}
        resultData.setEncoding(charsetName);
    }

    /**
     * Normalizes the extracted data, particularly handling title normalization.
     *
     * @param responseData the response data from crawling
     * @param dataMap the data map containing extracted field values
     */
    protected void normalizeData(final ResponseData responseData, final Map<String, Object> dataMap) {

        assertEquals("file.txt", file.getName(), "Name should be extracted correctly");
        assertTrue(file.getPath().endsWith("/shared/path/file.txt"), "Path should end correctly");
        assertEquals("shared", file.getShare(), "Share should be extracted correctly");
        assertNotNull(file.getParent(), "Parent should not be null");

                    }
                    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) {
        if (entryDn == null) {
            return null;

		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"

dc:title=title:string\n\

# html

# XPath to extract main content from HTML documents.
crawler.document.html.content.xpath=//BODY
# XPath to extract language attribute from HTML documents.
crawler.document.html.lang.xpath=//HTML/@lang
# XPath to extract digest (description) from HTML documents.
crawler.document.html.digest.xpath=//META[@name='description']/@content
# XPath to extract canonical URL from HTML documents.

labels.disabled=Désactivé
labels.pathmap_pt_crawling=Exploration
labels.pathmap_pt_displaying=Affichage
labels.pathmap_pt_both=Exploration/Affichage
labels.pathmap_pt_stored=Conversion d'URL extraite
labels.regular_name=Nom régulier
labels.duplicate_name=Nom en double
labels.duplicate_host_configuration=Hôte en double
labels.duplicate_host_title_details=Hôte en double

        }
        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) {

            httpClientPropertyMap.put(name, value);
        }
    }

    /**
     * Processes robots.txt for the given URL.
     * This method fetches and parses the robots.txt file to extract disallow/allow rules
     * and sitemap information.
     *
     * @param url The URL to process robots.txt for
     */
    protected void processRobotsTxt(final String url) {
        if (StringUtil.isBlank(url)) {

        // Simple implementation - could be enhanced with proper cluster discovery
        String hostname = serverAddress.getHostName();
        if (hostname != null && hostname.contains(".")) {
            // Extract potential cluster name from hostname
            String[] parts = hostname.split("\\.");
            if (parts.length > 1) {
                return parts[0]; // Use first part as cluster name
            }
        }