# syntax=docker/dockerfile:1.6

# Base Python image
FROM python:3.11-slim

# Environment for reliable, quiet, and unbuffered Python
ENV PYTHONDONTWRITEBYTECODE=1 \
    PYTHONUNBUFFERED=1 \
    PIP_NO_CACHE_DIR=1 \
    PIP_DISABLE_PIP_VERSION_CHECK=1 \
    PORT=7860

# Install system packages required for OCR and PDF rasterization
# - tesseract-ocr and language data (eng)
# - poppler-utils provides `pdftoppm` used by pdf2image
# - libgl1 needed by some Pillow operations in headless containers
RUN apt-get update && \
    apt-get install -y --no-install-recommends \
        tesseract-ocr \
        tesseract-ocr-eng \
        poppler-utils \
        libgl1 \
    && rm -rf /var/lib/apt/lists/*

# Set tessdata path (generally correct for Debian-based images)
ENV TESSDATA_PREFIX=/usr/share/tesseract-ocr/4.00/tessdata

# App directory
WORKDIR /app

# Install Python dependencies first for better layer caching
COPY requirements.txt /app/requirements.txt
RUN pip install --no-cache-dir -r /app/requirements.txt

# Copy application code
COPY . /app

# Expose default HF Spaces port
EXPOSE 7860

# Start the FastAPI server
# Note: Hugging Face sets PORT env var, but we default to 7860
CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]