final ResponseData responseData = new ResponseData();
        responseData.setUrl("http://example.com/test.xml");
        File file = ResourceUtil.getResourceAsFile("sitemaps/sitemap1.xml");
        responseData.setResponseBody(file, false);
        return responseData;
    }

    private ResponseData getTestData2_FAIL() {
        final ResponseData responseData = new ResponseData();

     * (non-Javadoc)
     *
     * @see
     * org.codelibs.fess.crawler.transformer.impl.AbstractTransformer#transform(org.fess.crawler.entity.ResponseData)
     */
    @Override
    public ResultData transform(final ResponseData responseData) {
        if (responseData == null || !responseData.hasResponseBody()) {
            throw new CrawlingAccessException("No response body.");
        }

 * rule.addRule("contentType", "text/html");
 * rule.setAllRequired(true); // Both URL and content type must match
 *
 * ResponseData responseData = new ResponseData();
 * responseData.setUrl("https://example.com/page1");
 * responseData.setContentType("text/html");
 *
 * boolean matches = rule.match(responseData); // Returns true
 * }
 * </pre>
 *
 */
public class RegexRule extends AbstractRule {

     *
     * @param responseData the response data from the crawled resource
     * @param resultData the result data to be processed
     * @return the access result containing the processed data
     */
    @Override
    protected AccessResult<?> createAccessResult(final ResponseData responseData, final ResultData resultData) {
        return super.createAccessResult(responseData, ingest(responseData, resultData));
    }

     * @param responseData The response data.
     */
    protected void checkMaxContentLength(final ResponseData responseData) {
        if (maxContentLength != null && responseData.getContentLength() > maxContentLength.longValue()) {
            throw new MaxLengthExceededException("The content length (" + responseData.getContentLength() + " byte) is over "

     *
     * @param responseData the response data containing the document to extract
     * @return the extractor instance for processing the document
     * @throws FessSystemException if no suitable extractor can be found
     */
    @Override
    protected Extractor getExtractor(final ResponseData responseData) {

        final byte[] data = new String("xyz").getBytes();
        final ResponseData responseData = new ResponseData();
        responseData.setUrl("http://www.example.com/submit?a=1&b=2");
        responseData.setResponseBody(data);
        responseData.setCharSet("UTF-8");
        setBaseDir();
        final ResultData resultData = fileTransformer.transform(responseData);

import org.codelibs.fess.crawler.entity.ResponseData;

/**
 * The ResponseProcessor interface defines a contract for processing response data.
 * Implementations of this interface are responsible for handling the response data
 * obtained during a crawling process.
 */
public interface ResponseProcessor {

    /**
     * Processes the given response data.
     *
     * @param responseData the response data to be processed
     */

        responseData.setResponseBody(file, false);
        final Rule rule = ruleManager.getRule(responseData);
        assertNotNull(rule);
        assertEquals("sitemapsRule", rule.getRuleId());
        CloseableUtil.closeQuietly(responseData);
    }

    public void test_getRule_sitemaps2() {
        final ResponseData responseData = new ResponseData();
        responseData.setUrl("http://www.example.com/sitemap1.xml.gz");

        };
        ResponseData responseData = new ResponseData();
        responseData.setUrl("http://test.com/");

        client.checkMaxContentLength(responseData);

        responseData.setContentLength(-1);
        client.checkMaxContentLength(responseData);

        responseData.setContentLength(1000L);
        client.checkMaxContentLength(responseData);

        responseData.setContentLength(1000000L);