}

        idx = url.indexOf('/');
        if (idx >= 0) {
            url = url.substring(0, idx);
        }

        if (url.equals(originalUrl)) {
            return getFessConfig().getCrawlerDocumentUnknownHostname();
        }

        return url;
    }

    /**
     * Extracts and processes the site path from a URL with proper encoding handling.

            @Override
            public boolean isCrawlerDocumentUseSiteEncodingOnEnglish() {
                return false;
            }

            @Override
            public String getCrawlerDocumentUnknownHostname() {
                return "unknown";
            }

            @Override
            public Integer getCrawlerDocumentMaxSiteLengthAsInteger() {
                return -1;
            }
        });

     * comment: Hostname to use when unknown in documents.
     * @return The value of found property. (NotNull: if not found, exception but basically no way)
     */
    String getCrawlerDocumentUnknownHostname();

    /**
     * Get the value for the key 'crawler.document.use.site.encoding.on.english'. <br>
     * The value is, e.g. false <br>