[SPARK-10858] YARN: archives/jar/files rename with # doesn't work unl

https://issues.apache.org/jira/browse/SPARK-10858

The issue here is that in resolveURI we default to calling new File(path).getAbsoluteFile().toURI().  But if the path passed in already has a # in it then File(path) will think that is supposed to be part of the actual file path and not a fragment so it changes # to %23. Then when we try to parse that  later in Client as a URI it doesn't recognize there is a fragment.

so to fix we just check if there is a fragment, still create the File like we did before and then add the fragment back on.

Author: Tom Graves <tgraves@yahoo-inc.com>

Closes #9035 from tgravescs/SPARK-10858.

2 files changed, 10 insertions, 3 deletions

diff --git a/core/src/main/scala/org/apache/spark/util/Utils.scala b/core/src/main/scala/org/apache/spark/util/Utils.scala
index 2bab4af2e7..e60c1b355a 100644
--- a/core/src/main/scala/org/apache/spark/util/Utils.scala
+++ b/core/src/main/scala/org/apache/spark/util/Utils.scala
@@ -1749,6 +1749,13 @@ private[spark] object Utils extends Logging {
       if (uri.getScheme() != null) {
         return uri
       }
+      // make sure to handle if the path has a fragment (applies to yarn
+      // distributed cache)
+      if (uri.getFragment() != null) {
+        val absoluteURI = new File(uri.getPath()).getAbsoluteFile().toURI()
+        return new URI(absoluteURI.getScheme(), absoluteURI.getHost(), absoluteURI.getPath(),
+          uri.getFragment())
+      }
     } catch {
       case e: URISyntaxException =>
     }
diff --git a/core/src/test/scala/org/apache/spark/util/UtilsSuite.scala b/core/src/test/scala/org/apache/spark/util/UtilsSuite.scala
index 1fb81ad565..68b0da76bc 100644
--- a/core/src/test/scala/org/apache/spark/util/UtilsSuite.scala
+++ b/core/src/test/scala/org/apache/spark/util/UtilsSuite.scala
@@ -384,7 +384,7 @@ class UtilsSuite extends SparkFunSuite with ResetSystemProperties with Logging {
     assertResolves("hdfs:/root/spark.jar", "hdfs:/root/spark.jar")
     assertResolves("hdfs:///root/spark.jar#app.jar", "hdfs:/root/spark.jar#app.jar")
     assertResolves("spark.jar", s"file:$cwd/spark.jar")
-    assertResolves("spark.jar#app.jar", s"file:$cwd/spark.jar%23app.jar")
+    assertResolves("spark.jar#app.jar", s"file:$cwd/spark.jar#app.jar")
     assertResolves("path to/file.txt", s"file:$cwd/path%20to/file.txt")
     if (Utils.isWindows) {
       assertResolves("C:\\path\\to\\file.txt", "file:/C:/path/to/file.txt")
@@ -414,10 +414,10 @@ class UtilsSuite extends SparkFunSuite with ResetSystemProperties with Logging {
     assertResolves("file:/jar1,file:/jar2", "file:/jar1,file:/jar2")
     assertResolves("hdfs:/jar1,file:/jar2,jar3", s"hdfs:/jar1,file:/jar2,file:$cwd/jar3")
     assertResolves("hdfs:/jar1,file:/jar2,jar3,jar4#jar5,path to/jar6",
-      s"hdfs:/jar1,file:/jar2,file:$cwd/jar3,file:$cwd/jar4%23jar5,file:$cwd/path%20to/jar6")
+      s"hdfs:/jar1,file:/jar2,file:$cwd/jar3,file:$cwd/jar4#jar5,file:$cwd/path%20to/jar6")
     if (Utils.isWindows) {
       assertResolves("""hdfs:/jar1,file:/jar2,jar3,C:\pi.py#py.pi,C:\path to\jar4""",
-        s"hdfs:/jar1,file:/jar2,file:$cwd/jar3,file:/C:/pi.py%23py.pi,file:/C:/path%20to/jar4")
+        s"hdfs:/jar1,file:/jar2,file:$cwd/jar3,file:/C:/pi.py#py.pi,file:/C:/path%20to/jar4")
     }
   }