Dockerfile

# ─────────────────────────────────────────────────────────────
# Reconciliation File Processing Service — Production Dockerfile
# Port: 7860
# ─────────────────────────────────────────────────────────────

FROM python:3.12-slim

LABEL maintainer="Reconciliation File Processing Service API"
LABEL description="Document-to-Markdown & PDF-to-image API"
LABEL version="2.2.0"
LABEL description="Production-ready: consolidated logging, unified app, cleanup loop, self-ping"

# ── System dependencies ──────────────────────────────────────
RUN apt-get update && apt-get install -y --no-install-recommends \
    curl \
    ffmpeg \
    libmagic1 \
    poppler-utils \
    && rm -rf /var/lib/apt/lists/*

# ── Non-root user ────────────────────────────────────────────
RUN groupadd --gid 1000 appuser && \
    useradd --uid 1000 --gid appuser --shell /bin/bash --create-home appuser

WORKDIR /app

# ── Python dependencies ──────────────────────────────────────
COPY requirements.txt .
RUN pip install --no-cache-dir --upgrade pip && \
    pip install --no-cache-dir -r requirements.txt && \
    python -m spacy download en_core_web_sm

# ── Application code ─────────────────────────────────────────
COPY --chown=appuser:appuser . .

# ── Ensure startup script exists and is executable ──────────
RUN test -f /app/start.sh || (echo "ERROR: start.sh not found" && exit 1) && \
    chmod +x /app/start.sh

# ── Create runtime directories ──────────────────────────────
RUN mkdir -p /app/logs /tmp/pdf2img_outputs /tmp/pdf2img_temp && \
    chown -R appuser:appuser /app/logs /tmp/pdf2img_outputs /tmp/pdf2img_temp

USER appuser

ENV PYTHONPATH=/app
ENV PYTHONUNBUFFERED=1
ENV OUTPUT_DIR=/tmp/pdf2img_outputs
ENV TEMP_DIR=/tmp/pdf2img_temp

EXPOSE 7860

HEALTHCHECK --interval=30s --timeout=10s --start-period=30s --retries=3 \
    CMD python -c "import urllib.request; urllib.request.urlopen('http://localhost:7860/ping')" || exit 1

CMD ["/bin/bash", "/app/start.sh"]