isZeroWidthCodePoint function

bool isZeroWidthCodePoint(
  1. int codePoint
)

Returns true if the given code point occupies 0 terminal cells.

Implementation

bool isZeroWidthCodePoint(int codePoint) {
  if (codePoint == 0) return true;
  // C0 and C1 control characters (except tab/newline/carriage return)
  if ((codePoint >= 0x01 && codePoint <= 0x1F) ||
      (codePoint >= 0x7F && codePoint <= 0x9F)) {
    return true;
  }
  // Soft Hyphen
  if (codePoint == 0x00AD) return true;
  // Combining Diacritical Marks
  if (codePoint >= 0x0300 && codePoint <= 0x036F) return true;
  if (codePoint >= 0x0483 && codePoint <= 0x0489) {
    return true; // Cyrillic combining
  }
  if (codePoint >= 0x0591 && codePoint <= 0x05BD) {
    return true; // Hebrew combining
  }
  // Hangul Jamo medial vowels & trailing consonants when isolated
  if (codePoint >= 0x1160 && codePoint <= 0x11FF) return true;
  // General Punctuation format controls: ZWSP, ZWNJ, ZWJ, LTR, RTL, etc.
  if (codePoint >= 0x200B && codePoint <= 0x200F) return true;
  // BiDi controls (LRE, RLE, PDF, LRO, RLO, etc.)
  if (codePoint >= 0x202A && codePoint <= 0x202E) return true;
  // Word joiner & Invisible operators
  if (codePoint >= 0x2060 && codePoint <= 0x206F) return true;
  // Standalone Variation Selectors 1..16
  if (codePoint >= 0xFE00 && codePoint <= 0xFE0F) return true;
  // Byte Order Mark / Zero Width No-Break Space
  if (codePoint == 0xFEFF) return true;
  // Interlinear annotation
  if (codePoint >= 0xFFF9 && codePoint <= 0xFFFB) return true;
  // Tags (Plane 14 language tag characters)
  if (codePoint >= 0xE0000 && codePoint <= 0xE007F) return true;

  return false;
}