From 80e70c56b9b7a939248aed072b25969c1f088fb4 Mon Sep 17 00:00:00 2001
From: Alexey Grigorev <alexeygrigorev@users.noreply.github.com>
Date: Mon, 21 Nov 2016 21:02:57 +0100
Subject: [PATCH] [jvm-packages] xgboost4j: publishing sources along with bins
 (#1797)

* xgboost4j: publishing sources along with bins

* description about building maven artifacts

* publishing scala source to local m2 as well
---
 doc/jvm/index.md     | 19 +++++++++++++++++++
 jvm-packages/pom.xml | 22 ++++++++++++++++++++++
 2 files changed, 41 insertions(+)

diff --git a/doc/jvm/index.md b/doc/jvm/index.md
index 128017509..0f01fb042 100644
--- a/doc/jvm/index.md
+++ b/doc/jvm/index.md
@@ -13,6 +13,25 @@ Before you install XGBoost4J, you need to define environment variable `JAVA_HOME
 
 After your `JAVA_HOME` is defined correctly, it is as simple as run `mvn package` under jvm-packages directory to install XGBoost4J. You can also skip the tests by running `mvn -DskipTests=true package`, if you are sure about the correctness of your local setup.
 
+To publish the artifacts to your local maven repository, run
+
+    mvn install
+
+Or, if you would like to skip tests, run 
+
+    mvn -DskipTests install
+
+This command will publish the xgboost binaries, the compiled java classes as well as the java sources to your local repository. Then you can use XGBoost4J in your Java projects by including the following dependency in `pom.xml`:
+
+    <dependency>
+      <groupId>ml.dmlc</groupId>
+      <artifactId>xgboost4j</artifactId>
+      <version>0.7</version>
+    </dependency>
+
+
+
+
 After integrating with Dataframe/Dataset APIs of Spark 2.0, XGBoost4J-Spark only supports compile with Spark 2.x. You can build XGBoost4J-Spark as a component of XGBoost4J by running `mvn package`, and you can specify the version of spark with `mvn -Dspark.version=2.0.0 package`.   (To continue working with Spark 1.x, the users are supposed to update pom.xml by modifying the properties like `spark.version`, `scala.version`, and `scala.binary.version`. Users also need to change the implemention by replacing SparkSession with SQLContext and the type of API parameters from Dataset[_] to Dataframe)
 
 Contents
diff --git a/jvm-packages/pom.xml b/jvm-packages/pom.xml
index d62d192af..089b725bc 100644
--- a/jvm-packages/pom.xml
+++ b/jvm-packages/pom.xml
@@ -77,6 +77,20 @@
                     </excludePackageNames>
                 </configuration>
             </plugin>
+            <plugin>
+                <groupId>org.apache.maven.plugins</groupId>
+                <artifactId>maven-source-plugin</artifactId>
+                <version>3.0.1</version>
+                <executions>
+                    <execution>
+                        <id>attach-sources</id>
+                        <phase>verify</phase>
+                        <goals>
+                            <goal>jar-no-fork</goal>
+                        </goals>
+                    </execution>
+                </executions>
+            </plugin>
             <plugin>
                 <groupId>net.alchim31.maven</groupId>
                 <artifactId>maven-site-plugin</artifactId>
@@ -145,6 +159,14 @@
                             <goal>compile</goal>
                         </goals>
                     </execution>
+                    <execution>
+                        <id>scala-compile-first</id>
+                        <phase>process-resources</phase>
+                        <goals>
+                            <goal>compile</goal>
+                            <goal>add-source</goal>
+                        </goals>
+                    </execution>
                 </executions>
             </plugin>