Repository: spark Updated Branches: refs/heads/master 90d72ec85 -> bfebfd8b2
[SPARK-4075][SPARK-4434] Fix the URI validation logic for Application Jar name. This PR adds a regression test for SPARK-4434. Author: Kousuke Saruta <[email protected]> Closes #3326 from sarutak/add-triple-slash-testcase and squashes the following commits: 82bc9cc [Kousuke Saruta] Fixed wrong grammar in comment 9149027 [Kousuke Saruta] Merge branch 'master' of git://git.apache.org/spark into add-triple-slash-testcase c1c80ca [Kousuke Saruta] Fixed style 4f30210 [Kousuke Saruta] Modified comments 9e09da2 [Kousuke Saruta] Fixed URI validation for jar file d4b99ef [Kousuke Saruta] [SPARK-4075] [Deploy] Jar url validation is not enough for Jar file ac79906 [Kousuke Saruta] Merge branch 'master' of git://git.apache.org/spark into add-triple-slash-testcase 6d4f47e [Kousuke Saruta] Added a test case as a regression check for SPARK-4434 Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/bfebfd8b Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/bfebfd8b Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/bfebfd8b Branch: refs/heads/master Commit: bfebfd8b28eeb7e75292333f7885aa0830fcb5fe Parents: 90d72ec Author: Kousuke Saruta <[email protected]> Authored: Tue Nov 18 12:17:33 2014 -0800 Committer: Andrew Or <[email protected]> Committed: Tue Nov 18 12:17:33 2014 -0800 ---------------------------------------------------------------------- .../org/apache/spark/deploy/ClientArguments.scala | 14 ++++++++++++-- .../org/apache/spark/deploy/ClientSuite.scala | 17 ++++++++++++++++- 2 files changed, 28 insertions(+), 3 deletions(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/spark/blob/bfebfd8b/core/src/main/scala/org/apache/spark/deploy/ClientArguments.scala ---------------------------------------------------------------------- diff --git a/core/src/main/scala/org/apache/spark/deploy/ClientArguments.scala b/core/src/main/scala/org/apache/spark/deploy/ClientArguments.scala index 39150de..2e1e529 100644 --- a/core/src/main/scala/org/apache/spark/deploy/ClientArguments.scala +++ b/core/src/main/scala/org/apache/spark/deploy/ClientArguments.scala @@ -17,6 +17,8 @@ package org.apache.spark.deploy +import java.net.{URI, URISyntaxException} + import scala.collection.mutable.ListBuffer import org.apache.log4j.Level @@ -73,7 +75,8 @@ private[spark] class ClientArguments(args: Array[String]) { if (!ClientArguments.isValidJarUrl(_jarUrl)) { println(s"Jar url '${_jarUrl}' is not in valid format.") - println(s"Must be a jar file path in URL format (e.g. hdfs://XX.jar, file://XX.jar)") + println(s"Must be a jar file path in URL format " + + "(e.g. hdfs://host:port/XX.jar, file:///XX.jar)") printUsageAndExit(-1) } @@ -114,5 +117,12 @@ private[spark] class ClientArguments(args: Array[String]) { } object ClientArguments { - def isValidJarUrl(s: String): Boolean = s.matches("(.+):(.+)jar") + def isValidJarUrl(s: String): Boolean = { + try { + val uri = new URI(s) + uri.getScheme != null && uri.getPath != null && uri.getPath.endsWith(".jar") + } catch { + case _: URISyntaxException => false + } + } } http://git-wip-us.apache.org/repos/asf/spark/blob/bfebfd8b/core/src/test/scala/org/apache/spark/deploy/ClientSuite.scala ---------------------------------------------------------------------- diff --git a/core/src/test/scala/org/apache/spark/deploy/ClientSuite.scala b/core/src/test/scala/org/apache/spark/deploy/ClientSuite.scala index 4161aed..d2dae34 100644 --- a/core/src/test/scala/org/apache/spark/deploy/ClientSuite.scala +++ b/core/src/test/scala/org/apache/spark/deploy/ClientSuite.scala @@ -23,12 +23,27 @@ import org.scalatest.Matchers class ClientSuite extends FunSuite with Matchers { test("correctly validates driver jar URL's") { ClientArguments.isValidJarUrl("http://someHost:8080/foo.jar";) should be (true) - ClientArguments.isValidJarUrl("file://some/path/to/a/jarFile.jar") should be (true) + + // file scheme with authority and path is valid. + ClientArguments.isValidJarUrl("file://somehost/path/to/a/jarFile.jar") should be (true) + + // file scheme without path is not valid. + // In this case, jarFile.jar is recognized as authority. + ClientArguments.isValidJarUrl("file://jarFile.jar") should be (false) + + // file scheme without authority but with triple slash is valid. + ClientArguments.isValidJarUrl("file:///some/path/to/a/jarFile.jar") should be (true) ClientArguments.isValidJarUrl("hdfs://someHost:1234/foo.jar") should be (true) ClientArguments.isValidJarUrl("hdfs://someHost:1234/foo") should be (false) ClientArguments.isValidJarUrl("/missing/a/protocol/jarfile.jar") should be (false) ClientArguments.isValidJarUrl("not-even-a-path.jar") should be (false) + + // This URI doesn't have authority and path. + ClientArguments.isValidJarUrl("hdfs:someHost:1234/jarfile.jar") should be (false) + + // Invalid syntax. + ClientArguments.isValidJarUrl("hdfs:") should be (false) } } --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
