Repository: spark Updated Branches: refs/heads/master a35b9d971 -> 379b0b0bb
[SPARK-20283][SQL] Add preOptimizationBatches ## What changes were proposed in this pull request? We currently have postHocOptimizationBatches, but not preOptimizationBatches. This patch adds preOptimizationBatches so the optimizer debugging extensions are symmetric. ## How was this patch tested? N/A Author: Reynold Xin <r...@databricks.com> Closes #17595 from rxin/SPARK-20283. Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/379b0b0b Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/379b0b0b Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/379b0b0b Branch: refs/heads/master Commit: 379b0b0bbdbba2278ce3bcf471bd75f6ffd9cf0d Parents: a35b9d9 Author: Reynold Xin <r...@databricks.com> Authored: Mon Apr 10 14:14:09 2017 -0700 Committer: Reynold Xin <r...@databricks.com> Committed: Mon Apr 10 14:14:09 2017 -0700 ---------------------------------------------------------------------- .../org/apache/spark/sql/execution/SparkOptimizer.scala | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/spark/blob/379b0b0b/sql/core/src/main/scala/org/apache/spark/sql/execution/SparkOptimizer.scala ---------------------------------------------------------------------- diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/SparkOptimizer.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/SparkOptimizer.scala index 2cdfb7a..1de4f50 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/execution/SparkOptimizer.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/SparkOptimizer.scala @@ -30,7 +30,7 @@ class SparkOptimizer( experimentalMethods: ExperimentalMethods) extends Optimizer(catalog, conf) { - override def batches: Seq[Batch] = (super.batches :+ + override def batches: Seq[Batch] = (preOptimizationBatches ++ super.batches :+ Batch("Optimize Metadata Only Query", Once, OptimizeMetadataOnlyQuery(catalog, conf)) :+ Batch("Extract Python UDF from Aggregate", Once, ExtractPythonUDFFromAggregate) :+ Batch("Prune File Source Table Partitions", Once, PruneFileSourcePartitions)) ++ @@ -38,6 +38,12 @@ class SparkOptimizer( Batch("User Provided Optimizers", fixedPoint, experimentalMethods.extraOptimizations: _*) /** + * Optimization batches that are executed before the regular optimization batches (also before + * the finish analysis batch). + */ + def preOptimizationBatches: Seq[Batch] = Nil + + /** * Optimization batches that are executed after the regular optimization batches, but before the * batch executing the [[ExperimentalMethods]] optimizer rules. This hook can be used to add * custom optimizer batches to the Spark optimizer. --------------------------------------------------------------------- To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org For additional commands, e-mail: commits-h...@spark.apache.org
