"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": {

          "type":       "keyword_marker",
          "keywords": ["sveiki", "pasaule", "meklēšana"]
        },
        "latvian_stemmer": {
          "type":       "stemmer",
          "language":   "latvian"
        },
        "latvian_override": {
          "type":       "stemmer_override",
          "rules": []
        },
        "lithuanian_stop": {
          "type":       "stop",

          "type":       "keyword_marker",
          "keywords": ["sveiki", "pasaule", "meklēšana"]
        },
        "latvian_stemmer": {
          "type":       "stemmer",
          "language":   "latvian"
        },
        "latvian_override": {
          "type":       "stemmer_override",
          "rules": []
        },
        "lithuanian_stop": {
          "type":       "stop",

  /**
   * US-ASCII: seven-bit ASCII, the Basic Latin block of the Unicode character set (ISO646-US).
   *
   * @deprecated Use {@link StandardCharsets#US_ASCII} instead.
   */
  @Deprecated @J2ktIncompatible @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).
   *

  /**
   * US-ASCII: seven-bit ASCII, the Basic Latin block of the Unicode character set (ISO646-US).
   *
   * @deprecated Use {@link StandardCharsets#US_ASCII} instead.
   */
  @Deprecated @J2ktIncompatible @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).
   *

          required: true
  - type: input
    id: language
    attributes:
      label: Target Language
      description: What language do you want to translate the FastAPI docs into?
      placeholder: e.g. Latin
    validations:
      required: true
  - type: textarea
    id: additional_info
    attributes:
      label: Additional Information
      description: Any other relevant information about your translation proposal

 * 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
 */

        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.