Merging latest changes from spark main branch

4 files changed, 123 insertions, 74 deletions

diff --git a/project/SparkBuild.scala b/project/SparkBuild.scala
index cea6c11371..7598060cb9 100644
--- a/project/SparkBuild.scala
+++ b/project/SparkBuild.scala
@@ -24,49 +24,68 @@ import AssemblyKeys._
 //import com.jsuereth.pgp.sbtplugin.PgpKeys._
 
 object SparkBuild extends Build {
-  // Hadoop version to build against. For example, "0.20.2", "0.20.205.0", or
-  // "1.0.4" for Apache releases, or "0.20.2-cdh3u5" for Cloudera Hadoop.
-  val HADOOP_VERSION = "1.0.4"
-  val HADOOP_MAJOR_VERSION = "1"
-  val HADOOP_YARN = false
+  // Hadoop version to build against. For example, "1.0.4" for Apache releases, or
+  // "2.0.0-mr1-cdh4.2.0" for Cloudera Hadoop. Note that these variables can be set
+  // through the environment variables SPARK_HADOOP_VERSION and SPARK_YARN.
+  val DEFAULT_HADOOP_VERSION = "1.0.4"
+  val DEFAULT_YARN = false
 
-  // For Hadoop 2 versions such as "2.0.0-mr1-cdh4.1.1", set the HADOOP_MAJOR_VERSION to "2"
-  //val HADOOP_VERSION = "2.0.0-mr1-cdh4.1.1"
-  //val HADOOP_MAJOR_VERSION = "2"
-  //val HADOOP_YARN = false
+  // HBase version; set as appropriate.
+  val HBASE_VERSION = "0.94.6"
 
-  // For Hadoop 2 YARN support
-  //val HADOOP_VERSION = "2.0.2-alpha"
-  //val HADOOP_MAJOR_VERSION = "2"
-  //val HADOOP_YARN = true
+  // Target JVM version
+  val SCALAC_JVM_VERSION = "jvm-1.5"
+  val JAVAC_JVM_VERSION = "1.5"
 
-  lazy val root = Project("root", file("."), settings = rootSettings) aggregate(core, repl, examples, bagel, graph, streaming, mllib, tools)
+  lazy val root = Project("root", file("."), settings = rootSettings) aggregate(allProjects: _*)
 
   lazy val core = Project("core", file("core"), settings = coreSettings)
 
-  lazy val repl = Project("repl", file("repl"), settings = replSettings) dependsOn (core) dependsOn(bagel) dependsOn(mllib)
+  lazy val repl = Project("repl", file("repl"), settings = replSettings)
+    .dependsOn(core, bagel, mllib)
 
-  lazy val examples = Project("examples", file("examples"), settings = examplesSettings) dependsOn (core) dependsOn (streaming)
+  lazy val examples = Project("examples", file("examples"), settings = examplesSettings)
+    .dependsOn(core, mllib, bagel, streaming)
 
-  lazy val tools = Project("tools", file("tools"), settings = examplesSettings) dependsOn (core) dependsOn (streaming)
+  lazy val tools = Project("tools", file("tools"), settings = toolsSettings) dependsOn(core) dependsOn(streaming)
 
-  lazy val bagel = Project("bagel", file("bagel"), settings = bagelSettings) dependsOn (core)
+  lazy val bagel = Project("bagel", file("bagel"), settings = bagelSettings) dependsOn(core)
 
-  lazy val graph = Project("graph", file("graph"), settings = graphSettings) dependsOn (core, bagel)
+  lazy val graph = Project("graph", file("graph"), settings = graphSettings) dependsOn(core)
 
-  lazy val streaming = Project("streaming", file("streaming"), settings = streamingSettings) dependsOn (core)
+  lazy val streaming = Project("streaming", file("streaming"), settings = streamingSettings) dependsOn(core)
 
-  lazy val mllib = Project("mllib", file("mllib"), settings = mllibSettings) dependsOn (core)
+  lazy val mllib = Project("mllib", file("mllib"), settings = mllibSettings) dependsOn(core)
+
+  lazy val yarn = Project("yarn", file("yarn"), settings = yarnSettings) dependsOn(core)
+
+  lazy val assemblyProj = Project("assembly", file("assembly"), settings = assemblyProjSettings)
+    .dependsOn(core, bagel, mllib, repl, streaming) dependsOn(maybeYarn: _*)
 
   // A configuration to set an alternative publishLocalConfiguration
   lazy val MavenCompile = config("m2r") extend(Compile)
   lazy val publishLocalBoth = TaskKey[Unit]("publish-local", "publish local for m2 and ivy")
 
+  // Allows build configuration to be set through environment variables
+  lazy val hadoopVersion = scala.util.Properties.envOrElse("SPARK_HADOOP_VERSION", DEFAULT_HADOOP_VERSION)
+  lazy val isYarnEnabled = scala.util.Properties.envOrNone("SPARK_YARN") match {
+    case None => DEFAULT_YARN
+    case Some(v) => v.toBoolean
+  }
+
+  // Conditionally include the yarn sub-project
+  lazy val maybeYarn = if(isYarnEnabled) Seq[ClasspathDependency](yarn) else Seq[ClasspathDependency]()
+  lazy val maybeYarnRef = if(isYarnEnabled) Seq[ProjectReference](yarn) else Seq[ProjectReference]()
+  lazy val allProjects = Seq[ProjectReference](
+    core, repl, examples, bagel, streaming, mllib, tools, assemblyProj) ++ maybeYarnRef
+
   def sharedSettings = Defaults.defaultSettings ++ Seq(
-    organization := "org.spark-project",
+    organization := "org.apache.spark",
     version := "0.8.0-SNAPSHOT",
     scalaVersion := "2.9.3",
-    scalacOptions := Seq("-unchecked", "-optimize", "-deprecation"),
+    scalacOptions := Seq("-unchecked", "-optimize", "-deprecation", 
+      "-target:" + SCALAC_JVM_VERSION),
+    javacOptions := Seq("-target", JAVAC_JVM_VERSION, "-source", JAVAC_JVM_VERSION),
     unmanagedJars in Compile <<= baseDirectory map { base => (base / "lib" ** "*.jar").classpath },
     retrieveManaged := true,
     retrievePattern := "[type]s/[artifact](-[revision])(-[classifier]).[ext]",
@@ -75,7 +94,7 @@ object SparkBuild extends Build {
 
     // Fork new JVMs for tests and set Java options for those
     fork := true,
-    javaOptions += "-Xmx2500m",
+    javaOptions += "-Xmx3g",
 
     // Only allow one test at a time, even across projects, since they run in the same JVM
     concurrentRestrictions in Global += Tags.limit(Tags.Test, 1),
@@ -92,17 +111,22 @@ object SparkBuild extends Build {
     //useGpg in Global := true,
 
     pomExtra := (
-      <url>http://spark-project.org/</url>
+      <parent>
+        <groupId>org.apache</groupId>
+        <artifactId>apache</artifactId>
+        <version>13</version>
+      </parent>
+      <url>http://spark.incubator.apache.org/</url>
       <licenses>
         <license>
-          <name>BSD License</name>
-          <url>https://github.com/mesos/spark/blob/master/LICENSE</url>
+          <name>Apache 2.0 License</name>
+          <url>http://www.apache.org/licenses/LICENSE-2.0.html</url>
           <distribution>repo</distribution>
         </license>
       </licenses>
       <scm>
-        <connection>scm:git:git@github.com:mesos/spark.git</connection>
-        <url>scm:git:git@github.com:mesos/spark.git</url>
+        <connection>scm:git:git@github.com:apache/incubator-spark.git</connection>
+        <url>scm:git:git@github.com:apache/incubator-spark.git</url>
       </scm>
       <developers>
         <developer>
@@ -110,10 +134,14 @@ object SparkBuild extends Build {
           <name>Matei Zaharia</name>
           <email>matei.zaharia@gmail.com</email>
           <url>http://www.cs.berkeley.edu/~matei</url>
-          <organization>U.C. Berkeley Computer Science</organization>
-          <organizationUrl>http://www.cs.berkeley.edu/</organizationUrl>
+          <organization>Apache Software Foundation</organization>
+          <organizationUrl>http://spark.incubator.apache.org</organizationUrl>
         </developer>
       </developers>
+      <issueManagement>
+        <system>JIRA</system>
+        <url>https://spark-project.atlassian.net/browse/SPARK</url>
+      </issueManagement>
     ),
 
 /*
@@ -128,7 +156,6 @@ object SparkBuild extends Build {
 */
 
     libraryDependencies ++= Seq(
-      "io.netty" % "netty" % "3.5.3.Final",
       "org.eclipse.jetty" % "jetty-server" % "7.6.8.v20121106",
       "org.scalatest" %% "scalatest" % "1.9.1" % "test",
       "org.scalacheck" %% "scalacheck" % "1.10.0" % "test",
@@ -159,17 +186,16 @@ object SparkBuild extends Build {
     name := "spark-core",
     resolvers ++= Seq(
       "JBoss Repository" at "http://repository.jboss.org/nexus/content/repositories/releases/",
-      "Spray Repository" at "http://repo.spray.cc/",
       "Cloudera Repository" at "https://repository.cloudera.com/artifactory/cloudera-repos/"
     ),
 
     libraryDependencies ++= Seq(
       "com.google.guava" % "guava" % "14.0.1",
       "com.google.code.findbugs" % "jsr305" % "1.3.9",
-      "log4j" % "log4j" % "1.2.16",
+      "log4j" % "log4j" % "1.2.17",
       "org.slf4j" % "slf4j-api" % slf4jVersion,
       "org.slf4j" % "slf4j-log4j12" % slf4jVersion,
-      "commons-daemon" % "commons-daemon" % "1.0.10",
+      "commons-daemon" % "commons-daemon" % "1.0.10",  // workaround for bug HADOOP-9407
       "com.ning" % "compress-lzf" % "0.8.4",
       "org.xerial.snappy" % "snappy-java" % "1.0.5",
       "org.ow2.asm" % "asm" % "4.0",
@@ -180,40 +206,21 @@ object SparkBuild extends Build {
       "it.unimi.dsi" % "fastutil" % "6.4.4",
       "colt" % "colt" % "1.2.0",
       "net.liftweb" % "lift-json_2.9.2" % "2.5",
-      "org.apache.mesos" % "mesos" % "0.9.0-incubating",
+      "org.apache.mesos" % "mesos" % "0.13.0",
       "io.netty" % "netty-all" % "4.0.0.Beta2",
       "org.apache.derby" % "derby" % "10.4.2.0" % "test",
+      "org.apache.hadoop" % "hadoop-client" % hadoopVersion excludeAll(excludeJackson, excludeNetty, excludeAsm),
+      "net.java.dev.jets3t" % "jets3t" % "0.7.1",
+      "org.apache.avro" % "avro" % "1.7.4",
+      "org.apache.avro" % "avro-ipc" % "1.7.4" excludeAll(excludeNetty),
       "com.codahale.metrics" % "metrics-core" % "3.0.0",
       "com.codahale.metrics" % "metrics-jvm" % "3.0.0",
-      "com.twitter" % "chill_2.9.3" % "0.3.0",
-      "com.twitter" % "chill-java" % "0.3.0"
-    ) ++ (
-      if (HADOOP_MAJOR_VERSION == "2") {
-        if (HADOOP_YARN) {
-          Seq(
-            // Exclude rule required for all ?
-            "org.apache.hadoop" % "hadoop-client" % HADOOP_VERSION excludeAll(excludeJackson, excludeNetty, excludeAsm),
-            "org.apache.hadoop" % "hadoop-yarn-api" % HADOOP_VERSION excludeAll(excludeJackson, excludeNetty, excludeAsm),
-            "org.apache.hadoop" % "hadoop-yarn-common" % HADOOP_VERSION excludeAll(excludeJackson, excludeNetty, excludeAsm),
-            "org.apache.hadoop" % "hadoop-yarn-client" % HADOOP_VERSION excludeAll(excludeJackson, excludeNetty, excludeAsm)
-          )
-        } else {
-          Seq(
-            "org.apache.hadoop" % "hadoop-core" % HADOOP_VERSION excludeAll(excludeJackson, excludeNetty, excludeAsm),
-            "org.apache.hadoop" % "hadoop-client" % HADOOP_VERSION excludeAll(excludeJackson, excludeNetty, excludeAsm)
-          )
-        }
-      } else {
-        Seq("org.apache.hadoop" % "hadoop-core" % HADOOP_VERSION excludeAll(excludeJackson, excludeNetty) )
-      }),
-    unmanagedSourceDirectories in Compile <+= baseDirectory{ _ /
-      ( if (HADOOP_YARN && HADOOP_MAJOR_VERSION == "2") {
-        "src/hadoop2-yarn/scala"
-      } else {
-        "src/hadoop" + HADOOP_MAJOR_VERSION + "/scala"
-      } )
-    }
-  ) ++ assemblySettings ++ extraAssemblySettings
+      "com.codahale.metrics" % "metrics-json" % "3.0.0",
+      "com.codahale.metrics" % "metrics-ganglia" % "3.0.0",
+      "com.twitter" % "chill_2.9.3" % "0.3.1",
+      "com.twitter" % "chill-java" % "0.3.1"
+    )
+  )
 
   def rootSettings = sharedSettings ++ Seq(
     publish := {}
@@ -222,14 +229,14 @@ object SparkBuild extends Build {
   def replSettings = sharedSettings ++ Seq(
     name := "spark-repl",
     libraryDependencies <+= scalaVersion("org.scala-lang" % "scala-compiler" % _)
-  ) ++ assemblySettings ++ extraAssemblySettings
+  )
 
   def examplesSettings = sharedSettings ++ Seq(
     name := "spark-examples",
     libraryDependencies ++= Seq(
       "com.twitter" % "algebird-core_2.9.2" % "0.1.11",
 
-      "org.apache.hbase" % "hbase" % "0.94.6" excludeAll(excludeNetty, excludeAsm),
+      "org.apache.hbase" % "hbase" % HBASE_VERSION excludeAll(excludeNetty, excludeAsm),
 
       "org.apache.cassandra" % "cassandra-all" % "1.2.5"
         exclude("com.google.guava", "guava")
@@ -241,7 +248,7 @@ object SparkBuild extends Build {
         exclude("org.apache.cassandra.deps", "avro")
         excludeAll(excludeSnappy)
     )
-  )
+  ) ++ assemblySettings ++ extraAssemblySettings
 
   def toolsSettings = sharedSettings ++ Seq(
     name := "spark-tools"
@@ -271,12 +278,37 @@ object SparkBuild extends Build {
       "org.twitter4j" % "twitter4j-stream" % "3.0.3" excludeAll(excludeNetty),
       "com.typesafe.akka" % "akka-zeromq" % "2.0.5" excludeAll(excludeNetty)
     )
+  )
+
+  def yarnSettings = sharedSettings ++ Seq(
+    name := "spark-yarn"
+  ) ++ extraYarnSettings
+
+  // Conditionally include the YARN dependencies because some tools look at all sub-projects and will complain
+  // if we refer to nonexistent dependencies (e.g. hadoop-yarn-api from a Hadoop version without YARN).
+  def extraYarnSettings = if(isYarnEnabled) yarnEnabledSettings else Seq()
+
+  def yarnEnabledSettings = Seq(
+    libraryDependencies ++= Seq(
+      // Exclude rule required for all ?
+      "org.apache.hadoop" % "hadoop-client" % hadoopVersion excludeAll(excludeJackson, excludeNetty, excludeAsm),
+      "org.apache.hadoop" % "hadoop-yarn-api" % hadoopVersion excludeAll(excludeJackson, excludeNetty, excludeAsm),
+      "org.apache.hadoop" % "hadoop-yarn-common" % hadoopVersion excludeAll(excludeJackson, excludeNetty, excludeAsm),
+      "org.apache.hadoop" % "hadoop-yarn-client" % hadoopVersion excludeAll(excludeJackson, excludeNetty, excludeAsm)
+    )
+  )
+
+  def assemblyProjSettings = sharedSettings ++ Seq(
+    name := "spark-assembly",
+    jarName in assembly <<= version map { v => "spark-assembly-" + v + "-hadoop" + hadoopVersion + ".jar" }
   ) ++ assemblySettings ++ extraAssemblySettings
 
-  def extraAssemblySettings() = Seq(test in assembly := {}) ++ Seq(
+  def extraAssemblySettings() = Seq(
+    test in assembly := {},
     mergeStrategy in assembly := {
       case m if m.toLowerCase.endsWith("manifest.mf") => MergeStrategy.discard
       case m if m.toLowerCase.matches("meta-inf.*\\.sf$") => MergeStrategy.discard
+      case "META-INF/services/org.apache.hadoop.fs.FileSystem" => MergeStrategy.concat
       case "reference.conf" => MergeStrategy.concat
       case _ => MergeStrategy.first
     }
diff --git a/project/build.properties b/project/build.properties
index 08e17131f6..9647277162 100644
--- a/project/build.properties
+++ b/project/build.properties
@@ -15,4 +15,4 @@
 # limitations under the License.
 #
 
-sbt.version=0.12.3
+sbt.version=0.12.4
diff --git a/project/plugins.sbt b/project/plugins.sbt
index 1b0f879b94..cfcd85082a 100644
--- a/project/plugins.sbt
+++ b/project/plugins.sbt
@@ -4,11 +4,11 @@ resolvers += "Typesafe Repository" at "http://repo.typesafe.com/typesafe/release
 
 resolvers += "Spray Repository" at "http://repo.spray.cc/"
 
-addSbtPlugin("com.eed3si9n" % "sbt-assembly" % "0.8.5")
+addSbtPlugin("com.eed3si9n" % "sbt-assembly" % "0.9.1")
 
-addSbtPlugin("com.typesafe.sbteclipse" % "sbteclipse-plugin" % "2.1.1")
+addSbtPlugin("com.typesafe.sbteclipse" % "sbteclipse-plugin" % "2.2.0")
 
-addSbtPlugin("com.github.mpeltonen" % "sbt-idea" % "1.2.0")
+addSbtPlugin("com.github.mpeltonen" % "sbt-idea" % "1.5.1")
 
 // For Sonatype publishing
 //resolvers += Resolver.url("sbt-plugin-releases", new URL("http://scalasbt.artifactoryonline.com/scalasbt/sbt-plugin-releases/"))(Resolver.ivyStylePatterns)
diff --git a/project/project/SparkPluginBuild.scala b/project/project/SparkPluginBuild.scala
index 999611982a..6a66bd1d06 100644
--- a/project/project/SparkPluginBuild.scala
+++ b/project/project/SparkPluginBuild.scala
@@ -1,7 +1,24 @@
+/*
+ * 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.
+ */
+
 import sbt._
 
 object SparkPluginDef extends Build {
   lazy val root = Project("plugins", file(".")) dependsOn(junitXmlListener)
   /* This is not published in a Maven repository, so we get it from GitHub directly */
   lazy val junitXmlListener = uri("git://github.com/ijuma/junit_xml_listener.git#fe434773255b451a38e8d889536ebc260f4225ce")
-}
\ No newline at end of file
+}