ala commented on code in PR #37228:
URL: https://github.com/apache/spark/pull/37228#discussion_r928840126
##########
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/FileSourceStrategy.scala:
##########
@@ -223,8 +216,25 @@ object FileSourceStrategy extends Strategy with
PredicateHelper with Logging {
}.toSeq
}.getOrElse(Seq.empty)
+ val fileFormatReaderGeneratedMetadataColumns: Seq[Attribute] =
+ metadataColumns.map(_.name).flatMap {
+ case FileFormat.ROW_INDEX =>
+
Some(AttributeReference(FileFormat.ROW_INDEX_TEMPORARY_COLUMN_NAME, LongType)())
+ case _ => None
+ }
+
+ val fileConstantMetadataColumns: Seq[Attribute] =
+ metadataColumns.filter(_.name != FileFormat.ROW_INDEX)
+
+ val readDataColumns = dataColumns
+ .filter(requiredAttributes.contains)
+ .filterNot(partitionColumns.contains)
+
+ val outputSchema = (readDataColumns ++
fileFormatReaderGeneratedMetadataColumns).toStructType
+
// outputAttributes should also include the metadata columns at the very
end
- val outputAttributes = readDataColumns ++ partitionColumns ++
metadataColumns
+ val outputAttributes = readDataColumns ++
fileFormatReaderGeneratedMetadataColumns ++
Review Comment:
Done!
--
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]
