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

import java.util.Date;

import org.apache.http.client.methods.HttpUriRequest;
import org.codelibs.fess.crawler.CrawlerContext;
import org.codelibs.fess.crawler.container.StandardCrawlerContainer;
import org.codelibs.fess.crawler.entity.ResponseData;

 */
package org.codelibs.fess.crawler.service;

import java.util.List;
import java.util.regex.Pattern;

/**
 * Service interface for managing URL filters.
 * Provides methods to add and remove include/exclude URL filters,
 * as well as retrieve the patterns of these filters.
 */
public interface UrlFilterService {

    /**
     * Adds a URL to the include filter list for the specified session.

/**
 * MimeTypeHelperImpl is a helper class that detects the MIME type of a given input stream or filename.
 * It uses the Apache Tika library to detect the MIME type.
 *
 * <p>
 * This class provides methods to:
 * </p>
 * <ul>
 *   <li>Detect the MIME type based on the input stream and filename.</li>
 *   <li>Normalize the filename to handle special characters.</li>

 * </p>
 *
 * <p>
 * The transform method takes a ResponseData object containing the XML content and returns a ResultData object with the extracted and formatted data.
 * </p>
 *
 * <p>

import org.codelibs.fess.suggest.request.RequestBuilder;
import org.opensearch.transport.client.Client;

/**
 * Builder for creating a {@link PopularWordsRequest} to fetch popular words.
 * This builder provides methods to set various parameters for the request.
 */
public class PopularWordsRequestBuilder extends RequestBuilder<PopularWordsRequest, PopularWordsResponse> {
    /**
     * Constructor for PopularWordsRequestBuilder.

import org.codelibs.fess.crawler.rule.Rule;
import org.codelibs.fess.crawler.rule.RuleManager;

/**
 * Implementation of the {@link RuleManager} interface.
 * Manages a list of rules for the crawler.
 * Provides methods to add, remove, check, and retrieve rules.
 *
 */
public class RuleManagerImpl implements RuleManager {

    /** The list of rules managed by this rule manager. */

 * using the Apache Tika library. It extends {@link PasswordBasedExtractor} to handle password-protected files.
 * </p>
 *
 * <p>
 * This class provides methods to extract text from an input stream, handling different scenarios such as:
 * </p>
 * <ul>
 *   <li>Normalizing text content</li>
 *   <li>Handling resource names and content types</li>

        urlQueueService.delete(sessionId);
        dataService.delete(sessionId);
        urlFilter.clear();
    }

    /**
     * Closes the crawler, releasing resources.
     * This method is called automatically when the crawler is used in a try-with-resources statement.
     */
    @Override
    public void close() {
        clientFactory.close();
    }

    /**

        // The first creation should increment the counter
        assertTrue("Instance count should be at least 1", SingletonTestComponent.getInstanceCount() >= 1);
    }

    /**
     * Test wrap method
     */
    public void test_wrap_basic() {
        TestComponent component = new TestComponent();

        PooledObject<TestComponent> pooledObject = factory.wrap(component);

            final SearchRequestBuilder builder = c.prepareSearch(index);
            callback.accept(builder);
            builder.setFetchSource(new String[] { "parentUrl", "method", "mimeType", "sessionId", "url", "executionTime", "createTime",
                    "contentLength", "lastModified", "ruleId", "httpStatusCode", "status" }, null);
            return builder.execute();
        });