yihua commented on code in PR #12075:
URL: https://github.com/apache/hudi/pull/12075#discussion_r1797464436
##########
hudi-client/hudi-spark-client/src/main/scala/org/apache/hudi/SparkFileFormatInternalRowReaderContext.scala:
##########
@@ -87,17 +88,15 @@ class
SparkFileFormatInternalRowReaderContext(parquetFileReader: SparkParquetRea
}
val structType = HoodieInternalRowUtils.getCachedSchema(requiredSchema)
if (FSUtils.isLogFile(filePath)) {
- val projection =
HoodieInternalRowUtils.getCachedUnsafeProjection(structType, structType)
- new CloseableMappingIterator[InternalRow, UnsafeRow](
+ val dataSchemaWithMergeCol = if (hasRowIndexField) {
+ HoodiePositionBasedSchemaHandler.addPositionalMergeCol(dataSchema)
+ } else {
+ dataSchema
+ }
+ new CloseableMappingIterator[InternalRow, InternalRow](
new
HoodieSparkFileReaderFactory(storage).newParquetFileReader(filePath)
-
.asInstanceOf[HoodieSparkParquetReader].getInternalRowIterator(dataSchema,
requiredSchema),
Review Comment:
Why does using `requiredSchema` not work here?
--
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]
