link-check.yml

# SPDX-FileCopyrightText: 2020 The HedgeDoc developers (see AUTHORS file)
#
# SPDX-License-Identifier: AGPL-3.0-only

name: Check links

on: 
  push:
  schedule:
    - cron: "0 3 * * *"

jobs:
  check-links:
    runs-on: ubuntu-latest
    name: Check for broken links
    steps:
      - name: Checkout repository
        uses: actions/checkout@v4
      - name: Setup Hugo
        uses: peaceiris/actions-hugo@v3
        with:
          hugo-version: 'latest'
          extended: true

      - name: Use Node.js 18
        uses: actions/setup-node@v4
        with:
          node-version: 18

      - name: Get yarn cache directory path
        id: yarn-cache-dir-path
        run: echo "::set-output name=dir::$(yarn cache dir)"

      - name: Cache node_modules
        uses: actions/cache@v4
        id: yarn-cache
        with:
          path: ${{ steps.yarn-cache-dir-path.outputs.dir }}
          key: ${{ runner.os }}-yarn-${{ hashFiles('**/yarn.lock') }}
          restore-keys: |
            ${{ runner.os }}-yarn-

      - name: Install dependencies
        run: yarn install --frozen-lockfile --prefer-offline && yarn add broken-link-checker

      - name: Run Hugo
        run: hugo server -e production --minify -b http://127.0.0.1:1313/ & sleep 5

      - name: Check for broken links
        # GitHub is excluded because we otherwise run into rate-limits and get many HTTP_429 link errors.
        # Domains under hedgedoc.org are excluded since they always fail due to our bot-protection mode on Cloudflare.
        run: node_modules/.bin/blc http://127.0.0.1:1313/ -ro --exclude "https://github.com/*" --exclude "https://docs.github.com/*" --exclude "https://docs.hedgedoc.org" --exclude "https://demo.hedgedoc.org" --exclude "https://hedgedoc.org"  --exclude "https://hackmd.io"