wombatu-kun commented on code in PR #18375:
URL: https://github.com/apache/hudi/pull/18375#discussion_r3035479919
##########
hudi-spark-datasource/hudi-spark/src/test/scala/org/apache/spark/sql/hudi/feature/TestQueryMergeOnReadOptimizedTable.scala:
##########
@@ -19,63 +19,72 @@
package org.apache.spark.sql.hudi.feature
+import org.apache.hudi.HoodieSparkUtils
+
import org.apache.spark.sql.hudi.common.HoodieSparkSqlTestBase
+import org.scalatest.Inspectors.forAll
class TestQueryMergeOnReadOptimizedTable extends HoodieSparkSqlTestBase {
- test("Test Query Merge_On_Read Read_Optimized table") {
- withTempDir { tmp =>
- val tableName = generateTableName
- val tablePath = s"${tmp.getCanonicalPath}/$tableName"
- // create table
- spark.sql(
- s"""
- |create table $tableName (
- | id int,
- | name string,
- | price double,
- | ts long,
- | partition long
- |) using hudi
- | partitioned by (partition)
- | location '$tablePath'
- | tblproperties (
- | type = 'mor',
- | primaryKey = 'id',
- | orderingFields = 'ts'
- | )
- """.stripMargin)
- // insert data to table
- withSQLConf("hoodie.parquet.max.file.size" -> "10000") {
- spark.sql(s"insert into $tableName values(1, 'a1', 10, 1000, 1000)")
- spark.sql(s"insert into $tableName values(2, 'a2', 10, 1000, 1000)")
- spark.sql(s"insert into $tableName values(3, 'a3', 10, 1000, 1000)")
- spark.sql(s"insert into $tableName values(4, 'a4', 10, 1000, 1000)")
- spark.sql(s"update $tableName set price = 11 where id = 1")
- spark.sql(s"update $tableName set price = 21 where id = 2")
- spark.sql(s"update $tableName set price = 31 where id = 3")
- spark.sql(s"update $tableName set price = 41 where id = 4")
- // expect that all complete parquet files can be scanned
- assertQueryResult(4, tablePath)
+ val baseFileFormats: List[String] = if (HoodieSparkUtils.gteqSpark3_4)
List("parquet", "lance") else List("parquet")
+
+ forAll(baseFileFormats) { (baseFileFormat: String) =>
+ test(s"Test Query Merge_On_Read Read_Optimized table - $baseFileFormat") {
+ withTempDir { tmp =>
+ val tableName = generateTableName
+ val tablePath = s"${tmp.getCanonicalPath}/$tableName"
+ // create table
+ spark.sql(
+ s"""
+ |create table $tableName (
+ | id int,
+ | name string,
+ | price double,
+ | ts long,
+ | partition long
+ |) using hudi
+ | partitioned by (partition)
+ | location '$tablePath'
+ | tblproperties (
+ | type = 'mor',
+ | primaryKey = 'id',
Review Comment:
Fixed, added merger impl config
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
