forked from apache/spark
-
Notifications
You must be signed in to change notification settings - Fork 1
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
[SPARK-6231][SQL/DF] Automatically resolve join condition ambiguity f…
…or self-joins. See the comment in join function for more information. Author: Reynold Xin <rxin@databricks.com> Closes apache#5919 from rxin/self-join-resolve and squashes the following commits: e2fb0da [Reynold Xin] Updated SQLConf comment. 7233a86 [Reynold Xin] Updated comment. 6be2b4d [Reynold Xin] Removed println 9f6b72f [Reynold Xin] [SPARK-6231][SQL/DF] Automatically resolve ambiguity in join condition for self-joins.
- Loading branch information
Showing
6 changed files
with
170 additions
and
43 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
86 changes: 86 additions & 0 deletions
86
sql/core/src/test/scala/org/apache/spark/sql/DataFrameJoinSuite.scala
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,86 @@ | ||
| /* | ||
| * 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.spark.sql | ||
|
|
||
| import org.apache.spark.sql.TestData._ | ||
| import org.apache.spark.sql.functions._ | ||
| import org.apache.spark.sql.test.TestSQLContext._ | ||
| import org.apache.spark.sql.test.TestSQLContext.implicits._ | ||
|
|
||
|
|
||
| class DataFrameJoinSuite extends QueryTest { | ||
|
|
||
| test("join - join using") { | ||
| val df = Seq(1, 2, 3).map(i => (i, i.toString)).toDF("int", "str") | ||
| val df2 = Seq(1, 2, 3).map(i => (i, (i + 1).toString)).toDF("int", "str") | ||
|
|
||
| checkAnswer( | ||
| df.join(df2, "int"), | ||
| Row(1, "1", "2") :: Row(2, "2", "3") :: Row(3, "3", "4") :: Nil) | ||
| } | ||
|
|
||
| test("join - join using self join") { | ||
| val df = Seq(1, 2, 3).map(i => (i, i.toString)).toDF("int", "str") | ||
|
|
||
| // self join | ||
| checkAnswer( | ||
| df.join(df, "int"), | ||
| Row(1, "1", "1") :: Row(2, "2", "2") :: Row(3, "3", "3") :: Nil) | ||
| } | ||
|
|
||
| test("join - self join") { | ||
| val df1 = testData.select(testData("key")).as('df1) | ||
| val df2 = testData.select(testData("key")).as('df2) | ||
|
|
||
| checkAnswer( | ||
| df1.join(df2, $"df1.key" === $"df2.key"), | ||
| sql("SELECT a.key, b.key FROM testData a JOIN testData b ON a.key = b.key").collect().toSeq) | ||
| } | ||
|
|
||
| test("join - using aliases after self join") { | ||
| val df = Seq(1, 2, 3).map(i => (i, i.toString)).toDF("int", "str") | ||
| checkAnswer( | ||
| df.as('x).join(df.as('y), $"x.str" === $"y.str").groupBy("x.str").count(), | ||
| Row("1", 1) :: Row("2", 1) :: Row("3", 1) :: Nil) | ||
|
|
||
| checkAnswer( | ||
| df.as('x).join(df.as('y), $"x.str" === $"y.str").groupBy("y.str").count(), | ||
| Row("1", 1) :: Row("2", 1) :: Row("3", 1) :: Nil) | ||
| } | ||
|
|
||
| test("[SPARK-6231] join - self join auto resolve ambiguity") { | ||
| val df = Seq((1, "1"), (2, "2")).toDF("key", "value") | ||
| checkAnswer( | ||
| df.join(df, df("key") === df("key")), | ||
| Row(1, "1", 1, "1") :: Row(2, "2", 2, "2") :: Nil) | ||
|
|
||
| checkAnswer( | ||
| df.join(df.filter($"value" === "2"), df("key") === df("key")), | ||
| Row(2, "2", 2, "2") :: Nil) | ||
|
|
||
| checkAnswer( | ||
| df.join(df, df("key") === df("key") && df("value") === 1), | ||
| Row(1, "1", 1, "1") :: Nil) | ||
|
|
||
| val left = df.groupBy("key").agg($"key", count("*")) | ||
| val right = df.groupBy("key").agg($"key", sum("key")) | ||
| checkAnswer( | ||
| left.join(right, left("key") === right("key")), | ||
| Row(1, 1, 1, 1) :: Row(2, 1, 2, 2) :: Nil) | ||
| } | ||
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
38 changes: 38 additions & 0 deletions
38
sql/hive/src/test/scala/org/apache/spark/sql/hive/HiveDataFrameJoinSuite.scala
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,38 @@ | ||
| /* | ||
| * 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.spark.sql.hive | ||
|
|
||
| import org.apache.spark.sql.{Row, QueryTest} | ||
| import org.apache.spark.sql.hive.test.TestHive.implicits._ | ||
|
|
||
|
|
||
| class HiveDataFrameJoinSuite extends QueryTest { | ||
|
|
||
| // We should move this into SQL package if we make case sensitivity configurable in SQL. | ||
| test("join - self join auto resolve ambiguity with case insensitivity") { | ||
| val df = Seq((1, "1"), (2, "2")).toDF("key", "value") | ||
| checkAnswer( | ||
| df.join(df, df("key") === df("Key")), | ||
| Row(1, "1", 1, "1") :: Row(2, "2", 2, "2") :: Nil) | ||
|
|
||
| checkAnswer( | ||
| df.join(df.filter($"value" === "2"), df("key") === df("Key")), | ||
| Row(2, "2", 2, "2") :: Nil) | ||
| } | ||
|
|
||
| } |