Skip to content

[SPARK-21333][Docs] Removed invalid joinTypes from javadoc of Dataset#joinWith #18462

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
coreywoodfield wants to merge 4 commits into from
Closed

[SPARK-21333][Docs] Removed invalid joinTypes from javadoc of Dataset#joinWith #18462

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
a643ef2
Removed invalid joinTypes from javadoc of Dataset#joinWith
coreywoodfield Jun 29, 2017
00af861
Added check for invalid join types in joinWith and tests
coreywoodfield Jul 4, 2017
c00daf8
Added check to make sure correct exception was being caught in test
coreywoodfield Jul 7, 2017
9aee54a
Analysis exception now contains joinType.sql instead of joinType
coreywoodfield Jul 7, 2017
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 5 additions & 1 deletion sql/core/src/main/scala/org/apache/spark/sql/Dataset.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -990,7 +990,7 @@ class Dataset[T] private[sql](
* @param condition Join expression.
* @param joinType Type of join to perform. Default `inner`. Must be one of:
* `inner`, `cross`, `outer`, `full`, `full_outer`, `left`, `left_outer`,
* `right`, `right_outer`, `left_semi`, `left_anti`.
* `right`, `right_outer`.
*
* @group typedrel
* @since 1.6.0
Expand All @@ -1007,6 +1007,10 @@ class Dataset[T] private[sql](
JoinType(joinType),
Some(condition.expr))).analyzed.asInstanceOf[Join]

if (joined.joinType == LeftSemi || joined.joinType == LeftAnti) {
throw new AnalysisException("Invalid join type in joinWith: " + joined.joinType.sql)
}

// For both join side, combine all outputs into a single column and alias it with "_1" or "_2",
// to match the schema for the encoder of the join result.
// Note that we do this before joining them, to enable the join operator to return null for one
Expand Down
16 changes: 16 additions & 0 deletions sql/core/src/test/scala/org/apache/spark/sql/DatasetSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,6 +21,7 @@ import java.io.{Externalizable, ObjectInput, ObjectOutput}
import java.sql.{Date, Timestamp}

import org.apache.spark.sql.catalyst.encoders.{OuterScopes, RowEncoder}
import org.apache.spark.sql.catalyst.plans.{LeftAnti, LeftSemi}
import org.apache.spark.sql.catalyst.util.sideBySide
import org.apache.spark.sql.execution.{LogicalRDD, RDDScanExec, SortExec}
import org.apache.spark.sql.execution.exchange.{BroadcastExchangeExec, ShuffleExchange}
Expand Down Expand Up @@ -321,6 +322,21 @@ class DatasetSuite extends QueryTest with SharedSQLContext {
((("b", 2), ("b", 2)), ("b", 2)))
}

test("joinWith join types") {
val ds1 = Seq(1, 2, 3).toDS().as("a")
val ds2 = Seq(1, 2).toDS().as("b")

val e1 = intercept[AnalysisException] {
ds1.joinWith(ds2, $"a.value" === $"b.value", "left_semi")
}.getMessage
assert(e1.contains("Invalid join type in joinWith: " + LeftSemi.sql))

val e2 = intercept[AnalysisException] {
ds1.joinWith(ds2, $"a.value" === $"b.value", "left_anti")
}.getMessage
assert(e2.contains("Invalid join type in joinWith: " + LeftAnti.sql))
}

test("groupBy function, keys") {
val ds = Seq(("a", 1), ("b", 1)).toDS()
val grouped = ds.groupByKey(v => (1, v._2))
Expand Down