JS String Slice - UTF-8, UTF-16, UTF-32, and Graphemes

unicode-slice.js

function utf16slice(str, start, end) {
  // UTF-16 code units - same as native
  return str.slice(start, end);
}

function utf8slice(str, start, end) {
  // UTF-8 bytes; slicing mid-codepoint yields U+FFFD
  const bytes = new TextEncoder().encode(str);
  return new TextDecoder().decode(bytes.slice(start, end));
}

function utf32slice(str, start, end) {
  // Unicode code points (surrogate pairs count as one)
  return Array.from(str).slice(start, end).join('');
}

function graphemeSlice(str, start, end) {
  // Visual graphemes — handles emoji ZWJ sequences, flags, combining marks, etc.
  const segmenter = new Intl.Segmenter(undefined, { granularity: 'grapheme' });
  const graphemes = Array.from(segmenter.segment(str), s => s.segment);
  return graphemes.slice(start, end).join('');
}