#
# Copyright (c) 2020-2025, NVIDIA CORPORATION. All rights reserved.
#
# Licensed 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.
#

FROM nvidia/cuda:12.9.0-devel-ubuntu22.04
ARG spark_uid=185

# Install Java and Python dependencies
ENV DEBIAN_FRONTEND="noninteractive"
RUN apt-get update && apt-get install -y --no-install-recommends \
    openjdk-8-jdk openjdk-8-jre \
    python3 python3-pip wget tini \
    && ln -s /usr/bin/python3 /usr/bin/python \
    && rm -rf /var/lib/apt/lists/*

ENV JAVA_HOME /usr/lib/jvm/java-1.8.0-openjdk-amd64
ENV PATH $PATH:/usr/lib/jvm/java-1.8.0-openjdk-amd64/jre/bin:/usr/lib/jvm/java-1.8.0-openjdk-amd64/bin

# Before building the Docker image, first either download Apache Spark 3.3+ from
# http://spark.apache.org/downloads.html or build and make a Spark distribution following the
# instructions in https://spark.apache.org/docs/3.5.6/building-spark.html (see
# https://nvidia.github.io/cudf-spark/docs/download.html for other supported versions).  If this
# Docker file is being used in the context of building your images from a Spark distribution, the
# Docker build command should be invoked from the top level directory of the Spark
# distribution. For example, docker build -t spark:3.5.6 -f Dockerfile.cuda .

RUN set -ex && \
    ln -s /lib /lib64 && \
    mkdir -p /opt/spark && \
    mkdir -p /opt/spark/jars && \
    mkdir -p /opt/spark/examples && \
    mkdir -p /opt/spark/work-dir && \
    mkdir -p /opt/sparkRapidsPlugin && \
    touch /opt/spark/RELEASE && \
    rm /bin/sh && \
    ln -sv /bin/bash /bin/sh && \
    echo "auth required pam_wheel.so use_uid" >> /etc/pam.d/su && \
    chgrp root /etc/passwd && chmod ug+rw /etc/passwd

COPY spark/jars /opt/spark/jars
COPY spark/bin /opt/spark/bin
COPY spark/sbin /opt/spark/sbin
COPY spark/kubernetes/dockerfiles/spark/entrypoint.sh /opt/
COPY spark/examples /opt/spark/examples
COPY spark/data /opt/spark/data

COPY rapids-4-spark_2.12-*.jar /opt/sparkRapidsPlugin
COPY getGpusResources.sh /opt/sparkRapidsPlugin
RUN chmod +x /opt/sparkRapidsPlugin/getGpusResources.sh

RUN mkdir -p /opt/spark/python
COPY spark/python/pyspark /opt/spark/python/pyspark
COPY spark/python/lib /opt/spark/python/lib

ENV SPARK_HOME /opt/spark

WORKDIR /opt/spark/work-dir
RUN chmod g+w /opt/spark/work-dir

ENTRYPOINT [ "/opt/entrypoint.sh" ]

# Specify the User that the actual main process will run as
USER ${spark_uid}