[Spark][Version Checksum] Incrementally compute VersionChecksum setTr… #6809
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| name: "Delta Spark Latest" | |
| on: [push, pull_request] | |
| jobs: | |
| test: | |
| name: "DSL: Scala ${{ matrix.scala }}, Shard ${{ matrix.shard }}" | |
| runs-on: ubuntu-20.04 | |
| strategy: | |
| matrix: | |
| # These Scala versions must match those in the build.sbt | |
| scala: [2.12.18, 2.13.13] | |
| # Important: This list of shards must be [0..NUM_SHARDS - 1] | |
| shard: [0, 1, 2, 3] | |
| env: | |
| SCALA_VERSION: ${{ matrix.scala }} | |
| # Important: This must be the same as the length of shards in matrix | |
| NUM_SHARDS: 4 | |
| steps: | |
| - uses: actions/checkout@v3 | |
| - uses: technote-space/get-diff-action@v4 | |
| id: git-diff | |
| with: | |
| PATTERNS: | | |
| ** | |
| .github/workflows/** | |
| !kernel/** | |
| !connectors/** | |
| - name: install java | |
| uses: actions/setup-java@v3 | |
| with: | |
| distribution: "zulu" | |
| java-version: "8" | |
| - name: Cache Scala, SBT | |
| uses: actions/cache@v3 | |
| with: | |
| path: | | |
| ~/.sbt | |
| ~/.ivy2 | |
| ~/.cache/coursier | |
| # Change the key if dependencies are changed. For each key, GitHub Actions will cache the | |
| # the above directories when we use the key for the first time. After that, each run will | |
| # just use the cache. The cache is immutable so we need to use a new key when trying to | |
| # cache new stuff. | |
| key: delta-sbt-cache-spark3.2-scala${{ matrix.scala }} | |
| - name: Install Job dependencies | |
| run: | | |
| sudo apt-get update | |
| sudo apt-get install -y make build-essential libssl-dev zlib1g-dev libbz2-dev libreadline-dev libsqlite3-dev wget curl llvm libncurses5-dev libncursesw5-dev xz-utils tk-dev libffi-dev liblzma-dev python-openssl git | |
| sudo apt install libedit-dev | |
| curl -LO https://github.com/bufbuild/buf/releases/download/v1.28.1/buf-Linux-x86_64.tar.gz | |
| mkdir -p ~/buf | |
| tar -xvzf buf-Linux-x86_64.tar.gz -C ~/buf --strip-components 1 | |
| rm buf-Linux-x86_64.tar.gz | |
| sudo apt install python3-pip --fix-missing | |
| sudo pip3 install pipenv==2021.5.29 | |
| curl https://pyenv.run | bash | |
| export PATH="~/.pyenv/bin:$PATH" | |
| eval "$(pyenv init -)" | |
| eval "$(pyenv virtualenv-init -)" | |
| pyenv install 3.8.18 | |
| pyenv global system 3.8.18 | |
| pipenv --python 3.8 install | |
| # Update the pip version to 24.0. By default `pyenv.run` installs the latest pip version | |
| # available. From version 24.1, `pip` doesn't allow installing python packages | |
| # with version string containing `-`. In Delta-Spark case, the pypi package generated has | |
| # `-SNAPSHOT` in version (e.g. `3.3.0-SNAPSHOT`) as the version is picked up from | |
| # the`version.sbt` file. | |
| pipenv run pip install pip==24.0 setuptools==69.5.1 wheel==0.43.0 | |
| pipenv run pip install pyspark==3.5.3 | |
| pipenv run pip install flake8==3.5.0 pypandoc==1.3.3 | |
| pipenv run pip install black==23.9.1 | |
| pipenv run pip install importlib_metadata==3.10.0 | |
| pipenv run pip install mypy==0.982 | |
| pipenv run pip install mypy-protobuf==3.3.0 | |
| pipenv run pip install cryptography==37.0.4 | |
| pipenv run pip install twine==4.0.1 | |
| pipenv run pip install wheel==0.33.4 | |
| pipenv run pip install setuptools==41.1.0 | |
| pipenv run pip install pydocstyle==3.0.0 | |
| pipenv run pip install pandas==1.1.3 | |
| pipenv run pip install pyarrow==8.0.0 | |
| pipenv run pip install numpy==1.20.3 | |
| if: steps.git-diff.outputs.diff | |
| - name: Scala structured logging style check | |
| run: | | |
| if [ -f ./dev/spark_structured_logging_style.py ]; then | |
| python3 ./dev/spark_structured_logging_style.py | |
| fi | |
| if: steps.git-diff.outputs.diff | |
| - name: Run Scala/Java and Python tests | |
| # when changing TEST_PARALLELISM_COUNT make sure to also change it in spark_master_test.yaml | |
| run: | | |
| TEST_PARALLELISM_COUNT=4 pipenv run python run-tests.py --group spark --shard ${{ matrix.shard }} | |
| if: steps.git-diff.outputs.diff |