ARG PYTHON_VERSION=3.9.18

FROM --platform=linux/amd64 amazonlinux:2 AS base
ARG PYTHON_VERSION

RUN yum install -y gcc openssl11-devel bzip2-devel libffi-devel tar gzip wget make && \
    wget https://www.python.org/ftp/python/${PYTHON_VERSION}/Python-${PYTHON_VERSION}.tgz && \
    tar xzf Python-${PYTHON_VERSION}.tgz && \
    cd Python-${PYTHON_VERSION} && \
    ./configure --enable-optimizations && \
    make install


RUN yum install -y python3 tar gzip
RUN yum -y update && yum -y install \
    curl \
    java-1.8.0-openjdk \
    java-1.8.0-openjdk-devel \
    && yum clean all

ENV VIRTUAL_ENV=/opt/venv
RUN python3 -m venv $VIRTUAL_ENV --copies
RUN cp -r /usr/local/lib/python3.9/* $VIRTUAL_ENV/lib/python3.9/

# Ensure our python3 executable references the virtual environment
ENV PATH="$VIRTUAL_ENV/bin:$PATH"

ENV PATH="${PATH}:/root/.local/bin"

# RUN python3 -m pip poetry
RUN python3 -m pip install --upgrade pip && \
    python3 -m pip install venv-pack==0.2.0

# ENV PATH="$PATH:/root/.local/bin"

WORKDIR /app

COPY . .

FROM base as build-poetry
ARG PYTHON_VERSION
# RUN export PATH="$HOME/.poetry/bin:$PATH"
RUN poetry self add poetry-plugin-bundle && \
    poetry bundle venv dist/bundle


RUN mkdir /output && \
    venv-pack -o /output/pyspark_${PYTHON_VERSION}.tar.gz --prefix dist/bundle --python-prefix /home/hadoop/environment

FROM scratch as export-poetry
ARG PYTHON_VERSION
COPY --from=build-poetry /output/pyspark_${PYTHON_VERSION}.tar.gz /