orphaned-files-check.yml

name: 'Orphaned files check'

# **What it does**: Checks that there are no files in ./assets/, ./data/reusables, or ./data/tables that aren't mentioned in any source file.
# **Why we have it**: To avoid orphans into the repo.
# **Who does it impact**: Docs content.

on:
  workflow_dispatch:
  schedule:
    - cron: '20 16 * * 1' # Run every Monday at 16:20 UTC / 8:20 PST
  pull_request:
    paths:
      - .github/workflows/orphaned-assets-check.yml
      - .github/workflows/orphaned-files-check.yml
      # In case any of the dependencies affect the script
      - 'package*.json'
      - src/assets/scripts/find-orphaned-assets.ts
      - src/content-render/scripts/reusables-cli/find/unused.ts
      - src/data-directory/scripts/find-orphaned-tables.ts
      - src/workflows/walk-files.ts
      - src/languages/lib/languages.ts
      - .github/actions/clone-translations/action.yml
      - .github/actions/node-npm-setup/action.yml

permissions:
  contents: read

jobs:
  orphaned-files-check:
    if: ${{ github.repository == 'github/docs-internal' }}
    runs-on: ubuntu-latest
    steps:
      - name: Generate GitHub App token
        id: app-token
        uses: actions/create-github-app-token@3ff1caaa28b64c9cc276ce0a02e2ff584f3900c5 # v2.0.2
        with:
          app-id: ${{ secrets.DOCS_BOT_APP_ID }}
          private-key: ${{ secrets.DOCS_BOT_APP_PRIVATE_KEY }}
          owner: github
          repositories: docs-internal,docs-internal.es-es,docs-internal.ja-jp,docs-internal.pt-br,docs-internal.zh-cn,docs-internal.ru-ru,docs-internal.fr-fr,docs-internal.ko-kr,docs-internal.de-de

      - name: Checkout English repo
        uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
        with:
          # Using a PAT is necessary so that the new commit will trigger the
          # CI in the PR. (Events from GITHUB_TOKEN don't trigger new workflows.)
          token: ${{ steps.app-token.outputs.token }}

      # It's important because translations are often a bit behind.
      # So if a translation is a bit behind, it might still be referencing
      # an asset even though none of the English content does.
      - name: Clone all translations
        uses: ./.github/actions/clone-translations
        with:
          token: ${{ steps.app-token.outputs.token }}

      - uses: ./.github/actions/node-npm-setup

      - name: Check for orphaned assets and reusables
        env:
          # Needed for gh
          GITHUB_TOKEN: ${{ steps.app-token.outputs.token }}
          DRY_RUN: ${{ github.event_name == 'pull_request'}}
        run: |
          set -e

          # The `-s` is to make npm run silent and not print verbose
          # information about the npm script alias.
          assetFilesToRemove=$(npm run -s find-orphaned-assets)
          reusableFilesToRemove=$(npm run -s reusables -- find unused | grep '^data/reusables' || true)
          tableFilesToRemove=$(npm run -s find-orphaned-tables)
          [ -z "$assetFilesToRemove" ] && [ -z "$reusableFilesToRemove" ] && [ -z "$tableFilesToRemove" ] && exit 0

          if [ -n "$assetFilesToRemove" ]; then
            echo $assetFilesToRemove | xargs git rm
          fi
          if [ -n "$reusableFilesToRemove" ]; then
            echo $reusableFilesToRemove | xargs git rm
          fi
          if [ -n "$tableFilesToRemove" ]; then
            echo $tableFilesToRemove | xargs git rm
          fi

          git status

          # If nothing to commit, exit now. It's fine. No orphans.
          git status -- ':!translations*' | grep 'nothing to commit' && exit 0

          # When run on a pull_request, we're just testing the tooling.
          # Exit before it actually pushes the possible changes.
          if [ "$DRY_RUN" = "true" ]; then
            echo "Dry-run mode when run in a pull request"
            exit 0
          fi

          # Replicated from the translation pipeline PR-maker Action
          git config --global user.name "docs-bot"
          git config --global user.email "77750099+docs-bot@users.noreply.github.com"

          date=$(date '+%Y-%m-%d-%H-%M')
          branchname=orphaned-files-$date-$GITHUB_RUN_ID

          git checkout -b $branchname
          git commit -m "Delete orphaned files $date"
          git push origin $branchname

          body=$(cat <<-EOM
            Found with the `npm run find-orphaned-assets`, `npm run -s reusables -- find unused`, and `npm run find-orphaned-tables` scripts.

            The orphaned files workflow file .github/workflows/orphaned-files-check.yml runs every Monday at 16:20 UTC / 8:20 PST.

            If you are the first responder, please spot check some of the unused assets, reusables, and tables to make sure they aren't referenced anywhere. Then, approve and merge the pull request.

            For more information, see [Doc: Orphaned Assets](https://github.com/github/docs-engineering/blob/main/docs/orphaned-assets.md) and [Doc: Reusables CLI](https://github.com/github/docs-internal/tree/main/src/content-render/scripts/reusables-cli).

            Generated by the [orphaned files workflow run]($GITHUB_SERVER_URL/$GITHUB_REPOSITORY/actions/runs/$GITHUB_RUN_ID).
          EOM
          )

          gh pr create \
            --title "Delete orphaned files ($date)" \
            --body "$body" \
            --repo github/docs-internal \
            --label docs-content-fr,workflow-generated

      - uses: ./.github/actions/slack-alert
        if: ${{ failure() && github.event_name == 'schedule' }}
        with:
          slack_token: ${{ secrets.SLACK_DOCS_BOT_TOKEN }}

      - uses: ./.github/actions/create-workflow-failure-issue
        if: ${{ failure() && github.event_name == 'schedule' }}
        with:
          token: ${{ steps.app-token.outputs.token }}