#13 put spark

fixes #13
fixes #3

Author: FRosner

Dockerfile

@@ -20,6 +20,9 @@ RUN rm -rf /var/lib/apt/lists/* && \
   apt-get install -y sudo && \
   apt-get clean all
 
+RUN curl -s http://d3kbcqa49mib13.cloudfront.net/spark-1.6.2-bin-hadoop2.6.tgz | tar -xz -C /usr/local
+RUN mv /usr/local/spark* /usr/local/spark
+
 RUN rm -f conf/zeppelin-env.sh
 RUN rm -f conf/zeppelin-site.xml
 RUN rm -f conf/interpreter.json

zeppelin-env.sh.template

@@ -4,16 +4,9 @@ export ZEPPELIN_NOTEBOOK_DIR="notebooks"   		# Where notebook at?
 
 #### Spark interpreter configuration ####
 
-## Use provided spark installation ##
-## defining SPARK_HOME makes Zeppelin run spark interpreter process using spark-submit
-##
-# export SPARK_HOME                             # (required) When it is defined, load it instead of Zeppelin embedded Spark libraries
+export SPARK_HOME=/usr/local/spark
 # export SPARK_SUBMIT_OPTIONS="--master spark://master:7077"                   # (optional) extra options to pass to spark submit. eg) "--driver-memory 512M --executor-memory 1G".
 
-## Use embedded spark binaries ##
-## without SPARK_HOME defined, Zeppelin still able to run spark interpreter process using embedded spark binaries.
-## however, it is not encouraged when you can define SPARK_HOME
-##
 # Options read in YARN client mode
 # export HADOOP_CONF_DIR         		# yarn-site.xml is located in configuration directory in HADOOP_CONF_DIR.
 # Pyspark (supported with Spark 1.2.1 and above)