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

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

# Fix DL4006
SHELL ["/bin/bash", "-o", "pipefail", "-c"]

USER root

# Spark dependencies
# Default values can be overridden at build time
# (ARGS are in lower case to distinguish them from ENV)
ARG spark_version="3.2.0"
ARG hadoop_version="3.2"
ARG spark_checksum="EBE51A449EBD070BE7D3570931044070E53C23076ABAD233B3C51D45A7C99326CF55805EE0D573E6EB7D6A67CFEF1963CD77D6DC07DD2FD70FD60DA9D1F79E5E"
ARG openjdk_version="11"

ENV APACHE_SPARK_VERSION="${spark_version}" \
    HADOOP_VERSION="${hadoop_version}"

RUN apt-get update --yes && \
    apt-get install --yes --no-install-recommends \
    "openjdk-${openjdk_version}-jre-headless" \
    ca-certificates-java && \
    apt-get clean && rm -rf /var/lib/apt/lists/*

# Spark installation
WORKDIR /tmp
RUN wget -q "https://archive.apache.org/dist/spark/spark-${APACHE_SPARK_VERSION}/spark-${APACHE_SPARK_VERSION}-bin-hadoop${HADOOP_VERSION}.tgz" && \
    echo "${spark_checksum} *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 --owner root --group root --no-same-owner && \
    rm "spark-${APACHE_SPARK_VERSION}-bin-hadoop${HADOOP_VERSION}.tgz"

WORKDIR /usr/local

# Configure Spark
ENV SPARK_HOME=/usr/local/spark
ENV SPARK_OPTS="--driver-java-options=-Xms1024M --driver-java-options=-Xmx4096M --driver-java-options=-Dlog4j.logLevel=info" \
    PATH="${PATH}:${SPARK_HOME}/bin"

RUN ln -s "spark-${APACHE_SPARK_VERSION}-bin-hadoop${HADOOP_VERSION}" spark && \
    # Add a link in the before_notebook hook in order to source automatically PYTHONPATH
    mkdir -p /usr/local/bin/before-notebook.d && \
    ln -s "${SPARK_HOME}/sbin/spark-config.sh" /usr/local/bin/before-notebook.d/spark-config.sh

# Fix Spark installation for Java 11 and Apache Arrow library
# see: https://github.com/apache/spark/pull/27356, https://spark.apache.org/docs/latest/#downloading
RUN cp -p "${SPARK_HOME}/conf/spark-defaults.conf.template" "${SPARK_HOME}/conf/spark-defaults.conf" && \
    echo 'spark.driver.extraJavaOptions -Dio.netty.tryReflectionSetAccessible=true' >> "${SPARK_HOME}/conf/spark-defaults.conf" && \
    echo 'spark.executor.extraJavaOptions -Dio.netty.tryReflectionSetAccessible=true' >> "${SPARK_HOME}/conf/spark-defaults.conf"

# Configure IPython system-wide
COPY ipython_kernel_config.py "/etc/ipython/"
RUN fix-permissions "/etc/ipython/"

USER ${NB_UID}

# Install pyarrow
RUN mamba install --quiet --yes \
    'pyarrow' && \
    mamba clean --all -f -y && \
    fix-permissions "${CONDA_DIR}" && \
    fix-permissions "/home/${NB_USER}"

WORKDIR "${HOME}"