"type":       "keyword_marker",
          "keywords_path": "${fess.dictionary.path}lv/protwords.txt"
        },
        "latvian_stemmer": {
          "type":       "stemmer",
          "language":   "latvian"
        },
        "latvian_override": {
          "type":       "stemmer_override",
          "rules_path": "${fess.dictionary.path}lv/stemmer_override.txt"
        },
        "lithuanian_stop": {

01BC          ; mapped                 ; 01BD          # 1.1  LATIN CAPITAL LETTER TONE FIVE
01BD..01C3    ; valid                                  # 1.1  LATIN SMALL LETTER TONE FIVE..LATIN LETTER RETROFLEX CLICK
01C4..01C6    ; mapped                 ; 0064 017E     # 1.1  LATIN CAPITAL LETTER DZ WITH CARON..LATIN SMALL LETTER DZ WITH CARON

  @GwtIncompatible // Charset not supported by GWT
  public static final Charset US_ASCII = StandardCharsets.US_ASCII;

  /**
   * ISO-8859-1: ISO Latin Alphabet Number 1 (ISO-LATIN-1).
   *
   * <p><b>Note:</b> this constant is now unnecessary and should be treated as deprecated; use
   * {@link StandardCharsets#ISO_8859_1} instead.
   *
   */
  public static final Charset ISO_8859_1 = StandardCharsets.ISO_8859_1;

  /**

        if (userFriendly.matches("(?i)(?:American|English|ASCII)")) {
          // 1-byte UTF-8 sequences - "American" ASCII text
          return 0x80;
        } else if (userFriendly.matches("(?i)(?:French|Latin|Western.*European)")) {
          // Mostly 1-byte UTF-8 sequences, mixed with occasional 2-byte
          // sequences - "Western European" text
          return 0x90;

        if (userFriendly.matches("(?i)(?:American|English|ASCII)")) {
          // 1-byte UTF-8 sequences - "American" ASCII text
          return 0x80;
        } else if (userFriendly.matches("(?i)(?:French|Latin|Western.*European)")) {
          // Mostly 1-byte UTF-8 sequences, mixed with occasional 2-byte
          // sequences - "Western European" text
          return 0x90;

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.

// 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.

    return JavaDigit.INSTANCE;
  }

  /**
   * Determines whether a character is a BMP letter according to {@linkplain
   * Character#isLetter(char) Java's definition}. If you only care to match letters of the Latin
   * alphabet, you can use {@code inRange('a', 'z').or(inRange('A', 'Z'))}.
   *
   * @deprecated Most letters are supplementary characters; see the class documentation.

genova.it
go.it
gorizia.it
gr.it
grosseto.it
iglesias-carbonia.it
iglesiascarbonia.it
im.it
imperia.it
is.it
isernia.it
kr.it
la-spezia.it
laquila.it
laspezia.it
latina.it
lc.it
le.it
lecce.it
lecco.it
li.it
livorno.it
lo.it
lodi.it
lt.it
lu.it
lucca.it
macerata.it
mantova.it
massa-carrara.it
massacarrara.it

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