yihua commented on code in PR #10144:
URL: https://github.com/apache/hudi/pull/10144#discussion_r1416117334
##########
hudi-spark-datasource/hudi-spark-common/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/HoodieFileGroupReaderBasedParquetFileFormat.scala:
##########
@@ -60,6 +62,7 @@ class HoodieFileGroupReaderBasedParquetFileFormat(tableState:
HoodieTableState,
shouldUseRecordPosition:
Boolean,
requiredFilters: Seq[Filter]
) extends ParquetFileFormat with
SparkAdapterSupport {
+ private val rawDataSchema: String = "raw_data_schema"
Review Comment:
Remove this since not used anymore?
##########
hudi-spark-datasource/hudi-spark-common/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/HoodieFileGroupReaderBasedParquetFileFormat.scala:
##########
@@ -310,6 +314,17 @@ class
HoodieFileGroupReaderBasedParquetFileFormat(tableState: HoodieTableState,
_: PartitionedFile => Iterator.empty
}
+ // Note that for CDC reader, the underlying data schema is stored in the
'options' to separate from the CDC schema.
Review Comment:
Adjust the docs based on the latest logic.
--
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]
