* 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.

import org.codelibs.fess.crawler.Constants;
import org.codelibs.fess.crawler.container.CrawlerContainer;
import org.codelibs.fess.crawler.entity.AccessResultData;
import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.crawler.entity.ResultData;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.exception.CrawlingAccessException;

 * either express or implied. See the License for the specific language
 * governing permissions and limitations under the License.
 */
package org.codelibs.fess.crawler.entity;

import java.io.Serializable;

/**
 * The Sitemap interface represents a sitemap entity with location and last modification date.
 * It extends the Serializable interface to allow sitemap objects to be serialized.
 */
public interface Sitemap extends Serializable {

        return xmlEncodingPattern;
    }

    /**
     * Returns the precompiled {@link Pattern} used to match XML tags within the content.
     * This pattern is utilized by the extractor to identify and process XML elements.
     *
     * @return the {@link Pattern} instance for XML tag matching
     */
    @Override
    protected Pattern getTagPattern() {
        return xmlTagPattern;
    }

    /**

     * @param entity The HTTP entity containing the token page content.
     */
    protected void parseTokenPage(final String tokenPattern, final List<Pair<String, String>> responseParams, final HttpEntity entity) {
        try {
            final String tokenName = getParameter(TOKEN_NAME);
            final String content = new String(InputStreamUtil.getBytes(entity.getContent()), Constants.UTF_8_CHARSET);

 *   <li>org.codelibs.fess.crawler.exception.CrawlerSystemException</li>
 *   <li>org.codelibs.fess.crawler.entity.AccessResultData</li>
 *   <li>org.codelibs.core.lang.StringUtil</li>
 * </ul>
 *
 * @see org.codelibs.fess.crawler.Constants
 * @see org.codelibs.fess.crawler.exception.CrawlerSystemException
 * @see org.codelibs.fess.crawler.entity.AccessResultData
 * @see org.codelibs.core.lang.StringUtil
 */
public final class XmlUtil {

import org.codelibs.fess.crawler.builder.RequestDataBuilder;
import org.codelibs.fess.crawler.container.CrawlerContainer;
import org.codelibs.fess.crawler.entity.AccessResultData;
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.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.exception.CrawlingAccessException;

import java.io.InputStream;

import org.codelibs.core.io.ResourceUtil;
import org.codelibs.fess.crawler.container.StandardCrawlerContainer;
import org.codelibs.fess.crawler.entity.Sitemap;
import org.codelibs.fess.crawler.entity.SitemapSet;
import org.codelibs.fess.crawler.entity.SitemapUrl;
import org.codelibs.fess.crawler.exception.CrawlingAccessException;
import org.dbflute.utflute.core.PlainTestCase;

/**
 * @author shinsuke
 *
 */

      "Licensor" shall mean the copyright owner or entity authorized by
      the copyright owner that is granting the License.

      "Legal Entity" shall mean the union of the acting entity and all
      other entities that control, are controlled by, or are under common
      control with that entity. For the purposes of this definition,
      "control" means (i) the power, direct or indirect, to cause the

import org.apache.logging.log4j.Logger;
import org.codelibs.core.lang.StringUtil;
import org.codelibs.fess.crawler.Constants;
import org.codelibs.fess.crawler.entity.SitemapFile;
import org.codelibs.fess.crawler.entity.SitemapSet;
import org.codelibs.fess.crawler.entity.SitemapUrl;
import org.codelibs.fess.crawler.exception.CrawlingAccessException;
import org.codelibs.fess.crawler.exception.SitemapsException;
import org.xml.sax.Attributes;