Skip to content
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.

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

[spark] refine MergeInto UT #3925

Merged
merged 2 commits into from
Aug 9, 2024
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
Original file line number Diff line number Diff line change
Expand Up @@ -18,4 +18,12 @@

package org.apache.paimon.spark.sql

class MergeIntoTableTest extends MergeIntoTableTestBase {}
import org.apache.paimon.spark.{PaimonPrimaryKeyBucketedTableTest, PaimonPrimaryKeyNonBucketTableTest}

class MergeIntoPrimaryKeyBucketedTableTest
extends MergeIntoTableTestBase
with PaimonPrimaryKeyBucketedTableTest {}

class MergeIntoPrimaryKeyNonBucketTableTest
extends MergeIntoTableTestBase
with PaimonPrimaryKeyNonBucketTableTest {}
Original file line number Diff line number Diff line change
Expand Up @@ -18,4 +18,12 @@

package org.apache.paimon.spark.sql

class MergeIntoTableTest extends MergeIntoTableTestBase {}
import org.apache.paimon.spark.{PaimonPrimaryKeyBucketedTableTest, PaimonPrimaryKeyNonBucketTableTest}

class MergeIntoPrimaryKeyBucketedTableTest
extends MergeIntoTableTestBase
with PaimonPrimaryKeyBucketedTableTest {}

class MergeIntoPrimaryKeyNonBucketTableTest
extends MergeIntoTableTestBase
with PaimonPrimaryKeyNonBucketTableTest {}
Original file line number Diff line number Diff line change
Expand Up @@ -18,4 +18,14 @@

package org.apache.paimon.spark.sql

class MergeIntoTableTest extends MergeIntoTableTestBase with MergeIntoNotMatchedBySourceTest {}
import org.apache.paimon.spark.{PaimonPrimaryKeyBucketedTableTest, PaimonPrimaryKeyNonBucketTableTest}

class MergeIntoPrimaryKeyBucketedTableTest
extends MergeIntoTableTestBase
with MergeIntoNotMatchedBySourceTest
with PaimonPrimaryKeyBucketedTableTest {}

class MergeIntoPrimaryKeyNonBucketTableTest
extends MergeIntoTableTestBase
with MergeIntoNotMatchedBySourceTest
with PaimonPrimaryKeyNonBucketTableTest {}
Original file line number Diff line number Diff line change
Expand Up @@ -18,4 +18,14 @@

package org.apache.paimon.spark.sql

class MergeIntoTableTest extends MergeIntoTableTestBase with MergeIntoNotMatchedBySourceTest {}
import org.apache.paimon.spark.{PaimonPrimaryKeyBucketedTableTest, PaimonPrimaryKeyNonBucketTableTest}

class MergeIntoPrimaryKeyBucketedTableTest
extends MergeIntoTableTestBase
with MergeIntoNotMatchedBySourceTest
with PaimonPrimaryKeyBucketedTableTest {}

class MergeIntoPrimaryKeyNonBucketTableTest
extends MergeIntoTableTestBase
with MergeIntoNotMatchedBySourceTest
with PaimonPrimaryKeyNonBucketTableTest {}
Original file line number Diff line number Diff line change
@@ -0,0 +1,106 @@
/*
* Licensed to the Apache Software Foundation (ASF) under one
* or more contributor license agreements. See the NOTICE file
* distributed with this work for additional information
* regarding copyright ownership. The ASF licenses this file
* to you under the Apache License, Version 2.0 (the
* "License"); you may not use this file except in compliance
* with the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/

package org.apache.paimon.spark

import org.apache.spark.sql.test.SharedSparkSession

import scala.collection.mutable

trait PaimonTableTest extends SharedSparkSession {

val bucket: Int

def appendPrimaryKey(primaryKeys: Seq[String], props: mutable.Map[String, String]): Unit

def createTable(
tableName: String,
columns: String,
primaryKeys: Seq[String],
partitionKeys: Seq[String] = Seq.empty,
props: Map[String, String] = Map.empty): Unit = {
val newProps: mutable.Map[String, String] =
mutable.Map.empty[String, String] ++ Map("bucket" -> bucket.toString) ++ props
appendPrimaryKey(primaryKeys, newProps)
createTable0(tableName, columns, partitionKeys, newProps.toMap)
}

private def createTable0(
tableName: String,
columns: String,
partitionKeys: Seq[String],
props: Map[String, String]): Unit = {
val partitioned = if (partitionKeys.isEmpty) {
""
} else {
s"PARTITIONED BY (${partitionKeys.mkString(", ")})"
}
val tblproperties = if (props.isEmpty) {
""
} else {
val kvs = props.map(kv => s"'${kv._1}' = '${kv._2}'").mkString(", ")
s"TBLPROPERTIES ($kvs)"
}
sql(s"""
| CREATE TABLE $tableName ($columns) USING PAIMON
| $partitioned
| $tblproperties
|""".stripMargin)
}
}

trait PaimonBucketedTable {
val bucket: Int = 3
}

trait PaimonNonBucketedTable {
val bucket: Int = -1
}

trait PaimonPrimaryKeyTable {
def appendPrimaryKey(primaryKeys: Seq[String], props: mutable.Map[String, String]): Unit = {
assert(primaryKeys.nonEmpty)
props += ("primary-key" -> primaryKeys.mkString(","))
}
}

trait PaimonAppendTable {
def appendPrimaryKey(primaryKeys: Seq[String], props: mutable.Map[String, String]): Unit = {
// nothing to do
}
}

trait PaimonPrimaryKeyBucketedTableTest
extends PaimonTableTest
with PaimonPrimaryKeyTable
with PaimonBucketedTable

trait PaimonPrimaryKeyNonBucketTableTest
extends PaimonTableTest
with PaimonPrimaryKeyTable
with PaimonNonBucketedTable

trait PaimonAppendBucketedTableTest
extends PaimonTableTest
with PaimonAppendTable
with PaimonBucketedTable

trait PaimonAppendNonBucketTableTest
extends PaimonTableTest
with PaimonAppendTable
with PaimonNonBucketedTable
Original file line number Diff line number Diff line change
Expand Up @@ -18,11 +18,11 @@

package org.apache.paimon.spark.sql

import org.apache.paimon.spark.PaimonSparkTestBase
import org.apache.paimon.spark.{PaimonSparkTestBase, PaimonTableTest}

import org.apache.spark.sql.Row

trait MergeIntoNotMatchedBySourceTest extends PaimonSparkTestBase {
trait MergeIntoNotMatchedBySourceTest extends PaimonSparkTestBase with PaimonTableTest {

import testImplicits._

Expand All @@ -31,10 +31,7 @@ trait MergeIntoNotMatchedBySourceTest extends PaimonSparkTestBase {

Seq((1, 100, "c11"), (3, 300, "c33")).toDF("a", "b", "c").createOrReplaceTempView("source")

spark.sql(s"""
|CREATE TABLE target (a INT, b INT, c STRING)
|TBLPROPERTIES ('primary-key'='a', 'bucket'='2')
|""".stripMargin)
createTable("target", "a INT, b INT, c STRING", Seq("a"))
spark.sql("INSERT INTO target values (1, 10, 'c1'), (2, 20, 'c2'), (5, 50, 'c5')")

spark.sql(s"""
Expand All @@ -58,10 +55,7 @@ trait MergeIntoNotMatchedBySourceTest extends PaimonSparkTestBase {

Seq((1, 100, "c11"), (3, 300, "c33")).toDF("a", "b", "c").createOrReplaceTempView("source")

spark.sql(s"""
|CREATE TABLE target (a INT, b INT, c STRING)
|TBLPROPERTIES ('primary-key'='a', 'bucket'='2')
|""".stripMargin)
createTable("target", "a INT, b INT, c STRING", Seq("a"))
spark.sql("INSERT INTO target values (1, 10, 'c1'), (2, 20, 'c2')")

spark.sql(s"""
Expand Down Expand Up @@ -89,10 +83,7 @@ trait MergeIntoNotMatchedBySourceTest extends PaimonSparkTestBase {
.toDF("a", "b", "c1", "c2")
.createOrReplaceTempView("source")

spark.sql(s"""
|CREATE TABLE target (a INT, b INT, c STRUCT<c1:STRING, c2:STRING>)
|TBLPROPERTIES ('primary-key'='a', 'bucket'='2')
|""".stripMargin)
createTable("target", "a INT, b INT, c STRUCT<c1:STRING, c2:STRING>", Seq("a"))
spark.sql("INSERT INTO target values (1, 10, struct('x', 'y')), (2, 20, struct('x', 'y'))")

spark.sql(s"""
Expand All @@ -118,10 +109,7 @@ trait MergeIntoNotMatchedBySourceTest extends PaimonSparkTestBase {
.toDF("a", "b", "c")
.createOrReplaceTempView("source")

spark.sql(s"""
|CREATE TABLE target (a INT, b INT, c STRING)
|TBLPROPERTIES ('primary-key'='a', 'bucket'='2')
|""".stripMargin)
createTable("target", "a INT, b INT, c STRING", Seq("a"))
spark.sql(
"INSERT INTO target values (1, 10, 'c1'), (2, 20, 'c2'), (3, 30, 'c3'), (4, 40, 'c4'), (5, 50, 'c5')")

Expand Down
Loading
Loading