Skip to content

[SPARK-56457][SQL] Fix Avro V2 formatName to match V1 FileFormat.toString #55319

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
LuciferYang wants to merge 1 commit into from
+34 −3
Closed

[SPARK-56457][SQL] Fix Avro V2 formatName to match V1 FileFormat.toString #55319

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
2 changes: 1 addition & 1 deletion connector/avro/src/main/scala/org/apache/spark/sql/v2/avro/AvroTable.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -51,5 +51,5 @@ case class AvroTable(

override def supportsDataType(dataType: DataType): Boolean = AvroUtils.supportsDataType(dataType)

override def formatName: String = "AVRO"
override def formatName: String = "Avro"
}
16 changes: 14 additions & 2 deletions connector/avro/src/test/scala/org/apache/spark/sql/avro/AvroSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,7 +22,7 @@ import java.net.URI
import java.nio.file.{Files, Paths, StandardCopyOption}
import java.sql.{Date, Timestamp}
import java.time.{LocalDate, LocalDateTime}
import java.util.UUID
import java.util.{Collections => JCollections, UUID}

import scala.jdk.CollectionConverters._

Expand All @@ -44,7 +44,7 @@ import org.apache.spark.sql.catalyst.util.DateTimeTestUtils
import org.apache.spark.sql.catalyst.util.DateTimeTestUtils.{withDefaultTimeZone, LA, UTC}
import org.apache.spark.sql.execution.{FormattedMode, SparkPlan}
import org.apache.spark.sql.execution.datasources.{CommonFileDataSourceSuite, DataSource, FilePartition}
import org.apache.spark.sql.execution.datasources.v2.BatchScanExec
import org.apache.spark.sql.execution.datasources.v2.{BatchScanExec, FileDataSourceV2, FileTable}
import org.apache.spark.sql.functions._
import org.apache.spark.sql.internal.LegacyBehaviorPolicy
import org.apache.spark.sql.internal.LegacyBehaviorPolicy._
Expand Down Expand Up @@ -3483,6 +3483,18 @@ class AvroV2Suite extends AvroSuite with ExplainSuiteHelper {
}
}

test("SPARK-56457: Avro V2 formatName matches V1 FileFormat.toString") {
val v2Provider = DataSource.lookupDataSourceV2("avro", spark.sessionState.conf)
assert(v2Provider.isDefined)
val dsV2 = v2Provider.get.asInstanceOf[FileDataSourceV2]
val v1Format = dsV2.fallbackFileFormat.getDeclaredConstructor().newInstance()
val emptyProps = JCollections.emptyMap[String, String]()
val v2Table = dsV2.getTable(
new StructType(), Array.empty, emptyProps).asInstanceOf[FileTable]
assert(v2Table.formatName == v1Format.toString,
s"V2 formatName '${v2Table.formatName}' != V1 toString '${v1Format.toString}'")
}

test("Geospatial types are not supported in Avro") {
withTempDir { dir =>
// Temporary directory for writing the test data.
Expand Down
19 changes: 19 additions & 0 deletions sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/v2/FileTableSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,6 +16,8 @@
*/
package org.apache.spark.sql.execution.datasources.v2

import java.util.{Collections => JCollections}

import scala.jdk.CollectionConverters._

import org.apache.hadoop.fs.FileStatus
Expand Down Expand Up @@ -95,6 +97,23 @@ class FileTableSuite extends QueryTest with SharedSparkSession {
}
}

test("SPARK-56457: V2 FileTable.formatName matches V1 FileFormat.toString") {
withSQLConf(SQLConf.USE_V1_SOURCE_LIST.key -> "") {
allFileBasedDataSources.foreach { format =>
val v2Provider = DataSource.lookupDataSourceV2(format, spark.sessionState.conf)
assert(v2Provider.isDefined, s"Expected V2 provider for $format")
val dsV2 = v2Provider.get.asInstanceOf[FileDataSourceV2]
val v1Format = dsV2.fallbackFileFormat.getDeclaredConstructor().newInstance()
val emptyProps = JCollections.emptyMap[String, String]()
val v2Table = dsV2.getTable(
new StructType(), Array.empty, emptyProps).asInstanceOf[FileTable]
assert(v2Table.formatName == v1Format.toString,
s"V2 formatName '${v2Table.formatName}' != " +
s"V1 toString '${v1Format.toString}' for format '$format'")
}
}
}

allFileBasedDataSources.foreach { format =>
test("SPARK-49519, SPARK-50287: Merge options of table and relation when " +
s"constructing ScanBuilder and WriteBuilder in FileFormat - $format") {
Expand Down