Fix court string matching with whitespace #239
Workflow file for this run
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: Benchmark Pull Request | |
| on: | |
| pull_request: | |
| repository_dispatch: | |
| types: [ reporters-db-pr ] | |
| env: | |
| main: "$(/usr/bin/git log -1 --format='%H')" | |
| jobs: | |
| benchmark: | |
| name: PR comment | |
| if: github.event_name == 'pull_request' | |
| runs-on: ubuntu-latest | |
| steps: | |
| #---------------------------------------------- | |
| # check-out repo and set-up python | |
| #---------------------------------------------- | |
| - name: Check out repository | |
| uses: actions/checkout@v4 | |
| - name: Set up python | |
| id: setup-python | |
| uses: actions/setup-python@v5 | |
| with: | |
| python-version: 3.12 | |
| #---------------------------------------------- | |
| # Alert PR to eyecite benchmark test | |
| #---------------------------------------------- | |
| - name: Add or Update comment on PR that Test is running | |
| uses: marocchino/sticky-pull-request-comment@v2 | |
| with: | |
| recreate: true | |
| message: | | |
| Eyecite Benchmarking in progress... | |
| For details, see: https://github.com/freelawproject/eyecite/actions/workflows/benchmark.yml | |
| This message will be updated when the test is completed. | |
| #---------------------------------------------- | |
| # ----- install & configure poetry ----- | |
| # We are indeed using a pre-release version of poetry | |
| # That we should drop once groups is released for main | |
| #---------------------------------------------- | |
| - name: Install Poetry | |
| uses: snok/[email protected] | |
| with: | |
| virtualenvs-create: true | |
| virtualenvs-in-project: true | |
| #---------------------------------------------- | |
| # load cached venv if cache exists | |
| #---------------------------------------------- | |
| - name: Load cached venv | |
| id: cached-poetry-dependencies | |
| uses: actions/cache@v3 | |
| with: | |
| path: .venv | |
| key: venv-${{ runner.os }}-${{ steps.setup-python.outputs.python-version }}-${{ hashFiles('**/poetry.lock') }} | |
| #---------------------------------------------- | |
| # install dependencies if cache does not exist | |
| #---------------------------------------------- | |
| - name: Install dependencies | |
| if: steps.cached-poetry-dependencies.outputs.cache-hit != 'true' | |
| run: poetry install --with benchmark --without dev | |
| - name: Setup variables I | |
| id: branch1 | |
| run: | | |
| echo ${{ github.event.issue.pull_request }} | |
| echo "::set-output name=filepath::benchmark/${{ env.main }}.json" | |
| echo "::set-output name=hash::${{ env.main }}" | |
| #---------------------------------------------- | |
| # Download Testing File | |
| # | |
| # We generated our testing datasets with the following command: | |
| # | |
| # root@maintenance:/opt/courtlistener# PGPASSWORD=$DB_PASSWORD psql \ | |
| # --host $DB_HOST \ | |
| # --username $DB_USER \ | |
| # --dbname courtlistener \ | |
| # --command \ | |
| # 'set statement_timeout to 0; | |
| # COPY ( | |
| # SELECT \ | |
| # id, plain_text, html, html_lawbox, html_columbia, html_anon_2020, xml_harvard \ | |
| # FROM \ | |
| # search_opinion \ | |
| # TABLESAMPLE BERNOULLI (0.1) \ | |
| # ) \ | |
| # TO STDOUT \ | |
| # WITH (FORMAT csv, ENCODING utf8, HEADER); \ | |
| # ' \ | |
| # | bzip2 \ | |
| # | aws s3 cp - s3://com-courtlistener-storage/bulk-data/eyecite/tests/ten-percent.csv.bz2 \ | |
| # --acl public-read | |
| #---------------------------------------------- | |
| - name: Download Testing File | |
| run: | | |
| curl https://storage.courtlistener.com/bulk-data/eyecite/tests/one-percent.csv.bz2 --output benchmark/bulk-file.csv.bz2 | |
| - name: Run first benchmark | |
| run: | | |
| poetry run python benchmark/benchmark.py --branches ${{ steps.branch1.outputs.hash }} | |
| git stash --include-untracked | |
| - uses: actions/checkout@v4 | |
| with: | |
| repository: freelawproject/eyecite | |
| ref: main | |
| - name: Load cached venv 2 | |
| id: cached-poetry-dependencies2 | |
| uses: actions/cache@v3 | |
| with: | |
| path: .venv | |
| key: venv-${{ runner.os }}-${{ steps.setup-python.outputs.python-version }}-${{ hashFiles('**/poetry.lock') }} | |
| #---------------------------------------------- | |
| # install dependencies if cache does not exist | |
| #---------------------------------------------- | |
| - name: Install dependencies 2 | |
| if: steps.cached-poetry-dependencies2.outputs.cache-hit != 'true' | |
| run: poetry install --with benchmark --without dev | |
| - name: Setup variables II | |
| id: branch2 | |
| run: | | |
| echo "::set-output name=filepath::benchmark/${{ env.main }}.json" | |
| echo "::set-output name=hash::${{ env.main }}" | |
| - name: Run second benchmark | |
| run: | | |
| git stash pop | |
| poetry run python benchmark/benchmark.py --branches ${{ steps.branch1.outputs.hash }} ${{ steps.branch2.outputs.hash }} --pr ${{ github.event.number }} | |
| mkdir results | |
| mv benchmark/output.csv benchmark/${{ steps.branch1.outputs.hash }}.json benchmark/${{ steps.branch2.outputs.hash }}.json benchmark/report.md benchmark/chart.png results/ | |
| #---------------------------------------------- | |
| # Upload to Github PR | |
| #---------------------------------------------- | |
| - name: Pushes test file | |
| uses: dmnemec/copy_file_to_another_repo_action@main | |
| env: | |
| API_TOKEN_GITHUB: ${{ secrets.FREELAWBOT_TOKEN }} | |
| with: | |
| user_email: '[email protected]' | |
| user_name: 'freelawbot' | |
| source_file: 'results/' | |
| destination_repo: 'freelawproject/eyecite' | |
| destination_folder: '${{ github.event.number }}' | |
| destination_branch: 'artifacts' | |
| commit_message: 'feat(ci): Add artifacts for PR# ${{ github.event.number }}' | |
| - name: Add or Update PR Comment from Generated Report | |
| uses: marocchino/sticky-pull-request-comment@v2 | |
| with: | |
| recreate: true | |
| path: results/report.md | |
| dispatch: | |
| name: Reporters-DB-Dipatch | |
| if: github.event_name == 'repository_dispatch' | |
| runs-on: ubuntu-latest | |
| steps: | |
| #---------------------------------------------- | |
| # check-out repo and set-up python | |
| #---------------------------------------------- | |
| - name: Check out repository | |
| uses: actions/checkout@v4 | |
| - name: Set up python | |
| id: setup-python | |
| uses: actions/setup-python@v5 | |
| with: | |
| python-version: 3.12 | |
| #---------------------------------------------- | |
| # Alert PR to eyecite benchmark test | |
| #---------------------------------------------- | |
| - name: Add or Update comment on PR that Test is running | |
| uses: marocchino/sticky-pull-request-comment@v2 | |
| with: | |
| recreate: true | |
| GITHUB_TOKEN: ${{ secrets.FREELAWBOT_TOKEN }} | |
| number: ${{ github.event.client_payload.pr_number }} | |
| repo: reporters-db | |
| message: | | |
| Eyecite Benchmarking in progress ... | |
| This message will be updated when the test is completed. | |
| #---------------------------------------------- | |
| # ----- install & configure poetry ----- | |
| #---------------------------------------------- | |
| - name: Install Poetry | |
| uses: snok/[email protected] | |
| with: | |
| virtualenvs-create: true | |
| virtualenvs-in-project: true | |
| #---------------------------------------------- | |
| # load cached venv if cache exists | |
| #---------------------------------------------- | |
| - name: Load cached venv | |
| id: cached-poetry-dependencies | |
| uses: actions/cache@v3 | |
| with: | |
| path: .venv | |
| key: venv-${{ runner.os }}-${{ steps.setup-python.outputs.python-version }}-${{ hashFiles('**/poetry.lock') }} | |
| #---------------------------------------------- | |
| # install dependencies if cache does not exist | |
| #---------------------------------------------- | |
| - name: Install dependencies | |
| if: steps.cached-poetry-dependencies.outputs.cache-hit != 'true' | |
| run: poetry install --with benchmark --without dev | |
| #---------------------------------------------- | |
| # run test suite | |
| #---------------------------------------------- | |
| - name: Run Tests | |
| run: | | |
| poetry run pip install "git+https://github.com/freelawproject/reporters-db.git" | |
| echo ${{ github.event.client_payload.pr_number }} | |
| curl https://storage.courtlistener.com/bulk-data/eyecite/tests/one-percent.csv.bz2 --output benchmark/bulk-file.csv.bz2 | |
| poetry run python benchmark/benchmark.py --branches original | |
| poetry run pip install "git+https://github.com/freelawproject/reporters-db.git@${{ github.event.client_payload.commit }}" | |
| poetry run python benchmark/benchmark.py --branches original update --reporters --pr ${{ github.event.client_payload.pr_number }} | |
| mkdir results | |
| mv benchmark/output.csv benchmark/original.json benchmark/update.json benchmark/report.md benchmark/chart.png results/ | |
| #---------------------------------------------- | |
| # Upload to Github PR | |
| #---------------------------------------------- | |
| - name: Pushes test file | |
| uses: dmnemec/copy_file_to_another_repo_action@main | |
| env: | |
| API_TOKEN_GITHUB: ${{ secrets.FREELAWBOT_TOKEN }} | |
| with: | |
| user_email: '[email protected]' | |
| user_name: 'freelawbot' | |
| source_file: 'results/' | |
| destination_repo: 'freelawproject/reporters-db' | |
| destination_folder: '${{ github.event.client_payload.pr_number }}' | |
| destination_branch: 'artifacts' | |
| commit_message: 'feat(ci): Add artifacts for PR #${{ github.event.client_payload.pr_number }}' | |
| #---------------------------------------------- | |
| # Upload to Github PR | |
| #---------------------------------------------- | |
| - name: Add or Update PR Comment from Generated Report | |
| uses: marocchino/sticky-pull-request-comment@v2 | |
| with: | |
| recreate: true | |
| GITHUB_TOKEN: ${{ secrets.FREELAWBOT_TOKEN }} | |
| path: results/report.md | |
| number: ${{ github.event.client_payload.pr_number }} | |
| repo: reporters-db | |