false, false, false, "keyword", 0, 0, null, null, false, null, null, null, null, null, false);
    protected final ColumnInfo _columnHostname = cci("hostname", "hostname", null, null, String.class, "hostname", null, false, false,
            false, "keyword", 0, 0, null, null, false, null, null, null, null, null, false);

    }

    /**
     * Gets host information including hostname and IP address.
     *
     * @return formatted string containing hostname and IP address
     */
    protected String getHostInfo() {
        final StringBuilder buf = new StringBuilder();
        try {
            final InetAddress ia = InetAddress.getLocalHost();
            final String hostname = ia.getHostName();

Die folgenden Argumente werden unterstützt:

* `allowed_hosts` – Eine Liste von Domain-Namen, die als Hostnamen zulässig sein sollten. Wildcard-Domains wie `*.example.com` werden unterstützt, um Subdomains zu matchen. Um jeden Hostnamen zu erlauben, verwenden Sie entweder `allowed_hosts=["*"]` oder lassen Sie diese Middleware weg.

labels.depth=Depth
labels.excludedPaths=Excluded Paths for Crawling
labels.excludedUrls=Excluded URLs for Crawling
labels.excludedDocPaths=Excluded Paths for Searching
labels.excludedDocUrls=Excluded URLs for Searching
labels.hostname=Hostname
labels.id=ID
labels.includedPaths=Included Paths for Crawling
labels.includedUrls=Included URLs for Crawling
labels.includedDocPaths=Included Paths for Searching
labels.includedDocUrls=Included URLs for Searching

labels.depth=Depth
labels.excludedPaths=Excluded Paths for Crawling
labels.excludedUrls=Excluded URLs for Crawling
labels.excludedDocPaths=Excluded Paths for Searching
labels.excludedDocUrls=Excluded URLs for Searching
labels.hostname=Hostname
labels.id=ID
labels.includedPaths=Included Paths for Crawling
labels.includedUrls=Included URLs for Crawling
labels.includedDocPaths=Included Paths for Searching
labels.includedDocUrls=Included URLs for Searching

    }

    /**
     * Gets the hostname of the local machine.
     *
     * @return The hostname.
     */
    public String getHostname() {
        final Map<String, String> env = getEnvMap();
        if (env.containsKey("COMPUTERNAME")) {
            return env.get("COMPUTERNAME");
        }
        if (env.containsKey("HOSTNAME")) {
            return env.get("HOSTNAME");
        }
        try {

import jakarta.annotation.PostConstruct;

/**
 * Helper class for managing duplicate host configurations in the Fess search system.
 * This class handles URL conversion based on duplicate host rules, allowing multiple
 * hostnames or URLs to be treated as equivalent for crawling and indexing purposes.
 * It maintains a list of DuplicateHost rules and applies them to URLs.
 *
 */
public class DuplicateHostHelper {

    Logger getLogger();

    /**
     * Extracts the host name from a URL string.
     * Removes protocol and path components to return just the hostname.
     *
     * @param u the URL string to extract host from
     * @return the host name, or empty string if URL is blank, or unknown hostname if parsing fails
     */
    default String getHost(final String u) {
        if (StringUtil.isBlank(u)) {

        final String[] toAddresses = form.notificationTo.split(",");
        final Map<String, Object> dataMap = new HashMap<>();
        dataMap.put("hostname", systemHelper.getHostname());

        final FessConfig fessConfig = ComponentUtil.getFessConfig();
        final Postbox postbox = ComponentUtil.getComponent(Postbox.class);
        try {

crawler.data.serializer=kryo
# Maximum length of site name in documents.
crawler.document.max.site.length=100
# Encoding for site names in documents.
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