prebid/Prebid.js

name: Check for Duplicated Code

on:
  pull_request_target:
    branches:
      - master

jobs:
  check-duplication:
    runs-on: ubuntu-latest

    steps:
    - name: Checkout code
      uses: actions/checkout@v4
      with:
        fetch-depth: 0  # Fetch all history for all branches
        ref: ${{ github.event.pull_request.head.sha }}

    - name: Set up Node.js
      uses: actions/setup-node@v4
      with:
        node-version: '20'

    - name: Install dependencies
      run: |
        npm install -g jscpd diff-so-fancy

    - name: Create jscpd config file
      run: |
        echo '{
          "threshold": 20,
          "minTokens": 100,
          "reporters": [
            "json"
          ],
          "output": "./",
          "pattern": "**/*.js",
          "ignore": "**/*spec.js"        
        }' > .jscpd.json

    - name: Run jscpd on entire codebase
      run: jscpd

    - name: Fetch base and target branches
      run: |
        git fetch origin +refs/heads/${{ github.event.pull_request.base.ref }}:refs/remotes/origin/${{ github.event.pull_request.base.ref }}
        git fetch origin +refs/pull/${{ github.event.pull_request.number }}/merge:refs/remotes/pull/${{ github.event.pull_request.number }}/merge

    - name: Get the diff
      run: git diff --name-only origin/${{ github.event.pull_request.base.ref }}...refs/remotes/pull/${{ github.event.pull_request.number }}/merge > changed_files.txt

    - name: List generated files (debug)
      run: ls -l

    - name: Upload unfiltered jscpd report
      if: always()
      uses: actions/upload-artifact@v4
      with:
        name: unfiltered-jscpd-report
        path: ./jscpd-report.json

    - name: Filter jscpd report for changed files
      run: |
        if [ ! -f ./jscpd-report.json ]; then
          echo "jscpd-report.json not found"
          exit 1
        fi
        echo "Filtering jscpd report for changed files..."
        CHANGED_FILES=$(jq -R -s -c 'split("\n")[:-1]' changed_files.txt)
        echo "Changed files: $CHANGED_FILES"
        jq --argjson changed_files "$CHANGED_FILES" '
          .duplicates | map(select(
            (.firstFile?.name as $fname | $changed_files | any(. == $fname)) or
            (.secondFile?.name as $sname | $changed_files | any(. == $sname))
          ))
        ' ./jscpd-report.json > filtered-jscpd-report.json
        cat filtered-jscpd-report.json

    - name: Check if filtered jscpd report exists
      id: check_filtered_report
      run: |
        if [ $(wc -l < ./filtered-jscpd-report.json) -gt 1 ]; then
          echo "filtered_report_exists=true" >> $GITHUB_ENV
        else
          echo "filtered_report_exists=false" >> $GITHUB_ENV
        fi

    - name: Upload filtered jscpd report
      if: env.filtered_report_exists == 'true'
      uses: actions/upload-artifact@v4
      with:
        name: filtered-jscpd-report
        path: ./filtered-jscpd-report.json

    - name: Post GitHub comment
      if: env.filtered_report_exists == 'true'
      uses: actions/github-script@v7
      with:
        script: |
          const fs = require('fs');
          const filteredReport = JSON.parse(fs.readFileSync('filtered-jscpd-report.json', 'utf8'));
          let comment = "Whoa there, partner! 🌵🤠 We wrangled some duplicated code in your PR:\n\n";
          function link(dup) {
             return `https://github.com/${{ github.event.repository.full_name }}/blob/${{ github.event.pull_request.head.sha }}/${dup.name}#L${dup.start + 1}-L${dup.end - 1}`
          }
          filteredReport.forEach(duplication => {
            const firstFile = duplication.firstFile;
            const secondFile = duplication.secondFile;
            const lines = duplication.lines;
            comment += `- [\`${firstFile.name}\`](${link(firstFile)}) has ${lines} duplicated lines with [\`${secondFile.name}\`](${link(secondFile)})\n`;
          });
          comment += "\nReducing code duplication by importing common functions from a library not only makes our code cleaner but also easier to maintain. Please move the common code from both files into a library and import it in each. We hate that we have to mention this, however, commits designed to hide from this utility by renaming variables or reordering an object are poor conduct. We will not look upon them kindly! Keep up the great work! 🚀";
          github.rest.issues.createComment({
            owner: context.repo.owner,
            repo: context.repo.repo,
            issue_number: context.issue.number,
            body: comment
          });

    - name: Fail if duplications are found
      if: env.filtered_report_exists == 'true'
      run: |
        echo "Duplications found, failing the check."
        exit 1