# ============================================
# Tool_OCR - Unified Docker Image
# Frontend (React + Vite) + Backend (FastAPI)
# Served by Nginx with reverse proxy
# ============================================

# ============================================
# Stage 1: Build Frontend
# ============================================
FROM node:20-alpine AS frontend-builder

WORKDIR /app/frontend

# Copy package files
COPY frontend/package*.json ./

# Install all dependencies (including devDependencies for build)
RUN npm ci

# Copy frontend source
COPY frontend/ ./

# Create production environment file
RUN echo "VITE_API_BASE_URL=" > .env.production

# Build frontend for production
RUN npm run build


# ============================================
# Stage 2: Build Backend + Final Image
# ============================================
FROM python:3.10-slim-bookworm

# Set working directory
WORKDIR /app

# Set environment variables
ENV PYTHONUNBUFFERED=1 \
    PYTHONDONTWRITEBYTECODE=1 \
    PIP_NO_CACHE_DIR=1 \
    PIP_DISABLE_PIP_VERSION_CHECK=1 \
    DEBIAN_FRONTEND=noninteractive

# Install system dependencies
# - nginx: web server and reverse proxy
# - supervisor: process manager for nginx + uvicorn
# - curl: for health checks
# - pandoc: for markdown to PDF conversion
# - poppler-utils: for pdf2image (PDF processing)
# - libpango-1.0-0, libpangocairo-1.0-0: for WeasyPrint
# - libgdk-pixbuf2.0-0: for WeasyPrint image handling
# - libffi-dev: for cryptography
# - fonts-noto-cjk: Chinese/Japanese/Korean font support
# - libgomp1, libgl1-mesa-glx, libglib2.0-0: for OpenCV and PaddleOCR
# - libmagic1: for python-magic file type detection
# - libreoffice-writer, libreoffice-impress: for Office document conversion (doc/docx/ppt/pptx)
RUN apt-get update && apt-get install -y --no-install-recommends \
    nginx \
    supervisor \
    curl \
    pandoc \
    poppler-utils \
    libpango-1.0-0 \
    libpangocairo-1.0-0 \
    libgdk-pixbuf2.0-0 \
    libffi-dev \
    fonts-noto-cjk \
    fonts-noto-cjk-extra \
    libgomp1 \
    libgl1-mesa-glx \
    libglib2.0-0 \
    libmagic1 \
    libreoffice-writer \
    libreoffice-impress \
    && rm -rf /var/lib/apt/lists/*

# Copy Python requirements
COPY requirements.txt .

# Install Python dependencies with extended timeout
# PaddlePaddle is 189MB and may take time to download
# Timeout: 600 seconds (10 minutes), Retries: 5
RUN pip install --timeout 600 --retries 5 -r requirements.txt

# Copy backend application
COPY backend/ ./backend/

# Copy frontend build from frontend-builder stage
COPY --from=frontend-builder /app/frontend/dist /app/frontend/dist

# Copy Nginx configuration
COPY docker/nginx.conf /etc/nginx/nginx.conf
COPY docker/default.conf /etc/nginx/conf.d/default.conf

# Copy supervisor configuration
COPY docker/supervisord.conf /etc/supervisor/conf.d/supervisord.conf

# Copy startup script and fix line endings (Windows CRLF -> Linux LF)
COPY docker/entrypoint.sh /entrypoint.sh
RUN sed -i 's/\r$//' /entrypoint.sh && chmod +x /entrypoint.sh

# Create necessary directories with proper permissions
RUN mkdir -p \
    /app/backend/uploads/temp \
    /app/backend/uploads/processed \
    /app/backend/uploads/images \
    /app/backend/storage/markdown \
    /app/backend/storage/json \
    /app/backend/storage/exports \
    /app/backend/models/paddleocr \
    /app/backend/logs \
    /var/log/supervisor \
    /var/log/nginx \
    /var/cache/nginx \
    /var/run \
    && chmod -R 755 /app \
    && chown -R www-data:www-data /var/log/nginx /var/cache/nginx

# Expose port (only one port needed!)
EXPOSE 12015

# Health check
HEALTHCHECK --interval=30s --timeout=10s --start-period=40s --retries=3 \
    CMD curl -f http://localhost:12015/health || exit 1

# Set working directory to backend for Python app
WORKDIR /app/backend

# Use entrypoint script to start supervisor
ENTRYPOINT ["/entrypoint.sh"]