Skip to content

[SPARK-23490][SQL]Check storage.locationUri with existing table in CreateTable #20660

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
wants to merge 1 commit into from
Closed

[SPARK-23490][SQL]Check storage.locationUri with existing table in CreateTable #20660

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
8 changes: 8 additions & 0 deletions sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/rules.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -118,6 +118,14 @@ case class PreprocessTableCreation(sparkSession: SparkSession) extends Rule[Logi
s"`${existingProvider.getSimpleName}`. It doesn't match the specified format " +
s"`${specifiedProvider.getSimpleName}`.")
}
tableDesc.storage.locationUri match {
case Some(location) if location.getPath != existingTable.location.getPath =>
throw new AnalysisException(
s"The location of the existing table ${tableIdentWithDB.quotedString} is " +
s"`${existingTable.location}`. It doesn't match the specified location " +
s"`${tableDesc.location}`.")
case _ =>
}

if (query.schema.length != existingTable.schema.length) {
throw new AnalysisException(
Expand Down
29 changes: 29 additions & 0 deletions sql/core/src/test/scala/org/apache/spark/sql/execution/command/DDLSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -508,6 +508,35 @@ abstract class DDLSuite extends QueryTest with SQLTestUtils {
}
}

test("create table - append to a non-partitioned table created with different paths") {
import testImplicits._
withTempDir { dir1 =>
withTempDir { dir2 =>
withTable("path_test") {
Seq(1L -> "a").toDF("v1", "v2")
.write
.mode(SaveMode.Append)
.format("json")
.option("path", dir1.getCanonicalPath)
.saveAsTable("path_test")

val ex = intercept[AnalysisException] {
Seq((3L, "c")).toDF("v1", "v2")
.write
.mode(SaveMode.Append)
.format("json")
.option("path", dir2.getCanonicalPath)
.saveAsTable("path_test")
}.getMessage
assert(ex.contains("The location of the existing table `default`.`path_test`"))

checkAnswer(
spark.table("path_test"), Row(1L, "a") :: Nil)
}
}
}
}

test("Refresh table after changing the data source table partitioning") {
import testImplicits._

Expand Down