voonhous commented on code in PR #17833:
URL: https://github.com/apache/hudi/pull/17833#discussion_r2739537839
##########
hudi-spark-datasource/hudi-spark4-common/src/main/scala/org/apache/spark/sql/adapter/BaseSpark4Adapter.scala:
##########
@@ -196,4 +198,86 @@ abstract class BaseSpark4Adapter extends SparkAdapter with
Logging {
storageConf.getBoolean(SQLConf.CASE_SENSITIVE.key,
sqlConf.caseSensitiveAnalysis),
getRebaseSpec("CORRECTED"))
}
+
+ override def getVariantDataType: Option[DataType] = {
+ Some(VariantType)
+ }
+
+ override def isDataTypeEqualForParquet(requiredType: DataType, fileType:
DataType): Option[Boolean] = {
+ /**
+ * Checks if a StructType is the physical representation of VariantType in
Parquet.
+ * VariantType is stored in Parquet as a struct with two binary fields:
"value" and "metadata".
+ */
+ def isVariantPhysicalSchema(structType: StructType): Boolean = {
+ if (structType.fields.length != 2) {
+ false
+ } else {
+ val fieldMap = structType.fields.map(f => (f.name, f.dataType)).toMap
+ fieldMap.contains("value") && fieldMap.contains("metadata") &&
+ fieldMap("value") == BinaryType && fieldMap("metadata") == BinaryType
+ }
+ }
+
+ // Handle VariantType comparisons
+ (requiredType, fileType) match {
+ case (_: VariantType, s: StructType) if isVariantPhysicalSchema(s) =>
Some(true)
+ case (s: StructType, _: VariantType) if isVariantPhysicalSchema(s) =>
Some(true)
+ case _ => None // Not a VariantType comparison, use default logic
+ }
+ }
+
+ override def isVariantType(dataType: DataType): Boolean = {
+ import org.apache.spark.sql.types.VariantType
+ dataType.isInstanceOf[VariantType]
+ }
+
+ override def createVariantValueWriter(
+ dataType: DataType,
+ writeValue: Consumer[Array[Byte]],
+ writeMetadata: Consumer[Array[Byte]]
+ ): BiConsumer[SpecializedGetters, Integer] = {
+ import org.apache.spark.sql.types.VariantType
+
+ if (!dataType.isInstanceOf[VariantType]) {
+ throw new IllegalArgumentException(s"Expected VariantType but got
$dataType")
+ }
+
+ (row: SpecializedGetters, ordinal: Integer) => {
+ val variant = row.getVariant(ordinal)
+ writeValue.accept(variant.getValue)
+ writeMetadata.accept(variant.getMetadata)
+ }
+ }
+
+ override def convertVariantFieldToParquetType(
+ dataType: DataType,
+ fieldName: String,
+ fieldSchema: HoodieSchema,
+ repetition: Repetition
+ ): org.apache.parquet.schema.Type = {
Review Comment:
Done
--
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]
