pr-link-scan.yml

# Copyright (C) 2025 Intel Corporation
# SPDX-License-Identifier: Apache-2.0

name: Check hyperlinks and relative path validity

permissions:
  contents: read

on:
  pull_request:
    branches: ["master", "master_next"]
    types: [opened, reopened, ready_for_review, synchronize]

# If there is a new commit, the previous jobs will be canceled
concurrency:
  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
  cancel-in-progress: true

jobs:
  check-the-validity-of-hyperlinks-in-README:
    # choose different runner label for internal and external CI
    runs-on: ${{ contains(github.repository, 'intel-innersource') && 'self-hosted' || 'ubuntu-latest' }}
    steps:
      - name: Clean Up Working Directory
        run: sudo rm -rf ${{github.workspace}}/*

      - name: Checkout Repo
        uses: actions/checkout@1e31de5234b9f8995739874a8ce0492dc87873e2
        with:
          fetch-depth: 0

      - name: Check the Validity of Hyperlinks
        env:
          BASE_SHA: ${{ github.event.pull_request.base.sha }}
        run: |
          cd ${{github.workspace}}
          export no_proxy="localhost,127.0.0.1"
          curl_timeout=10
          delay=1
          fail="FALSE"
          merged_commit=$(git log -1 --format='%H')
          changed_files="$(git diff --name-status --diff-filter=ARM $BASE_SHA ${merged_commit} | awk '/\.md$/ {print $NF}')"

          echo "no_proxy=$no_proxy"
          echo "http_proxy=$http_proxy"
          echo "https_proxy=$https_proxy"

          if  [ -n "$changed_files" ]; then
            for changed_file in $changed_files; do
              # echo $changed_file
              url_lines=$(grep -H -Eo '\]\(http[s]?://[^)]+\)' "$changed_file") || true
              if [ -n "$url_lines" ]; then
                for url_line in $url_lines; do
                  # echo $url_line
                  url=$(echo "$url_line"|cut -d '(' -f2 | cut -d ')' -f1|sed 's/\.git$//')
                  path=$(echo "$url_line"|cut -d':' -f1 | cut -d'/' -f2-)
                  if [[ "$url" == "https://dgpu-docs.intel.com/installation-guides/ubuntu/ubuntu-focal-dc.html" || "$url" == "https://ai.cloud.intel.com/" ]]; then
                    echo "Link "$url" from ${{github.workspace}}/$path needs to be verified by real person."
                  else
                    sleep $delay
                    response=$(curl --max-time "${curl_timeout}" -L -s -o /dev/null -w "%{http_code}" -A "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36"   -H "Accept: text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8"   -H "Accept-Language: en-US,en;q=0.5" "$url")|| true
                    if [ "$response" -ne 200 ]; then
                      echo "**********Validation $url failed ($response), try again**********"
                      response_retry=$(curl --max-time "${curl_timeout}" -s -o /dev/null -w "%{http_code}" "$url") || true
                      if [ "$response_retry" -eq 200 ]; then
                        echo "*****Retry successfully*****"
                      else
                        echo "******Retry $url failed ($response_retry), add simulated browser requests******"
                        response_browser=$(curl --max-time "${curl_timeout}" -s -o /dev/null -w "%{http_code}" -A "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36"   -H "Accept: text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8"   -H "Accept-Language: en-US,en;q=0.5" "$url")|| true
                        if [ "$response_browser" -eq 200 ]; then
                          echo "*****Retry successfully*****"
                        else
                          echo -e "::error:: Invalid link ($response_retry) from ${{github.workspace}}/$(echo "$url_line"|cut -d':' -f1): $url"
                          fail="TRUE"
                        fi
                      fi
                    fi
                  fi
                done
              fi
            done
          else
            echo "No changed .md file."
          fi

          if [[ "$fail" == "TRUE" ]]; then
            exit 1
          else
            echo "All hyperlinks are valid."
          fi
        shell: bash