rahil-c commented on code in PR #18190:
URL: https://github.com/apache/hudi/pull/18190#discussion_r2892954250
##########
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) {
Review Comment:
The test case is this one
https://github.com/apache/hudi/pull/18190/changes#diff-70e28ca555d1f86b32e1c2965c9c5435da6e59a0ac89f2d1ff24a54fe5af1f6aR625
Although now when running the test again with and without the check this
passes so i think you might be correct that this might not be necessary
--
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]
