codeql/.github/workflows/dataset_measure.yml

name: Collect database stats

on:
  push:
    branches:
      - main
      - 'rc/*'
    paths:
      - ql/lib/ruby.dbscheme
  pull_request:
    branches:
      - main
      - 'rc/*'
    paths:
      - ql/lib/ruby.dbscheme
  workflow_dispatch:

jobs:
  measure:
    env:
      CODEQL_THREADS: 4 # TODO: remove this once it's set by the CLI
    strategy:
      fail-fast: false
      matrix:
        repo: [rails/rails, discourse/discourse, spree/spree]
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v2

      - uses: ./.github/actions/fetch-codeql

      - uses: ./.github/actions/create-extractor-pack

      - name: Checkout ${{ matrix.repo }}
        uses: actions/checkout@v2
        with:
          repository: ${{ matrix.repo }}
          path: ${{ github.workspace }}/repo
      - name: Create database
        run: |
          codeql/codeql database create \
            --search-path "${{ github.workspace }}" \
            --threads 4 \
            --language ruby --source-root "${{ github.workspace }}/repo" \
            "${{ runner.temp }}/database"
      - name: Measure database
        run: |
          mkdir -p "stats/${{ matrix.repo }}"
          codeql/codeql dataset measure --threads 4 --output "stats/${{ matrix.repo }}/stats.xml" "${{ runner.temp }}/database/db-ruby"
      - uses: actions/upload-artifact@v2
        with:
          name: measurements
          path: stats
          retention-days: 1

  merge:
    runs-on: ubuntu-latest
    needs: measure
    steps:
      - uses: actions/checkout@v2
      - uses: actions/download-artifact@v2
        with:
          name: measurements
          path: stats
      - run: |
          python -m pip install --user lxml
          find stats -name 'stats.xml' | sort | xargs python scripts/merge_stats.py --output ql/lib/ruby.dbscheme.stats --normalise ruby_tokeninfo
      - uses: actions/upload-artifact@v2
        with:
          name: ruby.dbscheme.stats
          path: ql/lib/ruby.dbscheme.stats