[SPARK-13599][BUILD] remove transitive groovy dependencies from Hive

## What changes were proposed in this pull request?

Modifies the dependency declarations of the all the hive artifacts, to explicitly exclude the groovy-all JAR.

This stops the groovy classes *and everything else in that uber-JAR* from getting into spark-assembly JAR.

## How was this patch tested?

1. Pre-patch build was made: `mvn clean install -Pyarn,hive,hive-thriftserver`
1. spark-assembly expanded, observed to have the org.codehaus.groovy packages and JARs
1. A maven dependency tree was created `mvn dependency:tree -Pyarn,hive,hive-thriftserver  -Dverbose > target/dependencies.txt`
1. This text file examined to confirm that groovy was being imported as a dependency of `org.spark-project.hive`
1. Patch applied
1. Repeated step1: clean build of project with ` -Pyarn,hive,hive-thriftserver` set
1. Examined created spark-assembly, verified no org.codehaus packages
1. Verified that the maven dependency tree no longer references groovy

Note also that the size of the assembly JAR was 181628646 bytes before this patch, 166318515 after —15MB smaller. That's a good metric of things being excluded

Author: Steve Loughran <stevel@hortonworks.com>

Closes #11449 from steveloughran/fixes/SPARK-13599-groovy-dependency.

6 files changed, 21 insertions, 5 deletions

diff --git a/dev/deps/spark-deps-hadoop-2.2 b/dev/deps/spark-deps-hadoop-2.2
index 266e0ce88d..53533d088c 100644
--- a/dev/deps/spark-deps-hadoop-2.2
+++ b/dev/deps/spark-deps-hadoop-2.2
@@ -59,7 +59,6 @@ grizzly-http-2.1.2.jar
 grizzly-http-server-2.1.2.jar
 grizzly-http-servlet-2.1.2.jar
 grizzly-rcm-2.1.2.jar
-groovy-all-2.1.6.jar
 guice-3.0.jar
 guice-servlet-3.0.jar
 hadoop-annotations-2.2.0.jar
diff --git a/dev/deps/spark-deps-hadoop-2.3 b/dev/deps/spark-deps-hadoop-2.3
index 257751a090..1db9b798c3 100644
--- a/dev/deps/spark-deps-hadoop-2.3
+++ b/dev/deps/spark-deps-hadoop-2.3
@@ -54,7 +54,6 @@ eigenbase-properties-1.1.5.jar
 geronimo-annotation_1.0_spec-1.1.1.jar
 geronimo-jaspic_1.0_spec-1.0.jar
 geronimo-jta_1.1_spec-1.1.1.jar
-groovy-all-2.1.6.jar
 guice-3.0.jar
 guice-servlet-3.0.jar
 hadoop-annotations-2.3.0.jar
diff --git a/dev/deps/spark-deps-hadoop-2.4 b/dev/deps/spark-deps-hadoop-2.4
index 061ef2876b..b190997997 100644
--- a/dev/deps/spark-deps-hadoop-2.4
+++ b/dev/deps/spark-deps-hadoop-2.4
@@ -54,7 +54,6 @@ eigenbase-properties-1.1.5.jar
 geronimo-annotation_1.0_spec-1.1.1.jar
 geronimo-jaspic_1.0_spec-1.0.jar
 geronimo-jta_1.1_spec-1.1.1.jar
-groovy-all-2.1.6.jar
 guice-3.0.jar
 guice-servlet-3.0.jar
 hadoop-annotations-2.4.0.jar
diff --git a/dev/deps/spark-deps-hadoop-2.6 b/dev/deps/spark-deps-hadoop-2.6
index f171d5aa39..669d6d566f 100644
--- a/dev/deps/spark-deps-hadoop-2.6
+++ b/dev/deps/spark-deps-hadoop-2.6
@@ -58,7 +58,6 @@ eigenbase-properties-1.1.5.jar
 geronimo-annotation_1.0_spec-1.1.1.jar
 geronimo-jaspic_1.0_spec-1.0.jar
 geronimo-jta_1.1_spec-1.1.1.jar
-groovy-all-2.1.6.jar
 gson-2.2.4.jar
 guice-3.0.jar
 guice-servlet-3.0.jar
diff --git a/dev/deps/spark-deps-hadoop-2.7 b/dev/deps/spark-deps-hadoop-2.7
index a7a9dcdef0..b106be711f 100644
--- a/dev/deps/spark-deps-hadoop-2.7
+++ b/dev/deps/spark-deps-hadoop-2.7
@@ -58,7 +58,6 @@ eigenbase-properties-1.1.5.jar
 geronimo-annotation_1.0_spec-1.1.1.jar
 geronimo-jaspic_1.0_spec-1.0.jar
 geronimo-jta_1.1_spec-1.1.1.jar
-groovy-all-2.1.6.jar
 gson-2.2.4.jar
 guice-3.0.jar
 guice-servlet-3.0.jar
diff --git a/pom.xml b/pom.xml
index 2148379896..85c0131b4e 100644
--- a/pom.xml
+++ b/pom.xml
@@ -1327,6 +1327,10 @@
             <groupId>commons-logging</groupId>
             <artifactId>commons-logging</artifactId>
           </exclusion>
+          <exclusion>
+            <groupId>org.codehaus.groovy</groupId>
+            <artifactId>groovy-all</artifactId>
+          </exclusion>
         </exclusions>
       </dependency>
       <dependency>
@@ -1398,6 +1402,10 @@
             <groupId>commons-logging</groupId>
             <artifactId>commons-logging</artifactId>
           </exclusion>
+          <exclusion>
+            <groupId>org.codehaus.groovy</groupId>
+            <artifactId>groovy-all</artifactId>
+          </exclusion>
         </exclusions>
       </dependency>
 
@@ -1492,6 +1500,10 @@
             <groupId>commons-logging</groupId>
             <artifactId>commons-logging</artifactId>
           </exclusion>
+          <exclusion>
+            <groupId>org.codehaus.groovy</groupId>
+            <artifactId>groovy-all</artifactId>
+          </exclusion>
         </exclusions>
       </dependency>
 
@@ -1537,6 +1549,10 @@
             <groupId>org.apache.thrift</groupId>
             <artifactId>libthrift</artifactId>
           </exclusion>
+          <exclusion>
+            <groupId>org.codehaus.groovy</groupId>
+            <artifactId>groovy-all</artifactId>
+          </exclusion>
         </exclusions>
       </dependency>
 
@@ -1585,6 +1601,10 @@
             <groupId>commons-logging</groupId>
             <artifactId>commons-logging</artifactId>
           </exclusion>
+          <exclusion>
+            <groupId>org.codehaus.groovy</groupId>
+            <artifactId>groovy-all</artifactId>
+          </exclusion>
         </exclusions>
       </dependency>
       <dependency>
@@ -1809,6 +1829,7 @@
                         io.netty:netty and io.netty:netty-all.
                       -->
                       <exclude>org.jboss.netty</exclude>
+                      <exclude>org.codehaus.groovy</exclude>
                     </excludes>
                     <searchTransitive>true</searchTransitive>
                   </bannedDependencies>