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

The following examples show how to use org.apache.spark.sql.catalyst.plans.LeftSemi. 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: ReplaceOperatorSuite.scala    From drizzle-spark   with Apache License 2.0 5 votes vote down vote up 
package org.apache.spark.sql.catalyst.optimizer

import org.apache.spark.sql.catalyst.dsl.expressions._
import org.apache.spark.sql.catalyst.dsl.plans._
import org.apache.spark.sql.catalyst.plans.{LeftAnti, LeftSemi, PlanTest}
import org.apache.spark.sql.catalyst.plans.logical._
import org.apache.spark.sql.catalyst.rules.RuleExecutor

class ReplaceOperatorSuite extends PlanTest {

  object Optimize extends RuleExecutor[LogicalPlan] {
    val batches =
      Batch("Replace Operators", FixedPoint(100),
        ReplaceDistinctWithAggregate,
        ReplaceExceptWithAntiJoin,
        ReplaceIntersectWithSemiJoin) :: Nil
  }

  test("replace Intersect with Left-semi Join") {
    val table1 = LocalRelation('a.int, 'b.int)
    val table2 = LocalRelation('c.int, 'd.int)

    val query = Intersect(table1, table2)
    val optimized = Optimize.execute(query.analyze)

    val correctAnswer =
      Aggregate(table1.output, table1.output,
        Join(table1, table2, LeftSemi, Option('a <=> 'c && 'b <=> 'd))).analyze

    comparePlans(optimized, correctAnswer)
  }

  test("replace Except with Left-anti Join") {
    val table1 = LocalRelation('a.int, 'b.int)
    val table2 = LocalRelation('c.int, 'd.int)

    val query = Except(table1, table2)
    val optimized = Optimize.execute(query.analyze)

    val correctAnswer =
      Aggregate(table1.output, table1.output,
        Join(table1, table2, LeftAnti, Option('a <=> 'c && 'b <=> 'd))).analyze

    comparePlans(optimized, correctAnswer)
  }

  test("replace Distinct with Aggregate") {
    val input = LocalRelation('a.int, 'b.int)

    val query = Distinct(input)
    val optimized = Optimize.execute(query.analyze)

    val correctAnswer = Aggregate(input.output, input.output, input)

    comparePlans(optimized, correctAnswer)
  }
}
Example 2
Source File: RewriteSubquerySuite.scala    From XSQL   with Apache License 2.0 5 votes vote down vote up 
package org.apache.spark.sql.catalyst.optimizer

import org.apache.spark.sql.catalyst.dsl.expressions._
import org.apache.spark.sql.catalyst.dsl.plans._
import org.apache.spark.sql.catalyst.expressions.ListQuery
import org.apache.spark.sql.catalyst.plans.{LeftSemi, PlanTest}
import org.apache.spark.sql.catalyst.plans.logical.{LocalRelation, LogicalPlan}
import org.apache.spark.sql.catalyst.rules.RuleExecutor


class RewriteSubquerySuite extends PlanTest {

  object Optimize extends RuleExecutor[LogicalPlan] {
    val batches =
      Batch("Column Pruning", FixedPoint(100), ColumnPruning) ::
      Batch("Rewrite Subquery", FixedPoint(1),
        RewritePredicateSubquery,
        ColumnPruning,
        CollapseProject,
        RemoveRedundantProject) :: Nil
  }

  test("Column pruning after rewriting predicate subquery") {
    val relation = LocalRelation('a.int, 'b.int)
    val relInSubquery = LocalRelation('x.int, 'y.int, 'z.int)

    val query = relation.where('a.in(ListQuery(relInSubquery.select('x)))).select('a)

    val optimized = Optimize.execute(query.analyze)
    val correctAnswer = relation
      .select('a)
      .join(relInSubquery.select('x), LeftSemi, Some('a === 'x))
      .analyze

    comparePlans(optimized, correctAnswer)
  }

}
Example 3
Source File: ReplaceOperatorSuite.scala    From sparkoscope   with Apache License 2.0 5 votes vote down vote up 
package org.apache.spark.sql.catalyst.optimizer

import org.apache.spark.sql.catalyst.dsl.expressions._
import org.apache.spark.sql.catalyst.dsl.plans._
import org.apache.spark.sql.catalyst.plans.{LeftAnti, LeftSemi, PlanTest}
import org.apache.spark.sql.catalyst.plans.logical._
import org.apache.spark.sql.catalyst.rules.RuleExecutor

class ReplaceOperatorSuite extends PlanTest {

  object Optimize extends RuleExecutor[LogicalPlan] {
    val batches =
      Batch("Replace Operators", FixedPoint(100),
        ReplaceDistinctWithAggregate,
        ReplaceExceptWithAntiJoin,
        ReplaceIntersectWithSemiJoin) :: Nil
  }

  test("replace Intersect with Left-semi Join") {
    val table1 = LocalRelation('a.int, 'b.int)
    val table2 = LocalRelation('c.int, 'd.int)

    val query = Intersect(table1, table2)
    val optimized = Optimize.execute(query.analyze)

    val correctAnswer =
      Aggregate(table1.output, table1.output,
        Join(table1, table2, LeftSemi, Option('a <=> 'c && 'b <=> 'd))).analyze

    comparePlans(optimized, correctAnswer)
  }

  test("replace Except with Left-anti Join") {
    val table1 = LocalRelation('a.int, 'b.int)
    val table2 = LocalRelation('c.int, 'd.int)

    val query = Except(table1, table2)
    val optimized = Optimize.execute(query.analyze)

    val correctAnswer =
      Aggregate(table1.output, table1.output,
        Join(table1, table2, LeftAnti, Option('a <=> 'c && 'b <=> 'd))).analyze

    comparePlans(optimized, correctAnswer)
  }

  test("replace Distinct with Aggregate") {
    val input = LocalRelation('a.int, 'b.int)

    val query = Distinct(input)
    val optimized = Optimize.execute(query.analyze)

    val correctAnswer = Aggregate(input.output, input.output, input)

    comparePlans(optimized, correctAnswer)
  }
}
Example 4
Source File: ReplaceOperatorSuite.scala    From multi-tenancy-spark   with Apache License 2.0 5 votes vote down vote up 
package org.apache.spark.sql.catalyst.optimizer

import org.apache.spark.sql.catalyst.dsl.expressions._
import org.apache.spark.sql.catalyst.dsl.plans._
import org.apache.spark.sql.catalyst.plans.{LeftAnti, LeftSemi, PlanTest}
import org.apache.spark.sql.catalyst.plans.logical._
import org.apache.spark.sql.catalyst.rules.RuleExecutor

class ReplaceOperatorSuite extends PlanTest {

  object Optimize extends RuleExecutor[LogicalPlan] {
    val batches =
      Batch("Replace Operators", FixedPoint(100),
        ReplaceDistinctWithAggregate,
        ReplaceExceptWithAntiJoin,
        ReplaceIntersectWithSemiJoin) :: Nil
  }

  test("replace Intersect with Left-semi Join") {
    val table1 = LocalRelation('a.int, 'b.int)
    val table2 = LocalRelation('c.int, 'd.int)

    val query = Intersect(table1, table2)
    val optimized = Optimize.execute(query.analyze)

    val correctAnswer =
      Aggregate(table1.output, table1.output,
        Join(table1, table2, LeftSemi, Option('a <=> 'c && 'b <=> 'd))).analyze

    comparePlans(optimized, correctAnswer)
  }

  test("replace Except with Left-anti Join") {
    val table1 = LocalRelation('a.int, 'b.int)
    val table2 = LocalRelation('c.int, 'd.int)

    val query = Except(table1, table2)
    val optimized = Optimize.execute(query.analyze)

    val correctAnswer =
      Aggregate(table1.output, table1.output,
        Join(table1, table2, LeftAnti, Option('a <=> 'c && 'b <=> 'd))).analyze

    comparePlans(optimized, correctAnswer)
  }

  test("replace Distinct with Aggregate") {
    val input = LocalRelation('a.int, 'b.int)

    val query = Distinct(input)
    val optimized = Optimize.execute(query.analyze)

    val correctAnswer = Aggregate(input.output, input.output, input)

    comparePlans(optimized, correctAnswer)
  }
}
Example 5
Source File: RewriteSubquerySuite.scala    From Spark-2.3.1   with Apache License 2.0 5 votes vote down vote up 
package org.apache.spark.sql.catalyst.optimizer

import org.apache.spark.sql.catalyst.dsl.expressions._
import org.apache.spark.sql.catalyst.dsl.plans._
import org.apache.spark.sql.catalyst.expressions.ListQuery
import org.apache.spark.sql.catalyst.plans.{LeftSemi, PlanTest}
import org.apache.spark.sql.catalyst.plans.logical.{LocalRelation, LogicalPlan}
import org.apache.spark.sql.catalyst.rules.RuleExecutor


class RewriteSubquerySuite extends PlanTest {

  object Optimize extends RuleExecutor[LogicalPlan] {
    val batches =
      Batch("Column Pruning", FixedPoint(100), ColumnPruning) ::
      Batch("Rewrite Subquery", FixedPoint(1),
        RewritePredicateSubquery,
        ColumnPruning,
        CollapseProject,
        RemoveRedundantProject) :: Nil
  }

  test("Column pruning after rewriting predicate subquery") {
    val relation = LocalRelation('a.int, 'b.int)
    val relInSubquery = LocalRelation('x.int, 'y.int, 'z.int)

    val query = relation.where('a.in(ListQuery(relInSubquery.select('x)))).select('a)

    val optimized = Optimize.execute(query.analyze)
    val correctAnswer = relation
      .select('a)
      .join(relInSubquery.select('x), LeftSemi, Some('a === 'x))
      .analyze

    comparePlans(optimized, correctAnswer)
  }

}