yaooqinn commented on a change in pull request #33888:
URL: https://github.com/apache/spark/pull/33888#discussion_r701773655
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetReadSupport.scala
##########
@@ -323,9 +327,20 @@ object ParquetReadSupport {
* @return A list of clipped [[GroupType]] fields, which can be empty.
*/
private def clipParquetGroupFields(
- parquetRecord: GroupType, structType: StructType, caseSensitive:
Boolean): Seq[Type] = {
+ parquetRecord: GroupType,
+ structType: StructType,
+ caseSensitive: Boolean,
+ columnIndexAccess: Boolean): Seq[Type] = {
val toParquet = new SparkToParquetSchemaConverter(writeLegacyParquetFormat
= false)
- if (caseSensitive) {
+ if (columnIndexAccess) {
+ structType.zipWithIndex.map { case (f, i) =>
+ if (i >= parquetRecord.getFieldCount) {
+ toParquet.convertField(f)
Review comment:
addressed, but shall be applied in `else` branch
--
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]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
