Skip to content

[WIP][HUDI-4449] Support DataSourceV2 Read for Spark3.2 #6442

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
southernriver wants to merge 3 commits into from
Closed

[WIP][HUDI-4449] Support DataSourceV2 Read for Spark3.2 #6442

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
a7ef0e8
Support DataSourceV2 Read for Spark3.2
southernriver Aug 18, 2022
19b2ab9
fix code style.
southernriver Oct 31, 2022
8040b17
fix code style.
southernriver Oct 31, 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
1 change: 0 additions & 1 deletion hudi-client/hudi-spark-client/src/main/scala/org/apache/hudi/HoodieSparkUtils.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,7 +26,6 @@ import org.apache.hudi.common.model.HoodieRecord
import org.apache.spark.SPARK_VERSION
import org.apache.spark.rdd.RDD
import org.apache.spark.sql.DataFrame
import org.apache.spark.sql.catalyst.InternalRow
import org.apache.spark.sql.execution.SQLConfInjectingRDD
import org.apache.spark.sql.internal.SQLConf
import org.apache.spark.sql.types.{StringType, StructField, StructType}
Expand Down
20 changes: 20 additions & 0 deletions ...hudi-spark-client/src/main/scala/org/apache/spark/sql/HoodieCatalystExpressionUtils.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -168,6 +168,26 @@ object HoodieCatalystExpressionUtils {
}
}

/**
* Convert Filters to Catalyst Expressions and joined by And. If convert success return an
* Non-Empty Option[Expression],or else return None.
*/
def convertToCatalystExpression(filters: Array[Filter],
tableSchema: StructType): Option[Expression] = {
val expressions = filters.map(convertToCatalystExpression(_, tableSchema))
if (expressions.forall(p => p.isDefined)) {
if (expressions.isEmpty) {
None
} else if (expressions.length == 1) {
expressions.head
} else {
Some(expressions.map(_.get).reduce(org.apache.spark.sql.catalyst.expressions.And))
}
} else {
None
}
}

/**
* Converts [[Filter]] to Catalyst [[Expression]]
*/
Expand Down
5 changes: 5 additions & 0 deletions hudi-common/src/main/java/org/apache/hudi/common/config/HoodieCommonConfig.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -41,6 +41,11 @@ public class HoodieCommonConfig extends HoodieConfig {
.noDefaultValue()
.withDocumentation("The query instant for time travel. Without specified this option, we query the latest snapshot.");

public static final ConfigProperty<Boolean> READ_SUPPORT_V2_ENABLE = ConfigProperty
.key("hoodie.datasource.v2.read.enable")
.defaultValue(false)
.withDocumentation("If set to true, the query statement will use v2 to read");

public static final ConfigProperty<Boolean> RECONCILE_SCHEMA = ConfigProperty
.key("hoodie.datasource.write.reconcile.schema")
.defaultValue(false)
Expand Down
2 changes: 2 additions & 0 deletions ...spark-datasource/hudi-spark-common/src/main/scala/org/apache/hudi/DataSourceOptions.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -152,6 +152,8 @@ object DataSourceReadOptions {

val SCHEMA_EVOLUTION_ENABLED: ConfigProperty[Boolean] = HoodieCommonConfig.SCHEMA_EVOLUTION_ENABLE

val READ_SUPPORT_V2_ENABLE: ConfigProperty[Boolean] = HoodieCommonConfig.READ_SUPPORT_V2_ENABLE

/** @deprecated Use {@link QUERY_TYPE} and its methods instead */
@Deprecated
val QUERY_TYPE_OPT_KEY = QUERY_TYPE.key()
Expand Down
3 changes: 1 addition & 2 deletions ...tasource/hudi-spark/src/test/scala/org/apache/spark/sql/hudi/HoodieSparkSqlTestBase.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,7 +26,6 @@ import org.apache.spark.sql.catalyst.util.DateTimeUtils
import org.apache.spark.sql.{Row, SparkSession}
import org.apache.spark.util.Utils
import org.joda.time.DateTimeZone
import org.scalactic.source
import org.scalatest.{BeforeAndAfterAll, FunSuite, Tag}

import java.io.File
Expand Down Expand Up @@ -76,7 +75,7 @@ class HoodieSparkSqlTestBase extends FunSuite with BeforeAndAfterAll {
}
}

override protected def test(testName: String, testTags: Tag*)(testFun: => Any /* Assertion */)(implicit pos: source.Position): Unit = {
override protected def test(testName: String, testTags: Tag*)(testFun: => Any /* Assertion */)(implicit pos: org.scalactic.source.Position): Unit = {
Copy link
Contributor

@leesf leesf Aug 20, 2022

Choose a reason for hiding this comment

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

unnecessary change?

Copy link
Author

@southernriver southernriver Aug 22, 2022

Choose a reason for hiding this comment

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

Since I have introduced org.apache.spark.sql.hudi.source package dircetory for HoodieBatchScan, just avoid conflict.

super.test(testName, testTags: _*)(
try {
testFun
Expand Down
Loading