SPARK-1184: Update the distribution tar.gz to include spark-assembly jar

Author: markgrover

assembly/pom.xml

@@ -29,9 +29,12 @@
   <artifactId>spark-assembly_2.10</artifactId>
   <name>Spark Project Assembly</name>
   <url>http://spark.apache.org/</url>
+  <packaging>pom</packaging>
 
   <properties>
-    <spark.jar>${project.build.directory}/scala-${scala.binary.version}/${project.artifactId}-${project.version}-hadoop${hadoop.version}.jar</spark.jar>
+    <spark.jar.dir>scala-${scala.binary.version}</spark.jar.dir>
+    <spark.jar.basename>${project.artifactId}-${project.version}-hadoop${hadoop.version}.jar</spark.jar.basename>
+    <spark.jar>${project.build.directory}/${spark.jar.dir}/${spark.jar.basename}</spark.jar>
     <deb.pkg.name>spark</deb.pkg.name>
     <deb.install.path>/usr/share/spark</deb.install.path>
     <deb.user>root</deb.user>

assembly/src/main/assembly/assembly.xml

@@ -55,6 +55,15 @@
         <include>**/*</include>
       </includes>
     </fileSet>
+    <fileSet>
+      <directory>
+        ${project.parent.basedir}/assembly/target/${spark.jar.dir}
+      </directory>
+      <outputDirectory>/</outputDirectory>
+      <includes>
+        <include>${spark.jar.basename}</include>
+      </includes>
+    </fileSet>
   </fileSets>
 
   <dependencySets>
@@ -75,6 +84,8 @@
       <excludes>
         <exclude>org.apache.hadoop:*:jar</exclude>
         <exclude>org.apache.spark:*:jar</exclude>
+        <exclude>org.apache.zookeeper:*:jar</exclude>
+        <exclude>org.apache.avro:*:jar</exclude>
       </excludes>
     </dependencySet>
   </dependencySets>