duplicate-detection.yml

name: 🔍 Duplicate Detection

on:
  pull_request_target:
    branches: [ main ]
    types: [opened, synchronize, reopened]

permissions:
  contents: read
  pull-requests: write
  issues: write

jobs:
  check-duplicates:
    name: 🔎 Check for Duplicate Files
    runs-on: ubuntu-latest

    steps:
    - name: 📥 Checkout base branch
      uses: actions/checkout@v4
      with:
        ref: ${{ github.base_ref }}

    - name: 📥 Checkout PR branch
      uses: actions/checkout@v4
      with:
        ref: ${{ github.event.pull_request.head.sha }}
        path: pr-code

    - name: 🔍 Get changed files
      id: changed-files
      uses: tj-actions/changed-files@v40
      with:
        path: pr-code
        files: |
          C/**/*.c
          CPP/**/*.cpp
          Java/**/*.java
          Python/**/*.py
          JavaScript/**/*.js
          Go/**/*.go
          Rust/**/*.rs

    - name: 🔎 Detect duplicate implementations
      if: steps.changed-files.outputs.any_changed == 'true'
      id: duplicate-check
      run: |
        echo "Checking for potential duplicates..."
        duplicates=""
        warnings=""

        for new_file in ${{ steps.changed-files.outputs.all_changed_files }}; do
          # Remove pr-code/ prefix
          file_path="${new_file#pr-code/}"
          filename=$(basename "$file_path")
          base_name="${filename%.*}"

          # Normalize filename (remove underscores, hyphens, convert to lowercase)
          normalized=$(echo "$base_name" | tr '_-' ' ' | tr '[:upper:]' '[:lower:]')

          echo "Checking: $file_path (normalized: $normalized)"

          # Get directory and language
          lang_dir=$(echo "$file_path" | cut -d'/' -f1)
          category=$(echo "$file_path" | cut -d'/' -f2)

          # Search for similar files in the same category across the main branch
          echo "Searching in $lang_dir/$category/ for similar implementations..."

          # Check if directory exists in base branch
          if [ ! -d "$lang_dir/$category" ]; then
            echo "Directory $lang_dir/$category doesn't exist in base branch - this is a new contribution!"
            continue
          fi

          # Find files with similar names
          similar_files=$(find "$lang_dir/$category" -type f 2>/dev/null | while read existing_file; do
            existing_name=$(basename "$existing_file")
            existing_base="${existing_name%.*}"
            existing_normalized=$(echo "$existing_base" | tr '_-' ' ' | tr '[:upper:]' '[:lower:]')

            # Check if normalized names match
            if [ "$normalized" = "$existing_normalized" ]; then
              echo "$existing_file"
            fi
          done)

          if [ -n "$similar_files" ]; then
            duplicates="${duplicates}**⚠️ Potential Duplicate:** \`$file_path\`\n"
            duplicates="${duplicates}Similar file(s) already exist:\n"
            while IFS= read -r similar; do
              duplicates="${duplicates}- \`$similar\`\n"
            done <<< "$similar_files"
            duplicates="${duplicates}\n"
          fi
        done

        # Save results
        if [ -n "$duplicates" ]; then
          echo "found=true" >> $GITHUB_OUTPUT
          echo "duplicates<<EOF" >> $GITHUB_OUTPUT
          echo -e "$duplicates" >> $GITHUB_OUTPUT
          echo "EOF" >> $GITHUB_OUTPUT
        else
          echo "found=false" >> $GITHUB_OUTPUT
        fi

    - name: 💬 Comment on PR if duplicates found
      if: steps.duplicate-check.outputs.found == 'true'
      uses: actions/github-script@v7
      env:
        DUPLICATES_REPORT: ${{ steps.duplicate-check.outputs.duplicates }}
      with:
        script: |
          const duplicates = process.env.DUPLICATES_REPORT;

          // Check if we already commented about duplicates
          const comments = await github.rest.issues.listComments({
            owner: context.repo.owner,
            repo: context.repo.repo,
            issue_number: context.issue.number
          });

          const botComment = comments.data.find(comment =>
            comment.user.type === 'Bot' && comment.body.includes('🔍 Duplicate Detection Results')
          );

          const comment = `## 🔍 Duplicate Detection Results

          ### ⚠️ Potential Duplicates Found

          ${ duplicates }

          ### 📝 What This Means

          We found existing implementations that appear similar to your contribution. This doesn't necessarily mean your PR will be rejected, but please review:

          1. **Is this truly a duplicate?** Check the existing files to see if they implement the same algorithm
          2. **Is your implementation different/better?** If so, explain in your PR description:
             - What makes it different
             - Why it's an improvement
             - Any unique features or optimizations
          3. **Consider improving existing code** instead of adding a duplicate

          ### ✅ What To Do Next

          - **If it's a duplicate:** Consider withdrawing this PR and improving the existing implementation
          - **If it's different:** Add a clear explanation in your PR description about how it differs
          - **If unsure:** Ask the maintainers for guidance!

          ### 💡 Quality Over Quantity

          Remember: One high-quality, unique contribution is worth more than multiple duplicates! 🌟

          ---
          *This is an automated check. Maintainers will make the final decision.*`;

          // Only post if we haven't already commented
          if (!botComment) {
            await github.rest.issues.createComment({
              owner: context.repo.owner,
              repo: context.repo.repo,
              issue_number: context.issue.number,
              body: comment
            });
          } else {
            // Update existing comment
            await github.rest.issues.updateComment({
              owner: context.repo.owner,
              repo: context.repo.repo,
              comment_id: botComment.id,
              body: comment
            });
          }

    - name: ✅ Summary
      run: |
        if [ "${{ steps.duplicate-check.outputs.found }}" = "true" ]; then
          echo "⚠️ Potential duplicates detected - please review"
          echo "This is a warning, not a failure. Maintainers will review."
        else
          echo "✅ No duplicates detected - great job!"
        fi