FROM python:3.11-slim

# Install system dependencies: Tesseract OCR + poppler (pdf2image)
RUN apt-get update && apt-get install -y --no-install-recommends \
    tesseract-ocr \
    poppler-utils \
    && rm -rf /var/lib/apt/lists/*

WORKDIR /app

# Install Python dependencies
COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt \
    && python -m spacy download en_core_web_sm

# Copy source code
COPY src/ src/
COPY .env.example .env.example

# Pre-download NLTK data and HuggingFace model at build time (faster cold start)
RUN python -c "import nltk; nltk.download('punkt'); nltk.download('punkt_tab'); nltk.download('stopwords')"
RUN python -c "from transformers import pipeline; pipeline('sentiment-analysis', model='distilbert-base-uncased-finetuned-sst-2-english')"

# HuggingFace Spaces uses port 7860; override with PORT env var for local use
EXPOSE 7860

CMD ["sh", "-c", "uvicorn src.main:app --host 0.0.0.0 --port ${PORT:-7860}"]