velero/.github/workflows/pr-filepath-check.yml

name: Pull Request File Path Check
on: [pull_request]
jobs:

  filepath-check:
    name: Check for invalid characters in file paths
    runs-on: ubuntu-latest
    steps:

    - name: Check out the code
      uses: actions/checkout@v6

    - name: Validate file paths for Go module compatibility
      run: |
        # Go's module zip rejects filenames containing certain characters.
        # See golang.org/x/mod/module fileNameOK() for the full specification.
        #
        # Allowed ASCII: letters, digits, and: !#$%&()+,-.=@[]^_{}~ and space
        # Allowed non-ASCII: unicode letters only
        # Rejected: " ' * < > ? ` | / \ : and any non-letter unicode (control
        #           chars, format chars like U+200E LEFT-TO-RIGHT MARK, etc.)
        #
        # This check catches issues like the U+200E incident in PR #9552.

        EXIT_STATUS=0

        git ls-files -z | python3 -c "
        import sys, unicodedata

        data = sys.stdin.buffer.read()
        files = data.split(b'\x00')

        # Characters explicitly rejected by Go's fileNameOK
        # (path separators / and \ are inherent to paths so we check per-element)
        bad_ascii = set('\"' + \"'\" + '*<>?\`|:')

        allowed_ascii = set('!#$%&()+,-.=@[]^_{}~ ')

        def is_ok(ch):
            if ch.isascii():
                return ch.isalnum() or ch in allowed_ascii
            return ch.isalpha()

        bad_files = []  # list of (original_path, clean_path, char_desc)
        for f in files:
            if not f:
                continue
            try:
                name = f.decode('utf-8')
            except UnicodeDecodeError:
                print(f'::error::Non-UTF-8 bytes in filename: {f!r}')
                bad_files.append((repr(f), None, 'non-UTF-8 bytes'))
                continue

            # Check each path element (split on /)
            for element in name.split('/'):
                for ch in element:
                    if not is_ok(ch):
                        cp = ord(ch)
                        char_name = unicodedata.name(ch, f'U+{cp:04X}')
                        char_desc = f'U+{cp:04X} ({char_name})'
                        # Build cleaned path by stripping invalid chars
                        clean = '/'.join(
                            ''.join(c for c in elem if is_ok(c))
                            for elem in name.split('/')
                        )
                        print(f'::error file={name}::File \"{name}\" contains invalid char {char_desc}')
                        bad_files.append((name, clean, char_desc))
                        break

        if bad_files:
            print()
            print('The following files have characters that are invalid in Go module zip archives:')
            print()
            for original, clean, desc in bad_files:
                print(f'  {original}  — {desc}')
            print()
            print('To fix, rename the files to remove the problematic characters:')
            print()
            for original, clean, desc in bad_files:
                if clean:
                    print(f'  mv \"{original}\" \"{clean}\" && git add \"{clean}\"')
                    print(f'  # or: git mv \"{original}\" \"{clean}\"')
                else:
                    print(f'  # {original} — cannot auto-suggest rename (non-UTF-8)')
            print()
            print('See https://github.com/vmware-tanzu/velero/pull/9552 for context.')
            sys.exit(1)
        else:
            print('All file paths are valid for Go module zip.')
        " || EXIT_STATUS=1

        exit $EXIT_STATUS