},
      "latvian_stop": {
        "type":       "stop",
        "stopwords":  "_latvian_"
      },
      "latvian_keywords": {
        "type":       "keyword_marker",
        "keywords":   ["sveiki"]
      },
      "latvian_stemmer": {
        "type":       "stemmer",
        "language":   "latvian"
      },
      "lithuanian_stop": {
        "type":       "stop",

 * The Transliterator is initialized with a given ID during the construction of
 * the ICUNormalizer instance.</p>
 *
 * <p>Example usage:</p>
 * <pre>
 * ICUNormalizer normalizer = new ICUNormalizer("Any-Latin; NFD; [:Nonspacing Mark:] Remove; NFC");
 * String normalizedText = normalizer.normalize("text to normalize", "field");
 * </pre>
 *
 * @see com.ibm.icu.text.Transliterator
 */

// We avoid dependency on the unicode package, but check validity of the implementation
// in the tests.
func isSpace(r rune) bool {
	if r <= '\u00FF' {
		// Obvious ASCII ones: \t through \r plus space. Plus two Latin-1 oddballs.
		switch r {
		case ' ', '\t', '\n', '\v', '\f', '\r':
			return true
		case '\u0085', '\u00A0':
			return true
		}
		return false
	}
	// High-valued ones.

func BenchmarkIndexRuneASCII(b *testing.B) {
	benchBytes(b, indexSizes, bmIndexRuneASCII(IndexRune))
}

func BenchmarkIndexRuneUnicode(b *testing.B) {
	b.Run("Latin", func(b *testing.B) {
		// Latin is mostly 1, 2, 3 byte runes.
		benchBytes(b, indexSizes, bmIndexRuneUnicode(unicode.Latin, 'é'))
	})
	b.Run("Cyrillic", func(b *testing.B) {
		// Cyrillic is mostly 2 and 3 byte runes.

Fischer, Kevin Mader, khanhlvg, Kilaru Yasaswi Sri Chandra Gandhi, Koan-Sin Tan,
Koock Yoon, kouml, ktaebum, Kyuwon Kim, Lakshay Tokas, Laurent Le Brun,
leike666666, leonard951, Leslie-Fang, Letian Kang, Li, Guizi, Loo Rong Jie,
Lucas Hendren, Lukas Folle, Lukas Geiger, Luke Han, luxupu, lvli, Ma, Guokai,
Mahmoud Abuzaina, Maksym Kysylov, Mandar Deshpande, manhyuk, Manraj Singh

pkg unicode, var Kayah_Li *RangeTable
pkg unicode, var Kharoshthi *RangeTable
pkg unicode, var Khmer *RangeTable
pkg unicode, var L *RangeTable
pkg unicode, var Lao *RangeTable
pkg unicode, var Latin *RangeTable
pkg unicode, var Lepcha *RangeTable
pkg unicode, var Letter *RangeTable
pkg unicode, var Limbu *RangeTable
pkg unicode, var Linear_B *RangeTable
pkg unicode, var Lisu *RangeTable