Repository: spark Updated Branches: refs/heads/master 5d4dafe8f -> 88c9c467a
[SPARK-15562][ML] Delete temp directory after program exit in DataFrameExample ## What changes were proposed in this pull request? Temp directory used to save records is not deleted after program exit in DataFrameExample. Although it called deleteOnExit, it doesn't work as the directory is not empty. Similar things happend in ContextCleanerSuite. Update the code to make sure temp directory is deleted after program exit. ## How was this patch tested? unit tests and local build. Author: dding3 <ding.d...@intel.com> Closes #13328 from dding3/master. Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/88c9c467 Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/88c9c467 Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/88c9c467 Branch: refs/heads/master Commit: 88c9c467a31630c558719679ca0894873a268b27 Parents: 5d4dafe Author: dding3 <ding.d...@intel.com> Authored: Fri May 27 21:01:50 2016 -0500 Committer: Sean Owen <so...@cloudera.com> Committed: Fri May 27 21:01:50 2016 -0500 ---------------------------------------------------------------------- core/src/test/scala/org/apache/spark/ContextCleanerSuite.scala | 4 ++-- .../scala/org/apache/spark/examples/ml/DataFrameExample.scala | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/spark/blob/88c9c467/core/src/test/scala/org/apache/spark/ContextCleanerSuite.scala ---------------------------------------------------------------------- diff --git a/core/src/test/scala/org/apache/spark/ContextCleanerSuite.scala b/core/src/test/scala/org/apache/spark/ContextCleanerSuite.scala index 69ff6c7..6724af9 100644 --- a/core/src/test/scala/org/apache/spark/ContextCleanerSuite.scala +++ b/core/src/test/scala/org/apache/spark/ContextCleanerSuite.scala @@ -32,6 +32,7 @@ import org.apache.spark.internal.Logging import org.apache.spark.rdd.{RDD, ReliableRDDCheckpointData} import org.apache.spark.shuffle.sort.SortShuffleManager import org.apache.spark.storage._ +import org.apache.spark.util.Utils /** * An abstract base class for context cleaner tests, which sets up a context with a config @@ -206,8 +207,7 @@ class ContextCleanerSuite extends ContextCleanerSuiteBase { } test("automatically cleanup normal checkpoint") { - val checkpointDir = java.io.File.createTempFile("temp", "") - checkpointDir.deleteOnExit() + val checkpointDir = Utils.createTempDir() checkpointDir.delete() var rdd = newPairRDD() sc.setCheckpointDir(checkpointDir.toString) http://git-wip-us.apache.org/repos/asf/spark/blob/88c9c467/examples/src/main/scala/org/apache/spark/examples/ml/DataFrameExample.scala ---------------------------------------------------------------------- diff --git a/examples/src/main/scala/org/apache/spark/examples/ml/DataFrameExample.scala b/examples/src/main/scala/org/apache/spark/examples/ml/DataFrameExample.scala index c69027b..11faa61 100644 --- a/examples/src/main/scala/org/apache/spark/examples/ml/DataFrameExample.scala +++ b/examples/src/main/scala/org/apache/spark/examples/ml/DataFrameExample.scala @@ -28,6 +28,7 @@ import org.apache.spark.ml.linalg.Vector import org.apache.spark.mllib.linalg.Vectors import org.apache.spark.mllib.stat.MultivariateOnlineSummarizer import org.apache.spark.sql.{DataFrame, Row, SparkSession} +import org.apache.spark.util.Utils /** * An example of how to use [[org.apache.spark.sql.DataFrame]] for ML. Run with @@ -86,8 +87,7 @@ object DataFrameExample { println(s"Selected features column with average values:\n ${featureSummary.mean.toString}") // Save the records in a parquet file. - val tmpDir = Files.createTempDir() - tmpDir.deleteOnExit() + val tmpDir = Utils.createTempDir() val outputDir = new File(tmpDir, "dataframe").toString println(s"Saving to $outputDir as Parquet file.") df.write.parquet(outputDir) --------------------------------------------------------------------- To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org For additional commands, e-mail: commits-h...@spark.apache.org
