Skip to content

[SPARK-34261][SQL] Avoid side effect if create exists temporary function #31358

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
ulysses-you wants to merge 2 commits into from
Closed

[SPARK-34261][SQL] Avoid side effect if create exists temporary function #31358

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
da3e7b3
init
ulysses-you Jan 27, 2021
590b0b3
remove jar
ulysses-you Jan 27, 2021
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
4 changes: 4 additions & 0 deletions sql/core/src/main/scala/org/apache/spark/sql/execution/command/functions.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,6 +25,7 @@ import org.apache.spark.sql.catalyst.analysis.{FunctionRegistry, NoSuchFunctionE
import org.apache.spark.sql.catalyst.catalog.{CatalogFunction, FunctionResource}
import org.apache.spark.sql.catalyst.expressions.Attribute
import org.apache.spark.sql.catalyst.util.StringUtils
import org.apache.spark.sql.errors.QueryCompilationErrors
import org.apache.spark.sql.types.{StringType, StructField, StructType}


Expand Down Expand Up @@ -77,6 +78,9 @@ case class CreateFunctionCommand(
val catalog = sparkSession.sessionState.catalog
val func = CatalogFunction(FunctionIdentifier(functionName, databaseName), className, resources)
if (isTemp) {
if (!replace && catalog.isRegisteredFunction(func.identifier)) {
throw QueryCompilationErrors.functionAlreadyExistsError(func.identifier)
}
// We first load resources and then put the builder in the function registry.
catalog.loadFunctionResources(resources)
catalog.registerFunction(func, overrideIfExists = replace)
Expand Down
24 changes: 23 additions & 1 deletion sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveDDLSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -40,7 +40,7 @@ import org.apache.spark.sql.functions._
import org.apache.spark.sql.hive.HiveExternalCatalog
import org.apache.spark.sql.hive.HiveUtils.{CONVERT_METASTORE_ORC, CONVERT_METASTORE_PARQUET}
import org.apache.spark.sql.hive.orc.OrcFileOperator
import org.apache.spark.sql.hive.test.TestHiveSingleton
import org.apache.spark.sql.hive.test.{TestHiveSingleton, TestHiveSparkSession}
import org.apache.spark.sql.internal.{HiveSerDe, SQLConf}
import org.apache.spark.sql.internal.SQLConf.ORC_IMPLEMENTATION
import org.apache.spark.sql.internal.StaticSQLConf.CATALOG_IMPLEMENTATION
Expand Down Expand Up @@ -2905,4 +2905,26 @@ class HiveDDLSuite
}
}
}

test("SPARK-34261: Avoid side effect if create exists temporary function") {
withUserDefinedFunction("f1" -> true) {
sql("CREATE TEMPORARY FUNCTION f1 AS 'org.apache.hadoop.hive.ql.udf.UDFUUID'")

val jarName = "TestUDTF.jar"
val jar = spark.asInstanceOf[TestHiveSparkSession].getHiveFile(jarName).toURI.toString
spark.sparkContext.addedJars.keys.find(_.contains(jarName))
.foreach(spark.sparkContext.addedJars.remove)
assert(!spark.sparkContext.listJars().exists(_.contains(jarName)))
val msg = intercept[AnalysisException] {
sql("CREATE TEMPORARY FUNCTION f1 AS " +
s"'org.apache.hadoop.hive.ql.udf.UDFUUID' USING JAR '$jar'")
}.getMessage
assert(msg.contains("Function f1 already exists"))
assert(!spark.sparkContext.listJars().exists(_.contains(jarName)))

sql("CREATE OR REPLACE TEMPORARY FUNCTION f1 AS " +
s"'org.apache.hadoop.hive.ql.udf.UDFUUID' USING JAR '$jar'")
assert(spark.sparkContext.listJars().exists(_.contains(jarName)))
}
}
}