From 4106558435889261243d186f5f0b51c5f9e98d56 Mon Sep 17 00:00:00 2001
From: Aaron Davidson <aaron@databricks.com>
Date: Sun, 6 Apr 2014 17:48:41 -0700
Subject: SPARK-1314: Use SPARK_HIVE to determine if we include Hive in
 packaging

Previously, we based our decision regarding including datanucleus jars based on the existence of a spark-hive-assembly jar, which was incidentally built whenever "sbt assembly" is run. This means that a typical and previously supported pathway would start using hive jars.

This patch has the following features/bug fixes:

- Use of SPARK_HIVE (default false) to determine if we should include Hive in the assembly jar.
- Analagous feature in Maven with -Phive (previously, there was no support for adding Hive to any of our jars produced by Maven)
- assemble-deps fixed since we no longer use a different ASSEMBLY_DIR
- avoid adding log message in compute-classpath.sh to the classpath :)

Still TODO before mergeable:
- We need to download the datanucleus jars outside of sbt. Perhaps we can have spark-class download them if SPARK_HIVE is set similar to how sbt downloads itself.
- Spark SQL documentation updates.

Author: Aaron Davidson <aaron@databricks.com>

Closes #237 from aarondav/master and squashes the following commits:

5dc4329 [Aaron Davidson] Typo fixes
dd4f298 [Aaron Davidson] Doc update
dd1a365 [Aaron Davidson] Eliminate need for SPARK_HIVE at runtime by d/ling datanucleus from Maven
a9269b5 [Aaron Davidson] [WIP] Use SPARK_HIVE to determine if we include Hive in packaging
---
 sql/hive/pom.xml | 28 ++++++++++++++++++++++++++++
 1 file changed, 28 insertions(+)

(limited to 'sql/hive/pom.xml')

diff --git a/sql/hive/pom.xml b/sql/hive/pom.xml
index 63f592cb4b..a662da76ce 100644
--- a/sql/hive/pom.xml
+++ b/sql/hive/pom.xml
@@ -63,6 +63,10 @@
             <artifactId>hive-exec</artifactId>
             <version>${hive.version}</version>
         </dependency>
+        <dependency>
+            <groupId>org.codehaus.jackson</groupId>
+            <artifactId>jackson-mapper-asl</artifactId>
+        </dependency>
         <dependency>
             <groupId>org.apache.hive</groupId>
             <artifactId>hive-serde</artifactId>
@@ -87,6 +91,30 @@
                 <groupId>org.scalatest</groupId>
                 <artifactId>scalatest-maven-plugin</artifactId>
             </plugin>
+
+            <!-- Deploy datanucleus jars to the spark/lib_managed/jars directory -->
+            <plugin>
+                <groupId>org.apache.maven.plugins</groupId>
+                <artifactId>maven-dependency-plugin</artifactId>
+                <version>2.4</version>
+                <executions>
+                    <execution>
+                        <id>copy-dependencies</id>
+                        <phase>package</phase>
+                        <goals>
+                            <goal>copy-dependencies</goal>
+                        </goals>
+                        <configuration>
+                            <!-- basedir is spark/sql/hive/ -->
+                            <outputDirectory>${basedir}/../../lib_managed/jars</outputDirectory>
+                            <overWriteReleases>false</overWriteReleases>
+                            <overWriteSnapshots>false</overWriteSnapshots>
+                            <overWriteIfNewer>true</overWriteIfNewer>
+                            <includeGroupIds>org.datanucleus</includeGroupIds>
+                        </configuration>
+                    </execution>
+                </executions>
+            </plugin>
         </plugins>
     </build>
 </project>
-- 
cgit v1.2.3