clintropolis commented on code in PR #14408:
URL: https://github.com/apache/druid/pull/14408#discussion_r1286468245
##########
processing/src/main/java/org/apache/druid/query/aggregation/first/DoubleFirstAggregatorFactory.java:
##########
@@ -125,6 +138,21 @@ public BufferAggregator
factorizeBuffered(ColumnSelectorFactory metricFactory)
}
}
+ @Override
+ public VectorAggregator factorizeVector(
+ VectorColumnSelectorFactory columnSelectorFactory
+ )
+ {
+ ColumnCapabilities capabilities =
columnSelectorFactory.getColumnCapabilities(fieldName);
+ if (capabilities != null && Types.isNumeric(capabilities)) {
Review Comment:
oops sorry for the confusion, `Types.isNumeric` includes the null check on
`capabilities` so it isn't needed here
##########
processing/src/main/java/org/apache/druid/query/aggregation/first/NumericFirstVectorAggregator.java:
##########
@@ -0,0 +1,176 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements. See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership. The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing,
+ * software distributed under the License is distributed on an
+ * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+ * KIND, either express or implied. See the License for the
+ * specific language governing permissions and limitations
+ * under the License.
+ */
+
+package org.apache.druid.query.aggregation.first;
+
+import org.apache.druid.common.config.NullHandling;
+import org.apache.druid.query.aggregation.VectorAggregator;
+import org.apache.druid.segment.vector.VectorValueSelector;
+
+import javax.annotation.Nullable;
+import java.nio.ByteBuffer;
+
+/**
+ * Class for vectorized version of first/earliest aggregator over numeric types
+ */
+public abstract class NumericFirstVectorAggregator implements VectorAggregator
+{
+ static final int NULL_OFFSET = Long.BYTES;
+ static final int VALUE_OFFSET = NULL_OFFSET + Byte.BYTES;
+ final VectorValueSelector valueSelector;
+ private final boolean useDefault = NullHandling.replaceWithDefault();
+ private final VectorValueSelector timeSelector;
+ private long firstTime;
+
+ public NumericFirstVectorAggregator(VectorValueSelector timeSelector,
VectorValueSelector valueSelector)
+ {
+ this.timeSelector = timeSelector;
+ this.valueSelector = valueSelector;
+ firstTime = Long.MAX_VALUE;
+ }
+
+ @Override
+ public void init(ByteBuffer buf, int position)
+ {
+ buf.putLong(position, Long.MAX_VALUE);
+ buf.put(position + NULL_OFFSET, useDefault ? NullHandling.IS_NOT_NULL_BYTE
: NullHandling.IS_NULL_BYTE);
+ initValue(buf, position + VALUE_OFFSET);
+ }
+
+ @Override
+ public void aggregate(ByteBuffer buf, int position, int startRow, int endRow)
+ {
+ final long[] timeVector = timeSelector.getLongVector();
+ final boolean[] nullValueVector = valueSelector.getNullVector();
+ boolean nullAbsent = false;
+ firstTime = buf.getLong(position);
+ // check if nullVector is found or not
+ // the nullVector is null if no null values are found
+ // set the nullAbsent flag accordingly
+ if (nullValueVector == null) {
+ nullAbsent = true;
+ }
+
+ // the time vector is already sorted so the first element would be the
earliest
+ // traverse accordingly
Review Comment:
Sorry for not realizing this ... earlier(!), but actually this is only true
when the `timeSelector` is for the `__time` column. If this aggregator is being
used for `LATEST_BY` with some expression virtual column then this assumption
is not correct, since the time values could be produced from any column which
may or may not be sorted (and which might also have nulls, so we probably also
need to check null vector of the time selector).
It might be worth splitting out the implementation for earliest and
earliest_by since the sorted __time column is probably a decent optimization in
that specific case.
--
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]
