}
                    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;

            }

            // Extract links
            if (extractLinks) {
                extractLinkMetadata(document, extractData);
            }

            return extractData;
        } catch (final Exception e) {
            throw new ExtractException("Failed to extract Markdown content", e);
        }
    }

    /**
     * Extracts YAML front matter metadata from the document.
     *

		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 (extractor == null) {
            throw new CrawlerSystemException("Extractor instance is null. Cannot register null extractor.");
        }
        if (extractorMap.containsKey(key)) {
            final Extractor[] existingExtractors = extractorMap.get(key);

	"http://dbflute.org/meta/lastadi10.dtd">
<components namespace="fessCrawler">
	<include path="crawler/container.xml" />
	<component name="tikaExtractor"
		class="org.codelibs.fess.crawler.extractor.impl.TikaExtractor">
		<property name="maxCompressionRatio">2</property>
		<property name="maxUncompressionSize">10000000</property>
	</component>

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.

 */
package org.codelibs.fess.crawler.extractor.impl;

import java.io.InputStream;
import java.util.Map;

import org.codelibs.core.io.InputStreamUtil;
import org.codelibs.fess.crawler.Constants;
import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.exception.ExtractException;

/**
 * Extracts text content from an input stream as plain text.
 */

                    e.getMessage().contains("TAR") || e.getMessage().contains("extract"));
        }
    }

    /**
     * Test that ZipExtractor successfully extracts from valid archive.
     */
    public void test_ZipExtractor_validArchive_extractsSuccessfully() {
        final InputStream in = ResourceUtil.getResourceAsStream("extractor/zip/test.zip");

        final ExtractData result = zipExtractor.getText(in, null);

        final AtomicBoolean streamClosed = new AtomicBoolean(false);

        try (final InputStream originalStream = ResourceUtil.getResourceAsStream("extractor/msoffice/test.xls")) {
            final InputStream trackableStream = createTrackableInputStream(originalStream, streamClosed);
            final ExtractData result = extractor.getText(trackableStream, null);

        final Extractor extractor = new Extractor() {
            public ExtractData getText(final InputStream in, final Map<String, String> params) {
                return null;
            }
        };

        assertNull(extractorFactory.getExtractor("test"));
        extractorFactory.addExtractor("test", extractor);
        assertEquals(extractor, extractorFactory.getExtractor("test"));
    }