NO-JIRA: refactor(jupyter/datascience/Dockerfile.cpu): wrap multiple RUN commands with bash for consistency, readability, and improved error handling

jupyter/datascience/ubi9-python-3.12/Dockerfile.cpu

@@ -19,19 +19,22 @@ ARG TARGETARCH
 
 # Keep s390x special-case from original (create dummy binary) but
 # include explicit curl/unzip steps from the delta for non-s390x.
-RUN arch="${TARGETARCH:-$(uname -m)}" && \
-    arch=$(echo "$arch" | cut -d- -f1) && \
-    if [ "$arch" = "s390x" ]; then \
-        echo "Skipping mongocli build for ${arch}, creating dummy binary"; \
-        mkdir -p /tmp && printf '#!/bin/sh\necho "mongocli not supported on s390x"\n' > /tmp/mongocli && \
-        chmod +x /tmp/mongocli; \
-    else \
-        echo "Building mongocli for ${arch}"; \
-        curl -Lo mongodb-cli-mongocli-v${MONGOCLI_VERSION}.zip https://github.com/mongodb/mongodb-cli/archive/refs/tags/mongocli/v${MONGOCLI_VERSION}.zip && \
-        unzip ./mongodb-cli-mongocli-v${MONGOCLI_VERSION}.zip && \
-        cd ./mongodb-cli-mongocli-v${MONGOCLI_VERSION}/ && \
-        CGO_ENABLED=1 GOOS=linux GOARCH=${arch} GO111MODULE=on go build -a -tags strictfipsruntime -o /tmp/mongocli ./cmd/mongocli/; \
-    fi
+RUN /bin/bash <<'EOF'
+set -Eeuxo pipefail
+arch="${TARGETARCH:-$(uname -m)}"
+arch=$(echo "$arch" | cut -d- -f1)
+if [ "$arch" = "s390x" ]; then
+    echo "Skipping mongocli build for ${arch}, creating dummy binary"
+    mkdir -p /tmp && printf '#!/bin/sh\necho "mongocli not supported on s390x"\n' > /tmp/mongocli
+    chmod +x /tmp/mongocli
+else
+    echo "Building mongocli for ${arch}"
+    curl -Lo mongodb-cli-mongocli-v${MONGOCLI_VERSION}.zip https://github.com/mongodb/mongodb-cli/archive/refs/tags/mongocli/v${MONGOCLI_VERSION}.zip
+    unzip ./mongodb-cli-mongocli-v${MONGOCLI_VERSION}.zip
+    cd ./mongodb-cli-mongocli-v${MONGOCLI_VERSION}/
+    CGO_ENABLED=1 GOOS=linux GOARCH=${arch} GO111MODULE=on go build -a -tags strictfipsruntime -o /tmp/mongocli ./cmd/mongocli/
+fi
+EOF
 
 ####################
 # cpu-base         #
@@ -62,16 +65,19 @@ EOF
 # upgrade first to avoid fixable vulnerabilities end
 
 # Install useful OS packages
-RUN --mount=type=cache,target=/var/cache/dnf \
-    echo "Building for architecture: ${TARGETARCH}" && \
-    if [ "$TARGETARCH" = "s390x" ]; then \
-        PACKAGES="perl mesa-libGL skopeo gcc gcc-c++ make openssl-devel autoconf automake libtool cmake python3-devel pybind11-devel openblas-devel unixODBC-devel"; \
-    else \
-        PACKAGES="perl mesa-libGL skopeo"; \
-    fi && \
-    echo "Installing: $PACKAGES" && \
-    dnf install -y $PACKAGES && \
-    dnf clean all && rm -rf /var/cache/yum
+RUN --mount=type=cache,target=/var/cache/dnf /bin/bash <<'EOF'
+set -Eeuxo pipefail
+echo "Building for architecture: ${TARGETARCH}"
+if [ "$TARGETARCH" = "s390x" ]; then
+    PACKAGES="perl mesa-libGL skopeo gcc gcc-c++ make openssl-devel autoconf automake libtool cmake python3-devel pybind11-devel openblas-devel unixODBC-devel"
+else
+    PACKAGES="perl mesa-libGL skopeo"
+fi
+echo "Installing: $PACKAGES"
+dnf install -y $PACKAGES
+dnf clean all
+rm -rf /var/cache/yum
+EOF
 
 RUN /bin/bash <<'EOF'
 set -Eeuxo pipefail
@@ -134,55 +140,57 @@ WORKDIR /tmp/build-wheels
 
 # Build pyarrow on ppc64le and s390x
 RUN --mount=type=cache,target=/root/.cache/pip \
-    --mount=type=cache,target=/root/.cache/dnf \
-    if [ "$TARGETARCH" = "ppc64le" ] || [ "$TARGETARCH" = "s390x" ]; then \
-        # Install build dependencies (shared for pyarrow and onnx)
-        dnf install -y cmake make gcc-c++ pybind11-devel wget && \
-        dnf clean all && \
-        # Build and collect pyarrow wheel
-        git clone --depth 1 --branch "apache-arrow-17.0.0" https://github.com/apache/arrow.git && \
-        cd arrow/cpp && \
-        mkdir release && cd release && \
-        ARROW_S3_FLAG="" && \
-        if [ "$TARGETARCH" != "s390x" ]; then ARROW_S3_FLAG="-DARROW_S3=ON"; fi && \
-        cmake -DCMAKE_BUILD_TYPE=Release \
-              -DCMAKE_INSTALL_PREFIX=/usr/local \
-              -DARROW_PYTHON=ON \
-              -DARROW_PARQUET=ON \
-              -DARROW_ORC=ON \
-              -DARROW_FILESYSTEM=ON \
-              -DARROW_JSON=ON \
-              -DARROW_CSV=ON \
-              -DARROW_DATASET=ON \
-              -DARROW_DEPENDENCY_SOURCE=BUNDLED \
-              -DARROW_WITH_LZ4=OFF \
-              -DARROW_WITH_ZSTD=OFF \
-              -DARROW_WITH_SNAPPY=OFF \
-              ${ARROW_S3_FLAG} \
-              -DARROW_SUBSTRAIT=ON \
-              -DARROW_BUILD_TESTS=OFF \
-              -DARROW_BUILD_BENCHMARKS=OFF \
-              .. && \
-        make -j$(nproc) VERBOSE=1 && \
-        make install -j$(nproc) && \
-        cd ../../python && \
-        pip install --no-cache-dir -r requirements-build.txt && \
-        PYARROW_WITH_PARQUET=1 \
-        PYARROW_WITH_DATASET=1 \
-        PYARROW_WITH_FILESYSTEM=1 \
-        PYARROW_WITH_JSON=1 \
-        PYARROW_WITH_CSV=1 \
-        PYARROW_PARALLEL=$(nproc) \
-        python setup.py build_ext --build-type=release --bundle-arrow-cpp bdist_wheel && \
-        mkdir -p /tmp/wheels && \
-        cp dist/pyarrow-*.whl /tmp/wheels/ && \
-        chmod -R 777 /tmp/wheels && \
-        # Ensure wheels directory exists and has content
-        ls -la /tmp/wheels/; \
-    else \
-        # Create empty wheels directory for non-s390x
-        mkdir -p /tmp/wheels; \
-    fi
+    --mount=type=cache,target=/root/.cache/dnf /bin/bash <<'EOF'
+set -Eeuxo pipefail
+if [ "$TARGETARCH" = "ppc64le" ] || [ "$TARGETARCH" = "s390x" ]; then
+    # Install build dependencies (shared for pyarrow and onnx)
+    dnf install -y cmake make gcc-c++ pybind11-devel wget
+    dnf clean all
+    # Build and collect pyarrow wheel
+    git clone --depth 1 --branch "apache-arrow-17.0.0" https://github.com/apache/arrow.git
+    cd arrow/cpp
+    mkdir release && cd release
+    ARROW_S3_FLAG=""
+    if [ "$TARGETARCH" != "s390x" ]; then ARROW_S3_FLAG="-DARROW_S3=ON"; fi
+    cmake -DCMAKE_BUILD_TYPE=Release \
+          -DCMAKE_INSTALL_PREFIX=/usr/local \
+          -DARROW_PYTHON=ON \
+          -DARROW_PARQUET=ON \
+          -DARROW_ORC=ON \
+          -DARROW_FILESYSTEM=ON \
+          -DARROW_JSON=ON \
+          -DARROW_CSV=ON \
+          -DARROW_DATASET=ON \
+          -DARROW_DEPENDENCY_SOURCE=BUNDLED \
+          -DARROW_WITH_LZ4=OFF \
+          -DARROW_WITH_ZSTD=OFF \
+          -DARROW_WITH_SNAPPY=OFF \
+          ${ARROW_S3_FLAG} \
+          -DARROW_SUBSTRAIT=ON \
+          -DARROW_BUILD_TESTS=OFF \
+          -DARROW_BUILD_BENCHMARKS=OFF \
+          ..
+    make -j$(nproc) VERBOSE=1
+    make install -j$(nproc)
+    cd ../../python
+    pip install --no-cache-dir -r requirements-build.txt
+    PYARROW_WITH_PARQUET=1 \
+    PYARROW_WITH_DATASET=1 \
+    PYARROW_WITH_FILESYSTEM=1 \
+    PYARROW_WITH_JSON=1 \
+    PYARROW_WITH_CSV=1 \
+    PYARROW_PARALLEL=$(nproc) \
+    python setup.py build_ext --build-type=release --bundle-arrow-cpp bdist_wheel
+    mkdir -p /tmp/wheels
+    cp dist/pyarrow-*.whl /tmp/wheels/
+    chmod -R 777 /tmp/wheels
+    # Ensure wheels directory exists and has content
+    ls -la /tmp/wheels/
+else
+    # Create empty wheels directory for non-s390x
+    mkdir -p /tmp/wheels
+fi
+EOF
 
 #######################################################
 # common-builder (for Power-only)
@@ -264,6 +272,7 @@ USER 0
 # Dependencies for PDF export begin
 RUN ./utils/install_pdf_deps.sh
 ENV PATH="/usr/local/texlive/bin/linux:/usr/local/pandoc/bin:$PATH"
+
 # Dependencies for PDF export end
 
 USER 1001
@@ -299,8 +308,12 @@ WORKDIR /opt/app-root/bin
 USER root
 
 # Install useful OS packages
-RUN dnf install -y jq unixODBC unixODBC-devel postgresql git-lfs libsndfile libxcrypt-compat && \
-    dnf clean all && rm -rf /var/cache/yum
+RUN /bin/bash <<'EOF'
+set -Eeuxo pipefail
+dnf install -y jq unixODBC unixODBC-devel postgresql git-lfs libsndfile libxcrypt-compat
+dnf clean all
+rm -rf /var/cache/yum
+EOF
 
 # Copy dynamically-linked mongocli built in earlier build stage
 COPY --from=mongocli-builder /tmp/mongocli /opt/app-root/bin/
@@ -312,11 +325,14 @@ ENV PKG_CONFIG_PATH=/usr/local/lib/pkgconfig/
 
 # Copy wheels from build stage (ppc64le and s390x only)
 COPY --from=pyarrow-builder /tmp/wheels /tmp/wheels
-RUN if [ "$TARGETARCH" = "ppc64le" ] || [ "$TARGETARCH" = "s390x" ]; then \
-    pip install --no-cache-dir /tmp/wheels/*.whl; \
-else \
-    echo "Skipping wheel install for $TARGETARCH"; \
+RUN /bin/bash <<'EOF'
+set -Eeuxo pipefail
+if [ "$TARGETARCH" = "ppc64le" ] || [ "$TARGETARCH" = "s390x" ]; then
+    pip install --no-cache-dir /tmp/wheels/*.whl
+else
+    echo "Skipping wheel install for $TARGETARCH"
 fi
+EOF
 
 # Copy OpenBLAS,ONNX wheels for Power
 COPY --from=openblas-builder /root/OpenBLAS-${OPENBLAS_VERSION} /openblas
@@ -359,41 +375,43 @@ COPY ${DATASCIENCE_SOURCE_CODE}/pylock.toml ./
 # Copy Elyra setup to utils so that it's sourced at startup
 COPY ${DATASCIENCE_SOURCE_CODE}/setup-elyra.sh ${DATASCIENCE_SOURCE_CODE}/utils ./utils/
 
-RUN --mount=type=cache,target=/root/.cache/pip \
-    echo "Installing software and packages" && \
+RUN --mount=type=cache,target=/root/.cache/pip /bin/bash <<'EOF'
+set -Eeuxo pipefail
+echo "Installing software and packages"
+# This may have to download and compile some dependencies, and as we don't lock requirements from `build-system.requires`,
+#  we often don't know the correct hashes and `--require-hashes` would therefore fail on non amd64, where building is common.
+if [ "$TARGETARCH" = "ppc64le" ] || [ "$TARGETARCH" = "s390x" ]; then
+    # We need special flags and environment variables when building packages
+    GRPC_PYTHON_BUILD_SYSTEM_OPENSSL=1 \
+    CFLAGS="-O3" CXXFLAGS="-O3" \
+    uv pip install --strict --no-deps --no-cache --no-config --no-progress \
+        --verify-hashes --compile-bytecode --index-strategy=unsafe-best-match \
+        --requirements=./pylock.toml
+else
     # This may have to download and compile some dependencies, and as we don't lock requirements from `build-system.requires`,
-    #  we often don't know the correct hashes and `--require-hashes` would therefore fail on non amd64, where building is common.
-    if [ "$TARGETARCH" = "ppc64le" ] || [ "$TARGETARCH" = "s390x" ]; then \
-        # We need special flags and environment variables when building packages
-        GRPC_PYTHON_BUILD_SYSTEM_OPENSSL=1 \
-        CFLAGS="-O3" CXXFLAGS="-O3" \
-        uv pip install --strict --no-deps --no-cache --no-config --no-progress \
-            --verify-hashes --compile-bytecode --index-strategy=unsafe-best-match \
-            --requirements=./pylock.toml; \
-    else \
-        # This may have to download and compile some dependencies, and as we don't lock requirements from `build-system.requires`,
-        # we often don't know the correct hashes and `--require-hashes` would therefore fail on non amd64, where building is common.
-        uv pip install --strict --no-deps --no-cache --no-config --no-progress \
-            --verify-hashes --compile-bytecode --index-strategy=unsafe-best-match \
-            --requirements=./pylock.toml; \
-    fi && \
-    # setup path for runtime configuration
-    mkdir /opt/app-root/runtimes && \
-    mkdir /opt/app-root/pipeline-runtimes && \
-    # Remove default Elyra runtime-images \
-    rm /opt/app-root/share/jupyter/metadata/runtime-images/*.json && \
-    # Replace Notebook's launcher, "(ipykernel)" with Python's version 3.x.y \
-    sed -i -e "s/Python.*/$(python --version | cut -d '.' -f-2)\",/" \
-        /opt/app-root/share/jupyter/kernels/python3/kernel.json && \
-    # copy jupyter configuration
-    install -D -m 0644 /opt/app-root/bin/utils/jupyter_server_config.py \
-      /opt/app-root/etc/jupyter/jupyter_server_config.py && \
-    # Disable announcement plugin of jupyterlab \
-    jupyter labextension disable "@jupyterlab/apputils-extension:announcements" && \
-    # Apply JupyterLab addons \
-    /opt/app-root/bin/utils/addons/apply.sh && \
-    # Fix permissions to support pip in Openshift environments \
-    chmod -R g+w /opt/app-root/lib/python3.12/site-packages && \
-    fix-permissions /opt/app-root -P
+    # we often don't know the correct hashes and `--require-hashes` would therefore fail on non amd64, where building is common.
+    uv pip install --strict --no-deps --no-cache --no-config --no-progress \
+        --verify-hashes --compile-bytecode --index-strategy=unsafe-best-match \
+        --requirements=./pylock.toml
+fi
+# setup path for runtime configuration
+mkdir /opt/app-root/runtimes
+mkdir /opt/app-root/pipeline-runtimes
+# Remove default Elyra runtime-images
+rm /opt/app-root/share/jupyter/metadata/runtime-images/*.json
+# Replace Notebook's launcher, "(ipykernel)" with Python's version 3.x.y
+sed -i -e "s/Python.*/$(python --version | cut -d '.' -f-2)\",/" \
+    /opt/app-root/share/jupyter/kernels/python3/kernel.json
+# copy jupyter configuration
+install -D -m 0644 /opt/app-root/bin/utils/jupyter_server_config.py \
+  /opt/app-root/etc/jupyter/jupyter_server_config.py
+# Disable announcement plugin of jupyterlab
+jupyter labextension disable "@jupyterlab/apputils-extension:announcements"
+# Apply JupyterLab addons
+/opt/app-root/bin/utils/addons/apply.sh
+# Fix permissions to support pip in Openshift environments
+chmod -R g+w /opt/app-root/lib/python3.12/site-packages
+fix-permissions /opt/app-root -P
+EOF
 
 WORKDIR /opt/app-root/src