recommend/Dockerfile.low-mem

# -*- coding: utf-8 -*-
# 小内存优化版 Dockerfile（适用于 512MB-1GB 内存的 Linux 机器）
FROM python:3-slim

# 设置工作目录
WORKDIR /app

# 设置环境变量（优化内存使用）
ENV PYTHONUNBUFFERED=1 \
    PYTHONDONTWRITEBYTECODE=1 \
    FLASK_APP=web_app.py \
    FLASK_ENV=production \
    PYTHONHASHSEED=0 \
    MALLOC_ARENA_MAX=2

# 安装系统依赖（最小化安装）
RUN apt-get update && apt-get install -y --no-install-recommends \
    tesseract-ocr \
    tesseract-ocr-chi-sim \
    tesseract-ocr-eng \
    && rm -rf /var/lib/apt/lists/* \
    && apt-get clean

# 复制requirements文件
COPY requirements.txt .

# 创建最小化的 requirements.txt（移除GUI相关依赖）
RUN echo "scikit-learn>=1.3.0" > requirements-minimal.txt && \
    echo "pandas>=2.0.0" >> requirements-minimal.txt && \
    echo "numpy>=1.24.0" >> requirements-minimal.txt && \
    echo "joblib>=1.3.0" >> requirements-minimal.txt && \
    echo "requests>=2.31.0" >> requirements-minimal.txt && \
    echo "python-dotenv>=1.0.0" >> requirements-minimal.txt && \
    echo "python-dateutil>=2.8.0" >> requirements-minimal.txt && \
    echo "Pillow>=10.0.0" >> requirements-minimal.txt && \
    echo "pytesseract>=0.3.10" >> requirements-minimal.txt && \
    echo "opencv-python-headless>=4.8.0" >> requirements-minimal.txt && \
    echo "Flask>=3.0.0" >> requirements-minimal.txt && \
    echo "Werkzeug>=3.0.0" >> requirements-minimal.txt && \
    echo "gunicorn" >> requirements-minimal.txt

# 安装Python依赖（使用最小化依赖，opencv使用headless版本）
RUN pip install --no-cache-dir --upgrade pip && \
    pip install --no-cache-dir -r requirements-minimal.txt && \
    python -m pip install --force-reinstall gunicorn && \
    python -c "import gunicorn; print(f'Gunicorn version: {gunicorn.__version__}')" && \
    python -m gunicorn --version || echo "Gunicorn installed, using python -m gunicorn"

# 复制应用代码
COPY . .

# 创建必要的目录
RUN mkdir -p templates static/css static/js logs data models

# 设置权限
RUN chmod +x start_web.py

# 暴露端口
EXPOSE 7400

# 健康检查（不使用 requests，直接用 Python）
HEALTHCHECK --interval=30s --timeout=10s --start-period=10s --retries=3 \
    CMD python -c "import urllib.request; urllib.request.urlopen('http://localhost:7400/health').read()" || exit 1

# 使用gunicorn启动应用（小内存配置：单worker，减少内存占用）
# 使用 python -m gunicorn 确保可以找到 gunicorn（即使可执行文件不在PATH中也能工作）
CMD ["python", "-m", "gunicorn", "--bind", "0.0.0.0:7400", "--workers", "1", "--threads", "2", "--timeout", "120", "--worker-class", "sync", "--max-requests", "1000", "--max-requests-jitter", "100", "--preload", "--access-logfile", "-", "--error-logfile", "-", "web_app:app"]