flyrain commented on code in PR #7326:
URL: https://github.com/apache/iceberg/pull/7326#discussion_r1238898994
##########
spark/v3.3/spark/src/main/java/org/apache/iceberg/spark/procedures/CreateChangelogViewProcedure.java:
##########
@@ -228,22 +247,41 @@ private Dataset<Row> applyChangelogIterator(Dataset<Row>
df, Column[] repartitio
RowEncoder.apply(schema));
}
- private Dataset<Row> applyCarryoverRemoveIterator(Dataset<Row> df, Column[]
repartitionSpec) {
- Column[] sortSpec = sortSpec(df, repartitionSpec);
+ private Dataset<Row> applyCarryoverRemoveIterator(
+ Dataset<Row> df, Column[] repartitionSpec, boolean netChanges) {
+ Column[] sortSpec = sortSpec(df, repartitionSpec, netChanges);
StructType schema = df.schema();
return df.repartition(repartitionSpec)
.sortWithinPartitions(sortSpec)
.mapPartitions(
(MapPartitionsFunction<Row, Row>)
- rowIterator -> ChangelogIterator.removeCarryovers(rowIterator,
schema),
+ rowIterator ->
+ netChanges
+ ? ChangelogIterator.removeNetCarryovers(rowIterator,
schema)
+ : ChangelogIterator.removeCarryovers(rowIterator,
schema),
RowEncoder.apply(schema));
}
- private static Column[] sortSpec(Dataset<Row> df, Column[] repartitionSpec) {
- Column[] sortSpec = new Column[repartitionSpec.length + 1];
- System.arraycopy(repartitionSpec, 0, sortSpec, 0, repartitionSpec.length);
+ private static Column[] sortSpec(Dataset<Row> df, Column[] repartitionSpec,
boolean netChanges) {
+ Column[] sortSpec;
+
+ if (netChanges) {
+ Column changeOrdinal = df.col(MetadataColumns.CHANGE_ORDINAL.name());
+ Preconditions.checkState(
Review Comment:
I added it since this method take a flag `netchange`. When the flag is
`false`, repartition spec will have `changeOrdinal`. But I'm OK to remove it if
you think is not necessary.
--
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]
