#!/bin/sh
# docker-entrypoint.sh
#
# Re-derives PATH from JAVA_HOME and SPARK_HOME at container start, so that
# overriding either via docker-compose / .env actually changes which
# `java` and `spark-submit` binaries the gunicorn process picks up.
#
# Without this, the image's built-in PATH (set at build time from the
# Dockerfile's ENV) would still reference the old literal paths even
# after the env vars are overridden at runtime.
#
# Usage in Dockerfile:
#   ENTRYPOINT ["/usr/local/bin/docker-entrypoint.sh"]
#   CMD ["gunicorn", "main:app"]
set -e

# Defaults if not set (matches Dockerfile's build-time defaults)
: "${JAVA_HOME:=/usr/lib/jvm/java-17-openjdk-amd64}"
: "${SPARK_HOME:=/opt/spark}"

# Project venv always takes precedence
VENV_BIN="/app/.venv/bin"

# Strip any stale JAVA_HOME / SPARK_HOME bin dirs from PATH, then prepend
# the current ones so overrides actually take effect on a container restart.
# Uses awk instead of `paste -sd:` for portability (macOS paste is BSD and
# doesn't support -s).
PATH_CLEAN=$(echo "$PATH" | tr ':' '\n' | grep -v "/usr/lib/jvm/" | grep -v "/opt/spark/bin" | awk '{ printf "%s%s", $0, (NR==1?":":"") }' | sed 's/:$//')
export PATH="${VENV_BIN}:${JAVA_HOME}/bin:${SPARK_HOME}/bin:${PATH_CLEAN}"
export JAVA_HOME
export SPARK_HOME

echo "[entrypoint] JAVA_HOME=${JAVA_HOME}" >&2
echo "[entrypoint] SPARK_HOME=${SPARK_HOME}" >&2
echo "[entrypoint] PATH=${PATH}" >&2

# Run whatever CMD was passed (gunicorn main:app, or `python main.py`, etc.)
exec "$@"