ingest #189
This file contains hidden or 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: Ingest Content via Webhook | |
| on: | |
| repository_dispatch: | |
| types: [ingest] | |
| concurrency: | |
| group: ingestion | |
| jobs: | |
| checkRss: | |
| runs-on: "ubuntu-latest" | |
| steps: | |
| - uses: actions/checkout@v4 | |
| with: | |
| fetch-depth: 0 | |
| - name: Find and checkout latest updated branch | |
| id: brancher | |
| run: | | |
| LATEST_BRANCH=$(git for-each-ref --sort=-committerdate refs/remotes/origin/ --format='%(refname:short)' | grep '^origin/automated-' | head -n 1) | |
| if [[ -z "$LATEST_BRANCH" ]]; then | |
| BRANCH_NAME="main" | |
| else | |
| BRANCH_NAME=${LATEST_BRANCH#origin/} | |
| fi | |
| echo "Latest updated branch: $BRANCH_NAME" | |
| git checkout $BRANCH_NAME | |
| echo "latest-branch=$BRANCH_NAME" >> $GITHUB_OUTPUT | |
| - uses: actions/setup-node@v4 | |
| with: | |
| node-version: 22 | |
| - name: Get npm cache directory | |
| id: npm-cache-dir | |
| shell: bash | |
| run: echo "dir=$(npm config get cache)" >> ${GITHUB_OUTPUT} | |
| - uses: actions/cache@v4 | |
| id: npm-cache # use this to check for `cache-hit` ==> if: steps.npm-cache.outputs.cache-hit != 'true' | |
| with: | |
| path: ${{ steps.npm-cache-dir.outputs.dir }} | |
| key: ${{ runner.os }}-node-${{ hashFiles('**/package-lock.json') }} | |
| restore-keys: | | |
| ${{ runner.os }}-node- | |
| - run: npm install | |
| - run: npm run build | |
| env: | |
| DUCKDB_DATABASE_PATH: mrtdown.duckdb | |
| SENTRY_ORG: ${{ secrets.SENTRY_ORG }} | |
| SENTRY_PROJECT: ${{ secrets.SENTRY_PROJECT }} | |
| SENTRY_AUTH_TOKEN: ${{ secrets.SENTRY_AUTH_TOKEN }} | |
| SENTRY_RELEASE: production | |
| - run: npm run ingest:webhook | |
| env: | |
| OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }} | |
| MESSAGE: ${{ toJSON(github.event.client_payload) }} | |
| DUCKDB_DATABASE_PATH: mrtdown.duckdb | |
| - name: Check for changes | |
| id: make-changes | |
| run: |- | |
| if [[ -n $(git status --porcelain) ]]; then | |
| echo "There are uncommitted changes" | |
| echo "has_changes=true" >> $GITHUB_OUTPUT | |
| else | |
| echo "Working directory is clean" | |
| echo "has_changes=false" >> $GITHUB_OUTPUT | |
| fi | |
| - name: Target branch | |
| if: steps.make-changes.outputs.has_changes == 'true' | |
| id: target-branch | |
| run: |- | |
| if [[ "${{ steps.brancher.outputs.latest-branch }}" = "main" ]]; then | |
| echo "branch-name=automated-${{ github.run_id }}" >> $GITHUB_OUTPUT | |
| else | |
| echo "branch-name=${{ steps.brancher.outputs.latest-branch }}" >> $GITHUB_OUTPUT | |
| fi | |
| - name: Push changes | |
| if: steps.make-changes.outputs.has_changes == 'true' | |
| run: |- | |
| BRANCH_NAME="${{ steps.target-branch.outputs.branch-name }}" | |
| if [[ "${{ steps.brancher.outputs.latest-branch }}" = "main" ]]; then | |
| git checkout -b $BRANCH_NAME | |
| else | |
| git checkout $BRANCH_NAME | |
| fi | |
| git add -A | |
| git config user.email "41898282+github-actions[bot]@users.noreply.github.com" | |
| git config user.name "github-actions[bot]" | |
| git commit -m "chore(data): Automated changes" | |
| git push origin $BRANCH_NAME | |
| - name: Create Pull Request | |
| if: steps.make-changes.outputs.has_changes == 'true' && steps.brancher.outputs.latest-branch == 'main' | |
| uses: actions/github-script@v7 | |
| with: | |
| script: | | |
| const branchName = '${{ steps.target-branch.outputs.branch-name }}'; | |
| // Create PR using GitHub API | |
| const { data: pullRequest } = await github.rest.pulls.create({ | |
| owner: context.repo.owner, | |
| repo: context.repo.repo, | |
| title: `[Automated] Update Data`, | |
| body: ` | |
| # Automated Data | |
| This PR was automatically created by the scheduled GitHub Action workflow. | |
| `, | |
| head: branchName, | |
| base: 'main' | |
| }); | |
| console.log(`Pull Request created: ${pullRequest.html_url}`); |