rdblue commented on code in PR #6622:
URL: https://github.com/apache/iceberg/pull/6622#discussion_r1103896926
##########
spark/v3.3/spark/src/main/java/org/apache/iceberg/spark/source/SparkScanBuilder.java:
##########
@@ -158,6 +179,129 @@ public Filter[] pushedFilters() {
return pushedFilters;
}
+ @Override
+ public boolean pushAggregation(Aggregation aggregation) {
+ if (!canPushDownAggregation(aggregation)) {
+ return false;
+ }
+
+ AggregateEvaluator aggregateEvaluator;
+ try {
+ List<Expression> aggregates =
+ Arrays.stream(aggregation.aggregateExpressions())
+ .map(agg -> SparkAggregates.convert(agg))
+ .collect(Collectors.toList());
+ aggregateEvaluator = AggregateEvaluator.create(schema, aggregates);
+ } catch (UnsupportedOperationException | IllegalArgumentException e) {
+ LOG.info("Skipped aggregate pushdown: " + e);
+ return false;
+ }
+
+ if
(!metricsModeSupportsAggregatePushDown(aggregateEvaluator.aggregates())) {
+ return false;
+ }
+
+ TableScanContext context = new TableScanContext().reportWith(((BaseTable)
table).getReporter());
+ context.setColStats(true);
+ TableScan scan = new DataTableScan(table, table.schema(), context);
+ Snapshot snapshot = readSnapshot();
+ if (snapshot == null) {
+ LOG.info("Skipped aggregate pushdown: table snapshot is null");
+ return false;
+ }
+ scan = scan.useSnapshot(snapshot.snapshotId());
+ scan = configureSplitPlanning(scan);
+
+ try (CloseableIterable<FileScanTask> fileScanTasks = scan.planFiles()) {
+ List<FileScanTask> tasks = ImmutableList.copyOf(fileScanTasks);
+ for (FileScanTask task : tasks) {
+ if (!task.deletes().isEmpty()) {
+ LOG.info("Skipped aggregate pushdown: detected row level deletes.");
+ return false;
+ }
+ if (!aggregateEvaluator.update(task.file())) {
Review Comment:
Style: missing whitespace between `if` blocks.
--
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: issues-unsubscr...@iceberg.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@iceberg.apache.org
For additional commands, e-mail: issues-h...@iceberg.apache.org
