FROM python:3.12-slim

WORKDIR /app

# System dependencies for lxml, pdfplumber
RUN apt-get update && apt-get install -y \
    gcc g++ \
    libxml2-dev libxslt-dev \
    libfreetype6-dev \
    && rm -rf /var/lib/apt/lists/*

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

COPY . .

# Data directory
RUN mkdir -p /data

ENV PYTHONUNBUFFERED=1
ENV PYTHONPATH=/app

CMD ["python", "main.py"]
