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

import java.io.IOException;
import java.io.Reader;
import java.io.StringReader;

import org.codelibs.core.lang.StringUtil;
import org.codelibs.fess.crawler.util.TextUtil.TextNormalizeContext;
import org.dbflute.utflute.core.PlainTestCase;

/**
 * @author shinsuke

 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND,
 * either express or implied. See the License for the specific language
 * governing permissions and limitations under the License.
 */
package org.codelibs.fess.crawler.extractor.impl;

import java.util.regex.Pattern;

/**
 * Extracts text content from XML documents.
 */
public class XmlExtractor extends AbstractXmlExtractor {

    /**

        scheduledJobBhv.insertOrUpdate(scheduledJob, op -> {
            op.setRefreshPolicy(Constants.TRUE);
        });
    }

    /**
     * Gets a list of crawler jobs.
     * @return A list of crawler jobs.
     */
    public List<ScheduledJob> getCrawlerJobList() {
        return scheduledJobBhv.selectList(cb -> {
            cb.query().setCrawler_Equal(Constants.T);

                        fessConfig.getIndexDocumentCrawlerIndex() + ".filter")
                .execute(ActionListener.wrap(res -> logger.info("Deleted .crawler indices."),
                        e -> logger.warn("Failed to delete .crawler.* indices.", e)));
        saveInfo(messages -> messages.addSuccessStartedDataUpdate(GLOBAL));
        return redirect(getClass());
    }

    /**

 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND,
 * 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.util.List;

/**
 * @author shinsuke
 *
 */
public class TestEntity {
    private String title;

    private String body;

    private List<String> list;

import org.codelibs.fess.app.web.base.login.FessLoginAssist;
import org.codelibs.fess.crawler.builder.RequestDataBuilder;
import org.codelibs.fess.crawler.client.CrawlerClient;
import org.codelibs.fess.crawler.client.CrawlerClientFactory;
import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.crawler.util.CharUtil;
import org.codelibs.fess.entity.FacetQueryView;
import org.codelibs.fess.entity.HighlightInfo;

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

/**
 * The UrlQueue interface represents a queue of URLs to be processed by a web crawler.
 * It provides methods to get and set various properties of a URL queue entry.
 *
 * @param <IDTYPE> the type of the identifier for the URL queue entry
 */

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

import java.util.Map;

import org.codelibs.core.lang.ThreadUtil;

/**
 * Default implementation of the IntervalController.
 * This class provides a default way to manage delays between crawler operations.
 * It allows setting delays before processing, after processing, when no URLs are in the queue,

 * 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 org.codelibs.fess.crawler.Constants;
import org.dbflute.utflute.core.PlainTestCase;

/**
 * Test class for {@link AccessResultImpl}.
 */
public class AccessResultImplTest extends PlainTestCase {

 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND,
 * either express or implied. See the License for the specific language
 * governing permissions and limitations under the License.
 */
package org.codelibs.fess.crawler.serializer;

import java.io.ByteArrayInputStream;
import java.io.ByteArrayOutputStream;
import java.io.IOException;

import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;