extras/vagrantExample/src/main/vagrant/Vagrantfile - rya - Git at Google

 # Licensed to the Apache Software Foundation (ASF) under one
 # or more contributor license agreements.  See the NOTICE file
 # distributed with this work for additional information
 # regarding copyright ownership.  The ASF licenses this file
 # to you under the Apache License, Version 2.0 (the
 # "License"); you may not use this file except in compliance
 # with the License.  You may obtain a copy of the License at
 #
 #   http://www.apache.org/licenses/LICENSE-2.0
 #
 # Unless required by applicable law or agreed to in writing,
 # software distributed under the License is distributed on an
 # "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
 # KIND, either express or implied.  See the License for the
 # specific language governing permissions and limitations
 # under the License.

 # -*- mode: ruby -*-
 # vi: set ft=ruby :

 #
 # Builds a single node Rya on Accumulo on Hadoop and Zookeeper.
 # Deploys Rya, and the Eclipse rdf4j-workbench on Tomcat accessible from the host's browser.
 # See the accompanying readme for URL's, verification, and troubleshooting.
 #
 # Note: Machine's ip is 192.168.33.10
 # username : vagrant
 # password : vagrant
 #
 # accumulo instance : dev
 # accumulo username : root
 # accumulo password : root

 Vagrant.configure(2) do |config|

   config.vm.box = "ubuntu/trusty64"
   config.vm.box_url = "https://cloud-images.ubuntu.com/vagrant/trusty/current/trusty-server-cloudimg-amd64-vagrant-disk1.box"

   config.vm.provider "virtualbox" do |vb|
     vb.name = "rya-example-box"
     vb.memory = "4096"
 	vb.cpus = 4
   end

   config.vm.network :private_network, ip: "192.168.33.10"
   config.vm.hostname = "rya-example-box"

   config.vm.provision "shell", inline: <<-SHELL

     ###set -x  ## turn on command echo with expanded variables
     # List of dependency versions
     export ACCUMULO_VERSION=1.6.5
     ###export ACCUMULO_VERSION=1.7.1
     export HADOOP_VERSION=2.7.2
     export RYA_EXAMPLE_VERSION=4.0.0-incubating
     export RDF4J_VERSION=2.3.1
     export ZOOKEEPER_VERSION=3.4.5-cdh4.5.0

     mavenRepoUrl=http://repo1.maven.org/maven2/

     echo "Updating host file with permanent ip"
 	sudo sed -i 's/127.0.1.1/192.168.33.10/' /etc/hosts
     cat >> /etc/hosts <<EOF
 192.168.33.10 zoo1 zoo2 zoo3
 EOF

     sudo -E apt-get -qq update

     echo "Installing Java installer..."
     sudo -E add-apt-repository ppa:webupd8team/java || exit $?
     sudo -E apt-get -qq update || exit $?
     echo debconf shared/accepted-oracle-license-v1-1 select true | \
       sudo -E /usr/bin/debconf-set-selections
     echo debconf shared/accepted-oracle-license-v1-1 seen true | \
       sudo -E /usr/bin/debconf-set-selections
     sudo mkdir --parents /var/cache/oracle-jdk8-installer || exit $?
     echo verbose=off >> /var/cache/oracle-jdk8-installer/wgetrc || exit $?

     echo "Installing Java..."
     sudo -E apt-get -qq install -y oracle-java8-installer || exit $?
     sudo ln --force -s /usr/lib/jvm/java-8-oracle/ /usr/lib/jvm/default-java

     echo "Installing Tomcat..."
     sudo -E apt-get install -y tomcat7  || exit $?

     echo "Installing Unzip..."
     apt-get install unzip || exit $?

     echo "Setting up environment..."
     export JAVA_HOME=/usr/lib/jvm/java-8-oracle
     export HADOOP_HOME=/home/vagrant/hadoop-${HADOOP_VERSION}
     export ZOOKEEPER_HOME=/home/vagrant/zookeeper-${ZOOKEEPER_VERSION}
     export ZOO_LOG_DIR=${ZOOKEEPER_HOME}/logs/
     export ACCUMULO_HOME=/home/vagrant/accumulo-${ACCUMULO_VERSION}
     export PATHADD=$JAVA_HOME/bin:$ZOOKEEPER_HOME/bin:$ACCUMULO_HOME/bin:$HADOOP_HOME/bin
     export PATH=$PATH:$PATHADD

     export HADOOP_PREFIX="$HADOOP_HOME"
     export HADOOP_CONF_DIR="$HADOOP_PREFIX/etc/hadoop"
     export ACCUMULO_LOG_DIR=$ACCUMULO_HOME/logs
     export ACCUMULO_TSERVER_OPTS="-Xmx384m -Xms384m "
     export ACCUMULO_MASTER_OPTS="-Xmx128m -Xms128m"
     export ACCUMULO_MONITOR_OPTS="-Xmx64m -Xms64m"
     export ACCUMULO_GC_OPTS="-Xmx64m -Xms64m"
     export ACCUMULO_GENERAL_OPTS="-XX:+UseConcMarkSweepGC -XX:CMSInitiatingOccupancyFraction=75 -Djava.net.preferIPv4Stack=true"
     export ACCUMULO_OTHER_OPTS="-Xmx128m -Xms64m"
     export ACCUMULO_KILL_CMD='kill -9 %p'
     # Shell environment includes Accumulo resources.
     ACCUMULO_RC=/home/vagrant/.accumulo_rc.sh
     cat > ${ACCUMULO_RC}  <<EOF

         export JAVA_HOME=\'$JAVA_HOME\'
         export HADOOP_HOME=\'$HADOOP_HOME\'
         export ZOOKEEPER_HOME=\'$ZOOKEEPER_HOME\'
         export ZOO_LOG_DIR=\'$ZOO_LOG_DIR\'
         export ACCUMULO_HOME=\'$ACCUMULO_HOME\'
         export PATH=\\$PATH:$PATHADD

         export HADOOP_PREFIX=\'$HADOOP_PREFIX\'
         export HADOOP_CONF_DIR=\'$HADOOP_CONF_DIR\'
         export ACCUMULO_LOG_DIR=\'$ACCUMULO_LOG_DIR\'
         export ACCUMULO_TSERVER_OPTS=\'$ACCUMULO_TSERVER_OPTS\'
         export ACCUMULO_MASTER_OPTS=\'$ACCUMULO_MASTER_OPTS\'
         export ACCUMULO_MONITOR_OPTS=\'$ACCUMULO_MONITOR_OPTS\'
         export ACCUMULO_GC_OPTS=\'$ACCUMULO_GC_OPTS\'
         export ACCUMULO_GENERAL_OPTS=\'$ACCUMULO_GENERAL_OPTS\'
         export ACCUMULO_OTHER_OPTS=\'$ACCUMULO_OTHER_OPTS\'
         export ACCUMULO_KILL_CMD=\'$ACCUMULO_KILL_CMD\'

         ### command to list the 7 correct java processes: tomcat-catalina, zookeeper, and 5 Accumulo: tracer, master, monitor, tserver, gc.
         function ryaps() { ps -ef | grep java | tr ' ' '\\n' | egrep '^org\\.apache|^tracer|^master|^monitor|^tserver|^gc' | sed '/\\.Main/ N ; s/\\n/ /' ; }
 EOF
 	source ${ACCUMULO_RC} || exit 151

 	# include it at the beginning of both shell configuration files.

 	for BASHRC in /home/vagrant/.bashrc /home/vagrant/.bash_profile ;
     do touch ${BASHRC} ;
         cat - ${BASHRC} > ${BASHRC}.new <<EOF  && mv ${BASHRC}.new ${BASHRC} || exit 152
 source ${ACCUMULO_RC}
 EOF
 	done
     echo "Acquiring and Extracting ..."

     function echoerr() { printf "%s\n" "$*" >&2; }

     function download {
       ### curl --fail treat http status >= 400 as an error. --location follow redirects status>=300
       curl --silent --show-error --fail --location "$@"
       if [ $? -ne 0 ]; then
         echoerr "--------------------------"
         echoerr "-"
         echoerr "- download failed" "$@"
         echoerr "-"
         echoerr "-"   exiting ...
         echoerr "-"
         echoerr "--------------------------"
         exit 800
       fi
     }
     ### wait for a directory to exist or 60 seconds timeout
     function waitForDeploy {
         waitfordir="$1"
         timeout=60
         while [[ ! -d  "$waitfordir" ]]
         do
             sleep 5
             let timeout-=5
             if [[ $timeout -le "0" ]]; then
                 echo "Timeout waiting for war to deploy, $waitfordir still does not exist.";
                 exit 401
             fi
         done
     }

     echo "- Hadoop"
     hadoopUrl=http://apache.mirrors.tds.net/hadoop/common/hadoop-${HADOOP_VERSION}/hadoop-${HADOOP_VERSION}.tar.gz
     if [[ ! -d ${HADOOP_HOME} ]] ; then
         echo "Downloading $hadoopUrl"
         download $hadoopUrl \
         | tar -zxC /home/vagrant || exit 101
     fi

     echo "- Zookeeper"
     zookeeperUrl=http://archive-primary.cloudera.com/cdh4/cdh/4/zookeeper-${ZOOKEEPER_VERSION}.tar.gz
     if [[ ! -d ${ZOOKEEPER_HOME} ]] ; then
         echo "Downloading $zookeeperUrl"
         download $zookeeperUrl \
         | tar -zxC /home/vagrant || exit 102
     fi

     echo "- Accumulo"
     accumuloUrl=http://apache.mirrors.pair.com/accumulo/${ACCUMULO_VERSION}/accumulo-${ACCUMULO_VERSION}-bin.tar.gz
 	if [[ ! -d ${ACCUMULO_HOME} ]] ; then
 		echo "Downloading $accumuloUrl"
 		download $accumuloUrl \
 		| tar -zxC /home/vagrant || exit 103
 	fi

     echo "Configuring Zookeeper..."
     sudo mkdir --parents /var/zookeeper
     sudo chown vagrant:vagrant /var/zookeeper
     sudo cp ${ZOOKEEPER_HOME}/conf/zoo_sample.cfg ${ZOOKEEPER_HOME}/conf/zoo.cfg
     # Change the dataDir to /var/zookeeper -- strange that backslashes need to be escaped only on this line.
     sudo sed -i 's/^\\s*dataDir\\s*=.*$/dataDir=\\/var\\/zookeeper/' ${ZOOKEEPER_HOME}/conf/zoo.cfg  || exit 104
     # Conflicts with Accumulo and maybe Zookeeper
     sudo rm --force ${HADOOP_HOME}/share/hadoop/common/lib/slf4j-api-1.7.10.jar
     sudo rm --force ${HADOOP_HOME}/share/hadoop/common/lib/slf4j-log4j12-1.7.10.jar

     # Assure logs are creatable and writeable
     sudo mkdir --parents ${ZOO_LOG_DIR}
     sudo touch "${ZOO_LOG_DIR}/zookeeper.out"
     sudo chmod -R a+wX  ${ZOO_LOG_DIR}

     echo "Running Zookeeper..."
     sudo -E ${ZOOKEEPER_HOME}/bin/zkServer.sh start

     echo "Configuring Accumulo..."
     cp ${ACCUMULO_HOME}/conf/examples/1GB/standalone/* ${ACCUMULO_HOME}/conf/
     rm --force ${ACCUMULO_HOME}/conf/accumulo-site.xml
     cat >> ${ACCUMULO_HOME}/conf/accumulo-site.xml <<EOF
         <configuration>
             <property><name>instance.dfs.uri</name><value>file:///</value></property>
             <property><name>instance.dfs.dir</name><value>/data/accumulo</value></property>
             <property><name>instance.zookeeper.host</name><value>localhost:2181</value></property>
             <property><name>instance.secret</name><value>DONTTELL</value></property>
             <property><name>tserver.port.search</name><value>true</value></property>
             <property><name>logger.dir.walog</name><value>/data/accumulo/walogs</value></property>
             <property><name>tserver.cache.data.size</name><value>15M</value></property>
             <property><name>tserver.cache.index.size</name><value>15M</value></property>
             <property><name>tserver.memory.maps.max</name><value>256M</value></property>
             <property><name>tserver.walog.max.size</name><value>256M</value></property>
             <property><name>tserver.memory.maps.native.enabled</name><value>false</value></property>
             <property><name>trace.token.property.password</name><value>root</value></property>
             <property><name>gc.cycle.delay</name><value>4s</value></property>
             <property><name>gc.cycle.start</name><value>0s</value></property>
             <property><name>tserver.compaction.major.delay</name><value>3</value></property>
             <property><name>general.classpaths</name><value>
             /data/accumulo/lib/[^.].*.jar,
             ${HADOOP_HOME}/share/hadoop/common/.*.jar,
             ${HADOOP_HOME}/share/hadoop/common/lib/.*.jar,
             ${HADOOP_HOME}/share/hadoop/hdfs/.*.jar,
             ${HADOOP_HOME}/share/hadoop/mapreduce/.*.jar,
             ${HADOOP_HOME}/share/hadoop/yarn/.*.jar,
             ${ACCUMULO_HOME}/server/target/classes/,
             ${ACCUMULO_HOME}/lib/accumulo-server.jar,
             ${ACCUMULO_HOME}/core/target/classes/,
             ${ACCUMULO_HOME}/lib/accumulo-core.jar,
             ${ACCUMULO_HOME}/start/target/classes/,
             ${ACCUMULO_HOME}/lib/accumulo-start.jar,
             ${ACCUMULO_HOME}/fate/target/classes/,
             ${ACCUMULO_HOME}/lib/accumulo-fate.jar,
             ${ACCUMULO_HOME}/proxy/target/classes/,
             ${ACCUMULO_HOME}/lib/accumulo-proxy.jar,
             ${ACCUMULO_HOME}/lib/[^.].*.jar,
             /home/vagrant/${ZOOKEEPER_HOME}/zookeeper[^.].*.jar,
             $HADOOP_CONF_DIR,
             ${HADOOP_HOME}/[^.].*.jar,
             ${HADOOP_HOME}/lib/[^.].*.jar,
             </value></property>
             <property><name>general.dynamic.classpaths</name><value>/data/accumulo/lib/ext/[^.].*.jar</value></property>
             <property><name>trace.port.client</name><value>0</value></property>
             <property><name>monitor.port.client</name><value>0</value></property>
             <property><name>master.port.client</name><value>0</value></property>
             <property><name>tserver.port.client</name><value>0</value></property>
             <property><name>gc.port.client</name><value>0</value></property>
         </configuration>
 EOF
     cat > ${ACCUMULO_HOME}/conf/masters <<EOF
 rya-example-box
 EOF

 	cat > ${ACCUMULO_HOME}/conf/slaves <<EOF
 rya-example-box
 EOF
     sudo mkdir --parents /data
     sudo chown vagrant:vagrant /data
     mkdir --parents /data/accumulo/lib/ext

     sudo chmod -R a+rwX ${ACCUMULO_HOME}/logs/

     echo "Starting Accumulo..."
     echo "Init will fail during a re-provision, but you can ignore it:  'FATAL: It appears the directories [...] were previously initialized.'"
     echo "Also, you may see an indefinitely repeating: 'Waiting for accumulo to be initialized' which means Accumulo won't start."
     echo "Either issue can be resolved by removing the directory: 'sudo rm -r /data/accumulo' then re-provision. Warning: this will erase all Rya/Accumulo data."
     ${ACCUMULO_HOME}/bin/accumulo init --instance-name dev --password root
     ${ACCUMULO_HOME}/bin/start-all.sh  || exit 107

     sudo chmod -R a+rwX ${ACCUMULO_HOME}/logs/

     echo 'Done!'

 	echo "Installing RDF4J Server"
 	# creating log dir rdf4j-http-server-${RDF4J_VERSION}
 	sudo mkdir --parents /usr/share/tomcat7/.RDF4J
 	sudo chown -R tomcat7:tomcat7 /usr/share/tomcat7
     sudo ln --force -s /usr/share/tomcat7/.RDF4J/Server/logs /var/log/tomcat7/rdf4j-server
 	rdf4jwar=/var/lib/tomcat7/webapps/rdf4j-server.war
 	if [[ ! -s $rdf4jwar ]] ; then
 		echo "Downloading RDF4J Server"
 		download --output $rdf4jwar ${mavenRepoUrl}org/eclipse/rdf4j/rdf4j-http-server/${RDF4J_VERSION}/rdf4j-http-server-${RDF4J_VERSION}.war || exit 110
 	fi
 	echo "RDF4J http server deployed at http://rya-example-box:8080/rdf4j-server"

 	echo "Installing RDF4J Workbench"
 	workbench=/var/lib/tomcat7/webapps/rdf4j-workbench.war
 	if [[ ! -s $workbench ]] ; then
 		echo "Downloading RDF4J Workbench"
 		download --output $workbench ${mavenRepoUrl}org/eclipse/rdf4j/rdf4j-http-workbench/${RDF4J_VERSION}/rdf4j-http-workbench-${RDF4J_VERSION}.war || exit 111
 	fi
 	echo "RDF4J workbench deployed at http://rya-example-box:8080/rdf4j-workbench"

 	echo "Installing Rya"
 	ryaIndexing=rya.indexing.example-${RYA_EXAMPLE_VERSION}-distribution
 	if [[ ! -s ${ryaIndexing}.zip ]] ; then
 		# Eventually it'll be on maven...
 		echo "Downloading ${ryaIndexing} quietly, this will take some minutes with no output..."
 		download --output ${ryaIndexing}.zip ${mavenRepoUrl}org/apache/rya/rya.indexing.example/${RYA_EXAMPLE_VERSION}/${ryaIndexing}.zip?raw=1  || exit 112
 	fi
 	sudo mkdir --parents ${ryaIndexing}
 	sudo unzip -q -o ${ryaIndexing}.zip -d ${ryaIndexing}

     # before continueing, wait for tomcat to deploy wars:
     waitForDeploy /var/lib/tomcat7/webapps/rdf4j-workbench/WEB-INF/lib/
     waitForDeploy /var/lib/tomcat7/webapps/rdf4j-server/WEB-INF/lib/

 	# soft linking the files doesn't seem to work in tomcat, so we copy them instead :(
 	sudo cp ${ryaIndexing}/dist/lib/* /var/lib/tomcat7/webapps/rdf4j-workbench/WEB-INF/lib/ || exit 113
 	sudo cp ${ryaIndexing}/dist/lib/* /var/lib/tomcat7/webapps/rdf4j-server/WEB-INF/lib/    || exit 114

 	# These are older libs that breaks tomcat 7
 	sudo rm --force /var/lib/tomcat7/webapps/rdf4j-workbench/WEB-INF/lib/servlet-api-2.5.jar
 	sudo rm --force /var/lib/tomcat7/webapps/rdf4j-workbench/WEB-INF/lib/jsp-api-2.1.jar
 	sudo rm --force /var/lib/tomcat7/webapps/rdf4j-server/WEB-INF/lib/servlet-api-2.5.jar
 	sudo rm --force /var/lib/tomcat7/webapps/rdf4j-server/WEB-INF/lib/jsp-api-2.1.jar

 	sudo chown -R tomcat7:tomcat7 /var/lib/tomcat7/webapps/rdf4j-workbench/WEB-INF/lib/
 	sudo chown -R tomcat7:tomcat7 /var/lib/tomcat7/webapps/rdf4j-server/WEB-INF/lib/

 	echo "Downloading and installing new templates for RDF4J WorkBench"
 	ryaVagrant=rya.vagrant.example-${RYA_EXAMPLE_VERSION}
 	if [[ ! -s ${ryaVagrant}.jar ]] ; then
 		echo "Downloading ${ryaVagrant}"
 		download --output ${ryaVagrant}.jar  ${mavenRepoUrl}org/apache/rya/rya.vagrant.example/${RYA_EXAMPLE_VERSION}/${ryaVagrant}.jar?raw=1 || exit 120
 	fi
 	sudo mkdir --parents ${ryaVagrant}
 	sudo unzip -q -o ${ryaVagrant}.jar -d ${ryaVagrant}
 	sudo cp ${ryaVagrant}/*.xsl /var/lib/tomcat7/webapps/rdf4j-workbench/transformations/
     sudo chown tomcat7:tomcat7 /var/lib/tomcat7/webapps/rdf4j-workbench/transformations/*

 	echo "Deploying Rya Web"
 	ryaWar=web.rya-${RYA_EXAMPLE_VERSION}.war
 	if [[ ! -s ${ryaWar} ]] ; then
 		echo "Downloading ${ryaWar}"
 		download ${mavenRepoUrl}org/apache/rya/web.rya/${RYA_EXAMPLE_VERSION}/${ryaWar}.jar?raw=1 --output ${ryaWar} || exit 121
 	fi
 	sudo cp ${ryaWar} /var/lib/tomcat7/webapps/web.rya.war
 	# Wait for the war to deploy
     waitForDeploy /var/lib/tomcat7/webapps/web.rya/WEB-INF/classes/

 	# These are older libs that breaks tomcat 7
 	sudo rm --force /var/lib/tomcat7/webapps/web.rya/WEB-INF/lib/servlet-api-2.5*.jar
 	sudo rm --force /var/lib/tomcat7/webapps/web.rya/WEB-INF/lib/jsp-api-2.1.jar

 	echo "Modify Rya Web Config"
 	cat > /var/lib/tomcat7/webapps/web.rya/WEB-INF/classes/environment.properties <<EOF
 instance.name=dev
 instance.zk=localhost:2181
 instance.username=root
 instance.password=root
 rya.tableprefix=rya_
 rya.displayqueryplan=true
 EOF

 	echo "Rya web deployed at http://rya-example-box:8080/web.rya/sparqlQuery.jsp"

 	# restart tomcat
 	sudo -E service tomcat7 restart

 	echo "Finished and ready to use!"
     echo "You can re-apply these settings without losing data by running the command 'vagrant provision'"
   SHELL

 end
	# Licensed to the Apache Software Foundation (ASF) under one
	# or more contributor license agreements. See the NOTICE file
	# distributed with this work for additional information
	# regarding copyright ownership. The ASF licenses this file
	# to you under the Apache License, Version 2.0 (the
	# "License"); you may not use this file except in compliance
	# with the License. You may obtain a copy of the License at
	#
	# http://www.apache.org/licenses/LICENSE-2.0
	#
	# Unless required by applicable law or agreed to in writing,
	# software distributed under the License is distributed on an
	# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
	# KIND, either express or implied. See the License for the
	# specific language governing permissions and limitations
	# under the License.

	# -- mode: ruby --
	# vi: set ft=ruby :

	#
	# Builds a single node Rya on Accumulo on Hadoop and Zookeeper.
	# Deploys Rya, and the Eclipse rdf4j-workbench on Tomcat accessible from the host's browser.
	# See the accompanying readme for URL's, verification, and troubleshooting.
	#
	# Note: Machine's ip is 192.168.33.10
	# username : vagrant
	# password : vagrant
	#
	# accumulo instance : dev
	# accumulo username : root
	# accumulo password : root

	Vagrant.configure(2) do \|config\|

	config.vm.box = "ubuntu/trusty64"
	config.vm.box_url = "https://cloud-images.ubuntu.com/vagrant/trusty/current/trusty-server-cloudimg-amd64-vagrant-disk1.box"

	config.vm.provider "virtualbox" do \|vb\|
	vb.name = "rya-example-box"
	vb.memory = "4096"
	vb.cpus = 4
	end

	config.vm.network :private_network, ip: "192.168.33.10"
	config.vm.hostname = "rya-example-box"

	config.vm.provision "shell", inline: <<-SHELL

	###set -x ## turn on command echo with expanded variables
	# List of dependency versions
	export ACCUMULO_VERSION=1.6.5
	###export ACCUMULO_VERSION=1.7.1
	export HADOOP_VERSION=2.7.2
	export RYA_EXAMPLE_VERSION=4.0.0-incubating
	export RDF4J_VERSION=2.3.1
	export ZOOKEEPER_VERSION=3.4.5-cdh4.5.0

	mavenRepoUrl=http://repo1.maven.org/maven2/

	echo "Updating host file with permanent ip"
	sudo sed -i 's/127.0.1.1/192.168.33.10/' /etc/hosts
	cat >> /etc/hosts <<EOF
	192.168.33.10 zoo1 zoo2 zoo3
	EOF

	sudo -E apt-get -qq update

	echo "Installing Java installer..."
	sudo -E add-apt-repository ppa:webupd8team/java \|\| exit $?
	sudo -E apt-get -qq update \|\| exit $?
	echo debconf shared/accepted-oracle-license-v1-1 select true \| \
	sudo -E /usr/bin/debconf-set-selections
	echo debconf shared/accepted-oracle-license-v1-1 seen true \| \
	sudo -E /usr/bin/debconf-set-selections
	sudo mkdir --parents /var/cache/oracle-jdk8-installer \|\| exit $?
	echo verbose=off >> /var/cache/oracle-jdk8-installer/wgetrc \|\| exit $?

	echo "Installing Java..."
	sudo -E apt-get -qq install -y oracle-java8-installer \|\| exit $?
	sudo ln --force -s /usr/lib/jvm/java-8-oracle/ /usr/lib/jvm/default-java

	echo "Installing Tomcat..."
	sudo -E apt-get install -y tomcat7 \|\| exit $?

	echo "Installing Unzip..."
	apt-get install unzip \|\| exit $?

	echo "Setting up environment..."
	export JAVA_HOME=/usr/lib/jvm/java-8-oracle
	export HADOOP_HOME=/home/vagrant/hadoop-${HADOOP_VERSION}
	export ZOOKEEPER_HOME=/home/vagrant/zookeeper-${ZOOKEEPER_VERSION}
	export ZOO_LOG_DIR=${ZOOKEEPER_HOME}/logs/
	export ACCUMULO_HOME=/home/vagrant/accumulo-${ACCUMULO_VERSION}
	export PATHADD=$JAVA_HOME/bin:$ZOOKEEPER_HOME/bin:$ACCUMULO_HOME/bin:$HADOOP_HOME/bin
	export PATH=$PATH:$PATHADD

	export HADOOP_PREFIX="$HADOOP_HOME"
	export HADOOP_CONF_DIR="$HADOOP_PREFIX/etc/hadoop"
	export ACCUMULO_LOG_DIR=$ACCUMULO_HOME/logs
	export ACCUMULO_TSERVER_OPTS="-Xmx384m -Xms384m "
	export ACCUMULO_MASTER_OPTS="-Xmx128m -Xms128m"
	export ACCUMULO_MONITOR_OPTS="-Xmx64m -Xms64m"
	export ACCUMULO_GC_OPTS="-Xmx64m -Xms64m"
	export ACCUMULO_GENERAL_OPTS="-XX:+UseConcMarkSweepGC -XX:CMSInitiatingOccupancyFraction=75 -Djava.net.preferIPv4Stack=true"
	export ACCUMULO_OTHER_OPTS="-Xmx128m -Xms64m"
	export ACCUMULO_KILL_CMD='kill -9 %p'
	# Shell environment includes Accumulo resources.
	ACCUMULO_RC=/home/vagrant/.accumulo_rc.sh
	cat > ${ACCUMULO_RC} <<EOF

	export JAVA_HOME=\'$JAVA_HOME\'
	export HADOOP_HOME=\'$HADOOP_HOME\'
	export ZOOKEEPER_HOME=\'$ZOOKEEPER_HOME\'
	export ZOO_LOG_DIR=\'$ZOO_LOG_DIR\'
	export ACCUMULO_HOME=\'$ACCUMULO_HOME\'
	export PATH=\\$PATH:$PATHADD

	export HADOOP_PREFIX=\'$HADOOP_PREFIX\'
	export HADOOP_CONF_DIR=\'$HADOOP_CONF_DIR\'
	export ACCUMULO_LOG_DIR=\'$ACCUMULO_LOG_DIR\'
	export ACCUMULO_TSERVER_OPTS=\'$ACCUMULO_TSERVER_OPTS\'
	export ACCUMULO_MASTER_OPTS=\'$ACCUMULO_MASTER_OPTS\'
	export ACCUMULO_MONITOR_OPTS=\'$ACCUMULO_MONITOR_OPTS\'
	export ACCUMULO_GC_OPTS=\'$ACCUMULO_GC_OPTS\'
	export ACCUMULO_GENERAL_OPTS=\'$ACCUMULO_GENERAL_OPTS\'
	export ACCUMULO_OTHER_OPTS=\'$ACCUMULO_OTHER_OPTS\'
	export ACCUMULO_KILL_CMD=\'$ACCUMULO_KILL_CMD\'

	### command to list the 7 correct java processes: tomcat-catalina, zookeeper, and 5 Accumulo: tracer, master, monitor, tserver, gc.
	function ryaps() { ps -ef \| grep java \| tr ' ' '\\n' \| egrep '^org\\.apache\|^tracer\|^master\|^monitor\|^tserver\|^gc' \| sed '/\\.Main/ N ; s/\\n/ /' ; }
	EOF
	source ${ACCUMULO_RC} \|\| exit 151

	# include it at the beginning of both shell configuration files.

	for BASHRC in /home/vagrant/.bashrc /home/vagrant/.bash_profile ;
	do touch ${BASHRC} ;
	cat - ${BASHRC} > ${BASHRC}.new <<EOF && mv ${BASHRC}.new ${BASHRC} \|\| exit 152
	source ${ACCUMULO_RC}
	EOF
	done
	echo "Acquiring and Extracting ..."

	function echoerr() { printf "%s\n" "$*" >&2; }

	function download {
	### curl --fail treat http status >= 400 as an error. --location follow redirects status>=300
	curl --silent --show-error --fail --location "$@"
	if [ $? -ne 0 ]; then
	echoerr "--------------------------"
	echoerr "-"
	echoerr "- download failed" "$@"
	echoerr "-"
	echoerr "-" exiting ...
	echoerr "-"
	echoerr "--------------------------"
	exit 800
	fi
	}
	### wait for a directory to exist or 60 seconds timeout
	function waitForDeploy {
	waitfordir="$1"
	timeout=60
	while [[ ! -d "$waitfordir" ]]
	do
	sleep 5
	let timeout-=5
	if [[ $timeout -le "0" ]]; then
	echo "Timeout waiting for war to deploy, $waitfordir still does not exist.";
	exit 401
	fi
	done
	}

	echo "- Hadoop"
	hadoopUrl=http://apache.mirrors.tds.net/hadoop/common/hadoop-${HADOOP_VERSION}/hadoop-${HADOOP_VERSION}.tar.gz
	if [[ ! -d ${HADOOP_HOME} ]] ; then
	echo "Downloading $hadoopUrl"
	download $hadoopUrl \
	\| tar -zxC /home/vagrant \|\| exit 101
	fi

	echo "- Zookeeper"
	zookeeperUrl=http://archive-primary.cloudera.com/cdh4/cdh/4/zookeeper-${ZOOKEEPER_VERSION}.tar.gz
	if [[ ! -d ${ZOOKEEPER_HOME} ]] ; then
	echo "Downloading $zookeeperUrl"
	download $zookeeperUrl \
	\| tar -zxC /home/vagrant \|\| exit 102
	fi

	echo "- Accumulo"
	accumuloUrl=http://apache.mirrors.pair.com/accumulo/${ACCUMULO_VERSION}/accumulo-${ACCUMULO_VERSION}-bin.tar.gz
	if [[ ! -d ${ACCUMULO_HOME} ]] ; then
	echo "Downloading $accumuloUrl"
	download $accumuloUrl \
	\| tar -zxC /home/vagrant \|\| exit 103
	fi

	echo "Configuring Zookeeper..."
	sudo mkdir --parents /var/zookeeper
	sudo chown vagrant:vagrant /var/zookeeper
	sudo cp ${ZOOKEEPER_HOME}/conf/zoo_sample.cfg ${ZOOKEEPER_HOME}/conf/zoo.cfg
	# Change the dataDir to /var/zookeeper -- strange that backslashes need to be escaped only on this line.
	sudo sed -i 's/^\\sdataDir\\s=.*$/dataDir=\\/var\\/zookeeper/' ${ZOOKEEPER_HOME}/conf/zoo.cfg \|\| exit 104
	# Conflicts with Accumulo and maybe Zookeeper
	sudo rm --force ${HADOOP_HOME}/share/hadoop/common/lib/slf4j-api-1.7.10.jar
	sudo rm --force ${HADOOP_HOME}/share/hadoop/common/lib/slf4j-log4j12-1.7.10.jar

	# Assure logs are creatable and writeable
	sudo mkdir --parents ${ZOO_LOG_DIR}
	sudo touch "${ZOO_LOG_DIR}/zookeeper.out"
	sudo chmod -R a+wX ${ZOO_LOG_DIR}

	echo "Running Zookeeper..."
	sudo -E ${ZOOKEEPER_HOME}/bin/zkServer.sh start

	echo "Configuring Accumulo..."
	cp ${ACCUMULO_HOME}/conf/examples/1GB/standalone/* ${ACCUMULO_HOME}/conf/
	rm --force ${ACCUMULO_HOME}/conf/accumulo-site.xml
	cat >> ${ACCUMULO_HOME}/conf/accumulo-site.xml <<EOF
	<configuration>
	<property><name>instance.dfs.uri</name><value>file:///</value></property>
	<property><name>instance.dfs.dir</name><value>/data/accumulo</value></property>
	<property><name>instance.zookeeper.host</name><value>localhost:2181</value></property>
	<property><name>instance.secret</name><value>DONTTELL</value></property>
	<property><name>tserver.port.search</name><value>true</value></property>
	<property><name>logger.dir.walog</name><value>/data/accumulo/walogs</value></property>
	<property><name>tserver.cache.data.size</name><value>15M</value></property>
	<property><name>tserver.cache.index.size</name><value>15M</value></property>
	<property><name>tserver.memory.maps.max</name><value>256M</value></property>
	<property><name>tserver.walog.max.size</name><value>256M</value></property>
	<property><name>tserver.memory.maps.native.enabled</name><value>false</value></property>
	<property><name>trace.token.property.password</name><value>root</value></property>
	<property><name>gc.cycle.delay</name><value>4s</value></property>
	<property><name>gc.cycle.start</name><value>0s</value></property>
	<property><name>tserver.compaction.major.delay</name><value>3</value></property>
	<property><name>general.classpaths</name><value>
	/data/accumulo/lib/[^.].*.jar,
	${HADOOP_HOME}/share/hadoop/common/.*.jar,
	${HADOOP_HOME}/share/hadoop/common/lib/.*.jar,
	${HADOOP_HOME}/share/hadoop/hdfs/.*.jar,
	${HADOOP_HOME}/share/hadoop/mapreduce/.*.jar,
	${HADOOP_HOME}/share/hadoop/yarn/.*.jar,
	${ACCUMULO_HOME}/server/target/classes/,
	${ACCUMULO_HOME}/lib/accumulo-server.jar,
	${ACCUMULO_HOME}/core/target/classes/,
	${ACCUMULO_HOME}/lib/accumulo-core.jar,
	${ACCUMULO_HOME}/start/target/classes/,
	${ACCUMULO_HOME}/lib/accumulo-start.jar,
	${ACCUMULO_HOME}/fate/target/classes/,
	${ACCUMULO_HOME}/lib/accumulo-fate.jar,
	${ACCUMULO_HOME}/proxy/target/classes/,
	${ACCUMULO_HOME}/lib/accumulo-proxy.jar,
	${ACCUMULO_HOME}/lib/[^.].*.jar,
	/home/vagrant/${ZOOKEEPER_HOME}/zookeeper[^.].*.jar,
	$HADOOP_CONF_DIR,
	${HADOOP_HOME}/[^.].*.jar,
	${HADOOP_HOME}/lib/[^.].*.jar,
	</value></property>
	<property><name>general.dynamic.classpaths</name><value>/data/accumulo/lib/ext/[^.].*.jar</value></property>
	<property><name>trace.port.client</name><value>0</value></property>
	<property><name>monitor.port.client</name><value>0</value></property>
	<property><name>master.port.client</name><value>0</value></property>
	<property><name>tserver.port.client</name><value>0</value></property>
	<property><name>gc.port.client</name><value>0</value></property>
	</configuration>
	EOF
	cat > ${ACCUMULO_HOME}/conf/masters <<EOF
	rya-example-box
	EOF

	cat > ${ACCUMULO_HOME}/conf/slaves <<EOF
	rya-example-box
	EOF
	sudo mkdir --parents /data
	sudo chown vagrant:vagrant /data
	mkdir --parents /data/accumulo/lib/ext

	sudo chmod -R a+rwX ${ACCUMULO_HOME}/logs/

	echo "Starting Accumulo..."
	echo "Init will fail during a re-provision, but you can ignore it: 'FATAL: It appears the directories [...] were previously initialized.'"
	echo "Also, you may see an indefinitely repeating: 'Waiting for accumulo to be initialized' which means Accumulo won't start."
	echo "Either issue can be resolved by removing the directory: 'sudo rm -r /data/accumulo' then re-provision. Warning: this will erase all Rya/Accumulo data."
	${ACCUMULO_HOME}/bin/accumulo init --instance-name dev --password root
	${ACCUMULO_HOME}/bin/start-all.sh \|\| exit 107

	sudo chmod -R a+rwX ${ACCUMULO_HOME}/logs/

	echo 'Done!'

	echo "Installing RDF4J Server"
	# creating log dir rdf4j-http-server-${RDF4J_VERSION}
	sudo mkdir --parents /usr/share/tomcat7/.RDF4J
	sudo chown -R tomcat7:tomcat7 /usr/share/tomcat7
	sudo ln --force -s /usr/share/tomcat7/.RDF4J/Server/logs /var/log/tomcat7/rdf4j-server
	rdf4jwar=/var/lib/tomcat7/webapps/rdf4j-server.war
	if [[ ! -s $rdf4jwar ]] ; then
	echo "Downloading RDF4J Server"
	download --output $rdf4jwar ${mavenRepoUrl}org/eclipse/rdf4j/rdf4j-http-server/${RDF4J_VERSION}/rdf4j-http-server-${RDF4J_VERSION}.war \|\| exit 110
	fi
	echo "RDF4J http server deployed at http://rya-example-box:8080/rdf4j-server"

	echo "Installing RDF4J Workbench"
	workbench=/var/lib/tomcat7/webapps/rdf4j-workbench.war
	if [[ ! -s $workbench ]] ; then
	echo "Downloading RDF4J Workbench"
	download --output $workbench ${mavenRepoUrl}org/eclipse/rdf4j/rdf4j-http-workbench/${RDF4J_VERSION}/rdf4j-http-workbench-${RDF4J_VERSION}.war \|\| exit 111
	fi
	echo "RDF4J workbench deployed at http://rya-example-box:8080/rdf4j-workbench"

	echo "Installing Rya"
	ryaIndexing=rya.indexing.example-${RYA_EXAMPLE_VERSION}-distribution
	if [[ ! -s ${ryaIndexing}.zip ]] ; then
	# Eventually it'll be on maven...
	echo "Downloading ${ryaIndexing} quietly, this will take some minutes with no output..."
	download --output ${ryaIndexing}.zip ${mavenRepoUrl}org/apache/rya/rya.indexing.example/${RYA_EXAMPLE_VERSION}/${ryaIndexing}.zip?raw=1 \|\| exit 112
	fi
	sudo mkdir --parents ${ryaIndexing}
	sudo unzip -q -o ${ryaIndexing}.zip -d ${ryaIndexing}

	# before continueing, wait for tomcat to deploy wars:
	waitForDeploy /var/lib/tomcat7/webapps/rdf4j-workbench/WEB-INF/lib/
	waitForDeploy /var/lib/tomcat7/webapps/rdf4j-server/WEB-INF/lib/

	# soft linking the files doesn't seem to work in tomcat, so we copy them instead :(
	sudo cp ${ryaIndexing}/dist/lib/* /var/lib/tomcat7/webapps/rdf4j-workbench/WEB-INF/lib/ \|\| exit 113
	sudo cp ${ryaIndexing}/dist/lib/* /var/lib/tomcat7/webapps/rdf4j-server/WEB-INF/lib/ \|\| exit 114

	# These are older libs that breaks tomcat 7
	sudo rm --force /var/lib/tomcat7/webapps/rdf4j-workbench/WEB-INF/lib/servlet-api-2.5.jar
	sudo rm --force /var/lib/tomcat7/webapps/rdf4j-workbench/WEB-INF/lib/jsp-api-2.1.jar
	sudo rm --force /var/lib/tomcat7/webapps/rdf4j-server/WEB-INF/lib/servlet-api-2.5.jar
	sudo rm --force /var/lib/tomcat7/webapps/rdf4j-server/WEB-INF/lib/jsp-api-2.1.jar

	sudo chown -R tomcat7:tomcat7 /var/lib/tomcat7/webapps/rdf4j-workbench/WEB-INF/lib/
	sudo chown -R tomcat7:tomcat7 /var/lib/tomcat7/webapps/rdf4j-server/WEB-INF/lib/

	echo "Downloading and installing new templates for RDF4J WorkBench"
	ryaVagrant=rya.vagrant.example-${RYA_EXAMPLE_VERSION}
	if [[ ! -s ${ryaVagrant}.jar ]] ; then
	echo "Downloading ${ryaVagrant}"
	download --output ${ryaVagrant}.jar ${mavenRepoUrl}org/apache/rya/rya.vagrant.example/${RYA_EXAMPLE_VERSION}/${ryaVagrant}.jar?raw=1 \|\| exit 120
	fi
	sudo mkdir --parents ${ryaVagrant}
	sudo unzip -q -o ${ryaVagrant}.jar -d ${ryaVagrant}
	sudo cp ${ryaVagrant}/*.xsl /var/lib/tomcat7/webapps/rdf4j-workbench/transformations/
	sudo chown tomcat7:tomcat7 /var/lib/tomcat7/webapps/rdf4j-workbench/transformations/*

	echo "Deploying Rya Web"
	ryaWar=web.rya-${RYA_EXAMPLE_VERSION}.war
	if [[ ! -s ${ryaWar} ]] ; then
	echo "Downloading ${ryaWar}"
	download ${mavenRepoUrl}org/apache/rya/web.rya/${RYA_EXAMPLE_VERSION}/${ryaWar}.jar?raw=1 --output ${ryaWar} \|\| exit 121
	fi
	sudo cp ${ryaWar} /var/lib/tomcat7/webapps/web.rya.war
	# Wait for the war to deploy
	waitForDeploy /var/lib/tomcat7/webapps/web.rya/WEB-INF/classes/

	# These are older libs that breaks tomcat 7
	sudo rm --force /var/lib/tomcat7/webapps/web.rya/WEB-INF/lib/servlet-api-2.5*.jar
	sudo rm --force /var/lib/tomcat7/webapps/web.rya/WEB-INF/lib/jsp-api-2.1.jar

	echo "Modify Rya Web Config"
	cat > /var/lib/tomcat7/webapps/web.rya/WEB-INF/classes/environment.properties <<EOF
	instance.name=dev
	instance.zk=localhost:2181
	instance.username=root
	instance.password=root
	rya.tableprefix=rya_
	rya.displayqueryplan=true
	EOF

	echo "Rya web deployed at http://rya-example-box:8080/web.rya/sparqlQuery.jsp"

	# restart tomcat
	sudo -E service tomcat7 restart

	echo "Finished and ready to use!"
	echo "You can re-apply these settings without losing data by running the command 'vagrant provision'"
	SHELL

	end