.singleton("urlFilterService", UrlFilterServiceImpl.class)//
                .singleton("urlFilter", UrlFilterImpl.class)//
                .singleton("robotsTxtHelper", RobotsTxtHelper.class)//
                .singleton("httpClient", HcHttpClient.class);
        httpClient = container.getComponent("httpClient");
        urlFilter = container.getComponent("urlFilter");
    }

    public void test_doGet() {

 * by using appropriate extractors for each contained file type.
 *
 * @author shinsuke
 */
public class LhaExtractor extends AbstractExtractor {
    /** Logger for this class. */
    private static final Logger logger = LogManager.getLogger(LhaExtractor.class);

    /** Maximum content size for extraction. -1 means no limit. */
    protected long maxContentSize = -1;

    /**

import org.testcontainers.containers.GenericContainer;
import org.testcontainers.utility.MountableFile;

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

    private static final Logger logger = LogManager.getLogger(SmbClientTest.class);

    private static final String IMAGE_NAME = "dperson/samba:latest";

    private SmbClient smbClient;
    private GenericContainer<?> sambaServer;

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

import java.util.Collections;

import org.dbflute.utflute.core.PlainTestCase;

public class FormSchemeTest extends PlainTestCase {

    public void test_getTokenValue() {
        FormScheme formScheme = new FormScheme(Collections.emptyMap());

import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.dbflute.utflute.core.PlainTestCase;

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

    public MsWordExtractor msWordExtractor;

    @Override
    protected void setUp() throws Exception {
        super.setUp();

 */
package org.codelibs.fess.suggest.normalizer;

import com.ibm.icu.text.Transliterator;

/**
 * ICUNormalizer is a class that implements the Normalizer interface and provides
 * functionality to normalize text using ICU4J's Transliterator.
 *
 * <p>This class uses a specified Transliterator to perform text normalization.
 * The Transliterator is initialized with a given ID during the construction of

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

/**
 * Utility class for character-related operations.
 */
public final class CharUtil {
    /**
     * Private constructor to prevent instantiation of this utility class.
     */
    private CharUtil() {
    }

    /**
     * Checks if the given character is a valid URL character.
     *

import org.codelibs.fess.crawler.helper.MimeTypeHelper;

import jakarta.annotation.Resource;

/**
 * An abstract base class for implementing Extractor interfaces.
 * Provides common functionality such as access to CrawlerContainer components
 * and registration with the ExtractorFactory.
 *
 * <p>
 * This class handles the retrieval of essential crawler components like
 * {@link MimeTypeHelper} and {@link ExtractorFactory} from the

/**
 * Default implementation of the IntervalController.
 * This class provides a default way to manage delays between crawler operations.
 * It allows setting delays before processing, after processing, when no URLs are in the queue,
 * and when waiting for new URLs.
 * The delays are configurable via constructor parameters.
 *
 */
public class DefaultIntervalController extends AbstractIntervalController {

/**
 * SuggestBulkFileWriter is an implementation of the SuggestWriter interface.
 * This class is responsible for writing and deleting suggest items in bulk.
 *
 * <p>Currently, the methods in this class throw UnsupportedOperationException
 * as they are not yet implemented.</p>
 *
 * @see SuggestWriter
 */
public class SuggestBulkFileWriter implements SuggestWriter {
    /**