<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE components PUBLIC "-//DBFLUTE//DTD LastaDi 1.0//EN"
	"http://dbflute.org/meta/lastadi10.dtd">
<components namespace="fessCrawler">
	<include path="crawler/container.xml" />

	<component name="logHelper"
		class="org.codelibs.fess.helper.CrawlerLogHelper">
	</component>

            false, "Boolean", 0, 0, null, null, false, null, null, null, null, null, false);
    protected final ColumnInfo _columnCrawler = cci("crawler", "crawler", null, null, Boolean.class, "crawler", null, false, false, false,
            "Boolean", 0, 0, null, null, false, null, null, null, null, null, false);

import org.codelibs.core.lang.StringUtil;
import org.codelibs.fess.crawler.Constants;
import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.exception.ExtractException;
import org.codelibs.fess.crawler.extractor.Extractor;
import org.codelibs.fess.crawler.util.TextUtil;
import org.xml.sax.ContentHandler;
import org.xml.sax.SAXException;

<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>

import com.google.common.cache.Cache;
import com.google.common.cache.CacheBuilder;

import jakarta.annotation.PostConstruct;

/**
 * Helper class for managing crawling configurations.
 * Provides functionality to store, retrieve, and manage different types of crawling configurations
 * including web, file, and data configurations. Supports caching and session-based configuration management.
 */
public class CrawlingConfigHelper {

    private int currentPageNumber;

    /**
     * Crawling information ID.
     */
    public String id;

    /**
     * Session ID for the crawling session.
     */
    public String sessionId;

    /**
     * Creation time of the crawling information.
     */
    public String createdTime;

    /**
     * Clears all pagination state and crawling information fields.

{
  "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 {