Dockerfile

# Simple PDF — self-hosted PDF merge / clean / edit / OCR
FROM python:3.12-slim

ENV PYTHONDONTWRITEBYTECODE=1 \
    PYTHONUNBUFFERED=1 \
    PDF_EDITOR_HOST=0.0.0.0 \
    PDF_EDITOR_PORT=8000 \
    PDF_EDITOR_UPLOADS=/app/uploads

WORKDIR /app

RUN apt-get update && apt-get install -y --no-install-recommends \
    tesseract-ocr \
    tesseract-ocr-eng \
    tesseract-ocr-spa \
    libreoffice-writer-nogui \
    fonts-dejavu-core \
    fonts-liberation \
    libgl1 \
    libglib2.0-0 \
    curl \
    && rm -rf /var/lib/apt/lists/*

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

COPY app/ ./app/
COPY static/ ./static/
COPY templates/ ./templates/
COPY wsgi.py .

RUN useradd --create-home --uid 1000 --shell /usr/sbin/nologin appuser \
    && mkdir -p /app/uploads \
    && chown -R appuser:appuser /app

USER appuser

VOLUME ["/app/uploads"]

EXPOSE 8000

HEALTHCHECK --interval=30s --timeout=10s --start-period=40s --retries=3 \
    CMD curl -fsS http://127.0.0.1:8000/api/health || exit 1

CMD ["gunicorn", "--bind", "0.0.0.0:8000", "--workers", "2", "--timeout", "600", "wsgi:app"]