Dockerfile_base

# This base image comes shipped with java 8 (needed for scala)
FROM openjdk:8-jdk-alpine
# It also comes with Anaconda and Python (needed for PySpark and Zeppelin Python Interpreter)
COPY --from=continuumio/anaconda3:2019.07-alpine / /

# Set env variables
ENV DAEMON_RUN=true
ENV SPARK_VERSION=2.4.5
ENV HADOOP_VERSION=2.7
ENV SCALA_VERSION=2.12.3
ENV SCALA_HOME=/usr/share/scala
ENV SPARK_HOME=/spark
ENV SPARK_OPTS --driver-java-options=-Xms1024M --driver-java-options=-Xmx4096M --driver-java-options=-Dlog4j.logLevel=info
ENV PYTHONPATH $SPARK_HOME/python:$SPARK_HOME/python/lib/py4j-0.10.7-src.zip
ENV ZEPPELIN_HOME=/zeppelin
ENV ZEPPELIN_VERSION=0.8.2
ENV ZEPPELIN_ADDR="0.0.0.0"

# Add additional repo's for apk to use
RUN echo http://mirror.yandex.ru/mirrors/alpine/v3.3/main > /etc/apk/repositories; \
    echo http://mirror.yandex.ru/mirrors/alpine/v3.3/community >> /etc/apk/repositories

# Update commands
RUN apk --update add wget tar bash coreutils procps openssl

# Install Scala
RUN apk add --no-cache --virtual=.build-dependencies wget ca-certificates && \
    apk add --no-cache bash && \
    cd "/tmp" && \
    wget "https://downloads.typesafe.com/scala/${SCALA_VERSION}/scala-${SCALA_VERSION}.tgz" && \
    tar xzf "scala-${SCALA_VERSION}.tgz" && \
    mkdir "${SCALA_HOME}" && \
    rm "/tmp/scala-${SCALA_VERSION}/bin/"*.bat && \
    mv "/tmp/scala-${SCALA_VERSION}/bin" "/tmp/scala-${SCALA_VERSION}/lib" "${SCALA_HOME}" && \
    ln -s "${SCALA_HOME}/bin/"* "/usr/bin/" && \
    apk del .build-dependencies && \
    rm -rf "/tmp/"*

RUN export PATH="/usr/local/sbt/bin:$PATH" &&  apk update && apk add ca-certificates wget tar && mkdir -p "/usr/local/sbt"

# Get Apache Spark
RUN wget https://archive.apache.org/dist/spark/spark-${SPARK_VERSION}/spark-${SPARK_VERSION}-bin-hadoop${HADOOP_VERSION}.tgz

# Install Spark and move it to the folder "/spark" and then add this location to the PATH env variable
RUN tar -xzf spark-${SPARK_VERSION}-bin-hadoop${HADOOP_VERSION}.tgz && \
    mv spark-${SPARK_VERSION}-bin-hadoop${HADOOP_VERSION} /spark && \
    rm spark-${SPARK_VERSION}-bin-hadoop${HADOOP_VERSION}.tgz && \
    export PATH=$SPARK_HOME/bin:$PATH

# Install Zeppelin
RUN wget -O zeppelin-${ZEPPELIN_VERSION}-bin-all.tgz http://archive.apache.org/dist/zeppelin/zeppelin-${ZEPPELIN_VERSION}/zeppelin-${ZEPPELIN_VERSION}-bin-all.tgz && \
    tar -zxvf zeppelin-${ZEPPELIN_VERSION}-bin-all.tgz && \
    rm -rf zeppelin-${ZEPPELIN_VERSION}-bin-all.tgz && \
    mkdir -p ${ZEPPELIN_HOME} && \
    mv zeppelin-${ZEPPELIN_VERSION}-bin-all/* ${ZEPPELIN_HOME}/ && \
    chown -R root:root ${ZEPPELIN_HOME} && \
    mkdir -p ${ZEPPELIN_HOME}/logs ${ZEPPELIN_HOME}/run ${ZEPPELIN_HOME}/webapps && \
    # Allow process to edit /etc/passwd, to create a user entry for zeppelin
    chgrp root /etc/passwd && chmod ug+rw /etc/passwd && \
    # Give access to some specific folders
    chmod -R 755 "${ZEPPELIN_HOME}/logs" "${ZEPPELIN_HOME}/run" "${ZEPPELIN_HOME}/notebook" "${ZEPPELIN_HOME}/conf" && \
    # Allow process to create new folders (e.g. webapps)
    chmod 755 ${ZEPPELIN_HOME}

# Install custom packages not included in Anaconda
RUN /opt/conda/bin/conda install -c anaconda -y \
    pymongo \
    r-base \
    r-caret \
    r-crayon \
    r-devtools \
    r-forecast \
    r-knitr \
    r-ggplot2 \
    r-googleVis \
    r-hexbin \
    r-htmltools \
    r-htmlwidgets \
    r-irkernel \
    r-nycflights13 \
    r-randomforest \
    r-rcurl \
    r-rmarkdown \
    r-rodbc \
    r-rsqlite \
    r-shiny \
    r-tidyverse \
    unixodbc \
    && /opt/conda/bin/conda clean --all -f -y

ENV PATH="/opt/conda/bin:${PATH}"