Populate LabelStudio #5
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: Populate LabelStudio | |
| on: | |
| workflow_dispatch: | |
| inputs: | |
| crawl_id: | |
| description: 'Common Crawl Corpus' | |
| required: true | |
| default: 'CC-MAIN-2024-10' | |
| url: | |
| description: 'URL type' | |
| required: true | |
| default: '*.gov' | |
| keyword: | |
| description: 'keyword' | |
| required: true | |
| default: 'police' | |
| pages: | |
| description: 'num pages' | |
| required: true | |
| default: '2' | |
| record_type: | |
| description: 'record type' | |
| required: false | |
| jobs: | |
| run-script: | |
| runs-on: ubuntu-latest | |
| steps: | |
| - name: Checkout repository | |
| uses: actions/checkout@v3 | |
| with: | |
| ref: main | |
| - name: Set up Python | |
| uses: actions/setup-python@v4 | |
| with: | |
| python-version: '3.x' | |
| - name: Install dependencies | |
| run: | | |
| python -m pip install --upgrade pip | |
| pip install -r annotation_pipeline/requirements.txt | |
| - name: Run main script | |
| env: | |
| HUGGINGFACE_ACCESS_TOKEN: ${{ secrets.HUGGINGFACE_ACCESS_TOKEN }} | |
| LABEL_STUDIO_ACCESS_TOKEN: ${{ secrets.LABEL_STUDIO_ACCESS_TOKEN }} | |
| LABEL_STUDIO_PROJECT_ID: ${{ secrets.LABEL_STUDIO_PROJECT_ID }} | |
| LABEL_STUDIO_ORGANIZATION: ${{ secrets.LABEL_STUDIO_ORGANIZATION }} | |
| run: | | |
| if [ -n "${{ github.event.inputs.record_type }}" ]; then | |
| python annotation_pipeline/populate_labelstudio.py ${{ github.event.inputs.crawl_id }} "${{ github.event.inputs.url }}" ${{ github.event.inputs.keyword }} --pages ${{ github.event.inputs.pages }} --record_type "${{ github.event.inputs.record_type }}" | |
| else | |
| python annotation_pipeline/populate_labelstudio.py ${{ github.event.inputs.crawl_id }} "${{ github.event.inputs.url }}" ${{ github.event.inputs.keyword }} --pages ${{ github.event.inputs.pages }} | |
| fi | |
| - name: Check created/modified files | |
| run: | | |
| echo "Checking files in annotation_pipeline/data/" | |
| ls -R annotation_pipeline/data/ | |
| - name: Create new branch | |
| run: | | |
| BRANCH_NAME=bot-update-$(date +%Y%m%d%H%M%S) | |
| git checkout -b $BRANCH_NAME | |
| echo "BRANCH_NAME=$BRANCH_NAME" >> $GITHUB_ENV | |
| - name: Commit and push outputs | |
| run: | | |
| git config --global user.name "github-actions[bot]" | |
| git config --global user.email "[email protected]" | |
| git add annotation_pipeline/data/batch_info.csv | |
| git add annotation_pipeline/data/cache.json | |
| if [ -d "annotation_pipeline/data/tag_collector" ]; then | |
| git add annotation_pipeline/data/tag_collector/* | |
| fi | |
| git commit -m "Update batch info, cache, and collected urls & tags" | |
| git log -1 --stat | |
| git push --set-upstream origin $BRANCH_NAME | |
| - name: Create pull request | |
| env: | |
| GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }} | |
| BRANCH_NAME: ${{ env.BRANCH_NAME }} | |
| run: | | |
| PR_TITLE="Update batch info, cache, and collected urls & tags" | |
| PR_BODY="This PR was created automatically by a GitHub Action." | |
| echo "Creating PR from branch $BRANCH_NAME to main" | |
| curl -X POST -H "Authorization: token $GITHUB_TOKEN" \ | |
| -d "{\"title\":\"$PR_TITLE\",\"body\":\"$PR_BODY\",\"head\":\"$BRANCH_NAME\",\"base\":\"main\"}" \ | |
| https://api.github.com/repos/${{ github.repository }}/pulls |