normalize static method

String normalize(String ch)

Implementation

static String normalize(String ch) {
  initCjkMap();
  final block = unicodeBlock(ch);
  if (block == UnicodeBlock.unicodeBasicLatin) {
    if (ch.compareTo('A') < 0 ||
        (ch.compareTo('Z') > 0 && ch.compareTo('a') < 0) ||
        ch.compareTo('z') > 0) {
      ch = ' ';
    }
  } else if (block == UnicodeBlock.unicodeLatin1Supplement) {
    if (latin1Excluded.contains(ch)) {
      ch = ' ';
    }
  } else if (block == UnicodeBlock.unicodeLatinExtendedB) {
    // normalization for Romanian
    if (ch == '\u0219') {
      // Small S with comma below => with cedilla
      ch = '\u015f';
    }
    if (ch == '\u021b') {
      // Small T with comma below => with cedilla
      ch = '\u0163';
    }
  } else if (block == UnicodeBlock.unicodeGeneralPunctuation) {
    ch = ' ';
  } else if (block == UnicodeBlock.unicodeArabic) {
    if (ch == '\u06cc') {
      ch = '\u064a'; // Farsi yeh => Arabic yeh
    }
  } else if (block == UnicodeBlock.unicodeLatinExtendedAdditional) {
    if (ch.compareTo('\u1ea0') >= 0) {
      ch = '\u1ec3';
    }
  } else if (block == UnicodeBlock.unicodeHiragana) {
    ch = '\u3042';
  } else if (block == UnicodeBlock.unicodeKatakana) {
    ch = '\u30a2';
  } else if (block == UnicodeBlock.unicodeBopomofo ||
      block == UnicodeBlock.unicodeBopomofoExtended) {
    ch = '\u3105';
  } else if (block == UnicodeBlock.unicodeCjkUnifiedIdeographs) {
    ch = cjkMap[ch] ?? ch;
  } else if (block == UnicodeBlock.unicodeHangulSyllables) {
    ch = '\uac00';
  }
  return ch;
}