# backend-python Dockerfile 离线版本 v2 FROM maven:3-eclipse-temurin-8 AS datax-builder # 配置 Maven 阿里云镜像 RUN mkdir -p /root/.m2 && \ echo '\n\ \n\ \n\ \n\ aliyunmaven\n\ *\n\ 阿里云公共仓库\n\ https://maven.aliyun.com/repository/public\n\ \n\ \n\ ' > /root/.m2/settings.xml # 离线模式: 从构建参数获取本地 DataX 路径 ARG RESOURCES_DIR=./build-cache/resources ARG DATAX_LOCAL_PATH=${RESOURCES_DIR}/DataX # 复制本地 DataX 源码 COPY ${DATAX_LOCAL_PATH} /DataX COPY runtime/datax/ DataX/ RUN cd DataX && \ sed -i "s/com.mysql.jdbc.Driver/com.mysql.cj.jdbc.Driver/g" \ plugin-rdbms-util/src/main/java/com/alibaba/datax/plugin/rdbms/util/DataBaseType.java && \ mvn -U clean package assembly:assembly -Dmaven.test.skip=true # 使用预装 APT 包的基础镜像 FROM datamate-python-base:latest ENV PYTHONDONTWRITEBYTECODE=1 \ PYTHONUNBUFFERED=1 \ POETRY_VERSION=2.2.1 \ POETRY_NO_INTERACTION=1 \ POETRY_VIRTUALENVS_CREATE=false \ POETRY_CACHE_DIR=/tmp/poetry_cache ENV JAVA_HOME=/usr/lib/jvm/java-21-openjdk ENV PATH="/root/.local/bin:$JAVA_HOME/bin:$PATH" WORKDIR /app # 配置 pip 阿里云镜像并安装 Poetry RUN --mount=type=cache,target=/root/.cache/pip \ pip config set global.index-url https://mirrors.aliyun.com/pypi/simple/ && \ pip config set global.trusted-host mirrors.aliyun.com && \ pip install --upgrade --root-user-action=ignore pip \ && pip install --root-user-action=ignore pipx \ && pipx install "poetry==$POETRY_VERSION" COPY --from=datax-builder /DataX/target/datax/datax /opt/datax RUN cp /opt/datax/plugin/reader/mysqlreader/libs/mysql* /opt/datax/plugin/reader/starrocksreader/libs/ # Copy only dependency files first COPY runtime/datamate-python/pyproject.toml runtime/datamate-python/poetry.lock* /app/ # Install dependencies RUN --mount=type=cache,target=$POETRY_CACHE_DIR \ poetry install --no-root --only main # 离线模式: 使用本地 NLTK 数据 ARG RESOURCES_DIR=./build-cache/resources ARG NLTK_DATA_LOCAL_PATH=${RESOURCES_DIR}/nltk_data COPY ${NLTK_DATA_LOCAL_PATH} /usr/local/nltk_data ENV NLTK_DATA=/usr/local/nltk_data # Copy the rest of the application COPY runtime/datamate-python /app COPY runtime/datamate-python/deploy/docker-entrypoint.sh /docker-entrypoint.sh RUN chmod +x /docker-entrypoint.sh || true EXPOSE 18000 ENTRYPOINT ["/docker-entrypoint.sh"]