yma11 commented on code in PR #5624:
URL: https://github.com/apache/incubator-gluten/pull/5624#discussion_r1591724427
##########
gluten-iceberg/src/main/scala/org/apache/iceberg/spark/source/GlutenIcebergSourceUtil.scala:
##########
@@ -94,15 +97,24 @@ object GlutenIcebergSourceUtil {
throw new GlutenNotSupportException("Only support iceberg
SparkBatchQueryScan.")
}
- def getPartitionSchema(sparkScan: Scan): StructType = sparkScan match {
+ def getReadPartitionSchema(sparkScan: Scan): StructType = sparkScan match {
case scan: SparkBatchQueryScan =>
val tasks = scan.tasks().asScala
asFileScanTask(tasks.toList).foreach {
task =>
val spec = task.spec()
if (spec.isPartitioned) {
var partitionSchema = new StructType()
- val partitionFields = spec.partitionType().fields().asScala
+ val readFields = scan.readSchema().fields.map(_.name).toSet
+ // Iceberg will generate some non-table fields as partition
fields, such as x_bucket,
+ // which will not appear in readFields, they also cannot be
filtered.
+ val tableFields =
spec.schema().columns().asScala.map(_.name()).toSet
+ val partitionFields =
+ spec
+ .partitionType()
+ .fields()
+ .asScala
+ .filter(f => !tableFields.contains(f.name) ||
readFields.contains(f.name()))
Review Comment:
Can you explain the filter here? should it be
`!tableFields.contains(f.name) && readFields.contains(f.name())`?
--
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]
