suneet-amp commented on a change in pull request #8815: SQL: EARLIEST, LATEST aggregators. URL: https://github.com/apache/incubator-druid/pull/8815#discussion_r343347084
########## File path: sql/src/main/java/org/apache/druid/sql/calcite/aggregation/builtin/EarliestLatestSqlAggregator.java ########## @@ -0,0 +1,221 @@ +/* + * 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.sql.calcite.aggregation.builtin; + +import org.apache.calcite.rel.core.AggregateCall; +import org.apache.calcite.rel.core.Project; +import org.apache.calcite.rex.RexBuilder; +import org.apache.calcite.rex.RexLiteral; +import org.apache.calcite.rex.RexNode; +import org.apache.calcite.sql.SqlAggFunction; +import org.apache.calcite.sql.SqlFunctionCategory; +import org.apache.calcite.sql.SqlKind; +import org.apache.calcite.sql.type.InferTypes; +import org.apache.calcite.sql.type.OperandTypes; +import org.apache.calcite.sql.type.ReturnTypes; +import org.apache.calcite.sql.type.SqlTypeName; +import org.apache.druid.java.util.common.ISE; +import org.apache.druid.query.aggregation.AggregatorFactory; +import org.apache.druid.query.aggregation.first.DoubleFirstAggregatorFactory; +import org.apache.druid.query.aggregation.first.FloatFirstAggregatorFactory; +import org.apache.druid.query.aggregation.first.LongFirstAggregatorFactory; +import org.apache.druid.query.aggregation.first.StringFirstAggregatorFactory; +import org.apache.druid.query.aggregation.last.DoubleLastAggregatorFactory; +import org.apache.druid.query.aggregation.last.FloatLastAggregatorFactory; +import org.apache.druid.query.aggregation.last.LongLastAggregatorFactory; +import org.apache.druid.query.aggregation.last.StringLastAggregatorFactory; +import org.apache.druid.query.aggregation.post.FinalizingFieldAccessPostAggregator; +import org.apache.druid.segment.VirtualColumn; +import org.apache.druid.segment.column.ValueType; +import org.apache.druid.sql.calcite.aggregation.Aggregation; +import org.apache.druid.sql.calcite.aggregation.SqlAggregator; +import org.apache.druid.sql.calcite.expression.DruidExpression; +import org.apache.druid.sql.calcite.expression.Expressions; +import org.apache.druid.sql.calcite.planner.Calcites; +import org.apache.druid.sql.calcite.planner.PlannerContext; +import org.apache.druid.sql.calcite.rel.VirtualColumnRegistry; +import org.apache.druid.sql.calcite.table.RowSignature; + +import javax.annotation.Nullable; +import java.util.Collections; +import java.util.List; +import java.util.Objects; +import java.util.stream.Collectors; +import java.util.stream.Stream; + +public class EarliestLatestSqlAggregator implements SqlAggregator +{ + public static final SqlAggregator EARLIEST = new EarliestLatestSqlAggregator(EarliestOrLatest.EARLIEST); + public static final SqlAggregator LATEST = new EarliestLatestSqlAggregator(EarliestOrLatest.LATEST); + + enum EarliestOrLatest + { + EARLIEST { + @Override + AggregatorFactory createAggregatorFactory(String name, String fieldName, ValueType type, int maxStringBytes) + { + switch (type) { + case LONG: + return new LongFirstAggregatorFactory(name, fieldName); + case FLOAT: + return new FloatFirstAggregatorFactory(name, fieldName); + case DOUBLE: + return new DoubleFirstAggregatorFactory(name, fieldName); + case STRING: + return new StringFirstAggregatorFactory(name, fieldName, maxStringBytes); Review comment: :) I asked because I was wondering if we could short circuit that special case. You don't need to compare the timestamps in the aggregator - as long as a string exists for any row, we know the result will be an empty string. This edge case probably never happens - so again, feel free to ignore ---------------------------------------------------------------- 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. For queries about this service, please contact Infrastructure at: [email protected] With regards, Apache Git Services --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
