vaibhavk1992 commented on issue #713: URL: https://github.com/apache/incubator-xtable/issues/713#issuecomment-2945461309
Hi @vinishjail97, I was in the process of doing the changes required for integrating Delta Kernel, and it looks like they cascade across multiple files. To eliminate the dependency on SparkSession, we’ll also need to remove usage of Delta Lake (Spark-based) APIs and replace them with Delta Kernel equivalents. Specifically: DeltaConversionSource.java – Just looking at getCurrentTable method as it uses spark session We need to replace usage of DeltaLog and Snapshot with the corresponding Delta Kernel objects. Moreover we may also need to refactor the code as Snapshot is present in both kernel as well delta code so the references are picked correctly. DeltaTableExtractor.java – The Snapshot class in Delta Kernel is different in terms of methods from the Spark-based version, which means this file will require significant changes.It need some discovery and a bit more insight on the existing code. e.g snapshot.getMetadata(engine).getPartitionColumns() doesn't exist in delta kernel so we need to figure out such pieces in code. Let me know if you'd like me to discuss and share your thoughts about the refactoring plan further. -- 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...@xtable.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org
