school_compare/pipeline/Dockerfile

FROM python:3.13-slim

WORKDIR /opt/pipeline

# System dependencies
RUN apt-get update && apt-get install -y --no-install-recommends \
    gcc \
    libpq-dev \
    curl \
    && rm -rf /var/lib/apt/lists/*

# Python dependencies
COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt

# Install custom Singer taps
COPY plugins/ plugins/
RUN pip install --no-cache-dir \
    ./plugins/extractors/tap-uk-gias \
    ./plugins/extractors/tap-uk-ees \
    ./plugins/extractors/tap-uk-ofsted \
    ./plugins/extractors/tap-uk-parent-view \
    ./plugins/extractors/tap-uk-fbit \
    ./plugins/extractors/tap-uk-idaci

# Copy pipeline code
COPY meltano.yml .
COPY transform/ transform/
COPY scripts/ scripts/
COPY dags/ dags/

# Initialize Meltano project (generates catalog, installs target-postgres)
RUN meltano install

# dbt deps
RUN cd transform && dbt deps --profiles-dir . 2>/dev/null || true

ENV AIRFLOW_HOME=/opt/airflow
ENV AIRFLOW__CORE__DAGS_FOLDER=/opt/pipeline/dags
ENV PYTHONPATH=/opt/pipeline

CMD ["airflow", "api-server"]