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

    public PdfExtractor pdfExtractor;

    private PdfExtractor pdfExtractorForPdfPassword;

    @Override
    protected void setUp() throws Exception {
        super.setUp();
        StandardCrawlerContainer container = new StandardCrawlerContainer();
        container.singleton("pdfExtractor", PdfExtractor.class)//

         *
         * @param value The Date object to convert.
         * @return The ISO 8601 formatted date string, or null if value is not a Date.
         */
        @Override
        public String getAsString(final Object value) {
            if (value instanceof Date) {
                return DEFAULT_DATE_PRINTER.print(((Date) value).getTime());
            }
            return null;

        /**
         * Constructor for Kind.
         * @param kind The kind string.
         */
        Kind(final String kind) {
            this.kind = kind;
        }

        @Override
        public String toString() {
            return kind;
        }
    }

    private String text;

    private ZonedDateTime timestamp;

    private long queryFreq;

    private long docFreq;

        requestData.setUrl(url);
        return requestData;
    }

    /**
     * Closes the response data, deleting temporary files if any.
     * @throws IOException if an I/O error occurs.
     */
    @Override
    public void close() throws IOException {
        if (isTemporaryFile) {
            FileUtil.deleteInBackground(responseBodyFile);
        }
    }

        Thread[] threads = new Thread[threadCount];
        for (int i = 0; i < threadCount; i++) {
            threads[i] = new Thread(new Runnable() {
                @Override
                public void run() {
                    try {
                        for (int j = 0; j < iterationsPerThread; j++) {
                            // Access enum values

            + "^\\s*callto:", Pattern.CASE_INSENSITIVE);

    /** Thread-local XPathAPI instance for thread-safe XPath operations. */
    private final ThreadLocal<XPathAPI> xpathAPI = new ThreadLocal<>();

    @Override
    public ResultData transform(final ResponseData responseData) {
        if (responseData == null || !responseData.hasResponseBody()) {
            throw new CrawlingAccessException("No response body.");
        }

import org.dbflute.utflute.core.PlainTestCase;

/**
 * @author shinsuke
 *
 */
public class HtmlTransformerTest extends PlainTestCase {
    public HtmlTransformer htmlTransformer;

    @Override
    protected void setUp() throws Exception {
        super.setUp();
        htmlTransformer = new HtmlTransformer();
        htmlTransformer.setName("htmlTransformer");
        Map<String, String> featureMap = newHashMap();

     * This method fetches URLs from the queue, accesses content, processes responses,
     * and extracts child URLs until the crawling process is done or no more URLs are available.
     */
    @Override
    public void run() {
        log(logHelper, LogType.START_THREAD, crawlerContext);
        int threadCheckCount = 0;
        // set urlQueue to thread
        CrawlingParameterUtil.setCrawlerContext(crawlerContext);

        }
    }

    /**
     * Returns a string representation of this object.
     * @return A string representation.
     */
    @Override
    public String toString() {
        return "RobotsTxt [directiveMap=" + directiveMap + ", sitemapList=" + sitemapList + "]";
    }

     *
     * @param in the input stream to extract text from
     * @param params additional parameters
     * @return the extracted data
     * @throws ExtractException if extraction fails
     */
    @Override
    public ExtractData getText(final InputStream in, final Map<String, String> params) {
        if (logger.isDebugEnabled()) {
            logger.debug("Accessing {}", url);
        }

        // start