Github user pwendell commented on a diff in the pull request:
https://github.com/apache/spark/pull/204#discussion_r11469526
--- Diff:
core/src/main/scala/org/apache/spark/deploy/history/HistoryServerArguments.scala
---
@@ -0,0 +1,72 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.deploy.history
+
+import java.net.URI
+
+import org.apache.hadoop.fs.Path
+
+import org.apache.spark.util.Utils
+
+/**
+ * Command-line parser for the master.
+ */
+private[spark] class HistoryServerArguments(args: Array[String]) {
+ var logDir = ""
+
+ parse(args.toList)
+
+ private def parse(args: List[String]): Unit = {
+ args match {
+ case ("--dir" | "-d") :: value :: tail =>
+ logDir = value
+ parse(tail)
+
+ case ("--help" | "-h") :: tail =>
+ printUsageAndExit(0)
+
+ case Nil =>
+
+ case _ =>
+ printUsageAndExit(1)
+ }
+ validateLogDir()
+ }
+
+ private def validateLogDir() {
+ if (logDir == "") {
+ System.err.println("Logging directory must be specified.")
+ printUsageAndExit(1)
+ }
+ val fileSystem = Utils.getHadoopFileSystem(new URI(logDir))
+ val path = new Path(logDir)
+ if (!fileSystem.exists(path) || !fileSystem.getFileStatus(path).isDir)
{
+ System.err.println("Logging directory specified is invalid:
%s".format(logDir))
--- End diff --
Very minor - but I'm guessing the first error condition will happen way
more often than the second - and getting a message that says it's "invalid" is
a lot less clear than just saying it doesn't exist. What about breaking these
out and including more specific error messages in either case? Also it might be
nice to print the value of `fileSystem` in the error message, so it knows what
filesystem we inferred the path to be from.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
