lw309637554 commented on a change in pull request #2765:
URL: https://github.com/apache/hudi/pull/2765#discussion_r608395924
##########
File path:
hudi-client/hudi-spark-client/src/main/scala/org/apache/hudi/AvroConversionUtils.scala
##########
@@ -49,7 +51,48 @@ object AvroConversionUtils {
def convertStructTypeToAvroSchema(structType: StructType,
structName: String,
recordNamespace: String): Schema = {
- SchemaConverters.toAvroType(structType, nullable = false, structName,
recordNamespace)
+ getAvroSchemaWithDefaults(SchemaConverters.toAvroType(structType, nullable
= false, structName, recordNamespace))
+ }
+
+ def getAvroSchemaWithDefaults(schema: Schema): Schema = {
+
+ schema.getType match {
+ case Schema.Type.RECORD => {
+
+ val modifiedFields = schema.getFields.map(field => {
+ val newSchema = getAvroSchemaWithDefaults(field.schema())
+ field.schema().getType match {
+ case Schema.Type.UNION => {
+ val innerFields = newSchema.getTypes
+ val containsNullSchema =
innerFields.foldLeft(false)((nullFieldEncountered, schema) =>
nullFieldEncountered | schema.getType == Schema.Type.NULL)
+ if(containsNullSchema) {
+ // Need to re shuffel the fields in list becase to set null as
default, null schema must be head in union schema
+ val restructuredNewSchema =
Schema.createUnion(List(Schema.create(Schema.Type.NULL)) ++
innerFields.filter(innerSchema => !(innerSchema.getType == Schema.Type.NULL)))
+ new Schema.Field(field.name(), restructuredNewSchema,
field.doc(), JsonProperties.NULL_VALUE)
+ } else {
+ new Schema.Field(field.name(), newSchema, field.doc(),
field.defaultVal())
+ }
+ }
+ case _ => new Schema.Field(field.name(), newSchema, field.doc(),
field.defaultVal())
+ }
+ }).toList
+ Schema.createRecord(schema.getName, schema.getDoc,
schema.getNamespace, schema.isError, modifiedFields)
+ }
+
+ case Schema.Type.UNION => {
Review comment:
can we add some test case to test this type
--
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.
For queries about this service, please contact Infrastructure at:
[email protected]
