* <p>
 * This class uses a {@link SitemapsHelper} to parse the sitemap XML or text.
 * It then iterates through the sitemaps in the SitemapSet, extracts the URL
 * from each sitemap, and creates a new {@link RequestData} object for each URL.
 * These RequestData objects are added to a set of child URLs, which are then
 * passed to a {@link ChildUrlsException} to be processed by the crawler.
 * </p>
 *
 * <p>

     * The input object can be either a single string or a list of strings representing URLs.
     *
     * @param obj the object containing anchor URLs (String or List of Strings)
     * @return a set of RequestData objects for the anchor URLs, or null if no valid URLs found
     */
    protected Set<RequestData> getAnchorSet(final Object obj) {

            fail();
        } catch (final ChildUrlsException e) {
            final Set<RequestData> urlSet = e.getChildUrlList();
            assertEquals(1, urlSet.size());
            for (final RequestData requestData : urlSet.toArray(new RequestData[urlSet.size()])) {
                String url = requestData.getUrl();
                assertTrue(url.contains("dir1/test3.txt"));
            }
        } finally {

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

import java.util.Map;

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

/**
 * Interface representing a client for a web crawler.
 * This client is responsible for executing requests and handling responses.

     */
    @Override
    protected List<RequestData> convertChildUrlList(final List<RequestData> urlList) {
        if (urlList != null) {
            final PathMappingHelper pathMappingHelper = getPathMappingHelper();
            for (final RequestData requestData : urlList) {
                String url = requestData.getUrl();

import org.codelibs.fess.crawler.client.smb.SmbClient;
import org.codelibs.fess.crawler.client.storage.StorageClient;
import org.codelibs.fess.crawler.container.StandardCrawlerContainer;
import org.codelibs.fess.crawler.entity.RequestData;
import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.crawler.helper.impl.MimeTypeHelperImpl;
import org.dbflute.utflute.core.PlainTestCase;

/**
 * @author shinsuke
 *
 */

import java.util.Map;

import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
import org.codelibs.fess.crawler.container.CrawlerContainer;
import org.codelibs.fess.crawler.entity.RequestData;
import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.exception.MaxLengthExceededException;

import org.codelibs.fess.crawler.builder.RequestDataBuilder;
import org.codelibs.fess.crawler.client.AbstractCrawlerClient;
import org.codelibs.fess.crawler.client.AccessTimeoutTarget;
import org.codelibs.fess.crawler.entity.RequestData;
import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.crawler.exception.ChildUrlsException;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;

import org.codelibs.fess.crawler.CrawlerContext;
import org.codelibs.fess.crawler.container.CrawlerContainer;
import org.codelibs.fess.crawler.entity.AccessResult;
import org.codelibs.fess.crawler.entity.RequestData;
import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.crawler.entity.ResultData;
import org.codelibs.fess.crawler.entity.UrlQueue;
import org.codelibs.fess.crawler.processor.ResponseProcessor;

import org.codelibs.fess.crawler.builder.RequestDataBuilder;
import org.codelibs.fess.crawler.client.AbstractCrawlerClient;
import org.codelibs.fess.crawler.client.AccessTimeoutTarget;
import org.codelibs.fess.crawler.entity.RequestData;
import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.crawler.exception.ChildUrlsException;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;