Skip to content

Microbatch first last batch serial #2208

Microbatch first last batch serial

Microbatch first last batch serial #2208

Workflow file for this run

# **what?**
# Compares the schema of the dbt version of the given ref vs
# the latest official schema releases found in schemas.getdbt.com.
# If there are differences, the workflow will fail and upload the
# diff as an artifact. The metadata team should be alerted to the change.
#
# **why?**
# Reaction work may need to be done if artifact schema changes
# occur so we want to proactively alert to it.
#
# **when?**
# On pushes to `develop` and release branches. Manual runs are also enabled.
name: Artifact Schema Check
on:
pull_request:
types: [ opened, reopened, labeled, unlabeled, synchronize ]
paths-ignore: [ '.changes/**', '.github/**', 'tests/**', '**.md', '**.yml' ]
workflow_dispatch:
# no special access is needed
permissions: read-all
env:
LATEST_SCHEMA_PATH: ${{ github.workspace }}/new_schemas
SCHEMA_DIFF_ARTIFACT: ${{ github.workspace }}/schema_changes.txt
DBT_REPO_DIRECTORY: ${{ github.workspace }}/dbt
SCHEMA_REPO_DIRECTORY: ${{ github.workspace }}/schemas.getdbt.com
jobs:
checking-schemas:
name: "Post-merge schema changes required"
runs-on: ubuntu-latest
steps:
- name: Set up Python
uses: actions/setup-python@v5
with:
python-version: 3.9
- name: Checkout dbt repo
uses: actions/checkout@v4
with:
path: ${{ env.DBT_REPO_DIRECTORY }}
- name: Check for changes in core/dbt/artifacts
# https://github.com/marketplace/actions/paths-changes-filter
uses: dorny/paths-filter@v3
id: check_artifact_changes
with:
filters: |
artifacts_changed:
- 'core/dbt/artifacts/**'
list-files: shell
working-directory: ${{ env.DBT_REPO_DIRECTORY }}
- name: Succeed if no artifacts have changed
if: steps.check_artifact_changes.outputs.artifacts_changed == 'false'
run: |
echo "No artifact changes found in core/dbt/artifacts. CI check passed."
- name: Checkout schemas.getdbt.com repo
if: steps.check_artifact_changes.outputs.artifacts_changed == 'true'
uses: actions/checkout@v4
with:
repository: dbt-labs/schemas.getdbt.com
ref: 'main'
path: ${{ env.SCHEMA_REPO_DIRECTORY }}
- name: Generate current schema
if: steps.check_artifact_changes.outputs.artifacts_changed == 'true'
run: |
cd ${{ env.DBT_REPO_DIRECTORY }}
python3 -m venv env
source env/bin/activate
pip install --upgrade pip
pip install -r dev-requirements.txt -r editable-requirements.txt
python scripts/collect-artifact-schema.py --path ${{ env.LATEST_SCHEMA_PATH }}
# Copy generated schema files into the schemas.getdbt.com repo
# Do a git diff to find any changes
# Ignore any lines with date-like (yyyy-mm-dd) or version-like (x.y.z) changes
- name: Compare schemas
if: steps.check_artifact_changes.outputs.artifacts_changed == 'true'
run: |
cp -r ${{ env.LATEST_SCHEMA_PATH }}/dbt ${{ env.SCHEMA_REPO_DIRECTORY }}
cd ${{ env.SCHEMA_REPO_DIRECTORY }}
git diff -I='*[0-9]{4}-[0-9]{2}-[0-9]{2}' -I='*[0-9]+\.[0-9]+\.[0-9]+' --exit-code > ${{ env.SCHEMA_DIFF_ARTIFACT }}
- name: Upload schema diff
uses: actions/upload-artifact@v4
if: ${{ failure() && steps.check_artifact_changes.outputs.artifacts_changed == 'true' }}
with:
name: 'schema_changes.txt'
path: '${{ env.SCHEMA_DIFF_ARTIFACT }}'