bom-check.yml

name: bom-check

on:
  push:
    branches: main
  pull_request:
    branches: main

jobs:
  check-bom-consistency:
    runs-on: ubuntu-latest
    timeout-minutes: 10
    steps:
      - uses: actions/checkout@v6

      - name: Check for Unicode BOM in text files
        run: |
          echo "Checking for files with Unicode BOM..."
          echo "Repository standard: NO BOM (UTF-8 without BOM)"
          echo ""

          # Find all text files that contain BOM (EF BB BF at start)
          # Exclude binary files, .git directory, and common binary extensions
          files_with_bom=""

          while IFS= read -r -d '' file; do
            # Check if file starts with UTF-8 BOM (EF BB BF)
            if head -c 3 "$file" | od -An -tx1 | grep -q "ef bb bf"; then
              files_with_bom="$files_with_bom$file"$'\n'
            fi
          done < <(find . -type f \
            -not -path './.git/*' \
            -not -name '*.png' \
            -not -name '*.jpg' \
            -not -name '*.jpeg' \
            -not -name '*.gif' \
            -not -name '*.ico' \
            -not -name '*.woff' \
            -not -name '*.woff2' \
            -not -name '*.ttf' \
            -not -name '*.eot' \
            -not -name '*.pdf' \
            -not -name '*.zip' \
            -not -name '*.tar' \
            -not -name '*.gz' \
            -not -name '*.lock' \
            -print0)

          if [ -n "$files_with_bom" ]; then
            echo "ERROR: The following files contain Unicode BOM but should not:"
            echo "$files_with_bom"
            echo ""
            echo "To fix this, remove the BOM from these files."
            echo "You can use: sed -i '1s/^\xEF\xBB\xBF//' <filename>"
            echo "Or configure your editor to save files without BOM."
            exit 1
          else
            echo "SUCCESS: All text files are consistent (no BOM found)."
            exit 0
          fi