Skip to content

[SPARK-25389][SQL] INSERT OVERWRITE DIRECTORY STORED AS should prevent duplicate fields #22378

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
dongjoon-hyun wants to merge 1 commit into from
Closed

[SPARK-25389][SQL] INSERT OVERWRITE DIRECTORY STORED AS should prevent duplicate fields #22378

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
5 changes: 5 additions & 0 deletions sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/InsertIntoHiveDirCommand.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -34,6 +34,7 @@ import org.apache.spark.sql.catalyst.expressions.Attribute
import org.apache.spark.sql.catalyst.plans.logical.LogicalPlan
import org.apache.spark.sql.execution.SparkPlan
import org.apache.spark.sql.hive.client.HiveClientImpl
import org.apache.spark.sql.util.SchemaUtils

/**
* Command for writing the results of `query` to file system.
Expand Down Expand Up @@ -61,6 +62,10 @@ case class InsertIntoHiveDirCommand(

override def run(sparkSession: SparkSession, child: SparkPlan): Seq[Row] = {
assert(storage.locationUri.nonEmpty)
SchemaUtils.checkColumnNameDuplication(
outputColumnNames,
s"when inserting into ${storage.locationUri.get}",
sparkSession.sessionState.conf.caseSensitiveAnalysis)

val hiveTable = HiveClientImpl.toHiveTable(CatalogTable(
identifier = TableIdentifier(storage.locationUri.get.toString, Some("default")),
Expand Down
24 changes: 24 additions & 0 deletions sql/hive/src/test/scala/org/apache/spark/sql/hive/InsertSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,6 +26,7 @@ import org.apache.spark.sql.{QueryTest, _}
import org.apache.spark.sql.catalyst.parser.ParseException
import org.apache.spark.sql.catalyst.plans.logical.InsertIntoTable
import org.apache.spark.sql.hive.test.TestHiveSingleton
import org.apache.spark.sql.internal.SQLConf
import org.apache.spark.sql.test.SQLTestUtils
import org.apache.spark.sql.types._
import org.apache.spark.util.Utils
Expand Down Expand Up @@ -750,4 +751,27 @@ class InsertSuite extends QueryTest with TestHiveSingleton with BeforeAndAfter
}
}
}

Seq("LOCAL", "").foreach { local =>
Seq(true, false).foreach { caseSensitivity =>
Seq("orc", "parquet").foreach { format =>
test(s"SPARK-25389 INSERT OVERWRITE $local DIRECTORY ... STORED AS with duplicated names" +
s"(caseSensitivity=$caseSensitivity, format=$format)") {
withTempDir { dir =>
withSQLConf(SQLConf.CASE_SENSITIVE.key -> s"$caseSensitivity") {
val m = intercept[AnalysisException] {
sql(
s"""
|INSERT OVERWRITE $local DIRECTORY '${dir.toURI}'
|STORED AS $format
|SELECT 'id', 'id2' ${if (caseSensitivity) "id" else "ID"}
Copy link
Contributor

@cloud-fan cloud-fan Sep 11, 2018

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

do we miss a comma after 'id2'?

Copy link
Member Author

@dongjoon-hyun dongjoon-hyun Sep 11, 2018 •
edited
Loading

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

id2 is value and the following one appends alias; id or ID.

""".stripMargin)
}.getMessage
assert(m.contains("Found duplicate column(s) when inserting into"))
}
}
}
}
}
}
}