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

import java.io.IOException;
import java.io.InputStream;

/**
 * A wrapper for an {@link InputStream} that ignores the {@link #close()} method call.
 * This can be useful when you want to prevent the underlying input stream from being closed.
 *
 * <p>All other methods delegate to the wrapped input stream.</p>
 *
 */
public class IgnoreCloseInputStream extends InputStream {

 *
 * <p>
 * This exception can be thrown when there are problems accessing URLs, files, or any other resources needed for crawling.
 * It includes constructors to handle messages, causes, or both.
 * </p>
 *
 * <p>
 * The log level can be set to DEBUG, INFO, WARN, or ERROR, and the class provides methods to check if a specific log level is enabled.
 * </p>
 *

public class QueryLog {
    private final String q;
    private final String fq;

    /**
     * Constructor for QueryLog.
     * @param queryString The query string.
     * @param filterQueryString The filter query string (can be null).
     */
    public QueryLog(final String queryString, @Nullable final String filterQueryString) {
        q = queryString;
        fq = filterQueryString;
    }

    /**
     * Returns the query string.

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

import java.io.Serializable;
import java.util.ArrayList;
import java.util.List;

/**
 * Represents a set of Sitemaps, which can be either a UrlSet or an Index.
 * This class provides methods to manage a list of Sitemap objects and determine the type of the SitemapSet.
 *
 */
public class SitemapSet implements Serializable {

 *
 * <p>The factory maintains a map of regular expression patterns to crawler clients,
 * allowing for URL-based client selection. Clients can be added with specific patterns
 * and optionally at specific positions in the processing order.</p>
 *
 * <p>This factory is typically initialized through dependency injection and can be
 * configured with initialization parameters that are passed to all registered clients.</p>
 *
 * <p>Features:</p>
 * <ul>

 * </ul>
 *
 * <p>Timeout settings can be accessed via:</p>
 * <ul>
 *   <li>{@link #getScrollTimeout()}</li>
 *   <li>{@link #getSearchTimeout()}</li>
 *   <li>{@link #getIndexTimeout()}</li>
 *   <li>{@link #getIndicesTimeout()}</li>
 *   <li>{@link #getBulkTimeout()}</li>
 *   <li>{@link #getClusterTimeout()}</li>
 * </ul>
 *
 * <p>Default settings and array settings can be customized using:</p>
 * <ul>

         * - Symbol characters (!-/, :-@, [-`, {-~) are appended to the buffer.
         * - Duplicate terms can be removed based on the `duplicateTermRemoved` flag.
         * - The maximum size of alphanumeric and symbol terms can be limited by `maxAlphanumTermSize` and `maxSymbolTermSize` respectively.
         *

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

/**
 * Enum representing the status of a crawler.
 * It can be INITIALIZING, RUNNING, or DONE.
 */
public enum CrawlerStatus {
    /**
     * The crawler is initializing.
     */
    INITIALIZING,

    /**
     * The crawler is currently running.
     */

     * Datetime format. This format allows you to omit the time portion, if
     * desired, and use YYYY-MM-DD.
     *
     * Note that this tag is separate from the If-Modified-Since (304) header
     * the server can return, and search engines may use the information from
     * both sources differently.
     */
    private String lastmod;

    /**
     * How frequently the page is likely to change. This value provides general

 *   <li>Dependency injection using {@code @Resource} annotation</li>
 *   <li>Lifecycle management using {@code @PostConstruct} and {@code @PreDestroy} annotations</li>
 * </ul>
 *
 * <p>Components can be registered in two ways:
 * <ul>
 *   <li>As singletons, where one instance is shared throughout the container's lifecycle</li>
 *   <li>As prototypes, where a new instance is created each time the component is requested</li>