Skip to content

[spark] Disable v2 write in v1 append location unit tests #6329

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

Open
wants to merge 5 commits into
base: master
Choose a base branch
from
Open

[spark] Disable v2 write in v1 append location unit tests #6329

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
29c7039
[spark] Disable v2 write in v1 append location unit tests
kerwin-zk Sep 23, 2025
1a96bbc
[spark] Disable v2 write in v1 append location unit tests
kerwin-zk Sep 24, 2025
01f2aae
[spark] Disable v2 write in v1 append location unit tests
kerwin-zk Sep 24, 2025
9fbfccd
[spark] Disable v2 write in v1 append location unit tests
kerwin-zk Sep 24, 2025
2f350c9
[spark] Disable v2 write in v1 append location unit tests
kerwin-zk Sep 25, 2025
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
82 changes: 43 additions & 39 deletions paimon-spark/paimon-spark-3.4/src/test/scala/org/apache/paimon/spark/PaimonSinkTest.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -29,51 +29,55 @@ import java.sql.Date
class PaimonSinkTest extends PaimonSparkTestBase with StreamTest {

override protected def sparkConf: SparkConf = {
super.sparkConf.set("spark.sql.catalog.paimon.cache-enabled", "false")
super.sparkConf
.set("spark.sql.catalog.paimon.cache-enabled", "false")
.set("spark.paimon.write.use-v2-write", "false")
}

import testImplicits._

test("Paimon Sink: forEachBatch") {
failAfter(streamingTimeout) {
withTempDir {
checkpointDir =>
// define a pk table and test `forEachBatch` api
spark.sql(s"""
|CREATE TABLE T (a INT, b STRING)
|TBLPROPERTIES ('primary-key'='a', 'bucket'='3')
|""".stripMargin)
val location = loadTable("T").location().toString

val inputData = MemoryStream[(Int, String)]
val stream = inputData
.toDS()
.toDF("a", "b")
.writeStream
.option("checkpointLocation", checkpointDir.getCanonicalPath)
.foreachBatch {
(batch: Dataset[Row], id: Long) =>
batch.write.format("paimon").mode("append").save(location)
withSparkSQLConf(("spark.paimon.write.use-v2-write", "false")) {
failAfter(streamingTimeout) {
withTempDir {
checkpointDir =>
// define a pk table and test `forEachBatch` api
spark.sql(s"""
|CREATE TABLE T (a INT, b STRING)
|TBLPROPERTIES ('primary-key'='a', 'bucket'='3')
|""".stripMargin)
val location = loadTable("T").location().toString

val inputData = MemoryStream[(Int, String)]
val stream = inputData
.toDS()
.toDF("a", "b")
.writeStream
.option("checkpointLocation", checkpointDir.getCanonicalPath)
.foreachBatch {
(batch: Dataset[Row], id: Long) =>
batch.write.format("paimon").mode("append").save(location)
}
.start()

val query = () => spark.sql("SELECT * FROM T ORDER BY a")

try {
inputData.addData((1, "a"))
stream.processAllAvailable()
checkAnswer(query(), Row(1, "a") :: Nil)

inputData.addData((2, "b"))
stream.processAllAvailable()
checkAnswer(query(), Row(1, "a") :: Row(2, "b") :: Nil)

inputData.addData((2, "b2"))
stream.processAllAvailable()
checkAnswer(query(), Row(1, "a") :: Row(2, "b2") :: Nil)
} finally {
stream.stop()
}
.start()

val query = () => spark.sql("SELECT * FROM T ORDER BY a")

try {
inputData.addData((1, "a"))
stream.processAllAvailable()
checkAnswer(query(), Row(1, "a") :: Nil)

inputData.addData((2, "b"))
stream.processAllAvailable()
checkAnswer(query(), Row(1, "a") :: Row(2, "b") :: Nil)

inputData.addData((2, "b2"))
stream.processAllAvailable()
checkAnswer(query(), Row(1, "a") :: Row(2, "b2") :: Nil)
} finally {
stream.stop()
}
}
}
}
}
Expand Down
202 changes: 102 additions & 100 deletions ...park-3.4/src/test/scala/org/apache/paimon/spark/sql/CreateAndDeleteTagProcedureTest.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -29,107 +29,109 @@ class CreateAndDeleteTagProcedureTest extends PaimonSparkTestBase with StreamTes
import testImplicits._

test("Paimon Procedure: create and delete tag") {
failAfter(streamingTimeout) {
withTempDir {
checkpointDir =>
// define a pk table and test `forEachBatch` api
spark.sql(s"""
|CREATE TABLE T (a INT, b STRING)
|TBLPROPERTIES ('primary-key'='a', 'bucket'='3')
|""".stripMargin)
val location = loadTable("T").location().toString

val inputData = MemoryStream[(Int, String)]
val stream = inputData
.toDS()
.toDF("a", "b")
.writeStream
.option("checkpointLocation", checkpointDir.getCanonicalPath)
.foreachBatch {
(batch: Dataset[Row], _: Long) =>
batch.write.format("paimon").mode("append").save(location)
withSparkSQLConf(("spark.paimon.write.use-v2-write", "false")) {
Copy link
Contributor

Choose a reason for hiding this comment

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

When V2 write is enabled by default, it should bypass V2 write instead of throwing an exception in scenarios that do not support it.

failAfter(streamingTimeout) {
withTempDir {
checkpointDir =>
// define a pk table and test `forEachBatch` api
spark.sql(s"""
|CREATE TABLE T (a INT, b STRING)
|TBLPROPERTIES ('primary-key'='a', 'bucket'='3')
|""".stripMargin)
val location = loadTable("T").location().toString

val inputData = MemoryStream[(Int, String)]
val stream = inputData
.toDS()
.toDF("a", "b")
.writeStream
.option("checkpointLocation", checkpointDir.getCanonicalPath)
.foreachBatch {
(batch: Dataset[Row], _: Long) =>
batch.write.format("paimon").mode("append").save(location)
}
.start()

val query = () => spark.sql("SELECT * FROM T ORDER BY a")

try {
// snapshot-1
inputData.addData((1, "a"))
stream.processAllAvailable()
checkAnswer(query(), Row(1, "a") :: Nil)

// snapshot-2
inputData.addData((2, "b"))
stream.processAllAvailable()
checkAnswer(query(), Row(1, "a") :: Row(2, "b") :: Nil)

// snapshot-3
inputData.addData((2, "b2"))
stream.processAllAvailable()
checkAnswer(query(), Row(1, "a") :: Row(2, "b2") :: Nil)
checkAnswer(
spark.sql(
"CALL paimon.sys.create_tag(table => 'test.T', tag => 'test_tag', snapshot => 2)"),
Row(true) :: Nil)
checkAnswer(
spark.sql("SELECT tag_name FROM paimon.test.`T$tags`"),
Row("test_tag") :: Nil)
// test rename_tag
checkAnswer(
spark.sql(
"CALL paimon.sys.rename_tag(table => 'test.T', tag => 'test_tag', target_tag => 'test_tag_1')"),
Row(true) :: Nil)
checkAnswer(
spark.sql("SELECT tag_name FROM paimon.test.`T$tags`"),
Row("test_tag_1") :: Nil)
checkAnswer(
spark.sql("CALL paimon.sys.delete_tag(table => 'test.T', tag => 'test_tag_1')"),
Row(true) :: Nil)
checkAnswer(spark.sql("SELECT tag_name FROM paimon.test.`T$tags`"), Nil)
checkAnswer(
spark.sql(
"CALL paimon.sys.create_tag(table => 'test.T', tag => 'test_latestSnapshot_tag')"),
Row(true) :: Nil)
checkAnswer(
spark.sql("SELECT tag_name FROM paimon.test.`T$tags`"),
Row("test_latestSnapshot_tag") :: Nil)
checkAnswer(
spark.sql(
"CALL paimon.sys.delete_tag(table => 'test.T', tag => 'test_latestSnapshot_tag')"),
Row(true) :: Nil)
checkAnswer(spark.sql("SELECT tag_name FROM paimon.test.`T$tags`"), Nil)

// snapshot-4
inputData.addData((2, "c1"))
stream.processAllAvailable()
checkAnswer(query(), Row(1, "a") :: Row(2, "c1") :: Nil)

checkAnswer(
spark.sql("CALL paimon.sys.create_tag(table => 'test.T', tag => 's4')"),
Row(true) :: Nil)

// snapshot-5
inputData.addData((3, "c2"))
stream.processAllAvailable()
checkAnswer(query(), Row(1, "a") :: Row(2, "c1") :: Row(3, "c2") :: Nil)

checkAnswer(
spark.sql("CALL paimon.sys.create_tag(table => 'test.T', tag => 's5')"),
Row(true) :: Nil)

checkAnswer(
spark.sql("SELECT tag_name FROM paimon.test.`T$tags`"),
Row("s4") :: Row("s5") :: Nil)

checkAnswer(
spark.sql("CALL paimon.sys.delete_tag(table => 'test.T', tag => 's4,s5')"),
Row(true) :: Nil)

checkAnswer(spark.sql("SELECT tag_name FROM paimon.test.`T$tags`"), Nil)
} finally {
stream.stop()
}
.start()

val query = () => spark.sql("SELECT * FROM T ORDER BY a")

try {
// snapshot-1
inputData.addData((1, "a"))
stream.processAllAvailable()
checkAnswer(query(), Row(1, "a") :: Nil)

// snapshot-2
inputData.addData((2, "b"))
stream.processAllAvailable()
checkAnswer(query(), Row(1, "a") :: Row(2, "b") :: Nil)

// snapshot-3
inputData.addData((2, "b2"))
stream.processAllAvailable()
checkAnswer(query(), Row(1, "a") :: Row(2, "b2") :: Nil)
checkAnswer(
spark.sql(
"CALL paimon.sys.create_tag(table => 'test.T', tag => 'test_tag', snapshot => 2)"),
Row(true) :: Nil)
checkAnswer(
spark.sql("SELECT tag_name FROM paimon.test.`T$tags`"),
Row("test_tag") :: Nil)
// test rename_tag
checkAnswer(
spark.sql(
"CALL paimon.sys.rename_tag(table => 'test.T', tag => 'test_tag', target_tag => 'test_tag_1')"),
Row(true) :: Nil)
checkAnswer(
spark.sql("SELECT tag_name FROM paimon.test.`T$tags`"),
Row("test_tag_1") :: Nil)
checkAnswer(
spark.sql("CALL paimon.sys.delete_tag(table => 'test.T', tag => 'test_tag_1')"),
Row(true) :: Nil)
checkAnswer(spark.sql("SELECT tag_name FROM paimon.test.`T$tags`"), Nil)
checkAnswer(
spark.sql(
"CALL paimon.sys.create_tag(table => 'test.T', tag => 'test_latestSnapshot_tag')"),
Row(true) :: Nil)
checkAnswer(
spark.sql("SELECT tag_name FROM paimon.test.`T$tags`"),
Row("test_latestSnapshot_tag") :: Nil)
checkAnswer(
spark.sql(
"CALL paimon.sys.delete_tag(table => 'test.T', tag => 'test_latestSnapshot_tag')"),
Row(true) :: Nil)
checkAnswer(spark.sql("SELECT tag_name FROM paimon.test.`T$tags`"), Nil)

// snapshot-4
inputData.addData((2, "c1"))
stream.processAllAvailable()
checkAnswer(query(), Row(1, "a") :: Row(2, "c1") :: Nil)

checkAnswer(
spark.sql("CALL paimon.sys.create_tag(table => 'test.T', tag => 's4')"),
Row(true) :: Nil)

// snapshot-5
inputData.addData((3, "c2"))
stream.processAllAvailable()
checkAnswer(query(), Row(1, "a") :: Row(2, "c1") :: Row(3, "c2") :: Nil)

checkAnswer(
spark.sql("CALL paimon.sys.create_tag(table => 'test.T', tag => 's5')"),
Row(true) :: Nil)

checkAnswer(
spark.sql("SELECT tag_name FROM paimon.test.`T$tags`"),
Row("s4") :: Row("s5") :: Nil)

checkAnswer(
spark.sql("CALL paimon.sys.delete_tag(table => 'test.T', tag => 's4,s5')"),
Row(true) :: Nil)

checkAnswer(spark.sql("SELECT tag_name FROM paimon.test.`T$tags`"), Nil)
} finally {
stream.stop()
}
}
}
}
}
Expand Down
Loading