From b4c32c4952f7af2733258aa4e27f21e8832c8a3a Mon Sep 17 00:00:00 2001 From: Yadong Qi Date: Sat, 28 May 2016 10:19:29 -0700 Subject: [SPARK-15549][SQL] Disable bucketing when the output doesn't contain all bucketing columns ## What changes were proposed in this pull request? I create a bucketed table bucketed_table with bucket column i, ```scala case class Data(i: Int, j: Int, k: Int) sc.makeRDD(Array((1, 2, 3))).map(x => Data(x._1, x._2, x._3)).toDF.write.bucketBy(2, "i").saveAsTable("bucketed_table") ``` and I run the following SQLs: ```sql SELECT j FROM bucketed_table; Error in query: bucket column i not found in existing columns (j); SELECT j, MAX(k) FROM bucketed_table GROUP BY j; Error in query: bucket column i not found in existing columns (j, k); ``` I think we should add a check that, we only enable bucketing when it satisfies all conditions below: 1. the conf is enabled 2. the relation is bucketed 3. the output contains all bucketing columns ## How was this patch tested? Updated test cases to reflect the changes. Author: Yadong Qi Closes #13321 from watermen/SPARK-15549. --- .../org/apache/spark/sql/sources/BucketedReadSuite.scala | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'sql/hive') diff --git a/sql/hive/src/test/scala/org/apache/spark/sql/sources/BucketedReadSuite.scala b/sql/hive/src/test/scala/org/apache/spark/sql/sources/BucketedReadSuite.scala index f9891ac571..bab0092c37 100644 --- a/sql/hive/src/test/scala/org/apache/spark/sql/sources/BucketedReadSuite.scala +++ b/sql/hive/src/test/scala/org/apache/spark/sql/sources/BucketedReadSuite.scala @@ -362,4 +362,15 @@ class BucketedReadSuite extends QueryTest with SQLTestUtils with TestHiveSinglet assert(error.toString contains "Invalid bucket file") } } + + test("disable bucketing when the output doesn't contain all bucketing columns") { + withTable("bucketed_table") { + df1.write.format("parquet").bucketBy(8, "i").saveAsTable("bucketed_table") + + checkAnswer(hiveContext.table("bucketed_table").select("j"), df1.select("j")) + + checkAnswer(hiveContext.table("bucketed_table").groupBy("j").agg(max("k")), + df1.groupBy("j").agg(max("k"))) + } + } } -- cgit v1.2.3