<components namespace="fessCrawler">

	<component class="org.lastaflute.di.naming.StyledNamingConvention">
	</component>

	<!-- Container -->
	<component name="crawlerContainer"
		class="org.codelibs.fess.crawler.container.LastaCrawlerContainer">
	</component>

                                        <td><c:if test="${crawler=='on'}">
                                            <la:message key="labels.enabled"/>
                                        </c:if> <c:if test="${crawler!='on'}">
                                            <la:message key="labels.disabled"/>
                                        </c:if> <la:hidden property="crawler"/></td>
                                    </tr>

<!DOCTYPE components PUBLIC "-//DBFLUTE//DTD LastaDi 1.0//EN" 
	"http://dbflute.org/meta/lastadi10.dtd">
<components namespace="fessCrawler">
	<component name="urlQueueService"
		class="org.codelibs.fess.crawler.service.FessUrlQueueService">
		<arg>crawlerConfig</arg>
	</component>

{
  "title": "Sample Document",
  "author": "John Doe",
  "version": "1.0",
  "published": "2025-01-15",
  "tags": ["crawler", "extractor", "json"],
  "content": {
    "summary": "This is a sample JSON document for testing",
    "body": "The extractor should handle nested objects and arrays properly"
  },
  "metadata": {
    "created_at": "2025-01-01T00:00:00Z",
    "updated_at": "2025-01-15T12:00:00Z"
  }

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

import org.codelibs.fess.crawler.container.StandardCrawlerContainer;
import org.dbflute.utflute.core.PlainTestCase;

/**
 * @author shinsuke
 *
 */
public class UrlConvertHelperTest extends PlainTestCase {

    /**
     * Add an url pattern as a target.
     *
     * @param urlPattern Regular expression that is crawled
     */
    void addInclude(String urlPattern);

    /**
     * Add an url pattern as a non-target.
     *
     * @param urlPattern Regular expression that is not crawled
     */
    void addExclude(String urlPattern);

    /**
     * Process an url when it's added as a seed url.
     *

 */
package org.codelibs.fess.crawler.transformer.impl;

import java.util.ArrayList;
import java.util.List;
import java.util.concurrent.CountDownLatch;
import java.util.concurrent.ExecutorService;
import java.util.concurrent.Executors;
import java.util.concurrent.TimeUnit;
import java.util.concurrent.atomic.AtomicInteger;

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

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

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

/**
 * The RuleManager interface provides methods to manage rules for processing response data.

/*
 [Crawler Notification]
*/
subject: [FESS] Status Change: /*pmb.hostname:orElse('Unknown')*/
>>>
--- Server Info ---
Cluster Name: /*pmb.clustername:orElse('Unknown')*/
Host Name: /*pmb.hostname:orElse('Unknown')*/

--- Status ---

import org.codelibs.fess.crawler.exception.ChildUrlsException;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.exception.CrawlingAccessException;
import org.codelibs.fess.crawler.exception.MaxLengthExceededException;
import org.codelibs.fess.crawler.helper.ContentLengthHelper;
import org.codelibs.fess.crawler.helper.impl.MimeTypeHelperImpl;