chore(librarian): Migrate off bazel for librarian generate (#14367)

Fixes googleapis/librarian#1929

Author: parthea

.generator/Dockerfile

@@ -16,22 +16,15 @@
 # This stage installs all build dependencies and compiles all Python versions.
 FROM marketplace.gcr.io/google/ubuntu2404 AS builder
 
-# TODO(https://github.com/googleapis/librarian/issues/901): Install the necssary dependencies and build tools.
 RUN apt-get update && \
     apt-get install -y --no-install-recommends \
     # Essential for compiling C code
     build-essential \
-    # For downloading secure files
+    # For downloading and extracting secure files
     git \
     wget \
     ca-certificates \
-    # For running bazelisk commands
-    openjdk-17-jdk \
-    zip \
-    unzip \ 
-    # To avoid bazel error
-    # "python interpreter `python3` not found in PATH"
-    python3-dev \
+    unzip \
     # --- Critical libraries for a complete Python build ---
     libssl-dev \
     zlib1g-dev \
@@ -43,9 +36,6 @@ RUN apt-get update && \
     && apt-get clean && \
     rm -rf /var/lib/apt/lists/*
 
-# Set up environment variables for tool versions to make updates easier.
-ENV BAZELISK_VERSION=v1.26.0
-
 # Install multiple Python versions from source. `make altinstall` is used to
 # prevent replacing the system's default python binary.
 # TODO(http://github.com/googleapis/gapic-generator-python/issues/2435): Remove `3.10.18` when the linked issue is resolved.
@@ -68,77 +58,48 @@ RUN wget --no-check-certificate -O /tmp/get-pip.py 'https://bootstrap.pypa.io/ge
     done && \
     rm /tmp/get-pip.py
 
-# Install Bazelisk
-RUN wget https://github.com/bazelbuild/bazelisk/releases/download/${BAZELISK_VERSION}/bazelisk-linux-amd64 -O /usr/local/bin/bazelisk && \
-    chmod +x /usr/local/bin/bazelisk
-
-# Set the working directory for build-related tasks.
-WORKDIR /app
-
-# Create the group and user, but only if they don't already exist.
-ARG UID=1000
-ARG GID=1000
-
-RUN if ! getent group $GID > /dev/null; then \
-        groupadd -g $GID myuser; \
-    fi && \
-    if ! getent passwd $UID > /dev/null; then \
-        useradd -u $UID -g $GID -ms /bin/bash myuser; \
-    fi
-
-# Set ownership of the app directory now, before we copy files into it.
-RUN mkdir -p /app && chown $UID:$GID /app
-
-# We'll point both to the /bazel_cache directory which will be mounted as a volume.
-ENV BAZELISK_HOME="/bazel_cache/bazelisk"
-ENV BAZEL_HOME="/bazel_cache/bazel"
-
-# Ensure the cache directories within the non-root user's context exist and are writable.
-# This is crucial as Bazel creates subdirectories under BAZEL_HOME.
-RUN mkdir -p ${BAZEL_HOME}/_bazel_ubuntu/cache/repos \
-             ${BAZEL_HOME}/_bazel_ubuntu/output_base \
-             ${BAZELISK_HOME} && \
-    chown -R $UID:$GID ${BAZEL_HOME} ${BAZELISK_HOME}
-
 RUN /usr/local/bin/python3.9 -m venv bazel_env
 RUN . bazel_env/bin/activate
 
-RUN git clone https://github.com/googleapis/googleapis.git \
-    && cd googleapis \
-    && bazelisk --output_base=/bazel_cache/_bazel_ubuntu/output_base build --disk_cache=/bazel_cache/_bazel_ubuntu/cache/repos  --incompatible_strict_action_env //google/cloud/language/v1:language-v1-py
+# Download/extract protoc
+RUN wget https://github.com/protocolbuffers/protobuf/releases/download/v25.3/protoc-25.3-linux-x86_64.zip
+RUN unzip protoc-25.3-linux-x86_64.zip -d protoc
 
-# TODO(https://github.com/googleapis/librarian/issues/904): Install protoc for gencode.
+# Download/extract pandoc
+# Pandoc is required by gapic-generator-python for parsing documentation
+RUN wget https://github.com/jgm/pandoc/releases/download/3.7.0.2/pandoc-3.7.0.2-linux-amd64.tar.gz
+RUN tar -xvf pandoc-3.7.0.2-linux-amd64.tar.gz
+
+# Download synthtool
+RUN git clone --depth 1 https://github.com/googleapis/synthtool.git synthtool
 
 # --- Final Stage ---
 # This stage creates the lightweight final image, copying only the
 # necessary artifacts from the builder stage.
 FROM marketplace.gcr.io/google/ubuntu2404
 
+# Tell synthtool to pull templates from this docker image instead of from
+# the live repo.
+ENV SYNTHTOOL_TEMPLATES="/synthtool/synthtool/gcp/templates"
+
 # Install only the essential runtime libraries for Python.
 # These are the non "-dev" versions of the libraries used in the builder.
 RUN apt-get update && \
     apt-get install -y --no-install-recommends \
-    ca-certificates \
-    git \
-    libssl3 \
-    zlib1g \
-    libbz2-1.0 \
-    libffi8 \
+    # This is needed to avoid the following error:
+    # `ImportError: libsqlite3.so.0: cannot open shared object file: No such file or directory`.
+    # `libsqlite3-0` is used by the `coverage` PyPI package which is used when testing libraries
     libsqlite3-0 \
-    libreadline8 \
-    # For running bazelisk commands
-    openjdk-17-jdk \
-    # To avoid bazel error
-    # "python interpreter `python3` not found in PATH"
-    python3-dev \
-    # To avoid bazel error
-    # "Cannot find gcc or CC; either correct your path or set the CC environment variable"
-    build-essential \
-    # To avoid bazel error
-    # unzip command not found
-    unzip \ 
-    && apt-get clean && \
-    rm -rf /var/lib/apt/lists/*
+    && apt-get clean autoclean \
+    && apt-get autoremove -y \
+    && rm -rf /var/lib/apt/lists/* \
+    && rm -f /var/cache/apt/archives/*.deb
+
+COPY --from=builder protoc/bin /usr/local/bin
+COPY --from=builder protoc/include /usr/local/include
+
+COPY --from=builder pandoc-3.7.0.2/bin /usr/local/bin
+COPY --from=builder synthtool /synthtool
 
 # Copy all Python interpreters, their pip executables, and their standard libraries from the builder.
 COPY --from=builder /usr/local/bin/python3.9 /usr/local/bin/
@@ -151,26 +112,16 @@ COPY --from=builder /usr/local/lib/python3.10 /usr/local/lib/python3.10
 COPY --from=builder /usr/local/bin/python3.13 /usr/local/bin/
 COPY --from=builder /usr/local/lib/python3.13 /usr/local/lib/python3.13
 
-# Copy the bazelisk executable from the builder.
-COPY --from=builder /usr/local/bin/bazelisk /usr/local/bin/
-
-# Copy bazel cache from the builder.
-COPY --from=builder /bazel_cache /bazel_cache
-RUN chmod -R 777 /bazel_cache
-
 # Set the working directory in the container.
 WORKDIR /app
 
-# Create a virtual env and set the Path to fix the missing nox error
-# when running the post processor changes.
-RUN /usr/local/bin/python3.9 -m venv bazel_env
-RUN . bazel_env/bin/activate
-
-ENV PATH=/app/bazel_env/bin:$PATH
-
-RUN git clone --depth 1 https://github.com/googleapis/synthtool.git /tmp/synthtool && \
-bazel_env/bin/python3.9 -m pip install /tmp/synthtool nox && \
-rm -rf /tmp/synthtool
+# Install dependencies of the CLI such as click.
+# Install gapic-generator which is used to generate libraries.
+# Install nox which is used for running client library tests.
+# Install starlark-pyo3 which is used to parse BUILD.bazel files.
+COPY .generator/requirements.in .
+RUN python3.9 -m pip install -r requirements.in
+RUN python3.9 -m pip install /synthtool
 
 # Install build which is used to get the metadata of package config files.
 COPY .generator/requirements.in .
@@ -180,4 +131,8 @@ RUN python3.9 -m pip install -r requirements.in
 COPY .generator/cli.py .
 RUN chmod a+rx ./cli.py
 
+# Copy the script used to parse BUILD.bazel files.
+COPY .generator/parse_googleapis_content.py .
+RUN chmod a+rx ./parse_googleapis_content.py
+
 ENTRYPOINT ["python3.9", "./cli.py"]