Repository: spark Updated Branches: refs/heads/master b42059d2e -> 841972e22
[SPARK-10437] [SQL] Support aggregation expressions in Order By JIRA: https://issues.apache.org/jira/browse/SPARK-10437 If an expression in `SortOrder` is a resolved one, such as `count(1)`, the corresponding rule in `Analyzer` to make it work in order by will not be applied. Author: Liang-Chi Hsieh <vii...@appier.com> Closes #8599 from viirya/orderby-agg. Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/841972e2 Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/841972e2 Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/841972e2 Branch: refs/heads/master Commit: 841972e22c653ba58e9a65433fed203ff288f13a Parents: b42059d Author: Liang-Chi Hsieh <vii...@appier.com> Authored: Tue Sep 15 13:33:32 2015 -0700 Committer: Michael Armbrust <mich...@databricks.com> Committed: Tue Sep 15 13:33:32 2015 -0700 ---------------------------------------------------------------------- .../spark/sql/catalyst/analysis/Analyzer.scala | 14 ++++++++++---- .../org/apache/spark/sql/SQLQuerySuite.scala | 20 ++++++++++++++++++++ 2 files changed, 30 insertions(+), 4 deletions(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/spark/blob/841972e2/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala ---------------------------------------------------------------------- diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala index 591747b..02f34cb 100644 --- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala +++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala @@ -561,7 +561,7 @@ class Analyzer( } case sort @ Sort(sortOrder, global, aggregate: Aggregate) - if aggregate.resolved && !sort.resolved => + if aggregate.resolved => // Try resolving the ordering as though it is in the aggregate clause. try { @@ -598,9 +598,15 @@ class Analyzer( } } - Project(aggregate.output, - Sort(evaluatedOrderings, global, - aggregate.copy(aggregateExpressions = originalAggExprs ++ needsPushDown))) + // Since we don't rely on sort.resolved as the stop condition for this rule, + // we need to check this and prevent applying this rule multiple times + if (sortOrder == evaluatedOrderings) { + sort + } else { + Project(aggregate.output, + Sort(evaluatedOrderings, global, + aggregate.copy(aggregateExpressions = originalAggExprs ++ needsPushDown))) + } } catch { // Attempting to resolve in the aggregate can result in ambiguity. When this happens, // just return the original plan. http://git-wip-us.apache.org/repos/asf/spark/blob/841972e2/sql/core/src/test/scala/org/apache/spark/sql/SQLQuerySuite.scala ---------------------------------------------------------------------- diff --git a/sql/core/src/test/scala/org/apache/spark/sql/SQLQuerySuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/SQLQuerySuite.scala index 962b100..f998135 100644 --- a/sql/core/src/test/scala/org/apache/spark/sql/SQLQuerySuite.scala +++ b/sql/core/src/test/scala/org/apache/spark/sql/SQLQuerySuite.scala @@ -1562,6 +1562,26 @@ class SQLQuerySuite extends QueryTest with SharedSQLContext { |ORDER BY sum(b) + 1 """.stripMargin), Row("4", 3) :: Row("1", 7) :: Row("3", 11) :: Row("2", 15) :: Nil) + + checkAnswer( + sql( + """ + |SELECT count(*) + |FROM orderByData + |GROUP BY a + |ORDER BY count(*) + """.stripMargin), + Row(2) :: Row(2) :: Row(2) :: Row(2) :: Nil) + + checkAnswer( + sql( + """ + |SELECT a + |FROM orderByData + |GROUP BY a + |ORDER BY a, count(*), sum(b) + """.stripMargin), + Row("1") :: Row("2") :: Row("3") :: Row("4") :: Nil) } test("SPARK-7952: fix the equality check between boolean and numeric types") { --------------------------------------------------------------------- To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org For additional commands, e-mail: commits-h...@spark.apache.org
