Repository: spark Updated Branches: refs/heads/master 3f749f7ed -> 76f3c735a
[SPARK-14356] Update spark.sql.execution.debug to work on Datasets ## What changes were proposed in this pull request? Update DebugQuery to work on Datasets of any type, not just DataFrames. ## How was this patch tested? Added unit tests, checked in spark-shell. Author: Matei Zaharia <ma...@databricks.com> Closes #12140 from mateiz/debug-dataset. Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/76f3c735 Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/76f3c735 Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/76f3c735 Branch: refs/heads/master Commit: 76f3c735aa300d7ea6b17e64cc22d7e8fc3a8322 Parents: 3f749f7 Author: Matei Zaharia <ma...@databricks.com> Authored: Sun Apr 3 21:08:54 2016 -0700 Committer: Reynold Xin <r...@databricks.com> Committed: Sun Apr 3 21:08:54 2016 -0700 ---------------------------------------------------------------------- .../scala/org/apache/spark/sql/execution/debug/package.scala | 4 ++-- .../org/apache/spark/sql/execution/debug/DebuggingSuite.scala | 6 ++++++ 2 files changed, 8 insertions(+), 2 deletions(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/spark/blob/76f3c735/sql/core/src/main/scala/org/apache/spark/sql/execution/debug/package.scala ---------------------------------------------------------------------- diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/debug/package.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/debug/package.scala index 7b0c8eb..17eae88 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/execution/debug/package.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/debug/package.scala @@ -77,9 +77,9 @@ package object debug { } /** - * Augments [[DataFrame]]s with debug methods. + * Augments [[Dataset]]s with debug methods. */ - implicit class DebugQuery(query: DataFrame) extends Logging { + implicit class DebugQuery(query: Dataset[_]) extends Logging { def debug(): Unit = { val plan = query.queryExecution.executedPlan val visited = new collection.mutable.HashSet[TreeNodeRef]() http://git-wip-us.apache.org/repos/asf/spark/blob/76f3c735/sql/core/src/test/scala/org/apache/spark/sql/execution/debug/DebuggingSuite.scala ---------------------------------------------------------------------- diff --git a/sql/core/src/test/scala/org/apache/spark/sql/execution/debug/DebuggingSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/execution/debug/DebuggingSuite.scala index c0fce4b..8aa0114 100644 --- a/sql/core/src/test/scala/org/apache/spark/sql/execution/debug/DebuggingSuite.scala +++ b/sql/core/src/test/scala/org/apache/spark/sql/execution/debug/DebuggingSuite.scala @@ -19,6 +19,7 @@ package org.apache.spark.sql.execution.debug import org.apache.spark.SparkFunSuite import org.apache.spark.sql.test.SharedSQLContext +import org.apache.spark.sql.test.SQLTestData.TestData class DebuggingSuite extends SparkFunSuite with SharedSQLContext { @@ -26,6 +27,11 @@ class DebuggingSuite extends SparkFunSuite with SharedSQLContext { testData.debug() } + test("Dataset.debug()") { + import testImplicits._ + testData.as[TestData].debug() + } + test("debugCodegen") { val res = codegenString(sqlContext.range(10).groupBy("id").count().queryExecution.executedPlan) assert(res.contains("Subtree 1 / 2")) --------------------------------------------------------------------- To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org For additional commands, e-mail: commits-h...@spark.apache.org
