huaxingao commented on code in PR #6622:
URL: https://github.com/apache/iceberg/pull/6622#discussion_r1096627292


##########
spark/v3.3/spark/src/main/java/org/apache/iceberg/spark/source/SparkScanBuilder.java:
##########
@@ -158,6 +182,150 @@ public Filter[] pushedFilters() {
     return pushedFilters;
   }
 
+  @Override
+  public boolean pushAggregation(Aggregation aggregation) {
+    if (!pushDownAggregate(aggregation)) {
+      return false;
+    }
+
+    AggregateEvaluator aggregateEvaluator;
+    try {
+      List<BoundAggregate<?, ?>> aggregates =
+          Arrays.stream(aggregation.aggregateExpressions())
+              .map(agg -> SparkAggregates.convert(agg))
+              .map(expr -> Binder.bind(schema.asStruct(), expr, caseSensitive))
+              .map(bound -> (BoundAggregate<?, ?>) bound)
+              .collect(Collectors.toList());
+
+      for (BoundAggregate aggregate : aggregates) {
+        if (aggregate.aggregateComplexType()) {
+          return false;
+        }
+      }
+
+      aggregateEvaluator = AggregateEvaluator.create(aggregates);
+    } catch (Exception e) {
+      LOG.info("Can't push down aggregates: " + e.getMessage());
+      return false;
+    }
+
+    if 
(!metricsModeSupportsAggregatePushDown(aggregateEvaluator.aggregates())) {
+      LOG.info("The MetricsMode doesn't support aggregate push down.");
+      return false;
+    }
+
+    List<ManifestFile> manifests = getSnapshot().allManifests(table.io());
+
+    for (ManifestFile manifest : manifests) {
+      try (ManifestReader<DataFile> reader = ManifestFiles.read(manifest, 
table.io())) {
+        for (DataFile dataFile : reader) {
+          aggregateEvaluator.update(dataFile.copy());
+        }
+      } catch (IOException e) {
+        LOG.info("Can't push down aggregates: " + e.getMessage());
+        return false;
+      }
+    }
+
+    Object[] res = aggregateEvaluator.result();
+    applyDataTypeConversionIfNecessary(res);
+
+    List<Object> valuesInSparkInternalRow = java.util.Arrays.asList(res);
+    this.pushedAggregateRows = new InternalRow[1];
+    pushedAggregateRows[0] =
+        
InternalRow.fromSeq(JavaConverters.asScalaBuffer(valuesInSparkInternalRow).toSeq());
+    pushedAggregateSchema =
+        SparkSchemaUtil.convert(new 
Schema(aggregateEvaluator.resultType().fields()));
+    return true;
+  }
+
+  private boolean pushDownAggregate(Aggregation aggregation) {

Review Comment:
   Changed. Thanks



-- 
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

Reply via email to