},
      "limit_token_count_filter": {
        "type": "limit",
        "max_token_count": 2147483647
      },
      "stemmer_en_filter": {
        "type": "stemmer",
        "name": "english"
      },
      "arabic_stop": {
        "type":       "stop",
        "stopwords":  "_arabic_"
      },
      "arabic_keywords": {
        "type":       "keyword_marker",

      },
      "limit_token_count_filter": {
        "type": "limit",
        "max_token_count": 2147483647
      },
      "stemmer_en_filter": {
        "type": "stemmer",
        "name": "english"
      },
      "arabic_stop": {
        "type":       "stop",
        "stopwords":  "_arabic_"
      },
      "arabic_keywords": {
        "type":       "keyword_marker",

     */
    protected String getLanguageInstruction() {
        final Locale locale = getUserLocale();
        final String language = locale.getLanguage();
        if ("en".equals(language)) {
            return StringUtil.EMPTY;
        }
        return "IMPORTANT: You MUST respond in " + locale.getDisplayLanguage(Locale.ENGLISH) + ".";
    }

    /**

    return anyOf(sequence).negate();
  }

  /**
   * Returns a {@code char} matcher that matches any character in a given BMP range (both endpoints
   * are inclusive). For example, to match any lowercase letter of the English alphabet, use {@code
   * CharMatcher.inRange('a', 'z')}.
   *
   * @throws IllegalArgumentException if {@code endInclusive < startInclusive}
   */

crawler.document.site.encoding=UTF-8
# Hostname to use when unknown in documents.
crawler.document.unknown.hostname=unknown
# Whether to use site encoding for English documents.
crawler.document.use.site.encoding.on.english=false
# Whether to append data to documents.
crawler.document.append.data=true
# Whether to append filename to documents.
crawler.document.append.filename=false

    return anyOf(sequence).negate();
  }

  /**
   * Returns a {@code char} matcher that matches any character in a given BMP range (both endpoints
   * are inclusive). For example, to match any lowercase letter of the English alphabet, use {@code
   * CharMatcher.inRange('a', 'z')}.
   *
   * @throws IllegalArgumentException if {@code endInclusive < startInclusive}
   */

            ThreadLocal.withInitial(() -> new SimpleDateFormat("EEE, d MMM yyyy HH:mm:ss Z", Locale.ENGLISH));

    /** RFC 1123 date formatter */
    private static final DateTimeFormatter RFC_1123_FORMATTER =
            DateTimeFormatter.ofPattern("EEE, dd MMM yyyy HH:mm:ss zzz", Locale.ENGLISH).withZone(ZoneId.of("GMT"));

    /**
     * Parses the last modified date from a string value.

                        logger.warn("@odata.type is null: {}", memberOf);
                        continue;
                    }
                    memberType = memberType.toLowerCase(Locale.ENGLISH);
                    final String id = (String) memberOf.get("id");
                    if (StringUtil.isNotBlank(id)) {
                        if (memberType.contains("group")) {

        final Handlebars handlebars = new Handlebars(loader);

        Locale locale = ComponentUtil.getRequestManager().getUserLocale();
        if (locale == null) {
            locale = Locale.ENGLISH;
        }
        String url = DocumentUtil.getValue(doc, fessConfig.getIndexFieldUrl(), String.class);
        if (url == null) {

    private static final ThreadLocal<SimpleDateFormat> DATE_FORMAT_HOLDER =
            ThreadLocal.withInitial(() -> new SimpleDateFormat("EEE, d MMM yyyy HH:mm:ss Z", Locale.ENGLISH));

    /**
     * Parses the last modified date from a string value.
     * First attempts to parse using Apache DateUtils (which supports RFC 1123, RFC 1036, and ANSI C formats).