stats.yml

# Contains jobs corresponding to stats, including build stats due to changes in a PR.

name: Stats Checks & Reports

on:
  workflow_dispatch:
  schedule:
    - cron: "30 02 * * *"

permissions:
  pull-requests: write

jobs:
  find_open_pull_requests:
    name: Find open PRs
    runs-on: ubuntu-20.04
    outputs:
      matrix: ${{ steps.compute-pull-request-matrix.outputs.matrix }}
    env:
      GH_TOKEN: ${{ github.token }}
    steps:
      - uses: actions/checkout@v4

      - name: Compute PR matrix
        id: compute-pull-request-matrix
        # Remove spaces to ensure the matrix output is on one line. Reference:
        # https://stackoverflow.com/a/3232433.
        run: |
          CURRENT_OPEN_PR_INFO="$(gh pr list --json number,baseRefName,headRefName,headRepository,headRepositoryOwner | tr -d '[:space:]')"
          echo "matrix={\"prInfo\": $CURRENT_OPEN_PR_INFO}" >> "$GITHUB_OUTPUT"

  build_stats:
    name: Build Stats
    needs: find_open_pull_requests
    runs-on: ubuntu-20.04
    # Reduce parallelization due to high build times, and allow individual PRs to fail.
    strategy:
      fail-fast: false
      max-parallel: 5
      matrix: ${{ fromJson(needs.find_open_pull_requests.outputs.matrix) }}
    env:
      ENABLE_CACHING: false
      CACHE_DIRECTORY: ~/.bazel_cache
    steps:
      - name: Compute PR head owner/repo reference
        env:
          PR_HEAD_REPO: ${{ matrix.prInfo.headRepository.name }}
          PR_HEAD_REPO_OWNER: ${{ matrix.prInfo.headRepositoryOwner.login }}
        run: |
          echo "PR_HEAD=$PR_HEAD_REPO_OWNER/$PR_HEAD_REPO" >> "$GITHUB_ENV"
      - name: Print PR information for this run
        env:
          PR_BASE_REF_NAME: ${{ matrix.prInfo.baseRefName }}
          PR_HEAD_REF_NAME: ${{ matrix.prInfo.headRefName }}
          PR_NUMBER: ${{ matrix.prInfo.number }}
        run: |
          echo "PR $PR_NUMBER is merging into $PR_BASE_REF_NAME from https://github.com/$PR_HEAD branch $PR_HEAD_REF_NAME."

      - name: Set up JDK 11
        uses: actions/setup-java@v1
        with:
          java-version: 11

      - name: Set up Bazel
        uses: abhinavsingh/setup-bazel@v3
        with:
          version: 6.5.0

      # For reference on this & the later cache actions, see:
      # https://github.com/actions/cache/issues/239#issuecomment-606950711 &
      # https://github.com/actions/cache/issues/109#issuecomment-558771281. Note that these work
      # with Bazel since Bazel can share the most recent cache from an unrelated build and still
      # benefit from incremental build performance (assuming that actions/cache aggressively removes
      # older caches due to the 5GB cache limit size & Bazel's large cache size).
      - uses: actions/cache@v2
        id: cache
        with:
          path: ${{ env.CACHE_DIRECTORY }}
          key: ${{ runner.os }}-${{ env.CACHE_DIRECTORY }}-bazel-binary-${{ github.sha }}
          restore-keys: |
            ${{ runner.os }}-${{ env.CACHE_DIRECTORY }}-bazel-binary-
            ${{ runner.os }}-${{ env.CACHE_DIRECTORY }}-bazel-

      # This check is needed to ensure that Bazel's unbounded cache growth doesn't result in a
      # situation where the cache never updates (e.g. due to exceeding GitHub's cache size limit)
      # thereby only ever using the last successful cache version. This solution will result in a
      # few slower CI actions around the time cache is detected to be too large, but it should
      # incrementally improve thereafter.
      - name: Ensure cache size
        env:
          BAZEL_CACHE_DIR: ${{ env.CACHE_DIRECTORY }}
        run: |
          # See https://stackoverflow.com/a/27485157 for reference.
          EXPANDED_BAZEL_CACHE_PATH="${BAZEL_CACHE_DIR/#\~/$HOME}"
          CACHE_SIZE_MB=$(du -smc $EXPANDED_BAZEL_CACHE_PATH | grep total | cut -f1)
          echo "Total size of Bazel cache (rounded up to MBs): $CACHE_SIZE_MB"
          # Use a 4.5GB threshold since actions/cache compresses the results, and Bazel caches seem
          # to only increase by a few hundred megabytes across changes for unrelated branches. This
          # is also a reasonable upper-bound (local tests as of 2021-03-31 suggest that a full build
          # of the codebase (e.g. //...) from scratch only requires a ~2.1GB uncompressed/~900MB
          # compressed cache).
          if [[ "$CACHE_SIZE_MB" -gt 4500 ]]; then
            echo "Cache exceeds cut-off; resetting it (will result in a slow build)"
            rm -rf $EXPANDED_BAZEL_CACHE_PATH
          fi

      - name: Configure Bazel to use a local cache
        env:
          BAZEL_CACHE_DIR: ${{ env.CACHE_DIRECTORY }}
        run: |
          EXPANDED_BAZEL_CACHE_PATH="${BAZEL_CACHE_DIR/#\~/$HOME}"
          echo "Using $EXPANDED_BAZEL_CACHE_PATH as Bazel's cache path"
          echo "build --disk_cache=$EXPANDED_BAZEL_CACHE_PATH" >> $HOME/.bazelrc
        shell: bash

      # This checks out the actual true develop branch separately to ensure that the stats check is
      # run from the latest develop rather than the base branch (which might be different for
      # chained PRs).
      - name: Check out develop repository
        uses: actions/checkout@v4
        with:
          path: develop

      - name: Set up build environment
        uses: ./develop/.github/actions/set-up-android-bazel-build-environment

      - name: Check Bazel environment
        run: |
          cd develop
          bazel info

      - name: Check out base repository and branch
        env:
          PR_BASE_REF_NAME: ${{ matrix.prInfo.baseRefName }}
        uses: actions/checkout@v4
        with:
          fetch-depth: 0
          ref: ${{ env.PR_BASE_REF_NAME }}
          path: base

      - name: Check out head repository and branch
        env:
          PR_HEAD_REF_NAME: ${{ matrix.prInfo.headRefName }}
        uses: actions/checkout@v4
        with:
          fetch-depth: 0
          repository: ${{ env.PR_HEAD }}
          ref: ${{ env.PR_HEAD_REF_NAME }}
          path: head

      # Note that Bazel is shutdown between builds since multiple Bazel servers will otherwise end
      # up being active (due to multiple repositories being used) and this can quickly overwhelm CI
      # worker resources.
      - name: Build Oppia dev, alpha, beta, and GA (feature branch)
        run: |
          cd head
          git log -n 1
          bazel build -- //:oppia_dev //:oppia_alpha //:oppia_beta //:oppia_ga
          cp bazel-bin/oppia_dev.aab ../develop/oppia_dev_with_changes.aab
          cp bazel-bin/oppia_alpha.aab ../develop/oppia_alpha_with_changes.aab
          cp bazel-bin/oppia_beta.aab ../develop/oppia_beta_with_changes.aab
          cp bazel-bin/oppia_ga.aab ../develop/oppia_ga_with_changes.aab
          bazel shutdown

      - name: Build Oppia dev, alpha, beta, and GA (base branch)
        run: |
          cd base
          git log -n 1
          bazel build -- //:oppia_dev //:oppia_alpha //:oppia_beta //:oppia_ga
          cp bazel-bin/oppia_dev.aab ../develop/oppia_dev_without_changes.aab
          cp bazel-bin/oppia_alpha.aab ../develop/oppia_alpha_without_changes.aab
          cp bazel-bin/oppia_beta.aab ../develop/oppia_beta_without_changes.aab
          cp bazel-bin/oppia_ga.aab ../develop/oppia_ga_without_changes.aab
          bazel shutdown

      - name: Run stats analysis tool (develop branch)
        run: |
          cd develop
          git log -n 1
          bazel run //scripts:compute_aab_differences -- \
            $(pwd)/brief_build_summary.log $(pwd)/full_build_summary.log \
            dev $(pwd)/oppia_dev_without_changes.aab $(pwd)/oppia_dev_with_changes.aab \
            alpha $(pwd)/oppia_alpha_without_changes.aab $(pwd)/oppia_alpha_with_changes.aab \
            beta $(pwd)/oppia_beta_without_changes.aab $(pwd)/oppia_beta_with_changes.aab \
            ga $(pwd)/oppia_ga_without_changes.aab $(pwd)/oppia_ga_with_changes.aab

      - name: Find CI workflow run for PR
        id: find-workflow-run
        uses: actions/github-script@v7
        continue-on-error: true
        with:
          script: |
            const { owner, repo } = context.repo;
            const runsResponse = await github.rest.actions.listWorkflowRuns({
              owner,
              repo,
              workflow_id: 'stats.yml',
            });

            const runs = runsResponse.data.workflow_runs;
            runs.sort((a, b) => new Date(b.created_at).getTime() - new Date(a.created_at).getTime());

            const run = runs[1];
            if(!run) {
              core.setFailed('Could not find a succesful workflow run');
              return;
            }
            console.log(run.id);

            core.setOutput('run-id', run.id);

      - name: Download previous build summary
        uses: actions/download-artifact@v4
        with:
          name: brief_build_summary_${{ matrix.prInfo.number }}
          path: ./previous_build_logs
          github-token: ${{ secrets.GITHUB_TOKEN }}
          run-id: ${{ steps.find-workflow-run.outputs.run-id }}
        continue-on-error: true # Ignore errors if the file doesn't exist (first run)

      - name: Compare current build summary with the previous one
        id: build-comparison
        run: |
          if [ -f ./develop/brief_build_summary.log ]; then
            echo "Comparing current and previous build summaries..."
            if diff ./develop/brief_build_summary.log ./previous_build_logs/brief_build_summary.log > /dev/null; then
              echo "No changes detected; skipping comment."
              echo "skip_comment=true" >> $GITHUB_ENV
            else
              echo "Changes detected; proceeding with the comment."
              echo "skip_comment=false" >> $GITHUB_ENV
            fi
          else
            echo "No previous summary found; proceeding with the comment."
            echo "skip_comment=false" >> $GITHUB_ENV
          fi

      - name: Upload current build summary for future comparison
        uses: actions/upload-artifact@v4
        with:
          name: brief_build_summary_${{ matrix.prInfo.number }}
          path: ./develop/brief_build_summary.log

      # Reference: https://github.com/peter-evans/create-or-update-comment#setting-the-comment-body-from-a-file.
      # Also, for multi-line env values, see: https://docs.github.com/en/actions/using-workflows/workflow-commands-for-github-actions#multiline-strings.
      - name: Extract reports for uploading & commenting
        env:
          PR_NUMBER: ${{ matrix.prInfo.number }}
        id: compute-comment-body
        run: |
          {
            echo 'comment_body<<EOF'
            cat $GITHUB_WORKSPACE/develop/brief_build_summary.log
            echo EOF
          } >> "$GITHUB_OUTPUT"
          FULL_BUILD_SUMMARY_FILE_NAME="full_build_summary_pr_$PR_NUMBER.log"
          FULL_BUILD_SUMMARY_FILE_PATH="$GITHUB_WORKSPACE/develop/$FULL_BUILD_SUMMARY_FILE_NAME"
          echo "FULL_BUILD_SUMMARY_FILE_NAME=$FULL_BUILD_SUMMARY_FILE_NAME" >> "$GITHUB_ENV"
          echo "FULL_BUILD_SUMMARY_FILE_PATH=$FULL_BUILD_SUMMARY_FILE_PATH" >> "$GITHUB_ENV"
          cp "$GITHUB_WORKSPACE/develop/full_build_summary.log" "$FULL_BUILD_SUMMARY_FILE_PATH"

      - name: Add build stats summary comment
        if: ${{ env.skip_comment == 'false' }}
        env:
          PR_NUMBER: ${{ matrix.prInfo.number }}
        uses: peter-evans/create-or-update-comment@v1
        with:
          issue-number: ${{ env.PR_NUMBER }}
          body: ${{ steps.compute-comment-body.outputs.comment_body }}

      - uses: actions/upload-artifact@v4
        with:
          name: ${{ env.FULL_BUILD_SUMMARY_FILE_NAME }}
          path: ${{ env.FULL_BUILD_SUMMARY_FILE_PATH }}