* 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>

import org.apache.http.client.AuthCache;
import org.apache.http.client.CredentialsProvider;
import org.apache.http.client.config.RequestConfig;
import org.apache.http.client.methods.CloseableHttpResponse;
import org.apache.http.client.methods.HttpPost;
import org.apache.http.client.protocol.HttpClientContext;
import org.apache.http.config.RegistryBuilder;
import org.apache.http.entity.mime.HttpMultipartMode;

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>

/**
 * Helper class for parsing and validating sitemaps.
 * It supports XML sitemaps, XML sitemap indexes, and text sitemaps,
 * and can handle GZIP compressed sitemaps.
 * The class provides methods to check if an input stream is a valid sitemap,
 * and to parse an input stream into a {@link SitemapSet} object.
 * It uses SAX parser for XML sitemaps and XML sitemap indexes,
 * and handles potential exceptions during parsing.

 *   <li>While waiting for new URLs to be added to the queue ({@link #delayForWaitingNewUrl()})</li>
 * </ul>
 *
 * <p>
 * Subclasses are responsible for implementing the abstract methods to define the actual delay
 * mechanism for each of these stages.
 * </p>
 *
 * <p>
 * The class also provides a mechanism to ignore exceptions that may occur during the delay process.

import org.apache.http.client.CredentialsProvider;
import org.apache.http.client.config.CookieSpecs;
import org.apache.http.client.config.RequestConfig;
import org.apache.http.client.methods.HttpGet;
import org.apache.http.client.methods.HttpHead;
import org.apache.http.client.methods.HttpUriRequest;
import org.apache.http.client.protocol.HttpClientContext;
import org.apache.http.client.utils.DateUtils;
import org.apache.http.config.Lookup;