godfreyhe commented on a change in pull request #13291:
URL: https://github.com/apache/flink/pull/13291#discussion_r525005001
##########
File path:
flink-table/flink-table-planner-blink/src/main/scala/org/apache/flink/table/planner/plan/optimize/program/FlinkStreamProgram.scala
##########
@@ -91,6 +92,15 @@ object FlinkStreamProgram {
.build(), "convert enumerable table scan")
.build())
+ // rewrite before decorrelation
+ chainedProgram.addLast(
+ PRE_DECORRELATE_REWRITE,
+ FlinkHepRuleSetProgramBuilder.newBuilder
+ .setHepRulesExecutionType(HEP_RULES_EXECUTION_TYPE.RULE_SEQUENCE)
+ .setHepMatchOrder(HepMatchOrder.BOTTOM_UP)
+ .add(FlinkStreamRuleSets.PRE_DECORRELATION_RULES)
+ .build())
Review comment:
We should merge this program into `DECORRELATE`
##########
File path:
flink-table/flink-table-planner-blink/src/main/scala/org/apache/flink/table/planner/plan/rules/logical/CorrelateSortToRankRule.scala
##########
@@ -0,0 +1,186 @@
+/*
+ * 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.flink.table.planner.plan.rules.logical
+
+import org.apache.flink.table.planner.calcite.FlinkRelBuilder
+import org.apache.flink.table.runtime.operators.rank.{ConstantRankRange,
RankType}
+
+import org.apache.calcite.plan.RelOptRule.{any, operand}
+import org.apache.calcite.plan.{RelOptRule, RelOptRuleCall}
+import org.apache.calcite.rel.RelCollations
+import org.apache.calcite.rel.`type`.RelDataType
+import org.apache.calcite.rel.core.{Aggregate, Correlate, Filter, JoinRelType,
Project, Sort}
+import org.apache.calcite.rex.{RexCall, RexCorrelVariable, RexFieldAccess,
RexInputRef, RexLiteral, RexNode}
+import org.apache.calcite.sql.SqlKind
+import org.apache.calcite.util.ImmutableBitSet
+
+import java.util
+
+import scala.collection.JavaConversions._
+
+/**
+ * Planner rule that rewrites sort correlation to a Rank.
+ * Typically, the following plan
+ *
+ * {{{
+ * LogicalProject(state=[$0], name=[$1])
+ * +- LogicalCorrelate(correlation=[$cor0], joinType=[inner],
requiredColumns=[{0}])
+ * :- LogicalAggregate(group=[{0}])
+ * : +- LogicalProject(state=[$1])
+ * : +- LogicalTableScan(table=[[default_catalog, default_database,
cities]])
+ * +- LogicalSort(sort0=[$1], dir0=[DESC-nulls-last], fetch=[3])
+ * +- LogicalProject(name=[$0], pop=[$2])
+ * +- LogicalFilter(condition=[=($1, $cor0.state)])
+ * +- LogicalTableScan(table=[[default_catalog,
default_database, cities]])
+ * }}}
+ *
+ * <p>would be transformed to
+ *
+ * {{{
+ * LogicalProject(state=[$0], name=[$1])
+ * +- LogicalProject(state=[$1], name=[$0], pop=[$2])
+ * +- LogicalRank(rankType=[ROW_NUMBER], rankRange=[rankStart=1,
rankEnd=3],
+ * partitionBy=[$1], orderBy=[$2 DESC], select=[name=$0, state=$1,
pop=$2])
+ * +- LogicalTableScan(table=[[default_catalog, default_database,
cities]])
+ * }}}
Review comment:
it seems the rewrite is not correct, consider the following example:
```
SELECT state, name
FROM
(SELECT DISTINCT state FROM cities1) states,
LATERAL (
SELECT name, pop
FROM cities2
WHERE state = states.state
ORDER BY pop
DESC LIMIT 3
);
```
The outer table (`cities1`) and the inner table (`cities2`) are different.
----------------------------------------------------------------
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]
