danny0405 commented on code in PR #10003:
URL: https://github.com/apache/hudi/pull/10003#discussion_r1385866309
##########
hudi-spark-datasource/hudi-spark-common/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/HoodieFileGroupReaderBasedParquetFileFormat.scala:
##########
@@ -201,19 +208,65 @@ class
HoodieFileGroupReaderBasedParquetFileFormat(tableState: HoodieTableState,
length,
shouldUseRecordPosition)
reader.initRecordIterators()
-
reader.getClosableIterator.asInstanceOf[java.util.Iterator[InternalRow]].asScala
+ // Append partition values to rows and project to output schema
+ appendPartitionAndProject(
+
reader.getClosableIterator.asInstanceOf[java.util.Iterator[InternalRow]].asScala,
+ requiredSchemaWithMandatory,
+ partitionSchema,
+ outputSchema,
+ partitionValues)
+ }
+
+ private def appendPartitionAndProject(iter: Iterator[InternalRow],
+ inputSchema: StructType,
+ partitionSchema: StructType,
+ to: StructType,
+ partitionValues: InternalRow):
Iterator[InternalRow] = {
+ if (partitionSchema.isEmpty) {
+ projectSchema(iter, inputSchema, to)
Review Comment:
Do we still project the rows if the `iter` is already in the required output
schema?
--
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]
