkSession: SparkSession): Seq[Row] = {
    sparkSession.catalog.clearCache()
    Seq.empty[Row]
  }
}
Example 2
Source File: cache.scala    From Spark-2.3.1   with Apache License 2.0 5 votes vote down vote up 
package org.apache.spark.sql.execution.command

import org.apache.spark.sql.{Dataset, Row, SparkSession}
import org.apache.spark.sql.catalyst.TableIdentifier
import org.apache.spark.sql.catalyst.analysis.NoSuchTableException
import org.apache.spark.sql.catalyst.plans.QueryPlan
import org.apache.spark.sql.catalyst.plans.logical.LogicalPlan

case class CacheTableCommand(
    tableIdent: TableIdentifier,
    plan: Option[LogicalPlan],
    isLazy: Boolean) extends RunnableCommand {
  require(plan.isEmpty || tableIdent.database.isEmpty,
    "Database name is not allowed in CACHE TABLE AS SELECT")

  override protected def innerChildren: Seq[QueryPlan[_]] = plan.toSeq

  override def run(sparkSession: SparkSession): Seq[Row] = {
    plan.foreach { logicalPlan =>
      Dataset.ofRows(sparkSession, logicalPlan).createTempView(tableIdent.quotedString)
    }
    sparkSession.catalog.cacheTable(tableIdent.quotedString)

    if (!isLazy) {
      // Performs eager caching
      sparkSession.table(tableIdent).count()
    }

    Seq.empty[Row]
  }
}


case class UncacheTableCommand(
    tableIdent: TableIdentifier,
    ifExists: Boolean) extends RunnableCommand {

  override def run(sparkSession: SparkSession): Seq[Row] = {
    val tableId = tableIdent.quotedString
    if (!ifExists || sparkSession.catalog.tableExists(tableId)) {
      sparkSession.catalog.uncacheTable(tableId)
    }
    Seq.empty[Row]
  }
}


  override def makeCopy(newArgs: Array[AnyRef]): ClearCacheCommand = ClearCacheCommand()
}
Example 3
Source File: SaveIntoDataSourceCommand.scala    From Spark-2.3.1   with Apache License 2.0 5 votes vote down vote up 
package org.apache.spark.sql.execution.datasources

import org.apache.spark.sql.{Dataset, Row, SaveMode, SparkSession}
import org.apache.spark.sql.catalyst.plans.QueryPlan
import org.apache.spark.sql.catalyst.plans.logical.LogicalPlan
import org.apache.spark.sql.execution.command.RunnableCommand
import org.apache.spark.sql.internal.SQLConf
import org.apache.spark.sql.sources.CreatableRelationProvider


case class SaveIntoDataSourceCommand(
    query: LogicalPlan,
    dataSource: CreatableRelationProvider,
    options: Map[String, String],
    mode: SaveMode) extends RunnableCommand {

  override protected def innerChildren: Seq[QueryPlan[_]] = Seq(query)

  override def run(sparkSession: SparkSession): Seq[Row] = {
    dataSource.createRelation(
      sparkSession.sqlContext, mode, options, Dataset.ofRows(sparkSession, query))

    Seq.empty[Row]
  }

  override def simpleString: String = {
    val redacted = SQLConf.get.redactOptions(options)
    s"SaveIntoDataSourceCommand ${dataSource}, ${redacted}, ${mode}"
  }
}
Example 4
Source File: InsertIntoDataSourceCommand.scala    From Spark-2.3.1   with Apache License 2.0 5 votes vote down vote up 
package org.apache.spark.sql.execution.datasources

import org.apache.spark.sql._
import org.apache.spark.sql.catalyst.plans.QueryPlan
import org.apache.spark.sql.catalyst.plans.logical.LogicalPlan
import org.apache.spark.sql.execution.command.RunnableCommand
import org.apache.spark.sql.sources.InsertableRelation



case class InsertIntoDataSourceCommand(
    logicalRelation: LogicalRelation,
    query: LogicalPlan,
    overwrite: Boolean)
  extends RunnableCommand {

  override protected def innerChildren: Seq[QueryPlan[_]] = Seq(query)

  override def run(sparkSession: SparkSession): Seq[Row] = {
    val relation = logicalRelation.relation.asInstanceOf[InsertableRelation]
    val data = Dataset.ofRows(sparkSession, query)
    // Apply the schema of the existing table to the new data.
    val df = sparkSession.internalCreateDataFrame(data.queryExecution.toRdd, logicalRelation.schema)
    relation.insert(df, overwrite)

    // Re-cache all cached plans(including this relation itself, if it's cached) that refer to this
    // data source relation.
    sparkSession.sharedState.cacheManager.recacheByPlan(sparkSession, logicalRelation)

    Seq.empty[Row]
  }
}
Example 5
Source File: LogicalRelation.scala    From Spark-2.3.1   with Apache License 2.0 5 votes vote down vote up 
package org.apache.spark.sql.execution.datasources

import org.apache.spark.sql.catalyst.analysis.MultiInstanceRelation
import org.apache.spark.sql.catalyst.catalog.CatalogTable
import org.apache.spark.sql.catalyst.expressions.{AttributeMap, AttributeReference}
import org.apache.spark.sql.catalyst.plans.QueryPlan
import org.apache.spark.sql.catalyst.plans.logical.{LeafNode, LogicalPlan, Statistics}
import org.apache.spark.sql.sources.BaseRelation
import org.apache.spark.util.Utils


  override def newInstance(): LogicalRelation = {
    this.copy(output = output.map(_.newInstance()))
  }

  override def refresh(): Unit = relation match {
    case fs: HadoopFsRelation => fs.location.refresh()
    case _ =>  // Do nothing.
  }

  override def simpleString: String = s"Relation[${Utils.truncatedString(output, ",")}] $relation"
}

object LogicalRelation {
  def apply(relation: BaseRelation, isStreaming: Boolean = false): LogicalRelation =
    LogicalRelation(relation, relation.schema.toAttributes, None, isStreaming)

  def apply(relation: BaseRelation, table: CatalogTable): LogicalRelation =
    LogicalRelation(relation, relation.schema.toAttributes, Some(table), false)
}
Example 6
Source File: commands.scala    From multi-tenancy-spark   with Apache License 2.0 5 votes vote down vote up 
package org.apache.spark.sql.execution.command

import org.apache.spark.rdd.RDD
import org.apache.spark.sql.{Row, SparkSession}
import org.apache.spark.sql.catalyst.{CatalystTypeConverters, InternalRow}
import org.apache.spark.sql.catalyst.errors.TreeNodeException
import org.apache.spark.sql.catalyst.expressions.{Attribute, AttributeReference}
import org.apache.spark.sql.catalyst.plans.QueryPlan
import org.apache.spark.sql.catalyst.plans.logical
import org.apache.spark.sql.catalyst.plans.logical.LogicalPlan
import org.apache.spark.sql.execution.SparkPlan
import org.apache.spark.sql.execution.debug._
import org.apache.spark.sql.execution.streaming.IncrementalExecution
import org.apache.spark.sql.streaming.OutputMode
import org.apache.spark.sql.types._


case class ExplainCommand(
    logicalPlan: LogicalPlan,
    override val output: Seq[Attribute] =
      Seq(AttributeReference("plan", StringType, nullable = true)()),
    extended: Boolean = false,
    codegen: Boolean = false)
  extends RunnableCommand {

  // Run through the optimizer to generate the physical plan.
  override def run(sparkSession: SparkSession): Seq[Row] = try {
    val queryExecution =
      if (logicalPlan.isStreaming) {
        // This is used only by explaining `Dataset/DataFrame` created by `spark.readStream`, so the
        // output mode does not matter since there is no `Sink`.
        new IncrementalExecution(sparkSession, logicalPlan, OutputMode.Append(), "<unknown>", 0, 0)
      } else {
        sparkSession.sessionState.executePlan(logicalPlan)
      }
    val outputString =
      if (codegen) {
        codegenString(queryExecution.executedPlan)
      } else if (extended) {
        queryExecution.toString
      } else {
        queryExecution.simpleString
      }
    Seq(Row(outputString))
  } catch { case cause: TreeNodeException[_] =>
    ("Error occurred during query planning: \n" + cause.getMessage).split("\n").map(Row(_))
  }
}
Example 7
Source File: cache.scala    From multi-tenancy-spark   with Apache License 2.0 5 votes vote down vote up 
package org.apache.spark.sql.execution.command

import org.apache.spark.sql.{Dataset, Row, SparkSession}
import org.apache.spark.sql.catalyst.TableIdentifier
import org.apache.spark.sql.catalyst.analysis.NoSuchTableException
import org.apache.spark.sql.catalyst.plans.QueryPlan
import org.apache.spark.sql.catalyst.plans.logical.LogicalPlan

case class CacheTableCommand(
    tableIdent: TableIdentifier,
    plan: Option[LogicalPlan],
    isLazy: Boolean) extends RunnableCommand {
  require(plan.isEmpty || tableIdent.database.isEmpty,
    "Database name is not allowed in CACHE TABLE AS SELECT")

  override protected def innerChildren: Seq[QueryPlan[_]] = {
    plan.toSeq
  }

  override def run(sparkSession: SparkSession): Seq[Row] = {
    plan.foreach { logicalPlan =>
      Dataset.ofRows(sparkSession, logicalPlan).createTempView(tableIdent.quotedString)
    }
    sparkSession.catalog.cacheTable(tableIdent.quotedString)

    if (!isLazy) {
      // Performs eager caching
      sparkSession.table(tableIdent).count()
    }

    Seq.empty[Row]
  }
}


case class UncacheTableCommand(
    tableIdent: TableIdentifier,
    ifExists: Boolean) extends RunnableCommand {

  override def run(sparkSession: SparkSession): Seq[Row] = {
    val tableId = tableIdent.quotedString
    try {
      sparkSession.catalog.uncacheTable(tableId)
    } catch {
      case _: NoSuchTableException if ifExists => // don't throw
    }
    Seq.empty[Row]
  }
}


case object ClearCacheCommand extends RunnableCommand {

  override def run(sparkSession: SparkSession): Seq[Row] = {
    sparkSession.catalog.clearCache()
    Seq.empty[Row]
  }
}
Example 8
Source File: ddl.scala    From multi-tenancy-spark   with Apache License 2.0 5 votes vote down vote up 
package org.apache.spark.sql.execution.datasources

import org.apache.spark.sql._
import org.apache.spark.sql.catalyst.TableIdentifier
import org.apache.spark.sql.catalyst.catalog.{CatalogTable, CatalogUtils}
import org.apache.spark.sql.catalyst.plans.QueryPlan
import org.apache.spark.sql.catalyst.plans.logical.{Command, LogicalPlan}
import org.apache.spark.sql.execution.command.RunnableCommand
import org.apache.spark.sql.types._

case class CreateTable(
    tableDesc: CatalogTable,
    mode: SaveMode,
    query: Option[LogicalPlan]) extends Command {
  assert(tableDesc.provider.isDefined, "The table to be created must have a provider.")

  if (query.isEmpty) {
    assert(
      mode == SaveMode.ErrorIfExists || mode == SaveMode.Ignore,
      "create table without data insertion can only use ErrorIfExists or Ignore as SaveMode.")
  }

  override def innerChildren: Seq[QueryPlan[_]] = query.toSeq
}


case class CreateTempViewUsing(
    tableIdent: TableIdentifier,
    userSpecifiedSchema: Option[StructType],
    replace: Boolean,
    global: Boolean,
    provider: String,
    options: Map[String, String]) extends RunnableCommand {

  if (tableIdent.database.isDefined) {
    throw new AnalysisException(
      s"Temporary view '$tableIdent' should not have specified a database")
  }

  override def argString: String = {
    s"[tableIdent:$tableIdent " +
      userSpecifiedSchema.map(_ + " ").getOrElse("") +
      s"replace:$replace " +
      s"provider:$provider " +
      CatalogUtils.maskCredentials(options)
  }

  def run(sparkSession: SparkSession): Seq[Row] = {
    val dataSource = DataSource(
      sparkSession,
      userSpecifiedSchema = userSpecifiedSchema,
      className = provider,
      options = options)

    val catalog = sparkSession.sessionState.catalog
    val viewDefinition = Dataset.ofRows(
      sparkSession, LogicalRelation(dataSource.resolveRelation())).logicalPlan

    if (global) {
      catalog.createGlobalTempView(tableIdent.table, viewDefinition, replace)
    } else {
      catalog.createTempView(tableIdent.table, viewDefinition, replace)
    }

    Seq.empty[Row]
  }
}

case class RefreshTable(tableIdent: TableIdentifier)
  extends RunnableCommand {

  override def run(sparkSession: SparkSession): Seq[Row] = {
    // Refresh the given table's metadata. If this table is cached as an InMemoryRelation,
    // drop the original cached version and make the new version cached lazily.
    sparkSession.catalog.refreshTable(tableIdent.quotedString)
    Seq.empty[Row]
  }
}

case class RefreshResource(path: String)
  extends RunnableCommand {

  override def run(sparkSession: SparkSession): Seq[Row] = {
    sparkSession.catalog.refreshByPath(path)
    Seq.empty[Row]
  }
}
Example 9
Source File: InsertIntoDataSourceCommand.scala    From multi-tenancy-spark   with Apache License 2.0 5 votes vote down vote up 
package org.apache.spark.sql.execution.datasources

import org.apache.spark.sql._
import org.apache.spark.sql.catalyst.plans.QueryPlan
import org.apache.spark.sql.catalyst.plans.logical.{LogicalPlan, OverwriteOptions}
import org.apache.spark.sql.execution.command.RunnableCommand
import org.apache.spark.sql.sources.InsertableRelation



case class InsertIntoDataSourceCommand(
    logicalRelation: LogicalRelation,
    query: LogicalPlan,
    overwrite: OverwriteOptions)
  extends RunnableCommand {

  override protected def innerChildren: Seq[QueryPlan[_]] = Seq(query)

  override def run(sparkSession: SparkSession): Seq[Row] = {
    val relation = logicalRelation.relation.asInstanceOf[InsertableRelation]
    val data = Dataset.ofRows(sparkSession, query)
    // Apply the schema of the existing table to the new data.
    val df = sparkSession.internalCreateDataFrame(data.queryExecution.toRdd, logicalRelation.schema)
    relation.insert(df, overwrite.enabled)

    // Invalidate the cache.
    sparkSession.sharedState.cacheManager.invalidateCache(logicalRelation)

    Seq.empty[Row]
  }
}
Example 10
Source File: commands.scala    From sparkoscope   with Apache License 2.0 5 votes vote down vote up 
package org.apache.spark.sql.execution.command

import org.apache.spark.rdd.RDD
import org.apache.spark.sql.{Row, SparkSession}
import org.apache.spark.sql.catalyst.{CatalystTypeConverters, InternalRow}
import org.apache.spark.sql.catalyst.errors.TreeNodeException
import org.apache.spark.sql.catalyst.expressions.{Attribute, AttributeReference}
import org.apache.spark.sql.catalyst.plans.QueryPlan
import org.apache.spark.sql.catalyst.plans.logical
import org.apache.spark.sql.catalyst.plans.logical.LogicalPlan
import org.apache.spark.sql.execution.SparkPlan
import org.apache.spark.sql.execution.debug._
import org.apache.spark.sql.execution.streaming.IncrementalExecution
import org.apache.spark.sql.streaming.OutputMode
import org.apache.spark.sql.types._


case class ExplainCommand(
    logicalPlan: LogicalPlan,
    override val output: Seq[Attribute] =
      Seq(AttributeReference("plan", StringType, nullable = true)()),
    extended: Boolean = false,
    codegen: Boolean = false)
  extends RunnableCommand {

  // Run through the optimizer to generate the physical plan.
  override def run(sparkSession: SparkSession): Seq[Row] = try {
    val queryExecution =
      if (logicalPlan.isStreaming) {
        // This is used only by explaining `Dataset/DataFrame` created by `spark.readStream`, so the
        // output mode does not matter since there is no `Sink`.
        new IncrementalExecution(sparkSession, logicalPlan, OutputMode.Append(), "<unknown>", 0, 0)
      } else {
        sparkSession.sessionState.executePlan(logicalPlan)
      }
    val outputString =
      if (codegen) {
        codegenString(queryExecution.executedPlan)
      } else if (extended) {
        queryExecution.toString
      } else {
        queryExecution.simpleString
      }
    Seq(Row(outputString))
  } catch { case cause: TreeNodeException[_] =>
    ("Error occurred during query planning: \n" + cause.getMessage).split("\n").map(Row(_))
  }
}
Example 11
Source File: InsertIntoDataSourceCommand.scala    From drizzle-spark   with Apache License 2.0 5 votes vote down vote up 
package org.apache.spark.sql.execution.datasources

import org.apache.spark.sql._
import org.apache.spark.sql.catalyst.plans.QueryPlan
import org.apache.spark.sql.catalyst.plans.logical.LogicalPlan
import org.apache.spark.sql.execution.command.RunnableCommand
import org.apache.spark.sql.sources.InsertableRelation



case class InsertIntoDataSourceCommand(
    logicalRelation: LogicalRelation,
    query: LogicalPlan,
    overwrite: Boolean)
  extends RunnableCommand {

  override protected def innerChildren: Seq[QueryPlan[_]] = Seq(query)

  override def run(sparkSession: SparkSession): Seq[Row] = {
    val relation = logicalRelation.relation.asInstanceOf[InsertableRelation]
    val data = Dataset.ofRows(sparkSession, query)
    // Apply the schema of the existing table to the new data.
    val df = sparkSession.internalCreateDataFrame(data.queryExecution.toRdd, logicalRelation.schema)
    relation.insert(df, overwrite)

    // Invalidate the cache.
    sparkSession.sharedState.cacheManager.invalidateCache(logicalRelation)

    Seq.empty[Row]
  }
}
Example 12
Source File: ddl.scala    From sparkoscope   with Apache License 2.0 5 votes vote down vote up 
package org.apache.spark.sql.execution.datasources

import org.apache.spark.sql._
import org.apache.spark.sql.catalyst.TableIdentifier
import org.apache.spark.sql.catalyst.catalog.{CatalogTable, CatalogUtils}
import org.apache.spark.sql.catalyst.plans.QueryPlan
import org.apache.spark.sql.catalyst.plans.logical.{Command, LogicalPlan}
import org.apache.spark.sql.execution.command.RunnableCommand
import org.apache.spark.sql.types._

case class CreateTable(
    tableDesc: CatalogTable,
    mode: SaveMode,
    query: Option[LogicalPlan]) extends Command {
  assert(tableDesc.provider.isDefined, "The table to be created must have a provider.")

  if (query.isEmpty) {
    assert(
      mode == SaveMode.ErrorIfExists || mode == SaveMode.Ignore,
      "create table without data insertion can only use ErrorIfExists or Ignore as SaveMode.")
  }

  override def innerChildren: Seq[QueryPlan[_]] = query.toSeq
}


case class CreateTempViewUsing(
    tableIdent: TableIdentifier,
    userSpecifiedSchema: Option[StructType],
    replace: Boolean,
    global: Boolean,
    provider: String,
    options: Map[String, String]) extends RunnableCommand {

  if (tableIdent.database.isDefined) {
    throw new AnalysisException(
      s"Temporary view '$tableIdent' should not have specified a database")
  }

  override def argString: String = {
    s"[tableIdent:$tableIdent " +
      userSpecifiedSchema.map(_ + " ").getOrElse("") +
      s"replace:$replace " +
      s"provider:$provider " +
      CatalogUtils.maskCredentials(options)
  }

  def run(sparkSession: SparkSession): Seq[Row] = {
    val dataSource = DataSource(
      sparkSession,
      userSpecifiedSchema = userSpecifiedSchema,
      className = provider,
      options = options)

    val catalog = sparkSession.sessionState.catalog
    val viewDefinition = Dataset.ofRows(
      sparkSession, LogicalRelation(dataSource.resolveRelation())).logicalPlan

    if (global) {
      catalog.createGlobalTempView(tableIdent.table, viewDefinition, replace)
    } else {
      catalog.createTempView(tableIdent.table, viewDefinition, replace)
    }

    Seq.empty[Row]
  }
}

case class RefreshTable(tableIdent: TableIdentifier)
  extends RunnableCommand {

  override def run(sparkSession: SparkSession): Seq[Row] = {
    // Refresh the given table's metadata. If this table is cached as an InMemoryRelation,
    // drop the original cached version and make the new version cached lazily.
    sparkSession.catalog.refreshTable(tableIdent.quotedString)
    Seq.empty[Row]
  }
}

case class RefreshResource(path: String)
  extends RunnableCommand {

  override def run(sparkSession: SparkSession): Seq[Row] = {
    sparkSession.catalog.refreshByPath(path)
    Seq.empty[Row]
  }
}
Example 13
Source File: InsertIntoDataSourceCommand.scala    From sparkoscope   with Apache License 2.0 5 votes vote down vote up 
package org.apache.spark.sql.execution.datasources

import org.apache.spark.sql._
import org.apache.spark.sql.catalyst.plans.QueryPlan
import org.apache.spark.sql.catalyst.plans.logical.{LogicalPlan, OverwriteOptions}
import org.apache.spark.sql.execution.command.RunnableCommand
import org.apache.spark.sql.sources.InsertableRelation



case class InsertIntoDataSourceCommand(
    logicalRelation: LogicalRelation,
    query: LogicalPlan,
    overwrite: OverwriteOptions)
  extends RunnableCommand {

  override protected def innerChildren: Seq[QueryPlan[_]] = Seq(query)

  override def run(sparkSession: SparkSession): Seq[Row] = {
    val relation = logicalRelation.relation.asInstanceOf[InsertableRelation]
    val data = Dataset.ofRows(sparkSession, query)
    // Apply the schema of the existing table to the new data.
    val df = sparkSession.internalCreateDataFrame(data.queryExecution.toRdd, logicalRelation.schema)
    relation.insert(df, overwrite.enabled)

    // Invalidate the cache.
    sparkSession.sharedState.cacheManager.invalidateCache(logicalRelation)

    Seq.empty[Row]
  }
}
Example 14
Source File: cache.scala    From XSQL   with Apache License 2.0 5 votes vote down vote up 
package org.apache.spark.sql.execution.command

import org.apache.spark.sql.{Dataset, Row, SparkSession}
import org.apache.spark.sql.catalyst.TableIdentifier
import org.apache.spark.sql.catalyst.analysis.NoSuchTableException
import org.apache.spark.sql.catalyst.plans.QueryPlan
import org.apache.spark.sql.catalyst.plans.logical.LogicalPlan

case class CacheTableCommand(
    tableIdent: TableIdentifier,
    plan: Option[LogicalPlan],
    isLazy: Boolean) extends RunnableCommand {
  require(plan.isEmpty || tableIdent.database.isEmpty,
    "Database name is not allowed in CACHE TABLE AS SELECT")

  override protected def innerChildren: Seq[QueryPlan[_]] = plan.toSeq

  override def run(sparkSession: SparkSession): Seq[Row] = {
    plan.foreach { logicalPlan =>
      Dataset.ofRows(sparkSession, logicalPlan).createTempView(tableIdent.quotedString)
    }
    sparkSession.catalog.cacheTable(tableIdent.quotedString)

    if (!isLazy) {
      // Performs eager caching
      sparkSession.table(tableIdent).count()
    }

    Seq.empty[Row]
  }
}


case class UncacheTableCommand(
    tableIdent: TableIdentifier,
    ifExists: Boolean) extends RunnableCommand {

  override def run(sparkSession: SparkSession): Seq[Row] = {
    val tableId = tableIdent.quotedString
    if (!ifExists || sparkSession.catalog.tableExists(tableId)) {
      sparkSession.catalog.uncacheTable(tableId)
    }
    Seq.empty[Row]
  }
}


  override def makeCopy(newArgs: Array[AnyRef]): ClearCacheCommand = ClearCacheCommand()
}
Example 15
Source File: SaveIntoDataSourceCommand.scala    From XSQL   with Apache License 2.0 5 votes vote down vote up 
package org.apache.spark.sql.execution.datasources

import org.apache.spark.sql.{Dataset, Row, SaveMode, SparkSession}
import org.apache.spark.sql.catalyst.plans.QueryPlan
import org.apache.spark.sql.catalyst.plans.logical.LogicalPlan
import org.apache.spark.sql.execution.command.RunnableCommand
import org.apache.spark.sql.internal.SQLConf
import org.apache.spark.sql.sources.CreatableRelationProvider


case class SaveIntoDataSourceCommand(
    query: LogicalPlan,
    dataSource: CreatableRelationProvider,
    options: Map[String, String],
    mode: SaveMode) extends RunnableCommand {

  override protected def innerChildren: Seq[QueryPlan[_]] = Seq(query)

  override def run(sparkSession: SparkSession): Seq[Row] = {
    dataSource.createRelation(
      sparkSession.sqlContext, mode, options, Dataset.ofRows(sparkSession, query))

    Seq.empty[Row]
  }

  override def simpleString: String = {
    val redacted = SQLConf.get.redactOptions(options)
    s"SaveIntoDataSourceCommand ${dataSource}, ${redacted}, ${mode}"
  }
}
Example 16
Source File: InsertIntoDataSourceCommand.scala    From XSQL   with Apache License 2.0 5 votes vote down vote up 
package org.apache.spark.sql.execution.datasources

import org.apache.spark.sql._
import org.apache.spark.sql.catalyst.plans.QueryPlan
import org.apache.spark.sql.catalyst.plans.logical.LogicalPlan
import org.apache.spark.sql.execution.command.RunnableCommand
import org.apache.spark.sql.sources.InsertableRelation



case class InsertIntoDataSourceCommand(
    logicalRelation: LogicalRelation,
    query: LogicalPlan,
    overwrite: Boolean)
  extends RunnableCommand {

  override protected def innerChildren: Seq[QueryPlan[_]] = Seq(query)

  override def run(sparkSession: SparkSession): Seq[Row] = {
    val relation = logicalRelation.relation.asInstanceOf[InsertableRelation]
    val data = Dataset.ofRows(sparkSession, query)
    // Data has been casted to the target relation's schema by the PreprocessTableInsertion rule.
    relation.insert(data, overwrite)

    // Re-cache all cached plans(including this relation itself, if it's cached) that refer to this
    // data source relation.
    sparkSession.sharedState.cacheManager.recacheByPlan(sparkSession, logicalRelation)

    Seq.empty[Row]
  }
}
Example 17
Source File: LogicalRelation.scala    From XSQL   with Apache License 2.0 5 votes vote down vote up 
package org.apache.spark.sql.execution.datasources

import org.apache.spark.sql.catalyst.analysis.MultiInstanceRelation
import org.apache.spark.sql.catalyst.catalog.CatalogTable
import org.apache.spark.sql.catalyst.expressions.{AttributeMap, AttributeReference}
import org.apache.spark.sql.catalyst.plans.QueryPlan
import org.apache.spark.sql.catalyst.plans.logical.{LeafNode, LogicalPlan, Statistics}
import org.apache.spark.sql.sources.BaseRelation
import org.apache.spark.util.Utils


  override def newInstance(): LogicalRelation = {
    this.copy(output = output.map(_.newInstance()))
  }

  override def refresh(): Unit = relation match {
    case fs: HadoopFsRelation => fs.location.refresh()
    case _ =>  // Do nothing.
  }

  override def simpleString: String = s"Relation[${Utils.truncatedString(output, ",")}] $relation"
}

object LogicalRelation {
  def apply(relation: BaseRelation, isStreaming: Boolean = false): LogicalRelation =
    LogicalRelation(relation, relation.schema.toAttributes, None, isStreaming)

  def apply(relation: BaseRelation, table: CatalogTable): LogicalRelation =
    LogicalRelation(relation, relation.schema.toAttributes, Some(table), false)
}
Example 18
Source File: commands.scala    From drizzle-spark   with Apache License 2.0 5 votes vote down vote up 
package org.apache.spark.sql.execution.command

import org.apache.spark.rdd.RDD
import org.apache.spark.sql.{Row, SparkSession}
import org.apache.spark.sql.catalyst.{CatalystTypeConverters, InternalRow}
import org.apache.spark.sql.catalyst.errors.TreeNodeException
import org.apache.spark.sql.catalyst.expressions.{Attribute, AttributeReference}
import org.apache.spark.sql.catalyst.plans.QueryPlan
import org.apache.spark.sql.catalyst.plans.logical
import org.apache.spark.sql.catalyst.plans.logical.LogicalPlan
import org.apache.spark.sql.execution.SparkPlan
import org.apache.spark.sql.execution.debug._
import org.apache.spark.sql.execution.streaming.IncrementalExecution
import org.apache.spark.sql.streaming.OutputMode
import org.apache.spark.sql.types._


case class ExplainCommand(
    logicalPlan: LogicalPlan,
    override val output: Seq[Attribute] =
      Seq(AttributeReference("plan", StringType, nullable = true)()),
    extended: Boolean = false,
    codegen: Boolean = false)
  extends RunnableCommand {

  // Run through the optimizer to generate the physical plan.
  override def run(sparkSession: SparkSession): Seq[Row] = try {
    val queryExecution =
      if (logicalPlan.isStreaming) {
        // This is used only by explaining `Dataset/DataFrame` created by `spark.readStream`, so the
        // output mode does not matter since there is no `Sink`.
        new IncrementalExecution(sparkSession, logicalPlan, OutputMode.Append(), "<unknown>", 0)
      } else {
        sparkSession.sessionState.executePlan(logicalPlan)
      }
    val outputString =
      if (codegen) {
        codegenString(queryExecution.executedPlan)
      } else if (extended) {
        queryExecution.toString
      } else {
        queryExecution.simpleString
      }
    Seq(Row(outputString))
  } catch { case cause: TreeNodeException[_] =>
    ("Error occurred during query planning: \n" + cause.getMessage).split("\n").map(Row(_))
  }
}
Example 19
Source File: cache.scala    From drizzle-spark   with Apache License 2.0 5 votes vote down vote up 
package org.apache.spark.sql.execution.command

import org.apache.spark.sql.{Dataset, Row, SparkSession}
import org.apache.spark.sql.catalyst.TableIdentifier
import org.apache.spark.sql.catalyst.plans.QueryPlan
import org.apache.spark.sql.catalyst.plans.logical.LogicalPlan

case class CacheTableCommand(
    tableIdent: TableIdentifier,
    plan: Option[LogicalPlan],
    isLazy: Boolean) extends RunnableCommand {
  require(plan.isEmpty || tableIdent.database.isEmpty,
    "Database name is not allowed in CACHE TABLE AS SELECT")

  override protected def innerChildren: Seq[QueryPlan[_]] = {
    plan.toSeq
  }

  override def run(sparkSession: SparkSession): Seq[Row] = {
    plan.foreach { logicalPlan =>
      Dataset.ofRows(sparkSession, logicalPlan).createTempView(tableIdent.quotedString)
    }
    sparkSession.catalog.cacheTable(tableIdent.quotedString)

    if (!isLazy) {
      // Performs eager caching
      sparkSession.table(tableIdent).count()
    }

    Seq.empty[Row]
  }
}


case class UncacheTableCommand(tableIdent: TableIdentifier) extends RunnableCommand {

  override def run(sparkSession: SparkSession): Seq[Row] = {
    sparkSession.catalog.uncacheTable(tableIdent.quotedString)
    Seq.empty[Row]
  }
}


case object ClearCacheCommand extends RunnableCommand {

  override def run(sparkSession: SparkSession): Seq[Row] = {
    sparkSession.catalog.clearCache()
    Seq.empty[Row]
  }
}
Example 20
Source File: ddl.scala    From drizzle-spark   with Apache License 2.0 5 votes vote down vote up 
package org.apache.spark.sql.execution.datasources

import org.apache.spark.sql._
import org.apache.spark.sql.catalyst.TableIdentifier
import org.apache.spark.sql.catalyst.catalog.CatalogTable
import org.apache.spark.sql.catalyst.plans.QueryPlan
import org.apache.spark.sql.catalyst.plans.logical.{Command, LogicalPlan}
import org.apache.spark.sql.execution.command.RunnableCommand
import org.apache.spark.sql.types._

case class CreateTable(
    tableDesc: CatalogTable,
    mode: SaveMode,
    query: Option[LogicalPlan]) extends Command {
  assert(tableDesc.provider.isDefined, "The table to be created must have a provider.")

  if (query.isEmpty) {
    assert(
      mode == SaveMode.ErrorIfExists || mode == SaveMode.Ignore,
      "create table without data insertion can only use ErrorIfExists or Ignore as SaveMode.")
  }

  override def innerChildren: Seq[QueryPlan[_]] = query.toSeq
}


class CaseInsensitiveMap(map: Map[String, String]) extends Map[String, String]
  with Serializable {

  val baseMap = map.map(kv => kv.copy(_1 = kv._1.toLowerCase))

  override def get(k: String): Option[String] = baseMap.get(k.toLowerCase)

  override def + [B1 >: String](kv: (String, B1)): Map[String, B1] =
    baseMap + kv.copy(_1 = kv._1.toLowerCase)

  override def iterator: Iterator[(String, String)] = baseMap.iterator

  override def -(key: String): Map[String, String] = baseMap - key.toLowerCase
}