# Use an official Python runtime
FROM python:3.9-slim

# Set environment variables
ENV PYTHONDONTWRITEBYTECODE 1
ENV PYTHONUNBUFFERED 1
ENV NLTK_DATA /app/nltk_data

# Set working directory
WORKDIR /app

# Install system dependencies
RUN apt-get update && apt-get install -y \
    build-essential \
    && rm -rf /var/lib/apt/lists/*

# Create NLTK data directory
RUN mkdir -p /app/nltk_data

# Copy dependency files
COPY requirements.txt .

# Install Python dependencies
RUN pip install -r requirements.txt

# Download NLTK data to the correct directory
RUN python -c "import nltk; nltk.download('wordnet', download_dir='/app/nltk_data'); \
    nltk.download('punkt', download_dir='/app/nltk_data'); \
    nltk.download('averaged_perceptron_tagger', download_dir='/app/nltk_data'); \
    nltk.download('stopwords', download_dir='/app/nltk_data')"

# Copy the rest of the app
COPY . .

# Expose port
EXPOSE 7860

# Run the app
CMD gunicorn --bind 0.0.0.0:7860 app:app