cloud-fan commented on code in PR #37228:
URL: https://github.com/apache/spark/pull/37228#discussion_r945900814
##########
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/FileSourceStrategy.scala:
##########
@@ -223,8 +216,38 @@ object FileSourceStrategy extends Strategy with
PredicateHelper with Logging {
}.toSeq
}.getOrElse(Seq.empty)
- // outputAttributes should also include the metadata columns at the very
end
- val outputAttributes = readDataColumns ++ partitionColumns ++
metadataColumns
+ val fileConstantMetadataColumns: Seq[Attribute] =
+ metadataColumns.filter(_.name != FileFormat.ROW_INDEX)
+
+ val readDataColumns = dataColumns
+ .filter(requiredAttributes.contains)
+ .filterNot(partitionColumns.contains)
+
+ val fileFormatReaderGeneratedMetadataColumns: Seq[Attribute] =
+ metadataColumns.map(_.name).flatMap {
+ case FileFormat.ROW_INDEX =>
+ if ((readDataColumns ++ partitionColumns).map(_.name)
+ .contains(FileFormat.ROW_INDEX_TEMPORARY_COLUMN_NAME)) {
+ throw new
AnalysisException(FileFormat.ROW_INDEX_TEMPORARY_COLUMN_NAME +
+ " is a reserved column name that cannot be read in combination
with " +
+ s"${FileFormat.METADATA_NAME}.${FileFormat.ROW_INDEX} column.")
+ }
+
Some(AttributeReference(FileFormat.ROW_INDEX_TEMPORARY_COLUMN_NAME, LongType)())
+ case _ => None
+ }
+
+ val outputSchema = (readDataColumns ++
fileFormatReaderGeneratedMetadataColumns).toStructType
Review Comment:
shall we rename it to `outputDataSchema`? otherwise it's a bit confusing
that this is inconsistent with `outputAttributes`
--
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]
