pr-link-path-scan.yml

# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0

name: Check hyperlinks and relative path validity

on:
  pull_request:
    branches: [main]
    types: [opened, reopened, ready_for_review, synchronize]

jobs:
  check-the-validity-of-hyperlinks-in-README:
    runs-on: ubuntu-latest
    steps:
      - name: Clean Up Working Directory
        run: sudo rm -rf ${{github.workspace}}/*

      - name: Checkout Repo GenAIExamples
        uses: actions/checkout@v4
        with:
          fetch-depth: 0

      - name: Check the Validity of Hyperlinks
        run: |
          cd ${{github.workspace}}
          fail="FALSE"
          merged_commit=$(git log -1 --format='%H')
          changed_files="$(git diff --name-status --diff-filter=ARM ${{ github.event.pull_request.base.sha }} ${merged_commit} | awk '/\.md$/ {print $NF}')"
          if  [ -n "$changed_files" ]; then
            for changed_file in $changed_files; do
              # echo $changed_file
              url_lines=$(grep -H -Eo '\]\(http[s]?://[^)]+\)' "$changed_file" | grep -Ev 'GenAIExamples/blob/main') || true
              if [ -n "$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-)
                  response=$(curl -L -s -o /dev/null -w "%{http_code}" "$url")|| true
                  if [ "$response" -ne 200 ]; then
                    echo "**********Validation failed, try again**********"
                    response_retry=$(curl -s -o /dev/null -w "%{http_code}" "$url")
                    if [ "$response_retry" -eq 200 ]; then
                      echo "*****Retry successfully*****"
                    else
                      echo "Invalid link from ${{github.workspace}}/$path: $url"
                      fail="TRUE"
                    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

  check-the-validity-of-relative-path:
    runs-on: ubuntu-latest
    steps:
      - name: Clean up Working Directory
        run: sudo rm -rf ${{github.workspace}}/*

      - name: Checkout Repo GenAIExamples
        uses: actions/checkout@v4
        with:
          fetch-depth: 0

      - name: Checking Relative Path Validity
        run: |
          cd ${{github.workspace}}
          fail="FALSE"
          repo_name=${{ github.event.pull_request.head.repo.full_name }}
          if [ "$(echo "$repo_name"|cut -d'/' -f1)" != "opea-project" ]; then
            owner=$(echo "${{ github.event.pull_request.head.repo.full_name }}" |cut -d'/' -f1)
            branch="https://github.com/$owner/GenAIExamples/tree/${{ github.event.pull_request.head.ref }}"
          else
            branch="https://github.com/opea-project/GenAIExamples/blob/${{ github.event.pull_request.head.ref }}"
          fi
          link_head="https://github.com/opea-project/GenAIExamples/blob/main"

          merged_commit=$(git log -1 --format='%H')
          changed_files="$(git diff --name-status --diff-filter=ARM ${{ github.event.pull_request.base.sha }} ${merged_commit} | awk '/\.md$/ {print $NF}')"
          png_lines=$(grep -Eo '\]\([^)]+\)' --include='*.md' -r .|grep -Ev 'http')
          if [ -n "$png_lines" ]; then
            for png_line in $png_lines; do
              refer_path=$(echo "$png_line"|cut -d':' -f1 | cut -d'/' -f2-)
              png_path=$(echo "$png_line"|cut -d '(' -f2 | cut -d ')' -f1)

              if [[ "${png_path:0:1}" == "/" ]]; then
                check_path=$png_path
              elif [[ "$png_path" == *#* ]]; then
                relative_path=$(echo "$png_path" | cut -d '#' -f1)
                if [ -n "$relative_path" ]; then
                  check_path=$(dirname "$refer_path")/$relative_path
                  png_path=$(echo "$png_path" | awk -F'#' '{print "#" $2}')
                else
                  check_path=$refer_path
                fi
              else
                check_path=$(dirname "$refer_path")/$png_path
              fi

              if [ -e "$check_path" ]; then
                real_path=$(realpath $check_path)
                if [[ "$png_line" == *#* ]]; then
                  if [ -n "changed_files" ] && echo "$changed_files" | grep -q "^${refer_path}$"; then
                    url_dev=$branch$(echo "$real_path" | sed 's|.*/GenAIExamples||')$png_path
                    response=$(curl -I -L -s -o /dev/null -w "%{http_code}" "$url_dev")
                    if [ "$response" -ne 200 ]; then
                      echo "**********Validation failed, try again**********"
                      response_retry=$(curl -s -o /dev/null -w "%{http_code}" "$url_dev")
                      if [ "$response_retry" -eq 200 ]; then
                        echo "*****Retry successfully*****"
                      else
                        echo "Invalid path from ${{github.workspace}}/$refer_path: $png_path"
                        fail="TRUE"
                      fi
                    else
                      echo "Validation succeed $png_line"
                    fi
                  fi
                fi
              else
                echo "${{github.workspace}}/$refer_path:$png_path does not exist"
                fail="TRUE"
              fi
            done
          fi

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