Added dedicated Vagrant setup (closes #6) /cc @bigsnarfdude

.gitignore

@@ -10,4 +10,8 @@ project/boot/
 project/plugins/project/
 
 # Scala-IDE specific
-.scala_dependencies
+.scala_dependencies
+
+# Vagrant
+.vagrant
+

README.md

@@ -4,21 +4,25 @@
 
 This is a simple word count job written in Scala for the [Spark] [spark] cluster computing platform, with instructions for running on [Amazon Elastic MapReduce] [emr] in non-interactive mode. The code is ported directly from Twitter's [`WordCountJob`] [wordcount] for Scalding.
 
-This was built by the Professional Services team at [Snowplow Analytics] [snowplow], who use Spark on their [Data pipelines and algorithms] [data-pipelines-algos] projects.
+This was built by the Data Science team at [Snowplow Analytics] [snowplow], who use Spark on their [Data pipelines and algorithms] [data-pipelines-algos] projects.
 
-_See also:_ [Scalding Example Project] [scalding-example-project] | [Cascalog Example Project] [cascalog-example-project]
+_See also:_ [Spark Streaming Example Project] [spark-streaming-example-project] | [Scalding Example Project] [scalding-example-project]
 
 ## Building
 
-Assuming you already have [SBT] [sbt] installed:
+Assuming git, **[Vagrant] [vagrant-install]** and **[VirtualBox] [virtualbox-install]** installed:
 
-    $ git clone git://github.com/snowplow/spark-example-project.git
-    $ cd spark-example-project
-    $ sbt assembly
+```bash
+ host> git clone https://github.com/snowplow/spark-example-project
+ host> cd spark-example-project
+ host> vagrant up && vagrant ssh
+guest> cd /vagrant
+guest> sbt assembly
+```
 
 The 'fat jar' is now available as:
 
-    target/spark-example-project-0.2.0.jar
+    target/spark-example-project-0.3.0.jar
 
 ## Unit testing
 
@@ -118,16 +122,17 @@ limitations under the License.
 [snowplow]: http://snowplowanalytics.com
 [data-pipelines-algos]: http://snowplowanalytics.com/services/pipelines.html
 
+[vagrant-install]: http://docs.vagrantup.com/v2/installation/index.html
+[virtualbox-install]: https://www.virtualbox.org/wiki/Downloads
+
+[spark-streaming-example-project]: https://github.com/snowplow/spark-streaming-example-project
 [scalding-example-project]: https://github.com/snowplow/scalding-example-project
-[cascalog-example-project]: https://github.com/snowplow/cascalog-example-project
 
 [issue-1]: https://github.com/snowplow/spark-example-project/issues/1
 [issue-2]: https://github.com/snowplow/spark-example-project/issues/2
 [aws-spark-tutorial]: http://aws.amazon.com/articles/4926593393724923
 [spark-emr-howto]: https://forums.aws.amazon.com/thread.jspa?messageID=458398
 
-[sbt]: http://www.scala-sbt.org/release/docs/Getting-Started/Setup.html
-
 [emr]: http://aws.amazon.com/elasticmapreduce/
 [hello-txt]: https://github.com/snowplow/spark-example-project/raw/master/data/hello.txt
 [emr-client]: http://aws.amazon.com/developertools/2264

Vagrantfile

@@ -0,0 +1,19 @@
+Vagrant.configure("2") do |config|
+
+  config.vm.box = "ubuntu/trusty64"
+  config.vm.hostname = "huskimo"
+  config.ssh.forward_agent = true
+
+  config.vm.provider :virtualbox do |vb|
+    vb.name = Dir.pwd().split("/")[-1] + "-" + Time.now.to_f.to_i.to_s
+    vb.customize ["modifyvm", :id, "--natdnshostresolver1", "on"]
+    vb.customize [ "guestproperty", "set", :id, "--timesync-threshold", 10000 ]
+    # Scala is memory-hungry
+    vb.memory = 5120
+  end
+
+  config.vm.provision :shell do |sh|
+    sh.path = "vagrant/up.bash"
+  end
+
+end

vagrant/.gitignore

@@ -0,0 +1,3 @@
+.peru
+oss-playbooks
+ansible

vagrant/ansible.hosts

@@ -0,0 +1,2 @@
+[vagrant]
+127.0.0.1:2222

vagrant/peru.yaml

@@ -0,0 +1,14 @@
+imports:
+    ansible: ansible
+    ansible_playbooks: oss-playbooks
+
+curl module ansible:
+    # Equivalent of git cloning tags/v1.6.6 but much, much faster
+    url: https://codeload.github.com/ansible/ansible/zip/69d85c22c7475ccf8169b6ec9dee3ee28c92a314
+    unpack: zip
+    export: ansible-69d85c22c7475ccf8169b6ec9dee3ee28c92a314
+
+git module ansible_playbooks:
+    url: https://github.com/snowplow/ansible-playbooks.git
+    # Comment out to fetch a specific rev instead of master:
+    # rev: xxx

vagrant/up.bash

@@ -0,0 +1,50 @@
+#!/bin/bash
+set -e
+
+vagrant_dir=/vagrant/vagrant
+bashrc=/home/vagrant/.bashrc
+
+echo "========================================"
+echo "INSTALLING PERU AND ANSIBLE DEPENDENCIES"
+echo "----------------------------------------"
+apt-get update
+apt-get install -y language-pack-en git unzip libyaml-dev python3-pip python-yaml python-paramiko python-jinja2
+
+echo "==============="
+echo "INSTALLING PERU"
+echo "---------------"
+sudo pip3 install peru
+
+echo "======================================="
+echo "CLONING ANSIBLE AND PLAYBOOKS WITH PERU"
+echo "---------------------------------------"
+cd ${vagrant_dir} && peru sync -v
+echo "... done"
+
+env_setup=${vagrant_dir}/ansible/hacking/env-setup
+hosts=${vagrant_dir}/ansible.hosts
+
+echo "==================="
+echo "CONFIGURING ANSIBLE"
+echo "-------------------"
+touch ${bashrc}
+echo "source ${env_setup}" >> ${bashrc}
+echo "export ANSIBLE_HOSTS=${hosts}" >> ${bashrc}
+echo "... done"
+
+echo "=========================================="
+echo "RUNNING PLAYBOOKS WITH ANSIBLE*"
+echo "* no output while each playbook is running"
+echo "------------------------------------------"
+while read pb; do
+    su - -c "source ${env_setup} && ${vagrant_dir}/ansible/bin/ansible-playbook ${vagrant_dir}/${pb} --connection=local --inventory-file=${hosts}" vagrant
+done <${vagrant_dir}/up.playbooks
+
+guidance=${vagrant_dir}/up.guidance
+
+if [ -f ${guidance} ]; then
+    echo "==========="
+    echo "PLEASE READ"
+    echo "-----------"
+    cat $guidance
+fi

vagrant/up.guidance

@@ -0,0 +1,4 @@
+To get started:
+vagrant ssh
+cd /vagrant
+sbt test

vagrant/up.playbooks

@@ -0,0 +1,3 @@
+oss-playbooks/java7.yml
+oss-playbooks/scala.yml
+oss-playbooks/sbt.yml