nsivabalan commented on a change in pull request #2927:
URL: https://github.com/apache/hudi/pull/2927#discussion_r685700986
##########
File path:
hudi-client/hudi-spark-client/src/main/scala/org/apache/hudi/HoodieSparkUtils.scala
##########
@@ -92,22 +92,43 @@ object HoodieSparkUtils extends SparkAdapterSupport {
new InMemoryFileIndex(sparkSession, globbedPaths, Map(), Option.empty,
fileStatusCache)
}
- def createRdd(df: DataFrame, structName: String, recordNamespace: String):
RDD[GenericRecord] = {
- val avroSchema =
AvroConversionUtils.convertStructTypeToAvroSchema(df.schema, structName,
recordNamespace)
- createRdd(df, avroSchema, structName, recordNamespace)
+ def createRdd(df: DataFrame, structName: String, recordNamespace: String,
reconcileToLatestSchema: Boolean, latestTableSchema:
+ org.apache.hudi.common.util.Option[Schema] =
org.apache.hudi.common.util.Option.empty()): RDD[GenericRecord] = {
+ val dfWriteSchema =
AvroConversionUtils.convertStructTypeToAvroSchema(df.schema, structName,
recordNamespace)
+ var writeSchema : Schema = null;
+ var toReconcileSchema : Schema = null;
+ if (reconcileToLatestSchema && latestTableSchema.isPresent) {
Review comment:
With some of the callers, we just fetch the reconcileSchema config and
pass it in as is. So, caller passes last 2 args as is. And hence there are
chances that reconcileToLatestSchema is false, but latestTableSchema is
present.
--
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: commits-unsubscr...@hudi.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
