Dockerfile.spark-3-2-2-python-3-9

FROM python:3.9.13-bullseye

RUN apt-get update

# Java
RUN apt-get install -y openjdk-11-jdk gcc musl-dev zip unzip tini
ENV JAVA_HOME /usr/

# Hadoop
ARG HADOOP_VERSION="3.2.0"
ENV HADOOP_HOME /usr/hadoop-$HADOOP_VERSION
ENV HADOOP_CONF_DIR=$HADOOP_HOME/etc/hadoop
ENV PATH $PATH:$HADOOP_HOME/bin
RUN wget "https://archive.apache.org/dist/hadoop/common/hadoop-$HADOOP_VERSION/hadoop-$HADOOP_VERSION.tar.gz" \
    && tar -xzf "hadoop-$HADOOP_VERSION.tar.gz" -C /usr/ \
    && rm "hadoop-$HADOOP_VERSION.tar.gz"

# Spark
ARG SPARK_VERSION="3.2.2"
ENV SPARK_PACKAGE spark-$SPARK_VERSION
ENV SPARK_HOME /usr/$SPARK_PACKAGE-bin-without-hadoop
ENV SPARK_DIST_CLASSPATH="$HADOOP_HOME/etc/hadoop/*:$HADOOP_HOME/share/hadoop/common/lib/*:$HADOOP_HOME/share/hadoop/common/*:$HADOOP_HOME/share/hadoop/hdfs/*:$HADOOP_HOME/share/hadoop/hdfs/lib/*:$HADOOP_HOME/share/hadoop/hdfs/*:$HADOOP_HOME/share/hadoop/yarn/lib/*:$HADOOP_HOME/share/hadoop/yarn/*:$HADOOP_HOME/share/hadoop/mapreduce/lib/*:$HADOOP_HOME/share/hadoop/mapreduce/*:$HADOOP_HOME/share/hadoop/tools/lib/*"
ENV PATH $PATH:$SPARK_HOME/bin
RUN wget "https://downloads.apache.org/spark/$SPARK_PACKAGE/$SPARK_PACKAGE-bin-without-hadoop.tgz" \
    && tar -xzf "$SPARK_PACKAGE-bin-without-hadoop.tgz" -C /usr/ \
    && rm "$SPARK_PACKAGE-bin-without-hadoop.tgz"

COPY decom.sh /opt/decom.sh
COPY entrypoint.sh /opt/entrypoint.sh

RUN chmod +x /opt/decom.sh
RUN chmod +x /opt/entrypoint.sh

ENTRYPOINT [ "/opt/entrypoint.sh" ]