rahil-c commented on code in PR #18190:
URL: https://github.com/apache/hudi/pull/18190#discussion_r2892994627
##########
hudi-client/hudi-spark-client/src/main/scala/org/apache/spark/sql/avro/HoodieSparkSchemaConverters.scala:
##########
@@ -196,25 +233,29 @@ object HoodieSparkSchemaConverters {
val newRecordNames = existingRecordNames + fullName
val fields = hoodieSchema.getFields.asScala.map { f =>
val schemaType = toSqlTypeHelper(f.schema(), newRecordNames)
- val commentMetadata = if (f.doc().isPresent &&
!f.doc().get().isEmpty) {
- new MetadataBuilder().putString("comment", f.doc().get()).build()
- } else {
- Metadata.empty
- }
val fieldSchema = f.getNonNullSchema
- val metadata = if (fieldSchema.isBlobField) {
- // Mark blob fields with metadata for identification.
- // This assumes blobs are always part of a record and not the top
level schema itself
- new MetadataBuilder()
- .withMetadata(commentMetadata)
- .putString(HoodieSchema.TYPE_METADATA_FIELD,
HoodieSchemaType.BLOB.name())
- .build()
- } else {
- commentMetadata
+ val metadataBuilder = new MetadataBuilder()
+ .withMetadata(schemaType.metadata.getOrElse(Metadata.empty))
+ if (f.doc().isPresent && f.doc().get().nonEmpty) {
+ metadataBuilder.putString("comment", f.doc().get())
+ }
+ if (fieldSchema.getType == HoodieSchemaType.VECTOR) {
+ metadataBuilder.putString(HoodieSchema.TYPE_METADATA_FIELD,
fieldSchema.toTypeString())
+ } else if (fieldSchema.isBlobField) {
+ metadataBuilder.putString(HoodieSchema.TYPE_METADATA_FIELD,
HoodieSchemaType.BLOB.name())
Review Comment:
@voonhous nice catch I think we should standardize on this as well.
--
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]
