Dockerfile

# Multi-stage Docker build for OCR Dataset Generator
# Optimized for Hugging Face Spaces deployment

# ================================
# Stage 1: Dependencies
# ================================
FROM node:20-alpine AS deps

WORKDIR /app

# Copy package files from web folder
COPY web/package.json web/package-lock.json* ./

# Install dependencies
RUN npm ci

# ================================
# Stage 2: Builder
# ================================
FROM node:20-alpine AS builder

WORKDIR /app

# Copy dependencies from deps stage
COPY --from=deps /app/node_modules ./node_modules

# Copy web source files
COPY web/ ./

# Disable telemetry and build
ENV NEXT_TELEMETRY_DISABLED=1
RUN npm run build

# ================================
# Stage 3: Runner
# ================================
FROM node:20-alpine AS runner

WORKDIR /app

# Set production environment
ENV NODE_ENV=production
ENV NEXT_TELEMETRY_DISABLED=1

# Copy standalone build
COPY --from=builder /app/.next/standalone ./
COPY --from=builder /app/.next/static ./.next/static

# Copy public folder if it exists (use conditional copy pattern)
COPY --from=builder /app/public* ./public/

# Create HF Spaces persistent storage directory
RUN mkdir -p /data && chmod 777 /data
ENV DATA_DIR=/data

# HF Spaces uses port 7860
EXPOSE 7860
ENV PORT=7860
ENV HOSTNAME="0.0.0.0"

# Start the Next.js server
CMD ["node", "server.js"]