Repository: spark Updated Branches: refs/heads/master e66cabb02 -> 8148f19ca
[SPARK-22249][SQL] isin with empty list throws exception on cached DataFrame ## What changes were proposed in this pull request? As pointed out in the JIRA, there is a bug which causes an exception to be thrown if `isin` is called with an empty list on a cached DataFrame. The PR fixes it. ## How was this patch tested? Added UT. Author: Marco Gaido <marcogaid...@gmail.com> Closes #19494 from mgaido91/SPARK-22249. Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/8148f19c Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/8148f19c Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/8148f19c Branch: refs/heads/master Commit: 8148f19ca1f0e0375603cb4f180c1bad8b0b8042 Parents: e66cabb Author: Marco Gaido <marcogaid...@gmail.com> Authored: Tue Oct 17 09:41:23 2017 +0200 Committer: Sean Owen <so...@cloudera.com> Committed: Tue Oct 17 09:41:23 2017 +0200 ---------------------------------------------------------------------- .../execution/columnar/InMemoryTableScanExec.scala | 1 + .../columnar/InMemoryColumnarQuerySuite.scala | 15 +++++++++++++++ 2 files changed, 16 insertions(+) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/spark/blob/8148f19c/sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/InMemoryTableScanExec.scala ---------------------------------------------------------------------- diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/InMemoryTableScanExec.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/InMemoryTableScanExec.scala index af3636a..846ec03 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/InMemoryTableScanExec.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/InMemoryTableScanExec.scala @@ -102,6 +102,7 @@ case class InMemoryTableScanExec( case IsNull(a: Attribute) => statsFor(a).nullCount > 0 case IsNotNull(a: Attribute) => statsFor(a).count - statsFor(a).nullCount > 0 + case In(_: AttributeReference, list: Seq[Expression]) if list.isEmpty => Literal.FalseLiteral case In(a: AttributeReference, list: Seq[Expression]) if list.forall(_.isInstanceOf[Literal]) => list.map(l => statsFor(a).lowerBound <= l.asInstanceOf[Literal] && l.asInstanceOf[Literal] <= statsFor(a).upperBound).reduce(_ || _) http://git-wip-us.apache.org/repos/asf/spark/blob/8148f19c/sql/core/src/test/scala/org/apache/spark/sql/execution/columnar/InMemoryColumnarQuerySuite.scala ---------------------------------------------------------------------- diff --git a/sql/core/src/test/scala/org/apache/spark/sql/execution/columnar/InMemoryColumnarQuerySuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/execution/columnar/InMemoryColumnarQuerySuite.scala index 8d411eb..75d17bc 100644 --- a/sql/core/src/test/scala/org/apache/spark/sql/execution/columnar/InMemoryColumnarQuerySuite.scala +++ b/sql/core/src/test/scala/org/apache/spark/sql/execution/columnar/InMemoryColumnarQuerySuite.scala @@ -429,4 +429,19 @@ class InMemoryColumnarQuerySuite extends QueryTest with SharedSQLContext { checkAnswer(agg_without_cache, agg_with_cache) } } + + test("SPARK-22249: IN should work also with cached DataFrame") { + val df = spark.range(10).cache() + // with an empty list + assert(df.filter($"id".isin()).count() == 0) + // with a non-empty list + assert(df.filter($"id".isin(2)).count() == 1) + assert(df.filter($"id".isin(2, 3)).count() == 2) + df.unpersist() + val dfNulls = spark.range(10).selectExpr("null as id").cache() + // with null as value for the attribute + assert(dfNulls.filter($"id".isin()).count() == 0) + assert(dfNulls.filter($"id".isin(2, 3)).count() == 0) + dfNulls.unpersist() + } } --------------------------------------------------------------------- To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org For additional commands, e-mail: commits-h...@spark.apache.org
