import java.io.PrintStream;
import java.io.Reader;
import java.io.Writer;
import java.util.ArrayList;
import java.util.Arrays;
import java.util.Collections;
import java.util.List;
import java.util.Locale;
import java.util.Map;
import java.util.Properties;
import java.util.concurrent.ConcurrentHashMap;
import java.util.function.BiConsumer;
import java.util.stream.Collectors;

 * governing permissions and limitations under the License.
 */
package org.codelibs.fess.crawler;

import java.text.SimpleDateFormat;
import java.util.Date;
import java.util.Locale;

import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
import org.codelibs.core.lang.StringUtil;
import org.codelibs.fess.crawler.client.CrawlerClientFactory;

crawler.urlFilter.addExclude(".*login.*");
```

## Supported Protocols and Formats

### Protocols
- **HTTP/HTTPS**: Full web crawling support with cookies, authentication, redirects
- **File System**: Local and network file system access
- **FTP**: FTP server crawling with authentication
- **SMB/CIFS**: Windows network shares
- **Storage**: Cloud storage systems (MinIO, S3-compatible)

### Content Formats

    }

    /**
     * Gets the local IP address for passive mode FTP.
     *
     * @return The passive local host IP address
     */
    public String getPassiveLocalHost() {
        return passiveLocalHost;
    }

    /**
     * Sets the local IP address for passive mode FTP.
     *
     * @param passiveLocalHost The passive local host IP address
     */

            }
        }
    }

    /**
     * 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>

        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" };

        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
     */