andygrove commented on code in PR #674:
URL: https://github.com/apache/datafusion-comet/pull/674#discussion_r1680126583
##########
spark/src/main/spark-3.5/org/apache/spark/sql/comet/shims/ShimCometScanExec.scala:
##########
@@ -49,16 +48,14 @@ trait ShimCometScanExec {
filePartitions,
readSchema,
fileConstantMetadataColumns,
- Map.empty,
+ fsRelation.fileFormat.fileConstantMetadataExtractors,
options)
protected def invalidBucketFile(path: String, sparkVersion: String):
Throwable =
- new SparkException("INVALID_BUCKET_FILE", Map("path" -> path), null)
+ QueryExecutionErrors.invalidBucketFile(path)
- protected def isNeededForSchema(sparkSchema: StructType): Boolean = {
- // TODO: remove after PARQUET-2161 becomes available in Parquet (tracked
in SPARK-39634)
- ShimFileFormat.findRowIndexColumnIndexInSchema(sparkSchema) >= 0
- }
+ // see SPARK-39634
+ protected def isNeededForSchema(sparkSchema: StructType): Boolean = false
Review Comment:
I updated this to match the version in the 4.0 shims because
https://issues.apache.org/jira/browse/SPARK-39634 is marked as fixes in 3.5
##########
spark/src/main/spark-3.5/org/apache/spark/sql/comet/shims/ShimCometScanExec.scala:
##########
@@ -49,16 +48,14 @@ trait ShimCometScanExec {
filePartitions,
readSchema,
fileConstantMetadataColumns,
- Map.empty,
+ fsRelation.fileFormat.fileConstantMetadataExtractors,
options)
protected def invalidBucketFile(path: String, sparkVersion: String):
Throwable =
- new SparkException("INVALID_BUCKET_FILE", Map("path" -> path), null)
+ QueryExecutionErrors.invalidBucketFile(path)
- protected def isNeededForSchema(sparkSchema: StructType): Boolean = {
- // TODO: remove after PARQUET-2161 becomes available in Parquet (tracked
in SPARK-39634)
- ShimFileFormat.findRowIndexColumnIndexInSchema(sparkSchema) >= 0
- }
+ // see SPARK-39634
+ protected def isNeededForSchema(sparkSchema: StructType): Boolean = false
Review Comment:
I updated this to match the version in the 4.0 shims because
https://issues.apache.org/jira/browse/SPARK-39634 is marked as fixed in 3.5
--
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: github-unsubscr...@datafusion.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: github-unsubscr...@datafusion.apache.org
For additional commands, e-mail: github-h...@datafusion.apache.org
