# https://github.com/rancavil/hadoop-single-node-cluster
# https://mygit.th-deg.de/mh11395/hadoop-single-node-cluster/-/tree/master
FROM eclipse-temurin:17-jdk-noble
RUN apt-get update -y \
    && export DEBIAN_FRONTEND=noninteractive && apt-get install -y --no-install-recommends \
        sudo \
        curl \
        ssh \
    && apt-get clean
RUN useradd -m hduser && echo "hduser:supergroup" | chpasswd && adduser hduser sudo && echo "hduser     ALL=(ALL) NOPASSWD:ALL" >> /etc/sudoers && cd /usr/bin/ && sudo ln -s python3 python
COPY ssh_config /etc/ssh/ssh_config

WORKDIR /home/hduser
USER hduser
RUN ssh-keygen -t rsa -P '' -f ~/.ssh/id_rsa && cat ~/.ssh/id_rsa.pub >> ~/.ssh/authorized_keys && chmod 0600 ~/.ssh/authorized_keys

ENV HADOOP_HOME /home/hduser/hadoop
COPY hadoop-*.tar.gz ./
RUN cat hadoop-*.tar.gz \
  | gunzip \
  | tar -x -C /home/hduser/ \
 && rm -rf ${HADOOP_HOME}/share/doc
RUN rm -rf hadoop-*.tar.gz
RUN ln -s /home/hduser/hadoop-* $HADOOP_HOME

ENV HDFS_NAMENODE_USER hduser
ENV HDFS_DATANODE_USER hduser
ENV HDFS_SECONDARYNAMENODE_USER hduser

ENV YARN_RESOURCEMANAGER_USER hduser
ENV YARN_NODEMANAGER_USER hduser

RUN echo "export JAVA_HOME=/opt/java/openjdk/" >> $HADOOP_HOME/etc/hadoop/hadoop-env.sh
COPY core-site.xml $HADOOP_HOME/etc/hadoop/
COPY hdfs-site.xml $HADOOP_HOME/etc/hadoop/
COPY yarn-site.xml $HADOOP_HOME/etc/hadoop/

COPY docker-entrypoint.sh $HADOOP_HOME/etc/hadoop/

ENV PATH $PATH:$HADOOP_HOME/bin:$HADOOP_HOME/sbin

HEALTHCHECK --interval=5s --timeout=3s --retries=15 \
  CMD curl -f http://localhost:9870/ && curl -f http://localhost:8088/ || exit 1

EXPOSE 50090 8020 9000 9864 9866 9867 9870 10020 19888 8088 8030 8031 8032 8033 8040 8042 22
EXPOSE 49000-49005

WORKDIR /usr/local/bin
RUN sudo ln -s ${HADOOP_HOME}/etc/hadoop/docker-entrypoint.sh .
WORKDIR /home/hduser

ENTRYPOINT ["/usr/local/bin/docker-entrypoint.sh"]