diff options
| -rwxr-xr-x | bin/compute-classpath.sh | 22 | ||||
| -rw-r--r-- | project/SparkBuild.scala | 13 |
2 files changed, 28 insertions, 7 deletions
diff --git a/bin/compute-classpath.sh b/bin/compute-classpath.sh index c7819d4932..c16afd6b36 100755 --- a/bin/compute-classpath.sh +++ b/bin/compute-classpath.sh @@ -32,12 +32,26 @@ fi # Build up classpath CLASSPATH="$SPARK_CLASSPATH:$FWDIR/conf" -if [ -f "$FWDIR/RELEASE" ]; then - ASSEMBLY_JAR=`ls "$FWDIR"/jars/spark-assembly*.jar` + +# First check if we have a dependencies jar. If so, include binary classes with the deps jar +if [ -f "$FWDIR"/assembly/target/scala-$SCALA_VERSION/spark-assembly*hadoop*-deps.jar ]; then + CLASSPATH="$CLASSPATH:$FWDIR/core/target/scala-$SCALA_VERSION/classes" + CLASSPATH="$CLASSPATH:$FWDIR/repl/target/scala-$SCALA_VERSION/classes" + CLASSPATH="$CLASSPATH:$FWDIR/mllib/target/scala-$SCALA_VERSION/classes" + CLASSPATH="$CLASSPATH:$FWDIR/bagel/target/scala-$SCALA_VERSION/classes" + CLASSPATH="$CLASSPATH:$FWDIR/streaming/target/scala-$SCALA_VERSION/classes" + + DEPS_ASSEMBLY_JAR=`ls "$FWDIR"/assembly/target/scala-$SCALA_VERSION/spark-assembly*hadoop*-deps.jar` + CLASSPATH="$CLASSPATH:$DEPS_ASSEMBLY_JAR" else - ASSEMBLY_JAR=`ls "$FWDIR"/assembly/target/scala-$SCALA_VERSION/spark-assembly*hadoop*.jar` + # Else use spark-assembly jar from either RELEASE or assembly directory + if [ -f "$FWDIR/RELEASE" ]; then + ASSEMBLY_JAR=`ls "$FWDIR"/jars/spark-assembly*.jar` + else + ASSEMBLY_JAR=`ls "$FWDIR"/assembly/target/scala-$SCALA_VERSION/spark-assembly*hadoop*.jar` + fi + CLASSPATH="$CLASSPATH:$ASSEMBLY_JAR" fi -CLASSPATH="$CLASSPATH:$ASSEMBLY_JAR" # Add test classes if we're running from SBT or Maven with SPARK_TESTING set to 1 if [[ $SPARK_TESTING == 1 ]]; then diff --git a/project/SparkBuild.scala b/project/SparkBuild.scala index f2bbe5358f..965c4f3a63 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", @@ -303,7 +308,9 @@ 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( |