SPARK-1556. jets3t dep doesn't update properly with newer Hadoop versions

See related discussion at https://github.com/apache/spark/pull/468

This PR may still overstep what you have in mind, but let me put it on the table to start. Besides fixing the issue, it has one substantive change, and that is to manage Hadoop-specific things only in Hadoop-related profiles. This does _not_ remove `yarn.version`.

- Moves the YARN and Hadoop profiles together in pom.xml. Sorry that this makes the diff a little hard to grok but the changes are only as follows.
- Removes `hadoop.major.version`
- Introduce `hadoop-2.2` and `hadoop-2.3` profiles to control Hadoop-specific changes:
  - like the protobuf version issue - this was only 'solved' now by enabling YARN for 2.2+, which is really an orthogonal issue
  - like the jets3t version issue now
- Hadoop profiles set an appropriate default `hadoop.version`, that can be overridden
- _(YARN profiles in the parent now only exist to add the sub-module)_
- Fixes the jets3t dependency issue
 - and makes it a runtime dependency
 - and centralizes config of this guy in the parent pom
- Updates build docs
- Updates SBT build too
  - and fixes a regex problem along the way

Author: Sean Owen <sowen@cloudera.com>

Closes #629 from srowen/SPARK-1556 and squashes the following commits:

c3fa967 [Sean Owen] Fix hadoop-2.4 profile typo in doc
a2105fd [Sean Owen] Add hadoop-2.4 profile and don't set hadoop.version in profiles
274f4f9 [Sean Owen] Make jets3t a runtime dependency, and bring its exclusion up into parent config
bbed826 [Sean Owen] Use jets3t 0.9.0 for Hadoop 2.3+ (and correct similar regex issue in SBT build)
f21f356 [Sean Owen] Build changes to set up for jets3t fix

1 files changed, 50 insertions, 34 deletions

diff --git a/pom.xml b/pom.xml
index 08c3ac6443..e4b5c36d69 100644
--- a/pom.xml
+++ b/pom.xml
@@ -129,6 +129,7 @@
     <chill.version>0.3.6</chill.version>
     <codahale.metrics.version>3.0.0</codahale.metrics.version>
     <avro.version>1.7.4</avro.version>
+    <jets3t.version>0.7.1</jets3t.version>
 
     <PermGen>64m</PermGen>
     <MaxPermGen>512m</MaxPermGen>
@@ -560,10 +561,18 @@
           </exclusion>
         </exclusions>
       </dependency>
+      <!-- See SPARK-1556 for info on this dependency: -->
       <dependency>
         <groupId>net.java.dev.jets3t</groupId>
         <artifactId>jets3t</artifactId>
-        <version>0.7.1</version>
+        <version>${jets3t.version}</version>
+        <scope>runtime</scope>
+        <exclusions>
+          <exclusion>
+            <groupId>commons-logging</groupId>
+            <artifactId>commons-logging</artifactId>
+          </exclusion>
+        </exclusions>
       </dependency>
       <dependency>
         <groupId>org.apache.hadoop</groupId>
@@ -843,36 +852,6 @@
   </build>
 
   <profiles>
-    <!-- SPARK-1121: Adds an explicit dependency on Avro to work around a Hadoop 0.23.X issue -->
-    <profile>
-      <id>hadoop-0.23</id>
-      <dependencies>
-        <dependency>
-          <groupId>org.apache.avro</groupId>
-          <artifactId>avro</artifactId>
-        </dependency>
-      </dependencies>
-    </profile>
-
-    <profile>
-      <id>yarn-alpha</id>
-      <properties>
-        <hadoop.major.version>2</hadoop.major.version>
-        <!-- 0.23.* is same as 2.0.* - except hardened to run production jobs -->
-        <hadoop.version>0.23.7</hadoop.version>
-        <!--<hadoop.version>2.0.5-alpha</hadoop.version> -->
-      </properties>
-      <dependencies>
-        <dependency>
-          <groupId>org.apache.avro</groupId>
-          <artifactId>avro</artifactId>
-        </dependency>
-      </dependencies>
-      <modules>
-        <module>yarn</module>
-      </modules>
-
-    </profile>
 
     <!-- Ganglia integration is not included by default due to LGPL-licensed code -->
     <profile>
@@ -907,17 +886,54 @@
 
     </profile>
 
+    <!-- A series of build profiles where customizations for particular Hadoop releases can be made -->
+
     <profile>
-      <id>yarn</id>
+      <id>hadoop-0.23</id>
+      <!-- SPARK-1121: Adds an explicit dependency on Avro to work around a Hadoop 0.23.X issue -->
+      <dependencies>
+        <dependency>
+          <groupId>org.apache.avro</groupId>
+          <artifactId>avro</artifactId>
+        </dependency>
+      </dependencies>
+    </profile>
+
+    <profile>
+      <id>hadoop-2.2</id>
+      <properties>
+        <protobuf.version>2.5.0</protobuf.version>
+      </properties>
+    </profile>
+
+    <profile>
+      <id>hadoop-2.3</id>
       <properties>
-        <hadoop.major.version>2</hadoop.major.version>
-        <hadoop.version>2.2.0</hadoop.version>
         <protobuf.version>2.5.0</protobuf.version>
+        <jets3t.version>0.9.0</jets3t.version>
       </properties>
+    </profile>
+
+    <profile>
+      <id>hadoop-2.4</id>
+      <properties>
+        <protobuf.version>2.5.0</protobuf.version>
+        <jets3t.version>0.9.0</jets3t.version>
+      </properties>
+    </profile>
+
+    <profile>
+      <id>yarn-alpha</id>
       <modules>
         <module>yarn</module>
       </modules>
+    </profile>
 
+    <profile>
+      <id>yarn</id>
+      <modules>
+        <module>yarn</module>
+      </modules>
     </profile>
 
     <!-- Build without Hadoop dependencies that are included in some runtime environments. -->