You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@calcite.apache.org by GitBox <gi...@apache.org> on 2021/01/20 09:08:48 UTC
[GitHub] [calcite] vlsi commented on a change in pull request #2329: [CALCITE-3221] Add a sort-merge union algorithm
vlsi commented on a change in pull request #2329:
URL: https://github.com/apache/calcite/pull/2329#discussion_r560796382
##########
File path: core/src/test/java/org/apache/calcite/test/enumerable/EnumerableMergeUnionTest.java
##########
@@ -0,0 +1,282 @@
+/*
+ * 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.calcite.test.enumerable;
+
+import org.apache.calcite.adapter.enumerable.EnumerableRules;
+import org.apache.calcite.adapter.java.ReflectiveSchema;
+import org.apache.calcite.config.CalciteConnectionProperty;
+import org.apache.calcite.config.Lex;
+import org.apache.calcite.plan.RelOptPlanner;
+import org.apache.calcite.runtime.Hook;
+import org.apache.calcite.test.CalciteAssert;
+import org.apache.calcite.test.JdbcTest;
+
+import org.junit.jupiter.api.Test;
+
+import java.util.function.Consumer;
+
+/**
+ * Unit test for
+ * {@link org.apache.calcite.adapter.enumerable.EnumerableMergeUnion}.
+ */
+class EnumerableMergeUnionTest {
+
+ @Test void mergeUnionAllOrderByEmpid() {
+ tester(false,
+ new JdbcTest.HrSchemaBig(),
+ "select * from (select empid, name from emps where name like 'G%' union all select empid, name from emps where name like '%l') order by empid")
+ .explainContains("EnumerableMergeUnion(all=[true])\n"
+ + " EnumerableSort(sort0=[$0], dir0=[ASC])\n"
+ + " EnumerableCalc(expr#0..4=[{inputs}], expr#5=['G%'], expr#6=[LIKE($t2, $t5)], empid=[$t0], name=[$t2], $condition=[$t6])\n"
+ + " EnumerableTableScan(table=[[s, emps]])\n"
+ + " EnumerableSort(sort0=[$0], dir0=[ASC])\n"
+ + " EnumerableCalc(expr#0..4=[{inputs}], expr#5=['%l'], expr#6=[LIKE($t2, $t5)], empid=[$t0], name=[$t2], $condition=[$t6])\n"
+ + " EnumerableTableScan(table=[[s, emps]])\n")
+ .returnsOrdered(
+ "empid=1; name=Bill",
+ "empid=6; name=Guy",
+ "empid=10; name=Gabriel",
+ "empid=10; name=Gabriel",
+ "empid=12; name=Paul",
+ "empid=29; name=Anibal",
+ "empid=40; name=Emmanuel",
+ "empid=45; name=Pascal");
+ }
+
+ @Test void mergeUnionOrderByEmpid() {
+ tester(false,
+ new JdbcTest.HrSchemaBig(),
+ "select * from (select empid, name from emps where name like 'G%' union select empid, name from emps where name like '%l') order by empid")
+ .explainContains("EnumerableMergeUnion(all=[false])\n"
+ + " EnumerableSort(sort0=[$0], dir0=[ASC])\n"
+ + " EnumerableCalc(expr#0..4=[{inputs}], expr#5=['G%'], expr#6=[LIKE($t2, $t5)], empid=[$t0], name=[$t2], $condition=[$t6])\n"
+ + " EnumerableTableScan(table=[[s, emps]])\n"
+ + " EnumerableSort(sort0=[$0], dir0=[ASC])\n"
+ + " EnumerableCalc(expr#0..4=[{inputs}], expr#5=['%l'], expr#6=[LIKE($t2, $t5)], empid=[$t0], name=[$t2], $condition=[$t6])\n"
+ + " EnumerableTableScan(table=[[s, emps]])\n")
+ .returnsOrdered(
+ "empid=1; name=Bill",
+ "empid=6; name=Guy",
+ "empid=10; name=Gabriel",
+ "empid=12; name=Paul",
+ "empid=29; name=Anibal",
+ "empid=40; name=Emmanuel",
+ "empid=45; name=Pascal");
+ }
+
+ @Test void mergeUnionAllOrderByName() {
+ tester(false,
+ new JdbcTest.HrSchemaBig(),
+ "select * from (select empid, name from emps where name like 'G%' union all select empid, name from emps where name like '%l') order by name")
+ .explainContains("EnumerableMergeUnion(all=[true])\n"
+ + " EnumerableSort(sort0=[$1], dir0=[ASC])\n"
+ + " EnumerableCalc(expr#0..4=[{inputs}], expr#5=['G%'], expr#6=[LIKE($t2, $t5)], empid=[$t0], name=[$t2], $condition=[$t6])\n"
+ + " EnumerableTableScan(table=[[s, emps]])\n"
+ + " EnumerableSort(sort0=[$1], dir0=[ASC])\n"
+ + " EnumerableCalc(expr#0..4=[{inputs}], expr#5=['%l'], expr#6=[LIKE($t2, $t5)], empid=[$t0], name=[$t2], $condition=[$t6])\n"
+ + " EnumerableTableScan(table=[[s, emps]])\n")
+ .returnsOrdered(
+ "empid=29; name=Anibal",
+ "empid=1; name=Bill",
+ "empid=40; name=Emmanuel",
+ "empid=10; name=Gabriel",
+ "empid=10; name=Gabriel",
+ "empid=6; name=Guy",
+ "empid=45; name=Pascal",
+ "empid=12; name=Paul");
+ }
+
+ @Test void mergeUnionOrderByName() {
+ tester(false,
+ new JdbcTest.HrSchemaBig(),
+ "select * from (select empid, name from emps where name like 'G%' union select empid, name from emps where name like '%l') order by name")
+ .explainContains("EnumerableMergeUnion(all=[false])\n"
+ + " EnumerableSort(sort0=[$1], dir0=[ASC])\n"
+ + " EnumerableCalc(expr#0..4=[{inputs}], expr#5=['G%'], expr#6=[LIKE($t2, $t5)], empid=[$t0], name=[$t2], $condition=[$t6])\n"
+ + " EnumerableTableScan(table=[[s, emps]])\n"
+ + " EnumerableSort(sort0=[$1], dir0=[ASC])\n"
+ + " EnumerableCalc(expr#0..4=[{inputs}], expr#5=['%l'], expr#6=[LIKE($t2, $t5)], empid=[$t0], name=[$t2], $condition=[$t6])\n"
+ + " EnumerableTableScan(table=[[s, emps]])\n")
+ .returnsOrdered(
+ "empid=29; name=Anibal",
+ "empid=1; name=Bill",
+ "empid=40; name=Emmanuel",
+ "empid=10; name=Gabriel",
+ "empid=6; name=Guy",
+ "empid=45; name=Pascal",
+ "empid=12; name=Paul");
+ }
+
+ @Test void mergeUnionOrderByNameWithLimit() {
+ tester(false,
+ new JdbcTest.HrSchemaBig(),
+ "select * from (select empid, name from emps where name like 'G%' union select empid, name from emps where name like '%l') order by name limit 3")
+ .explainContains("EnumerableLimit(fetch=[3])\n"
Review comment:
Can you please propagate limit to the downstream nodes?
In other words, if you want 3 rows from the union, then you could limit each branch with 3 so they can use limited sort rather than sorting of the full result.
WDYT?
----------------------------------------------------------------
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:
users@infra.apache.org