kasakrisz commented on a change in pull request #2401: URL: https://github.com/apache/hive/pull/2401#discussion_r657781122
########## File path: ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/views/HiveAggregatePartitionIncrementalRewritingRule.java ########## @@ -0,0 +1,152 @@ +package org.apache.hadoop.hive.ql.optimizer.calcite.rules.views;/* + * 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. + */ + +import com.google.common.collect.ImmutableList; +import org.apache.calcite.plan.RelOptRule; +import org.apache.calcite.plan.RelOptRuleCall; +import org.apache.calcite.rel.RelNode; +import org.apache.calcite.rel.core.Aggregate; +import org.apache.calcite.rel.core.JoinRelType; +import org.apache.calcite.rel.core.Union; +import org.apache.calcite.rel.metadata.RelMetadataQuery; +import org.apache.calcite.rel.type.RelDataTypeField; +import org.apache.calcite.rex.RexBuilder; +import org.apache.calcite.rex.RexInputRef; +import org.apache.calcite.rex.RexNode; +import org.apache.calcite.rex.RexTableInputRef; +import org.apache.calcite.rex.RexUtil; +import org.apache.calcite.sql.SqlAggFunction; +import org.apache.calcite.sql.fun.SqlStdOperatorTable; +import org.apache.calcite.tools.RelBuilder; +import org.apache.hadoop.hive.ql.optimizer.calcite.HiveRelFactories; +import org.apache.hadoop.hive.ql.optimizer.calcite.RelOptHiveTable; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +import java.util.ArrayList; +import java.util.List; +import java.util.Set; + +import static org.apache.hadoop.hive.ql.optimizer.calcite.HiveCalciteUtil.findRexTableInputRefs; + +/** + * Rule to prepare the plan for incremental view maintenance if the view is partitioned and insert only: + * Insert overwrite the partitions which are affected since the last rebuild only and leave the + * rest of the partitions intact. + * + * Assume that we have a materialized view partitioned on column a and writeId was 1 at the last rebuild: + * + * CREATE MATERIALIZED VIEW mat1 PARTITIONED ON (a) STORED AS ORC TBLPROPERTIES ("transactional"="true", "transactional_properties"="insert_only") AS + * SELECT a, b, sum(c) sumc FROM t1 GROUP BY b, a; + * + * 1. Query all rows from source tables since the last rebuild. + * 2. Query all rows from MV which are in any of the partitions queried in 1. + * 3. Take the union of rows from 1. and 2. and perform the same aggregations defined in the MV + * + * SELECT b, sum(sumc), a FROM ( Review comment: fixed -- 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] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
