# Copyright (c) Jupyter Development Team.
# Distributed under the terms of the Modified BSD License.
FROM jupyter/scipy-notebook

LABEL maintainer="Jupyter Project <jupyter@googlegroups.com>"

USER root

# Spark dependencies
ENV APACHE_SPARK_VERSION 2.3.0
ENV HADOOP_VERSION 2.7

RUN apt-get -y update && \
    apt-get install --no-install-recommends -y openjdk-8-jre-headless ca-certificates-java && \
    apt-get clean && \
    rm -rf /var/lib/apt/lists/*

# Install pyarrow
RUN conda install --quiet -y 'pyarrow' && \
    fix-permissions $CONDA_DIR && \
    fix-permissions /home/$NB_USER

RUN cd /tmp && \
        wget -q http://apache.claz.org/spark/spark-${APACHE_SPARK_VERSION}/spark-${APACHE_SPARK_VERSION}-bin-hadoop${HADOOP_VERSION}.tgz && \
        echo "258683885383480BA01485D6C6F7DC7CFD559C1584D6CEB7A3BBCF484287F7F57272278568F16227BE46B4F92591768BA3D164420D87014A136BF66280508B46 *spark-${APACHE_SPARK_VERSION}-bin-hadoop${HADOOP_VERSION}.tgz" | sha512sum -c - && \
        tar xzf spark-${APACHE_SPARK_VERSION}-bin-hadoop${HADOOP_VERSION}.tgz -C /usr/local && \
        rm spark-${APACHE_SPARK_VERSION}-bin-hadoop${HADOOP_VERSION}.tgz
RUN cd /usr/local && ln -s spark-${APACHE_SPARK_VERSION}-bin-hadoop${HADOOP_VERSION} spark

# Mesos dependencies
RUN . /etc/os-release && \
    apt-key adv --keyserver keyserver.ubuntu.com --recv E56151BF && \
    DISTRO=$ID && \
    CODENAME=$VERSION_CODENAME && \
    echo "deb http://repos.mesosphere.io/${DISTRO} ${CODENAME} main" > /etc/apt/sources.list.d/mesosphere.list && \
    apt-get -y update && \
    apt-get --no-install-recommends -y --force-yes install mesos=1.2\* && \
    apt-get clean && \
    rm -rf /var/lib/apt/lists/*

# Spark and Mesos config
ENV SPARK_HOME /usr/local/spark
ENV PYTHONPATH $SPARK_HOME/python:$SPARK_HOME/python/lib/py4j-0.10.6-src.zip
ENV MESOS_NATIVE_LIBRARY /usr/local/lib/libmesos.so
ENV SPARK_OPTS --driver-java-options=-Xms1024M --driver-java-options=-Xmx4096M --driver-java-options=-Dlog4j.logLevel=info

USER $NB_UID