FROM python:3.12-slim

# 安装 lxml 必要的 C 库
RUN apt-get update && apt-get install -y \
    gcc \
    libxml2-dev \
    libxslt-dev \
    && rm -rf /var/lib/apt/lists/*

WORKDIR /app

# 确保安装了 FastAPI 和 Uvicorn
RUN pip install --no-cache-dir \
    pandas \
    pyarrow \
    requests \
    beautifulsoup4 \
    lxml \
    supabase \
    fastapi \
    uvicorn \
    datasets \
    tqdm

COPY . .

# 设置环境变量，确保日志实时输出到日志窗口
ENV PYTHONUNBUFFERED=1

EXPOSE 7860

# 启动 FastAPI (它会自动触发 sync_job)
# CMD ["python", "sync_job.py"]

# ... 其他配置不变 ...
COPY start.sh .
RUN chmod +x start.sh

# Hugging Face 默认端口
EXPOSE 7860
CMD ["./start.sh"]