Skip to content

[SPARK-40521][SQL] Return only exists partitions in PartitionsAlreadyExistException from Hive's create partition #38134

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
MaxGekk wants to merge 3 commits into from
Closed

[SPARK-40521][SQL] Return only exists partitions in PartitionsAlreadyExistException from Hive's create partition #38134

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
99a21b8
Return only exists partitions in the error from ALTER TABLE .. ADD PA…
MaxGekk Oct 6, 2022
19e8751
Merge remote-tracking branch 'origin/master' into fix-hive-partition-…
MaxGekk Oct 6, 2022
4826f57
Merge remote-tracking branch 'origin/master' into fix-hive-partition-…
MaxGekk Oct 7, 2022
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
18 changes: 0 additions & 18 deletions ...c/test/scala/org/apache/spark/sql/execution/command/AlterTableAddPartitionSuiteBase.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,7 +20,6 @@ package org.apache.spark.sql.execution.command
import java.time.{Duration, Period}

import org.apache.spark.sql.{AnalysisException, QueryTest, Row}
import org.apache.spark.sql.catalyst.analysis.PartitionsAlreadyExistException
import org.apache.spark.sql.internal.SQLConf

/**
Expand Down Expand Up @@ -167,23 +166,6 @@ trait AlterTableAddPartitionSuiteBase extends QueryTest with DDLCommandTestUtils
}
}

test("partition already exists") {
withNamespaceAndTable("ns", "tbl") { t =>
sql(s"CREATE TABLE $t (id bigint, data string) $defaultUsing PARTITIONED BY (id)")
sql(s"ALTER TABLE $t ADD PARTITION (id=2) LOCATION 'loc1'")

val errMsg = intercept[PartitionsAlreadyExistException] {
sql(s"ALTER TABLE $t ADD PARTITION (id=1) LOCATION 'loc'" +
" PARTITION (id=2) LOCATION 'loc1'")
}.getMessage
assert(errMsg.contains("The following partitions already exists"))

sql(s"ALTER TABLE $t ADD IF NOT EXISTS PARTITION (id=1) LOCATION 'loc'" +
" PARTITION (id=2) LOCATION 'loc1'")
checkPartitions(t, Map("id" -> "1"), Map("id" -> "2"))
}
}

test("SPARK-33474: Support typed literals as partition spec values") {
withNamespaceAndTable("ns", "tbl") { t =>
sql(s"CREATE TABLE $t(name STRING, part DATE) USING PARQUET PARTITIONED BY (part)")
Expand Down
21 changes: 21 additions & 0 deletions ...rc/test/scala/org/apache/spark/sql/execution/command/v1/AlterTableAddPartitionSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,6 +18,7 @@
package org.apache.spark.sql.execution.command.v1

import org.apache.spark.sql.{AnalysisException, Row}
import org.apache.spark.sql.catalyst.analysis.PartitionsAlreadyExistException
import org.apache.spark.sql.execution.command
import org.apache.spark.sql.internal.SQLConf

Expand Down Expand Up @@ -135,6 +136,26 @@ trait AlterTableAddPartitionSuiteBase extends command.AlterTableAddPartitionSuit
}
}
}

// TODO: Move this test to the common trait as soon as it is migrated on checkError()
test("partition already exists") {
withNamespaceAndTable("ns", "tbl") { t =>
sql(s"CREATE TABLE $t (id bigint, data string) $defaultUsing PARTITIONED BY (id)")
sql(s"ALTER TABLE $t ADD PARTITION (id=2) LOCATION 'loc1'")

val errMsg = intercept[PartitionsAlreadyExistException] {
sql(s"ALTER TABLE $t ADD PARTITION (id=1) LOCATION 'loc'" +
" PARTITION (id=2) LOCATION 'loc1'")
}.getMessage
assert(errMsg ===
"""The following partitions already exists in table 'tbl' database 'ns':
|Map(id -> 2)""".stripMargin)

sql(s"ALTER TABLE $t ADD IF NOT EXISTS PARTITION (id=1) LOCATION 'loc'" +
" PARTITION (id=2) LOCATION 'loc1'")
checkPartitions(t, Map("id" -> "1"), Map("id" -> "2"))
}
}
}

/**
Expand Down
19 changes: 19 additions & 0 deletions ...rc/test/scala/org/apache/spark/sql/execution/command/v2/AlterTableAddPartitionSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,6 +18,7 @@
package org.apache.spark.sql.execution.command.v2

import org.apache.spark.sql.{AnalysisException, Row}
import org.apache.spark.sql.catalyst.analysis.PartitionsAlreadyExistException
import org.apache.spark.sql.execution.command

/**
Expand Down Expand Up @@ -99,4 +100,22 @@ class AlterTableAddPartitionSuite
}
}
}

// TODO: Move this test to the common trait as soon as it is migrated on checkError()
test("partition already exists") {
withNamespaceAndTable("ns", "tbl") { t =>
sql(s"CREATE TABLE $t (id bigint, data string) $defaultUsing PARTITIONED BY (id)")
sql(s"ALTER TABLE $t ADD PARTITION (id=2) LOCATION 'loc1'")

val errMsg = intercept[PartitionsAlreadyExistException] {
sql(s"ALTER TABLE $t ADD PARTITION (id=1) LOCATION 'loc'" +
" PARTITION (id=2) LOCATION 'loc1'")
}.getMessage
assert(errMsg === s"The following partitions already exists in table $t:2 -> id")
Copy link
Member Author

@MaxGekk MaxGekk Oct 6, 2022

Choose a reason for hiding this comment

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

Here is another mistake. Must be id -> 2, I think. I will fix this separately as soon as I have this test in.

Copy link
Member Author

@MaxGekk MaxGekk Oct 7, 2022

Choose a reason for hiding this comment

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

Here is the fix: #38152


sql(s"ALTER TABLE $t ADD IF NOT EXISTS PARTITION (id=1) LOCATION 'loc'" +
" PARTITION (id=2) LOCATION 'loc1'")
checkPartitions(t, Map("id" -> "1"), Map("id" -> "2"))
}
}
}
6 changes: 5 additions & 1 deletion sql/hive/src/main/scala/org/apache/spark/sql/hive/client/HiveClientImpl.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -635,7 +635,11 @@ private[hive] class HiveClientImpl(
ignoreIfExists: Boolean): Unit = withHiveState {
def replaceExistException(e: Throwable): Unit = e match {
case _: HiveException if e.getCause.isInstanceOf[AlreadyExistsException] =>
throw new PartitionsAlreadyExistException(db, table, parts.map(_.spec))
val t = shim.getTable(client, db, table)
val exists = parts.filter { part =>
shim.getPartition(client, t, part.spec.asJava, forceCreate = false) != null
}
throw new PartitionsAlreadyExistException(db, table, exists.map(_.spec))
case _ => throw e
}
try {
Expand Down