refactor: optimize base image build process

Author: brainlds

src/backend/base.Dockerfile

@@ -2,53 +2,49 @@ FROM python:3.10-slim
 
 ARG PANDOC_ARCH=amd64
 ENV PANDOC_ARCH=$PANDOC_ARCH
+ENV PATH="${PATH}:/root/.local/bin"
 
 WORKDIR /app
 
-RUN echo \
-    deb https://mirrors.aliyun.com/debian/ bookworm main non-free non-free-firmware contrib \
-    deb-src https://mirrors.aliyun.com/debian/ bookworm main non-free non-free-firmware contrib \
-    deb https://mirrors.aliyun.com/debian-security/ bookworm-security main \
-    deb-src https://mirrors.aliyun.com/debian-security/ bookworm-security main \
-    deb https://mirrors.aliyun.com/debian/ bookworm-updates main non-free non-free-firmware contrib \
-    deb-src https://mirrors.aliyun.com/debian/ bookworm-updates main non-free non-free-firmware contrib \
-    deb https://mirrors.aliyun.com/debian/ bookworm-backports main non-free non-free-firmware contrib \
-    deb-src https://mirrors.aliyun.com/debian/ bookworm-backports main non-free non-free-firmware contrib \
-    > /etc/apt/sources.list
-
-
-
-# Install lib
-RUN apt-get update && apt-get install gcc g++ curl build-essential postgresql-server-dev-all wget libreoffice -y
-RUN apt-get update && apt-get install procps -y
-
-# Install pandoc
-RUN mkdir -p /opt/pandoc \
-    && cd /opt/pandoc \
-    && wget https://github.com/jgm/pandoc/releases/download/3.6.4/pandoc-3.6.4-linux-${PANDOC_ARCH}.tar.gz \
-    && tar xvf pandoc-3.6.4-linux-${PANDOC_ARCH}.tar.gz \
-    && cd pandoc-3.6.4 \
-    && cp bin/pandoc /usr/bin/ \
-    && cd ..
-
-# Install font
-RUN apt install vim fonts-wqy-zenhei -y
-# opencv
-RUN apt-get update && apt-get install -y libglib2.0-0 libsm6 libxrender1 libxext6 libgl1
+# 使用国内源 + 安装依赖（合并指令、清理缓存、禁用推荐包）
+RUN echo "\
+deb https://mirrors.aliyun.com/debian/ bookworm main non-free non-free-firmware contrib\n\
+deb https://mirrors.aliyun.com/debian-security/ bookworm-security main\n\
+deb https://mirrors.aliyun.com/debian/ bookworm-updates main non-free non-free-firmware contrib\n\
+deb https://mirrors.aliyun.com/debian/ bookworm-backports main non-free non-free-firmware contrib" \
+> /etc/apt/sources.list && \
+    apt-get update && \
+    apt-get install -y --no-install-recommends \
+    gcc g++ curl build-essential postgresql-server-dev-all libreoffice \
+    wget procps vim fonts-wqy-zenhei \
+    libglib2.0-0 libsm6 libxrender1 libxext6 libgl1 \
+    && rm -rf /var/lib/apt/lists/*
+
+
+# 安装 pandoc
+RUN mkdir -p /opt/pandoc && \
+    cd /opt/pandoc && \
+    wget https://github.com/jgm/pandoc/releases/download/3.6.4/pandoc-3.6.4-linux-${PANDOC_ARCH}.tar.gz && \
+    tar xvf pandoc-3.6.4-linux-${PANDOC_ARCH}.tar.gz && \
+    cp pandoc-3.6.4/bin/pandoc /usr/bin/ && \
+    rm -rf /opt/pandoc
+
+# 安装 Poetry
 RUN curl -sSL https://install.python-poetry.org | python3 - --version 1.8.2
-# # Add Poetry to PATH
-ENV PATH="${PATH}:/root/.local/bin"
 
+# 拷贝项目依赖文件
 COPY ./pyproject.toml ./
 
+# 安装 Python 依赖
 RUN python -m pip install --upgrade pip && \
-    pip install shapely==2.0.1
+    pip install shapely==2.0.1 && \
+    poetry config virtualenvs.create false && \
+    poetry install --no-interaction --no-ansi --without dev
+
+# 安装 NLTK 数据
+RUN python -c "import nltk; nltk.download('punkt'); nltk.download('punkt_tab'); nltk.download('averaged_perceptron_tagger'); nltk.download('averaged_perceptron_tagger_eng')"
 
-# Install dependencies
-RUN poetry config virtualenvs.create false
-RUN poetry install --no-interaction --no-ansi --without dev
+COPY . .
 
-# install nltk_data
-RUN python -c "import nltk; nltk.download('punkt'); nltk.download('punkt_tab'); nltk.download('averaged_perceptron_tagger'); nltk.download('averaged_perceptron_tagger_eng'); "
+CMD ["sh", "entrypoint.sh"]
 
-CMD ["sh entrypoint.sh"]