Repository: incubator-carbondata Updated Branches: refs/heads/master abc807dbd -> 417685704
Problem : select * with order by and limit for join is not working Solution : updated logical plan for join Project: http://git-wip-us.apache.org/repos/asf/incubator-carbondata/repo Commit: http://git-wip-us.apache.org/repos/asf/incubator-carbondata/commit/10d898c8 Tree: http://git-wip-us.apache.org/repos/asf/incubator-carbondata/tree/10d898c8 Diff: http://git-wip-us.apache.org/repos/asf/incubator-carbondata/diff/10d898c8 Branch: refs/heads/master Commit: 10d898c86e90d5e51f52fa4a1e8b95b34f506a92 Parents: abc807d Author: joobisb <joob...@gmail.com> Authored: Thu Apr 20 21:57:32 2017 +0530 Committer: ravipesala <ravi.pes...@gmail.com> Committed: Fri Apr 21 22:39:43 2017 +0530 ---------------------------------------------------------------------- .../joinquery/OrderByLimitTestCase.scala | 90 ++++++++++++++++++++ .../spark/sql/CarbonCatalystOperators.scala | 4 + 2 files changed, 94 insertions(+) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/incubator-carbondata/blob/10d898c8/integration/spark-common-test/src/test/scala/org/apache/carbondata/spark/testsuite/joinquery/OrderByLimitTestCase.scala ---------------------------------------------------------------------- diff --git a/integration/spark-common-test/src/test/scala/org/apache/carbondata/spark/testsuite/joinquery/OrderByLimitTestCase.scala b/integration/spark-common-test/src/test/scala/org/apache/carbondata/spark/testsuite/joinquery/OrderByLimitTestCase.scala new file mode 100644 index 0000000..ecf4542 --- /dev/null +++ b/integration/spark-common-test/src/test/scala/org/apache/carbondata/spark/testsuite/joinquery/OrderByLimitTestCase.scala @@ -0,0 +1,90 @@ +/* + * 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.carbondata.spark.testsuite.joinquery + +import org.apache.spark.sql.Row +import org.apache.spark.sql.common.util.QueryTest +import org.scalatest.BeforeAndAfterAll + +/** + * Test Class for join query with orderby and limit + */ + +class OrderByLimitTestCase extends QueryTest with BeforeAndAfterAll { + + override def beforeAll { + sql( + "CREATE TABLE carbon1 (empno int, empname String, designation String, doj Timestamp, " + + "workgroupcategory int, workgroupcategoryname String, deptno int, deptname String, " + + "projectcode int, projectjoindate Timestamp, projectenddate Timestamp,attendance int," + + "utilization int,salary int) STORED BY 'org.apache.carbondata.format'") + sql( + s"""LOAD DATA local inpath '$resourcesPath/data.csv' INTO TABLE carbon1 OPTIONS + |('DELIMITER'= ',', 'QUOTECHAR'= '\"')""".stripMargin); + + sql( + "CREATE TABLE carbon2 (empno int, empname String, designation String, doj Timestamp, " + + "workgroupcategory int, workgroupcategoryname String, deptno int, deptname String, " + + "projectcode int, projectjoindate Timestamp, projectenddate Timestamp,attendance int," + + "utilization int,salary int) STORED BY 'org.apache.carbondata.format'") + sql( + s"""LOAD DATA local inpath '$resourcesPath/data.csv' INTO TABLE carbon2 OPTIONS + |('DELIMITER'= ',', 'QUOTECHAR'= '\"')""".stripMargin); + + sql( + "CREATE TABLE carbon1_hive (empno int, empname String, designation String, doj Timestamp, " + + "workgroupcategory int, workgroupcategoryname String, deptno int, deptname String, " + + "projectcode int, projectjoindate Timestamp, projectenddate Timestamp,attendance int," + + "utilization int,salary int) row format delimited fields terminated by ','") + sql( + s"LOAD DATA local inpath '$resourcesPath/datawithoutheader.csv' INTO TABLE carbon1_hive ") + + sql( + "CREATE TABLE carbon2_hive (empno int, empname String, designation String, doj Timestamp, " + + "workgroupcategory int, workgroupcategoryname String, deptno int, deptname String, " + + "projectcode int, projectjoindate Timestamp, projectenddate Timestamp,attendance int," + + "utilization int,salary int) row format delimited fields terminated by ','") + sql( + s"LOAD DATA local inpath '$resourcesPath/datawithoutheader.csv' INTO TABLE carbon2_hive "); + + + } + + test("test join with orderby limit") { + checkAnswer( + sql( + "select a.empno,a.empname,a.workgroupcategoryname from carbon1 a full outer join carbon2 " + + "b on substr(a.workgroupcategoryname," + + "1,3)" + + "=substr(b.workgroupcategoryname,1,3) order by a.empname limit 5"), + sql( + "select a.empno,a.empname,a.workgroupcategoryname from carbon1_hive a full outer join " + + "carbon2_hive b on " + + "substr(a" + + ".workgroupcategoryname,1,3)=substr(b.workgroupcategoryname,1,3) order by a.empname limit" + + " 5") + ) + } + + override def afterAll { + sql("drop table carbon1") + sql("drop table carbon2") + sql("drop table carbon1_hive") + sql("drop table carbon2_hive") + } +} http://git-wip-us.apache.org/repos/asf/incubator-carbondata/blob/10d898c8/integration/spark2/src/main/scala/org/apache/spark/sql/CarbonCatalystOperators.scala ---------------------------------------------------------------------- diff --git a/integration/spark2/src/main/scala/org/apache/spark/sql/CarbonCatalystOperators.scala b/integration/spark2/src/main/scala/org/apache/spark/sql/CarbonCatalystOperators.scala index 5917369..5b47fcf 100644 --- a/integration/spark2/src/main/scala/org/apache/spark/sql/CarbonCatalystOperators.scala +++ b/integration/spark2/src/main/scala/org/apache/spark/sql/CarbonCatalystOperators.scala @@ -46,6 +46,10 @@ case class CarbonDictionaryCatalystDecoder( val logicalOut = CarbonDictionaryDecoder.updateAttributes(child.output, relations, aliasMap) CarbonDictionaryDecoder.convertOutput(logicalOut, relations, profile, aliasMap) + case Join(l: LogicalRelation, r: LogicalRelation, _, _) => + val logicalOut = + CarbonDictionaryDecoder.updateAttributes(child.output, relations, aliasMap) + CarbonDictionaryDecoder.convertOutput(logicalOut, relations, profile, aliasMap) case _ => CarbonDictionaryDecoder.convertOutput(child.output, relations, profile, aliasMap) } }
