Skip to content

Commit

Permalink
ci: Clean up of Makefile and Gitpod setup (#464)
Browse files Browse the repository at this point in the history
* switch to Dockerfile, same configuration as the kedro branch.

Signed-off-by: Nok <nok.lam.chan@quantumblack.com>

* simplify setup

Signed-off-by: Nok <nok.lam.chan@quantumblack.com>

* update makefile

Signed-off-by: Nok <nok.lam.chan@quantumblack.com>

* simplified install in background while not slowing down startup

Signed-off-by: Nok <nok.lam.chan@quantumblack.com>

* fix command

Signed-off-by: Nok <nok.lam.chan@quantumblack.com>

* fix setup

Signed-off-by: Nok <nok.lam.chan@quantumblack.com>

* combined makefile

Signed-off-by: Nok <nok.lam.chan@quantumblack.com>

---------

Signed-off-by: Nok <nok.lam.chan@quantumblack.com>
  • Loading branch information
noklam authored Aug 28, 2024
1 parent 1eb2bf7 commit cf1617b
Show file tree
Hide file tree
Showing 2 changed files with 36 additions and 60 deletions.
28 changes: 10 additions & 18 deletions .gitpod.yml
Original file line number Diff line number Diff line change
@@ -1,6 +1,4 @@
# Learn more from ready-to-use templates: https://www.gitpod.io/docs/introduction/getting-started/quickstart
image: gitpod/workspace-python-3.10:2023-04-20-16-32-37

image: gitpod/workspace-python-3.11

tasks:
# We want packages installed during the pre-build init steps to go to /workspace
Expand All @@ -12,22 +10,16 @@ tasks:
echo PIP_USER=no >> ~/.bashrc && export PIP_USER=no
init: |
make sign-off
pip install uv
uv venv
echo source .venv/bin/activate >> ~/.bashrc
source ~/.bashrc
make install-test-requirements plugin=kedro-datasets
command: |
pre-commit install --install-hooks
clear
github:
prebuilds:
# enable for the master/default branch (defaults to true)
master: true
# enable for all branches in this repo (defaults to false)
branches: true
# enable for pull requests coming from this repo (defaults to true)
pullRequests: true
# enable for pull requests coming from forks (defaults to false)
pullRequestsFromForks: true
# add a "Review in Gitpod" button as a comment to pull requests (defaults to true)
addComment: false
# add a "Review in Gitpod" button to pull requests (defaults to false)
addBadge: true
- name: system
init: |
sudo apt-get update && sudo apt-get install -y --no-install-recommends libgl1 make
sudo apt-get install -y --no-install-recommends libatk-bridge2.0-0 libcups2 ca-certificates fonts-liberation libasound2 libatk-bridge2.0-0 libatk1.0-0 libc6 libcairo2 libcups2 libdbus-1-3 libexpat1 libfontconfig1 libgbm1 libgcc1 libglib2.0-0 libgtk-3-0 libnspr4 libnss3 libpango-1.0-0 libpangocairo-1.0-0 libstdc++6 libx11-6 libx11-xcb1 libxcb1 libxcomposite1 libxcursor1 libxdamage1 libxext6 libxfixes3 libxi6 libxrandr2 libxrender1 libxss1 libxtst6 lsb-release wget xdg-utils
68 changes: 26 additions & 42 deletions Makefile
Original file line number Diff line number Diff line change
Expand Up @@ -5,13 +5,6 @@ package:
rm -Rf dist;\
python -m build

pypi:
python -m pip install twine -U
python -m twine upload $(plugin)/dist/*

install: package
cd $(plugin) && pip install -U dist/*.whl

install-pip-setuptools:
python -m pip install -U pip setuptools wheel

Expand All @@ -25,46 +18,14 @@ mypy:
test:
cd $(plugin) && pytest tests --cov-config pyproject.toml --numprocesses 4 --dist loadfile

# Run test_tensorflow_model_dataset separately, because these tests are flaky when run as part of the full test-suite
dataset-tests: dataset-doctests
cd kedro-datasets && pytest tests --cov-config pyproject.toml --numprocesses 4 --dist loadfile --ignore tests/tensorflow
cd kedro-datasets && pytest tests/tensorflow/test_tensorflow_model_dataset.py --no-cov

extra_pytest_args-no-spark=--ignore kedro_datasets/databricks --ignore kedro_datasets/spark
extra_pytest_args=
dataset-doctest%:
if [ "${*}" != 's-no-spark' ] && [ "${*}" != 's' ]; then \
echo "make: *** No rule to make target \`${@}\`. Stop."; \
exit 2; \
fi; \
\
# The ignored datasets below require complicated setup with cloud/database clients which is overkill for the doctest examples.
cd kedro-datasets && pytest kedro_datasets --doctest-modules --doctest-continue-on-failure --no-cov \
--ignore kedro_datasets/pandas/gbq_dataset.py \
--ignore kedro_datasets/partitions/partitioned_dataset.py \
--ignore kedro_datasets/redis/redis_dataset.py \
--ignore kedro_datasets/snowflake/snowpark_dataset.py \
--ignore kedro_datasets/spark/spark_hive_dataset.py \
--ignore kedro_datasets/spark/spark_jdbc_dataset.py \
$(extra_pytest_arg${*})

test-sequential:
cd $(plugin) && pytest tests --cov-config pyproject.toml

e2e-tests:
cd $(plugin) && behave

secret-scan:
trufflehog --max_depth 1 --exclude_paths trufflehog-ignore.txt .

clean:
cd $(plugin);\
rm -rf build dist pip-wheel-metadata .pytest_cache;\
find . -regex ".*/__pycache__" -exec rm -rf {} +;\
find . -regex ".*\.egg-info" -exec rm -rf {} +;\

install-test-requirements:
cd $(plugin) && pip install ".[test]"
cd $(plugin) && uv pip install ".[test]"

install-pre-commit:
pre-commit install --install-hooks
Expand All @@ -79,12 +40,12 @@ sign-off:
echo '--in-place "$$1"' >> .git/hooks/commit-msg
chmod +x .git/hooks/commit-msg

## kedro-datasets specific

# kedro-datasets related only
test-no-spark: dataset-doctests-no-spark
cd kedro-datasets && pytest tests --no-cov --ignore tests/spark --ignore tests/databricks --numprocesses 4 --dist loadfile

test-no-spark-sequential: dataset-doctests-no-spark
cd kedro-datasets && pytest tests --no-cov --ignore tests/spark --ignore tests/databricks

# kedro-datasets/snowflake tests skipped from default scope
test-snowflake-only:
Expand All @@ -93,3 +54,26 @@ test-snowflake-only:

check-datasets-docs:
cd kedro-datasets && python -m sphinx -WETan -j auto -D language=en -b linkcheck -d _build/doctrees docs/source _build/linkcheck

# Run test_tensorflow_model_dataset separately, because these tests are flaky when run as part of the full test-suite
dataset-tests: dataset-doctests
cd kedro-datasets && pytest tests --cov-config pyproject.toml --numprocesses 4 --dist loadfile --ignore tests/tensorflow
cd kedro-datasets && pytest tests/tensorflow/test_tensorflow_model_dataset.py --no-cov

extra_pytest_args-no-spark=--ignore kedro_datasets/databricks --ignore kedro_datasets/spark
extra_pytest_args=
dataset-doctest%:
if [ "${*}" != 's-no-spark' ] && [ "${*}" != 's' ]; then \
echo "make: *** No rule to make target \`${@}\`. Stop."; \
exit 2; \
fi; \
\
# The ignored datasets below require complicated setup with cloud/database clients which is overkill for the doctest examples.
cd kedro-datasets && pytest kedro_datasets --doctest-modules --doctest-continue-on-failure --no-cov \
--ignore kedro_datasets/pandas/gbq_dataset.py \
--ignore kedro_datasets/partitions/partitioned_dataset.py \
--ignore kedro_datasets/redis/redis_dataset.py \
--ignore kedro_datasets/snowflake/snowpark_dataset.py \
--ignore kedro_datasets/spark/spark_hive_dataset.py \
--ignore kedro_datasets/spark/spark_jdbc_dataset.py \
$(extra_pytest_arg${*})

0 comments on commit cf1617b

Please sign in to comment.