[SPARK-13579][BUILD] Stop building the main Spark assembly.

This change modifies the "assembly/" module to just copy needed
dependencies to its build directory, and modifies the packaging
script to pick those up (and remove duplicate jars packages in the
examples module).

I also made some minor adjustments to dependencies to remove some
test jars from the final packaging, and remove jars that conflict with each
other when packaged separately (e.g. servlet api).

Also note that this change restores guava in applications' classpaths, even
though it's still shaded inside Spark. This is now needed for the Hadoop
libraries that are packaged with Spark, which now are not processed by
the shade plugin.

Author: Marcelo Vanzin <vanzin@cloudera.com>

Closes #11796 from vanzin/SPARK-13579.

1 files changed, 31 insertions, 70 deletions

diff --git a/assembly/pom.xml b/assembly/pom.xml
index 477d4931c3..22cbac06ca 100644
--- a/assembly/pom.xml
+++ b/assembly/pom.xml
@@ -33,9 +33,8 @@
 
   <properties>
     <sbt.project.name>assembly</sbt.project.name>
-    <spark.jar.dir>scala-${scala.binary.version}</spark.jar.dir>
-    <spark.jar.basename>spark-assembly-${project.version}-hadoop${hadoop.version}.jar</spark.jar.basename>
-    <spark.jar>${project.build.directory}/${spark.jar.dir}/${spark.jar.basename}</spark.jar>
+    <build.testJarPhase>none</build.testJarPhase>
+    <build.copyDependenciesPhase>package</build.copyDependenciesPhase>
   </properties>
 
   <dependencies>
@@ -69,6 +68,17 @@
       <artifactId>spark-repl_${scala.binary.version}</artifactId>
       <version>${project.version}</version>
     </dependency>
+
+    <!--
+      Because we don't shade dependencies anymore, we need to restore Guava to compile scope so
+      that the libraries Spark depend on have it available. We'll package the version that Spark
+      uses (14.0.1) which is not the same as Hadoop dependencies, but works.
+    -->
+    <dependency>
+      <groupId>com.google.guava</groupId>
+      <artifactId>guava</artifactId>
+      <scope>${hadoop.deps.scope}</scope>
+    </dependency>
   </dependencies>
 
   <build>
@@ -87,75 +97,26 @@
           <skip>true</skip>
         </configuration>
       </plugin>
-        <!-- zip pyspark archives to run python application on yarn mode -->
-        <plugin>
-          <groupId>org.apache.maven.plugins</groupId>
-            <artifactId>maven-antrun-plugin</artifactId>
-            <executions>
-              <execution>
-                <phase>package</phase>
-                  <goals>
-                    <goal>run</goal>
-                  </goals>
-              </execution>
-            </executions>
-            <configuration>
-              <target>
-                <delete dir="${basedir}/../python/lib/pyspark.zip"/>
-                <zip destfile="${basedir}/../python/lib/pyspark.zip">
-                  <fileset dir="${basedir}/../python/" includes="pyspark/**/*"/>
-                </zip>
-              </target>
-            </configuration>
-        </plugin>
-      <!-- Use the shade plugin to create a big JAR with all the dependencies -->
+      <!-- zip pyspark archives to run python application on yarn mode -->
       <plugin>
         <groupId>org.apache.maven.plugins</groupId>
-        <artifactId>maven-shade-plugin</artifactId>
-        <configuration>
-          <shadedArtifactAttached>false</shadedArtifactAttached>
-          <outputFile>${spark.jar}</outputFile>
-          <artifactSet>
-            <includes>
-              <include>*:*</include>
-            </includes>
-          </artifactSet>
-          <filters>
-            <filter>
-              <artifact>*:*</artifact>
-              <excludes>
-                <exclude>org/datanucleus/**</exclude>
-                <exclude>META-INF/*.SF</exclude>
-                <exclude>META-INF/*.DSA</exclude>
-                <exclude>META-INF/*.RSA</exclude>
-              </excludes>
-            </filter>
-          </filters>
-        </configuration>
-        <executions>
-          <execution>
-            <phase>package</phase>
-            <goals>
-              <goal>shade</goal>
-            </goals>
-            <configuration>
-              <transformers>
-                <transformer implementation="org.apache.maven.plugins.shade.resource.ServicesResourceTransformer" />
-                <transformer implementation="org.apache.maven.plugins.shade.resource.AppendingTransformer">
-                  <resource>META-INF/services/org.apache.hadoop.fs.FileSystem</resource>
-                </transformer>
-                <transformer implementation="org.apache.maven.plugins.shade.resource.AppendingTransformer">
-                  <resource>reference.conf</resource>
-                </transformer>
-                <transformer implementation="org.apache.maven.plugins.shade.resource.DontIncludeResourceTransformer">
-                  <resource>log4j.properties</resource>
-                </transformer>
-                <transformer implementation="org.apache.maven.plugins.shade.resource.ApacheLicenseResourceTransformer"/>
-                <transformer implementation="org.apache.maven.plugins.shade.resource.ApacheNoticeResourceTransformer"/>
-              </transformers>
-            </configuration>
-          </execution>
-        </executions>
+          <artifactId>maven-antrun-plugin</artifactId>
+          <executions>
+            <execution>
+              <phase>package</phase>
+                <goals>
+                  <goal>run</goal>
+                </goals>
+            </execution>
+          </executions>
+          <configuration>
+            <target>
+              <delete dir="${basedir}/../python/lib/pyspark.zip"/>
+              <zip destfile="${basedir}/../python/lib/pyspark.zip">
+                <fileset dir="${basedir}/../python/" includes="pyspark/**/*"/>
+              </zip>
+            </target>
+          </configuration>
       </plugin>
     </plugins>
   </build>