This is an automated email from the ASF dual-hosted git repository. maxgekk pushed a commit to branch master in repository https://gitbox.apache.org/repos/asf/spark.git
The following commit(s) were added to refs/heads/master by this push: new 02b39f0b880 [SPARK-41985][SQL][FOLLOWUP] Remove alias in GROUP BY only when the expr is resolved 02b39f0b880 is described below commit 02b39f0b880a2ecf63167355d9644e91c98588a8 Author: Wenchen Fan <wenc...@databricks.com> AuthorDate: Fri Feb 3 15:40:33 2023 +0300 [SPARK-41985][SQL][FOLLOWUP] Remove alias in GROUP BY only when the expr is resolved ### What changes were proposed in this pull request? This is a followup of https://github.com/apache/spark/pull/39508 to fix a regression. We should not remove aliases from grouping expressions if they are not resolved, as the alias may be necessary for resolution, such as `CreateNamedStruct`. ### Why are the changes needed? fix a regression ### Does this PR introduce _any_ user-facing change? no ### How was this patch tested? new test Closes #39867 from cloud-fan/column. Lead-authored-by: Wenchen Fan <wenc...@databricks.com> Co-authored-by: Wenchen Fan <cloud0...@gmail.com> Signed-off-by: Max Gekk <max.g...@gmail.com> --- .../sql/catalyst/analysis/ResolveReferencesInAggregate.scala | 8 +++++++- sql/core/src/test/resources/sql-tests/inputs/group-by.sql | 3 +++ .../src/test/resources/sql-tests/results/group-by.sql.out | 11 +++++++++++ 3 files changed, 21 insertions(+), 1 deletion(-) diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveReferencesInAggregate.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveReferencesInAggregate.scala index 4af2ecc91ab..1a9ed4ce16e 100644 --- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveReferencesInAggregate.scala +++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveReferencesInAggregate.scala @@ -96,7 +96,13 @@ object ResolveReferencesInAggregate extends SQLConfHelper // can't find the grouping expressions via `semanticEquals` and the analysis will fail. // Example rules: ResolveGroupingAnalytics (See SPARK-31670 for more details) and // ResolveLateralColumnAliasReference. - groupingExpressions = resolvedGroupExprs.map(trimAliases), + groupingExpressions = resolvedGroupExprs.map { e => + // Only trim the alias if the expression is resolved, as the alias may be needed to resolve + // the expression, such as `NamePlaceHolder` in `CreateNamedStruct`. + // Note: this rule will be invoked even if the Aggregate is fully resolved. So alias in + // GROUP BY will be removed eventually, by following iterations. + if (e.resolved) trimAliases(e) else e + }, aggregateExpressions = resolvedAggExprsWithOuter) } diff --git a/sql/core/src/test/resources/sql-tests/inputs/group-by.sql b/sql/core/src/test/resources/sql-tests/inputs/group-by.sql index 1615c43cc7e..c812403ba2c 100644 --- a/sql/core/src/test/resources/sql-tests/inputs/group-by.sql +++ b/sql/core/src/test/resources/sql-tests/inputs/group-by.sql @@ -34,6 +34,9 @@ SELECT a + b, COUNT(b) FROM testData GROUP BY a + b; SELECT a + 2, COUNT(b) FROM testData GROUP BY a + 1; SELECT a + 1 + 1, COUNT(b) FROM testData GROUP BY a + 1; +-- struct() in group by +SELECT count(1) FROM testData GROUP BY struct(a + 0.1 AS aa); + -- Aggregate with nulls. SELECT SKEWNESS(a), KURTOSIS(a), MIN(a), MAX(a), AVG(a), VARIANCE(a), STDDEV(a), SUM(a), COUNT(a) FROM testData; diff --git a/sql/core/src/test/resources/sql-tests/results/group-by.sql.out b/sql/core/src/test/resources/sql-tests/results/group-by.sql.out index 0402039fafa..6e7592d6978 100644 --- a/sql/core/src/test/resources/sql-tests/results/group-by.sql.out +++ b/sql/core/src/test/resources/sql-tests/results/group-by.sql.out @@ -145,6 +145,17 @@ struct<((a + 1) + 1):int,count(b):bigint> NULL 1 +-- !query +SELECT count(1) FROM testData GROUP BY struct(a + 0.1 AS aa) +-- !query schema +struct<count(1):bigint> +-- !query output +2 +2 +2 +3 + + -- !query SELECT SKEWNESS(a), KURTOSIS(a), MIN(a), MAX(a), AVG(a), VARIANCE(a), STDDEV(a), SUM(a), COUNT(a) FROM testData --------------------------------------------------------------------- To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org For additional commands, e-mail: commits-h...@spark.apache.org