factory.setFeature(org.codelibs.fess.crawler.Constants.FEATURE_EXTERNAL_GENERAL_ENTITIES, false);
            factory.setFeature(org.codelibs.fess.crawler.Constants.FEATURE_EXTERNAL_PARAMETER_ENTITIES, false);
            final SAXParser parser = factory.newSAXParser();
            parser.setProperty(XMLConstants.ACCESS_EXTERNAL_DTD, StringUtil.EMPTY);
            parser.setProperty(XMLConstants.ACCESS_EXTERNAL_SCHEMA, StringUtil.EMPTY);

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

/**
 * MaxLengthExceededException is thrown when the content length exceeds the maximum allowed length.
 * It extends CrawlingAccessException, indicating a crawling-related access issue.
 *
 */
public class MaxLengthExceededException extends CrawlingAccessException {

import java.util.concurrent.atomic.AtomicInteger;

import org.codelibs.core.collection.LruHashSet;
import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.crawler.filter.UrlFilter;
import org.codelibs.fess.crawler.interval.IntervalController;
import org.codelibs.fess.crawler.rule.Rule;
import org.codelibs.fess.crawler.rule.RuleManager;
import org.dbflute.utflute.core.PlainTestCase;

/**
 * Test class for CrawlerContext.

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

/**
 * RobotsTxtException is an exception class that represents an error related to robots.txt processing during web crawling.
 * It extends CrawlerSystemException and provides constructors to create instances with a message and/or a cause.
 *
 */

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

import java.util.List;

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

/**
 * Service interface for managing URL queues.
 * Provides methods for adding, retrieving, and managing URLs within a crawling session.
 *
 * @param <QUEUE> the type of URL queue
 */

import org.codelibs.fess.crawler.Constants;
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;

    /** The key of the configuration. e.g. u002eu06d4u2e3cu3002 */
    String CRAWLER_DOCUMENT_FULLSTOP_CHARS = "crawler.document.fullstop.chars";

    /** The key of the configuration. e.g. UTF-8 */
    String CRAWLER_CRAWLING_DATA_ENCODING = "crawler.crawling.data.encoding";

    /** The key of the configuration. e.g. http,https */
    String CRAWLER_WEB_PROTOCOLS = "crawler.web.protocols";

/**
 * Search request body for web crawling configuration administration API.
 */
public class SearchBody extends BaseSearchBody {

    /**
     * Default constructor.
     */
    public SearchBody() {
        super();
    }

    /** Name of the web crawling configuration */
    public String name;

    /** URLs to crawl */
    public String urls;

 * 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.io.Serializable;
import java.util.HashMap;
import java.util.Map;
import java.util.Set;

import org.apache.tika.metadata.ClimateForcast;
import org.apache.tika.metadata.CreativeCommons;

     * The script data or code for the scheduled job.
     */
    @CustomSize(maxKey = "form.admin.max.input.size")
    public String scriptData;

    /**
     * Whether this job is related to crawling.
     */
    public String crawler;

    /**
     * Whether job logging is enabled.
     */
    public String jobLogging;

    /**
     * Whether the scheduled job is available/enabled.
     */