SPARK-1798. Tests should clean up temp files

Three issues related to temp files that tests generate – these should be touched up for hygiene but are not urgent.

Modules have a log4j.properties which directs the unit-test.log output file to a directory like `[module]/target/unit-test.log`. But this ends up creating `[module]/[module]/target/unit-test.log` instead of former.

The `work/` directory is not deleted by "mvn clean", in the parent and in modules. Neither is the `checkpoint/` directory created under the various external modules.

Many tests create a temp directory, which is not usually deleted. This can be largely resolved by calling `deleteOnExit()` at creation and trying to call `Utils.deleteRecursively` consistently to clean up, sometimes in an `@After` method.

_If anyone seconds the motion, I can create a more significant change that introduces a new test trait along the lines of `LocalSparkContext`, which provides management of temp directories for subclasses to take advantage of._

Author: Sean Owen <sowen@cloudera.com>

Closes #732 from srowen/SPARK-1798 and squashes the following commits:

5af578e [Sean Owen] Try to consistently delete test temp dirs and files, and set deleteOnExit() for each
b21b356 [Sean Owen] Remove work/ and checkpoint/ dirs with mvn clean
bdd0f41 [Sean Owen] Remove duplicate module dir in log4j.properties output path for tests
(cherry picked from commit 7120a2979d0a9f0f54a88b2416be7ca10e74f409)

Signed-off-by: Patrick Wendell <pwendell@gmail.com>

2 files changed, 5 insertions, 14 deletions

diff --git a/mllib/src/test/resources/log4j.properties b/mllib/src/test/resources/log4j.properties
index 4265ba6e5d..ddfc4ac6b2 100644
--- a/mllib/src/test/resources/log4j.properties
+++ b/mllib/src/test/resources/log4j.properties
@@ -19,7 +19,7 @@
 log4j.rootCategory=INFO, file
 log4j.appender.file=org.apache.log4j.FileAppender
 log4j.appender.file.append=false
-log4j.appender.file.file=mllib/target/unit-tests.log
+log4j.appender.file.file=target/unit-tests.log
 log4j.appender.file.layout=org.apache.log4j.PatternLayout
 log4j.appender.file.layout.ConversionPattern=%d{yy/MM/dd HH:mm:ss.SSS} %p %c{1}: %m%n
 
diff --git a/mllib/src/test/scala/org/apache/spark/mllib/util/MLUtilsSuite.scala b/mllib/src/test/scala/org/apache/spark/mllib/util/MLUtilsSuite.scala
index 3f64baf6fe..3d05fb6898 100644
--- a/mllib/src/test/scala/org/apache/spark/mllib/util/MLUtilsSuite.scala
+++ b/mllib/src/test/scala/org/apache/spark/mllib/util/MLUtilsSuite.scala
@@ -32,6 +32,7 @@ import com.google.common.io.Files
 import org.apache.spark.mllib.linalg.{DenseVector, SparseVector, Vectors}
 import org.apache.spark.mllib.regression.LabeledPoint
 import org.apache.spark.mllib.util.MLUtils._
+import org.apache.spark.util.Utils
 
 class MLUtilsSuite extends FunSuite with LocalSparkContext {
 
@@ -67,6 +68,7 @@ class MLUtilsSuite extends FunSuite with LocalSparkContext {
         |-1 2:4.0 4:5.0 6:6.0
       """.stripMargin
     val tempDir = Files.createTempDir()
+    tempDir.deleteOnExit()
     val file = new File(tempDir.getPath, "part-00000")
     Files.write(lines, file, Charsets.US_ASCII)
     val path = tempDir.toURI.toString
@@ -90,7 +92,7 @@ class MLUtilsSuite extends FunSuite with LocalSparkContext {
     assert(multiclassPoints(1).label === -1.0)
     assert(multiclassPoints(2).label === -1.0)
 
-    deleteQuietly(tempDir)
+    Utils.deleteRecursively(tempDir)
   }
 
   test("saveAsLibSVMFile") {
@@ -107,7 +109,7 @@ class MLUtilsSuite extends FunSuite with LocalSparkContext {
       .toSet
     val expected = Set("1.1 1:1.23 3:4.56", "0.0 1:1.01 2:2.02 3:3.03")
     assert(lines === expected)
-    deleteQuietly(tempDir)
+    Utils.deleteRecursively(tempDir)
   }
 
   test("appendBias") {
@@ -158,16 +160,5 @@ class MLUtilsSuite extends FunSuite with LocalSparkContext {
     }
   }
 
-  /** Delete a file/directory quietly. */
-  def deleteQuietly(f: File) {
-    if (f.isDirectory) {
-      f.listFiles().foreach(deleteQuietly)
-    }
-    try {
-      f.delete()
-    } catch {
-      case _: Throwable =>
-    }
-  }
 }