FreshRSS/.github/workflows/link-checker.yml

name: Link Checker

on:
  push:
    branches: [ edge ]
  pull_request:
    branches: [ edge ]
  schedule:
    - cron: '30 12 1 * *'
  workflow_dispatch:

permissions:
  contents: read

concurrency:
  group: link-checker-${{ github.ref }}
  cancel-in-progress: false

jobs:
  linkChecker:
    name: linkChecker
    runs-on: ubuntu-26.04
    steps:
      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
        with:
          persist-credentials: false
          fetch-depth: 0

      # Check local links across the repository first to catch broken links in
      # files that are not part of the PR's changed files.
      - name: Check local links (offline run)
        if: github.event_name == 'pull_request'
        uses: lycheeverse/lychee-action@e7477775783ea5526144ba13e8db5eec57747ce8 # v2.9.0
        with:
          fail: true
          failIfEmpty: false
          args: >
            --offline
            .

      - name: Get changed files
        if: github.event_name == 'pull_request'
        env:
          BASE_SHA: ${{ github.event.pull_request.base.sha }}
          HEAD_SHA: ${{ github.event.pull_request.head.sha }}
        run: |
          git diff --name-only --diff-filter=ACMR \
            "$BASE_SHA" \
            "$HEAD_SHA" \
            > changed-files.txt

          # Lychee does not apply `extensions` from the config to files passed via `--files-from`.
          # Filter the changed files so only allowed file types are checked.
          python3 <<'PY'
          import pathlib
          import tomllib

          with open("lychee.toml", "rb") as fp:
              config = tomllib.load(fp)
          extensions = {e.lstrip(".").lower() for e in config["extensions"]}

          files = pathlib.Path("changed-files.txt").read_text().splitlines()
          files = [
              f for f in files
              if (
                  pathlib.PurePath(f).suffix.lstrip(".").lower() in extensions
                  or (
                      not pathlib.PurePath(f).suffix
                      and pathlib.PurePath(f).name.startswith(".")
                      and pathlib.PurePath(f).name.lstrip(".").lower() in extensions
                  )
                  or (
                      not pathlib.PurePath(f).suffix
                      and not pathlib.PurePath(f).name.startswith(".")
                      and config.get("default_extension") in extensions
                  )
              )
          ]

          pathlib.Path("changed-files.txt").write_text(
              "\n".join(files) + ("\n" if files else "")
          )
          PY

      - name: Restore lychee cache
        id: restore-cache
        uses: actions/cache/restore@55cc8345863c7cc4c66a329aec7e433d2d1c52a9 # v6.1.0
        with:
          path: .lycheecache
          key: cache-lychee-${{ github.sha }}
          restore-keys: cache-lychee-

      - name: Run lychee
        uses: lycheeverse/lychee-action@e7477775783ea5526144ba13e8db5eec57747ce8 # v2.9.0
        with:
          # PAT with read-only permissions used to avoid GitHub rate limits (allows 5,000 requests per hour)
          # Won't be available to forks in pull requests due to restrictions, so falls back to default
          # GITHUB_TOKEN with 1,000 requests per hour instead.
          token: ${{ secrets.LYCHEE_GITHUB_TOKEN || secrets.GITHUB_TOKEN }}

          fail: true
          failIfEmpty: false # Avoid failing in PRs with no links in changed files (`true` is the default)

          # Config is loaded from lychee.toml
          args: >
            ${{ github.event_name == 'pull_request' && '--files-from changed-files.txt' || '.' }}

      - name: Save lychee cache
        uses: actions/cache/save@55cc8345863c7cc4c66a329aec7e433d2d1c52a9 # v6.1.0
        if: always()
        with:
          path: .lycheecache
          key: ${{ steps.restore-cache.outputs.cache-primary-key }}