import org.codelibs.fess.crawler.service.DataService;
import org.codelibs.fess.crawler.service.UrlQueueService;

/**
 * Utility class for managing crawling parameters using ThreadLocal variables.
 * This class provides methods to set and get various parameters related to the crawling process.
 *
 * <p>This class is final and cannot be instantiated.</p>
 *
 * <p>The following parameters are managed:</p>
 * <ul>

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

import java.util.regex.Pattern;

/**
 * Extracts text content from XML documents.
 */
public class XmlExtractor extends AbstractXmlExtractor {

    /**
     * Creates a new XmlExtractor instance.
     */
    public XmlExtractor() {
        super();
    }

    /**
     * Pattern for XML encoding.

        container.singleton("mimeTypeHelper", MimeTypeHelperImpl.class)
                .singleton("tikaExtractor", TikaExtractor.class)
                .<ExtractorFactory> singleton("extractorFactory", ExtractorFactory.class, factory -> {
                    TikaExtractor tikaExtractor = container.getComponent("tikaExtractor");
                    factory.addExtractor("text/plain", tikaExtractor);

<!DOCTYPE components PUBLIC "-//DBFLUTE//DTD LastaDi 1.0//EN"
	"http://dbflute.org/meta/lastadi10.dtd">
<components namespace="fessCrawler">
	<include path="crawler/container.xml" />

	<component name="urlFilter"
		class="org.codelibs.fess.crawler.filter.impl.UrlFilterImpl" instance="prototype">
	</component>

import org.codelibs.jcifs.smb.ntlmssp.Type2Message;
import org.codelibs.jcifs.smb.ntlmssp.Type3Message;

/**
 * JcifsEngine is a NTLM Engine implementation based on JCIFS.
 *
 * @author shinsuke
 *
 */
public class JcifsEngine implements NTLMEngine {

    /** Flags for Type 1 NTLM message. */
    protected static final int TYPE_1_FLAGS = NtlmFlags.NTLMSSP_NEGOTIATE_56 | NtlmFlags.NTLMSSP_NEGOTIATE_128

import java.util.regex.Pattern;

import org.codelibs.fess.crawler.entity.ResponseData;
import org.dbflute.utflute.core.PlainTestCase;

/**
 * @author shinsuke
 *
 */
public class RegexRuleTest extends PlainTestCase {

    public void test_match_default() {
        final RegexRule regexRule = new RegexRule();
        regexRule.defaultRule = true;
        regexRule.allRequired = true;

 *     System.out.println(document);
 * }
 *
 * reader.close(); // Close the reader to release resources
 * }
 * </pre>
 */
public class ESSourceReader implements DocumentReader {
    private static final Logger logger = LogManager.getLogger(ESSourceReader.class);

    /** Queue of documents. */
    protected final Queue<Map<String, Object>> queue = new ConcurrentLinkedQueue<>();

/**
 * @author shinsuke
 *
 */
public class SitemapsHelperTest extends PlainTestCase {
    public SitemapsHelper sitemapsHelper;

    @Override
    protected void setUp() throws Exception {
        super.setUp();
        StandardCrawlerContainer container = new StandardCrawlerContainer().singleton("sitemapsHelper", SitemapsHelper.class);
        sitemapsHelper = container.getComponent("sitemapsHelper");
    }

 * FileSystemClient is CrawlerClient implementation to crawl files on a file
 * system.
 *
 * @author shinsuke
 *
 */
public class FileSystemClient extends AbstractCrawlerClient {

    /** Logger instance for this class */
    private static final Logger logger = LogManager.getLogger(FileSystemClient.class);

    /** Key for file attribute view in metadata */
    public static final String FILE_ATTRIBUTE_VIEW = "fileAttributeView";

import org.codelibs.fess.crawler.exception.CrawlerSystemException;

import jakarta.annotation.PostConstruct;
import jakarta.annotation.Resource;

/**
 * A factory class for managing and creating crawler clients based on URL patterns.
 * This class implements AutoCloseable to properly handle resource cleanup.
 *
 * <p>The factory maintains a map of regular expression patterns to crawler clients,