*/
public class CrawlerPooledObjectFactory<T> extends BasePooledObjectFactory<T> {
    /**
     * Constructs a new CrawlerPooledObjectFactory.
     */
    public CrawlerPooledObjectFactory() {
        // Default constructor
    }

    /**
     * The container that provides crawler components.
     */
    @Resource
    protected CrawlerContainer crawlerContainer;

    /**

     * @param suffix The suffix string to be used in generating the file's name.
     * @param directory The directory in which the file is to be created, or null if the default temporary-file directory is to be used.
     * @return The created temporary file.
     */
    protected File createTempFile(final String prefix, final String suffix, final File directory) {
        try {

     * discovery of new URLs on very large sites.
     */
    private String lastmod;

    /**
     * Creates a new SitemapFile instance.
     */
    public SitemapFile() {
        // Default constructor
    }

    /*
     * (non-Javadoc)
     *
     * @see org.codelibs.fess.crawler.entity.Sitemap#getLoc()
     */
    @Override
    public String getLoc() {
        return loc;
    }

 * The CrawlerContainer interface provides methods for managing components
 * within a crawler container. It includes methods to retrieve components,
 * check availability, and destroy the container. Additionally, it provides
 * a default method to initialize the container with specific protocol handlers.
 *
 */
public interface CrawlerContainer {

    /**
     * Retrieves a component by its name.
     *
     * @param <T> the type of the component

    /** The type of this sitemap set (URLSET or INDEX). */
    private String type = URLSET;

    /**
     * Creates a new SitemapSet instance with default type URLSET.
     */
    public SitemapSet() {
        // Default constructor
    }

    /**
     * Adds a sitemap to this set.
     * @param sitemap the sitemap to add
     */
    public void addSitemap(final Sitemap sitemap) {

 *   <li>secretKey - The secret key for authentication</li>
 *   <li>connectTimeout - Connection timeout in milliseconds (default: 10000)</li>
 *   <li>writeTimeout - Write timeout in milliseconds (default: 10000)</li>
 *   <li>readTimeout - Read timeout in milliseconds (default: 10000)</li>
 * </ul>
 *
 * <p>The client supports URLs in the format: {@code storage://bucket-name/object-path}
 *
 * <p>Features:
 * <ul>

 * Extracts the filename from the parameters.
 */
public class FilenameExtractor extends AbstractExtractor {

    /**
     * Constructs a new FilenameExtractor.
     */
    public FilenameExtractor() {
        // Default constructor
    }

    /**
     * Extracts the filename from the parameters.
     * @param in The input stream (not used).
     * @param params The parameters, expected to contain ExtractData.RESOURCE_NAME_KEY.

     * If set to true, exceptions will be caught and ignored. If set to false,
     * exceptions will be re-thrown as {@link CrawlerSystemException}.
     * Default value is true.
     */
    protected boolean ignoreException = true;

    /**
     * Constructs a new AbstractIntervalController.
     */
    public AbstractIntervalController() {
        // NOP
    }

     */
    protected int initialBufferSize = 10000;

    /**
     * If true, duplicated terms are replaced.
     */
    protected boolean replaceDuplication = false;

    /**
     * Space characters. Default includes common space characters.
     */
    protected int[] spaceChars = { '\u0020', '\u00a0', '\u3000', '\ufffd' };

    /**
     * Memory size.
     */
    protected int memorySize = 1024 * 1024; //1mb

    protected boolean useFilenameOnOctetStream = true;

    /**
     * Creates a new MimeTypeHelperImpl instance.
     * Initializes the MimeTypes instance using the default configuration.
     * @throws CrawlerSystemException if the MIME types configuration cannot be loaded
     */
    public MimeTypeHelperImpl() {
        try {