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.

        }
        buf.append(segment);
        return buf.toString();
    }

    /**
     * Gets the site path for display purposes.
     * Extracts and formats the site path from document URL.
     *
     * @param docMap the document data map
     * @return the formatted site path
     */
    public Object getSitePath(final Map<String, Object> docMap) {

        assertQueryContext(
                "{\"function_score\":{\"query\":{\"prefix\":{\"site\":{\"value\":\"fess.codelibs.org\",\"boost\":1.0}}},\"functions\":[{\"filter\":{\"match_all\":{\"boost\":1.0}},\"field_value_factor\":{\"field\":\"boost\",\"factor\":1.0,\"modifier\":\"none\"}}],\"score_mode\":\"multiply\",\"max_boost\":3.4028235E38,\"boost\":1.0}}",
                Map.of("site", List.of("fess.codelibs.org*")), //
                Set.of("fess.codelibs.org"), //

					<excludes>
						<exclude>**/*min.js</exclude>
						<exclude>**/*min.css</exclude>
						<exclude>**/plugins/**/*.js</exclude>
						<exclude>**/WEB-INF/site/**</exclude>
					</excludes>
					<sourceDirectory>src/main/webapp/js</sourceDirectory>
				</configuration>
			</plugin>
			<plugin>
				<groupId>org.dbflute</groupId>

        }
        // segment
        putResultDataBody(dataMap, fessConfig.getIndexFieldSegment(), sessionId);
        // host
        putResultDataBody(dataMap, fessConfig.getIndexFieldHost(), getHost(url));
        // site
        putResultDataBody(dataMap, fessConfig.getIndexFieldSite(), getSite(url, urlEncoding));
        // filename
        if (StringUtil.isNotBlank(fileName)) {

    that 99.99% of servers do it right this fallback is obsolete.
 *  Fix: Do not honor cookies set on a public domain. Previously a malicious site could inject
    cookies on top-level domains like `co.uk` because our cookie parser didn't honor the [public
    suffix][public_suffix] list. Alongside this fix is a new API, `HttpUrl.topPrivateDomain()`,