}
        }
    }

    /**
     * Polls the next URL queue entry for the specified session.
     * This method manages local caches and fetches from OpenSearch when needed.
     *
     * @param sessionId The session ID.
     * @return The next URL queue entry, or null if none available.
     */
    @Override

import org.codelibs.fess.crawler.extractor.Extractor;
import org.jodconverter.core.office.OfficeException;
import org.jodconverter.core.office.OfficeManager;
import org.jodconverter.local.LocalConverter;

import jakarta.annotation.PostConstruct;
import jakarta.annotation.PreDestroy;

/**
 * Extracts text content from various document formats using JODConverter.
 */

        urlFilter.processUrl("https://example.com/");
        urlFilter.processUrl("http://test.com/path/to/page");
        urlFilter.processUrl("ftp://files.server.com/documents/");
        urlFilter.processUrl("file:///local/path/file.txt");

        // Should complete without errors
        assertNotNull(urlFilter);
    }

    /**
     * Test processUrl with null URL
     */
    public void test_processUrl_nullUrl() {

			<groupId>jp.gr.java_conf.dangan</groupId>
			<artifactId>jlha</artifactId>
			<version>${jlha.version}</version>
		</dependency>
		<dependency>
			<groupId>org.jodconverter</groupId>
			<artifactId>jodconverter-local</artifactId>
			<version>${jodconverter.version}</version>
		</dependency>
		<dependency>
			<groupId>com.sun.mail</groupId>
			<artifactId>jakarta.mail</artifactId>
			<version>${jakarta.mail.version}</version>

import org.codelibs.core.io.ResourceUtil;
import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.dbflute.utflute.core.PlainTestCase;
import org.jodconverter.local.office.LocalOfficeManager;

/**
 * @author shinsuke
 *
 */
public class JodExtractorTest extends PlainTestCase {
    private static final Logger logger = LogManager.getLogger(JodExtractorTest.class);

      <match value="eval &quot;exec /usr/bin/python" type="string" offset="0"/>
      <match value="#!/usr/local/bin/python" type="string" offset="0"/>
      <match value="#! /usr/local/bin/python" type="string" offset="0"/>
      <match value="eval &quot;exec /usr/local/bin/python" type="string" offset="0"/>
      <match value="/bin/env python" type="string" offset="1"/>
    </magic>
    <glob pattern="*.py"/>

        String[] emptyArray = crawlerContext.removeSitemaps();
        assertNotNull(emptyArray);
        assertEquals(0, emptyArray.length);
    }

    /**
     * Test thread-local nature of sitemaps
     */
    public void test_sitemaps_threadLocal() throws Exception {
        final String[] thread1Sitemaps = new String[] { "http://thread1.com/sitemap.xml" };

	<!--
	<component name="jodExtractor"
		class="org.codelibs.fess.crawler.extractor.impl.JodExtractor">
		<property name="officeManager">
			@org.jodconverter.local.office.LocalOfficeManager@.builder().portNumbers(12002).build()
		</property>
	</component>
	-->

	<component name="extractorFactory"
		class="org.codelibs.fess.crawler.extractor.ExtractorFactory">

        Rule matchedRule2 = ruleManager.getRule(responseData2);
        assertEquals("pdfRule", matchedRule2.getRuleId());

        ResponseData responseData3 = new ResponseData();
        responseData3.setUrl("file:///local/file.txt");
        Rule matchedRule3 = ruleManager.getRule(responseData3);
        assertNull(matchedRule3); // No match
    }

    /**
     * Test rule order preservation
     */

            + "^\\s*unsaved:|" //
            + "^\\s*data:|" //
            + "^\\s*android-app:|" //
            + "^\\s*ios-app:|" //
            + "^\\s*callto:", Pattern.CASE_INSENSITIVE);

    /** Thread-local XPathAPI instance for thread-safe XPath operations. */
    private final ThreadLocal<XPathAPI> xpathAPI = new ThreadLocal<>();

    @Override
    public ResultData transform(final ResponseData responseData) {