diff options
Diffstat (limited to 'project/SparkBuild.scala')
| -rw-r--r-- | project/SparkBuild.scala | 35 |
1 files changed, 30 insertions, 5 deletions
diff --git a/project/SparkBuild.scala b/project/SparkBuild.scala index 43db97f680..b71e1b3a56 100644 --- a/project/SparkBuild.scala +++ b/project/SparkBuild.scala @@ -60,6 +60,8 @@ object SparkBuild extends Build { lazy val assemblyProj = Project("assembly", file("assembly"), settings = assemblyProjSettings) .dependsOn(core, bagel, mllib, repl, streaming) dependsOn(maybeYarn: _*) + lazy val assembleDeps = TaskKey[Unit]("assemble-deps", "Build assembly of dependencies and packages Spark projects") + // 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") @@ -74,8 +76,11 @@ object SparkBuild extends Build { // 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 + + // Everything except assembly, tools and examples belong to packageProjects + lazy val packageProjects = Seq[ProjectReference](core, repl, bagel, streaming, mllib) ++ maybeYarnRef + + lazy val allProjects = packageProjects ++ Seq[ProjectReference](examples, tools, assemblyProj) def sharedSettings = Defaults.defaultSettings ++ Seq( organization := "org.apache.spark", @@ -100,7 +105,13 @@ object SparkBuild extends Build { // also check the local Maven repository ~/.m2 resolvers ++= Seq(Resolver.file("Local Maven Repo", file(Path.userHome + "/.m2/repository"))), - // For Sonatype publishing + // Shared between both core and streaming. + resolvers ++= Seq("Akka Repository" at "http://repo.akka.io/releases/"), + + // Shared between both examples and streaming. + resolvers ++= Seq("Mqtt Repository" at "https://repo.eclipse.org/content/repositories/paho-releases/"), + + // For Sonatype publishing resolvers ++= Seq("sonatype-snapshots" at "https://oss.sonatype.org/content/repositories/snapshots", "sonatype-staging" at "https://oss.sonatype.org/service/local/staging/deploy/maven2/"), @@ -212,7 +223,7 @@ object SparkBuild extends Build { "org.apache.mesos" % "mesos" % "0.13.0", "net.java.dev.jets3t" % "jets3t" % "0.7.1", "org.apache.derby" % "derby" % "10.4.2.0" % "test", - "org.apache.hadoop" % "hadoop-client" % hadoopVersion excludeAll(excludeJackson, excludeNetty, excludeAsm), + "org.apache.hadoop" % "hadoop-client" % hadoopVersion excludeAll(excludeJackson, excludeNetty, excludeAsm, excludeCglib), "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", @@ -272,8 +283,19 @@ object SparkBuild extends Build { def streamingSettings = sharedSettings ++ Seq( name := "spark-streaming", + resolvers ++= Seq( + "Akka Repository" at "http://repo.akka.io/releases/", + "Apache repo" at "https://repository.apache.org/content/repositories/releases" + ), + libraryDependencies ++= Seq( "org.apache.flume" % "flume-ng-sdk" % "1.2.0" % "compile" excludeAll(excludeNetty, excludeSnappy), + "com.sksamuel.kafka" %% "kafka" % "0.8.0-beta1" + exclude("com.sun.jdmk", "jmxtools") + exclude("com.sun.jmx", "jmxri") + exclude("net.sf.jopt-simple", "jopt-simple") + excludeAll(excludeNetty), + "org.eclipse.paho" % "mqtt-client" % "0.4.0", "com.github.sgroschupf" % "zkclient" % "0.1" excludeAll(excludeNetty), "org.twitter4j" % "twitter4j-stream" % "3.0.3" excludeAll(excludeNetty), "com.typesafe.akka" %% "akka-zeromq" % "2.2.3" excludeAll(excludeNetty) @@ -300,7 +322,9 @@ object SparkBuild extends Build { def assemblyProjSettings = sharedSettings ++ Seq( name := "spark-assembly", - jarName in assembly <<= version map { v => "spark-assembly-" + v + "-hadoop" + hadoopVersion + ".jar" } + assembleDeps in Compile <<= (packageProjects.map(packageBin in Compile in _) ++ Seq(packageDependency in Compile)).dependOn, + jarName in assembly <<= version map { v => "spark-assembly-" + v + "-hadoop" + hadoopVersion + ".jar" }, + jarName in packageDependency <<= version map { v => "spark-assembly-" + v + "-hadoop" + hadoopVersion + "-deps.jar" } ) ++ assemblySettings ++ extraAssemblySettings def extraAssemblySettings() = Seq( @@ -308,6 +332,7 @@ object SparkBuild extends Build { 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 "log4j.properties" => MergeStrategy.discard case "META-INF/services/org.apache.hadoop.fs.FileSystem" => MergeStrategy.concat case "reference.conf" => MergeStrategy.concat case _ => MergeStrategy.first |