class="org.codelibs.fess.crawler.extractor.impl.MsPowerPointExtractor" />
	<component name="msPublisherExtractor"
		class="org.codelibs.fess.crawler.extractor.impl.MsPublisherExtractor" />
	<component name="msVisioExtractor"
		class="org.codelibs.fess.crawler.extractor.impl.MsVisioExtractor" />
	<component name="pdfExtractor"
		class="org.codelibs.fess.crawler.extractor.impl.PdfExtractor" />
	<component name="lhaExtractor"

        if (StringUtil.isNotBlank(xpath)) {
            return xpath;
        }
        return fessConfig.getCrawlerDocumentHtmlDigestXpath();
    }

    /**
     * Extracts the canonical URL from the HTML document.
     *
     * @param responseData the response data from crawling
     * @param document the parsed HTML document
     * @return the canonical URL if found, null otherwise

     */
    abstract E castForTesting(InternalEntry<K, V, ?> entry);

    /** Unsafely extracts the key reference queue used by this segment. */
    ReferenceQueue<K> getKeyReferenceQueueForTesting() {
      throw new AssertionError();
    }

    /** Unsafely extracts the value reference queue used by this segment. */
    ReferenceQueue<V> getValueReferenceQueueForTesting() {

        }
        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) {

                        logger.debug("entryDn: {}", entryDn);
                    }
                    consumer.accept(entryDn);
                }
            }
        }
    }

    /**
     * Extracts the role name from an LDAP entry DN.
     *
     * @param entryDn the LDAP entry DN
     * @return the extracted role name, or null if not found
     */
    protected String getSearchRoleName(final String entryDn) {