# syntax=docker/dockerfile:1
#
# Spark Executor MCP — runtime image.
# Build deps with uv (frozen, prod-only), then drop in the source on top of
# ppython:3.12-slim-bookworm with Spark + YARN configs mounted for the spark-submit /
# yarn CLI calls inside the MCP tools.

FROM python:3.12-slim-bookworm

# --- uv (official binary) ---
COPY --from=ghcr.io/astral-sh/uv:latest /uv /uvx /usr/local/bin/

# --- Spark + Hadoop config (matches the original Dockerfile) ---

ARG SPARK_VERSION=3.1.2

RUN sed -i 's|deb.debian.org|mirrors.tuna.tsinghua.edu.cn|g' /etc/apt/sources.list.d/debian.sources && \
    apt-get update && \
    apt-cache search openjdk && \
    apt-get install -y --no-install-recommends \
        curl \
        ca-certificates \
        tar \
        openjdk-11-jre-headless && \
    curl -L \
      https://mirrors.tuna.tsinghua.edu.cn/apache/spark/spark-${SPARK_VERSION}/spark-${SPARK_VERSION}-bin-hadoop2.7.tgz \
      -o /tmp/spark.tgz && \
    mkdir -p /opt && \
    tar -xzf /tmp/spark.tgz -C /opt && \
    mv /opt/spark-${SPARK_VERSION}-bin-hadoop2.7 /opt/spark && \
    rm -f /tmp/spark.tgz && \
    apt-get clean && \
    rm -rf /var/lib/apt/lists/* && \
    # Defensive: rewrite the first line of every bin/* script to use a
    # known-good shebang. Some Spark distributions have shipped with
    # 'bach' (typo for 'bash') in the shebang, which makes the kernel
    # refuse to exec the script at all. Idempotent and cheap.
    find /opt/spark/bin -type f -exec sed -i '1s|^.*$|#!/usr/bin/env bash|' {} +

ENV JAVA_HOME=/usr/lib/jvm/java-11-openjdk-amd64
ENV SPARK_HOME=/opt/spark
ENV PATH=${JAVA_HOME}/bin:${SPARK_HOME}/bin:${PATH}

# Hadoop/Yarn 配置目录（运行时挂载）
RUN mkdir -p /etc/hadoop/conf

# 默认值，可在 docker run 时覆盖
ENV HADOOP_CONF_DIR=/etc/hadoop/conf
ENV YARN_CONF_DIR=/etc/hadoop/conf

# --- App ---
WORKDIR /app

# Install Python deps first so this layer caches independently of source.
# --frozen pins to uv.lock exactly; --no-dev skips pytest etc. for a slim
# production image; --no-install-project defers copying the source.
COPY pyproject.toml uv.lock ./
RUN uv sync --index-url=https://pypi.tuna.tsinghua.edu.cn/simple/ --frozen --no-dev --no-install-project

# Now copy the source and let uv wire it in.
COPY main.py ./
COPY spark_executor ./spark_executor
COPY common ./common
COPY gunicorn.conf.py ./
RUN uv sync --index-url=https://pypi.tuna.tsinghua.edu.cn/simple/ --frozen --no-dev

# Put the venv on PATH so `python` / `gunicorn` / `uvicorn` resolve to the project env.
ENV PATH=/app/.venv/bin:$PATH
ENV PYTHONUNBUFFERED=1

# Entrypoint re-derives PATH from JAVA_HOME and SPARK_HOME at container
# start, so overriding either via docker-compose / .env actually changes
# which `java` and `spark-submit` binaries the gunicorn process picks up.
COPY docker-entrypoint.sh /usr/local/bin/docker-entrypoint.sh
RUN chmod +x /usr/local/bin/docker-entrypoint.sh
ENTRYPOINT ["/usr/local/bin/docker-entrypoint.sh"]

# gunicorn is the prod entrypoint — multiple ASGI workers, graceful
# shutdown, stdout/stderr logs. Config knobs are env-var driven (see
# gunicorn.conf.py).
#
# Common overrides via -e flags at `docker run`:
#   -e GUNICORN_WORKERS=4
#   -e GUNICORN_TIMEOUT=180
#   -e GUNICORN_BIND=0.0.0.0:9000
EXPOSE 8000
CMD ["gunicorn", "main:app"]