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

/**
 * UrlFilter checks if a given url is a target one.
 *
 * @author shinsuke
 *
 */
public interface UrlFilter {

    /**
     * Initialize a url filter by sessionId.
     *
     * @param sessionId Session ID
     */
    void init(String sessionId);

    /**

        crawler.crawlerContext.setMaxThreadCheckCount(3);
        crawler.crawlerContext.setMaxAccessCount(maxCount);
        crawler.crawlerContext.setNumOfThread(numOfThread);
        crawler.urlFilter.addInclude(url + ".*");
        crawler.urlFilter.addExclude(url + "/dir1/.*");
        final String sessionId = crawler.execute();
        assertEquals(maxCount, dataService.getCount(sessionId));
        dataService.delete(sessionId);
    }

        crawler.crawlerContext.setMaxThreadCheckCount(3);
        crawler.crawlerContext.setMaxAccessCount(maxCount);
        crawler.crawlerContext.setNumOfThread(numOfThread);
        crawler.urlFilter.addInclude(url + ".*");
        crawler.urlFilter.addExclude(url + "/dir1/.*");
        final String sessionId = crawler.execute();
        assertEquals(maxCount, dataService.getCount(sessionId));
        dataService.delete(sessionId);
    }

        assertEquals(0, urlFilter.cachedIncludeSet.size());
        assertEquals(0, urlFilter.cachedExcludeSet.size());

        urlFilter.addExclude(".*[test.*");

        assertEquals(0, urlFilter.cachedIncludeSet.size());
        assertEquals(0, urlFilter.cachedExcludeSet.size());

        final String sessionId = "id1";
        urlFilter.init(sessionId);
        assertEquals(0, urlFilter.cachedIncludeSet.size());

                .singleton("urlFilter", UrlFilterImpl.class)//
                .singleton("robotsTxtHelper", RobotsTxtHelper.class)//
                .singleton("httpClient", HcHttpClient.class);
        httpClient = container.getComponent("httpClient");
        urlFilter = container.getComponent("urlFilter");
    }

    public void test_doGet() {

    }

    public void setUrlFilter(final UrlFilter urlFilter) {
        this.urlFilter = urlFilter;
    }

    public RuleManager getRuleManager() {
        return ruleManager;
    }

    public void setRuleManager(final RuleManager ruleManager) {
        this.ruleManager = ruleManager;
    }

    public IntervalController getIntervalController() {
        return intervalController;
    }

import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.filter.UrlFilter;
import org.codelibs.fess.crawler.service.UrlFilterService;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;

import jakarta.annotation.Resource;

/**
 * @author shinsuke
 *
 */
public class UrlFilterImpl implements UrlFilter {

    private static final Logger logger = LoggerFactory.getLogger(UrlFilterImpl.class);

        return status;
    }

    public void setStatus(final CrawlerStatus status) {
        this.status = status;
    }

    public UrlFilter getUrlFilter() {
        return urlFilter;
    }

    public void setUrlFilter(final UrlFilter urlFilter) {
        this.urlFilter = urlFilter;
    }

    public RuleManager getRuleManager() {
        return ruleManager;
    }

            crawler.addUrl(url);
            crawler.getCrawlerContext().setMaxAccessCount(maxCount);
            crawler.getCrawlerContext().setNumOfThread(numOfThread);
            crawler.urlFilter.addInclude(url + ".*");
            final String sessionId = crawler.execute();
            assertEquals(maxCount, dataService.getCount(sessionId));
            dataService.delete(sessionId);
        } finally {

        final List<UrlQueue<?>> childList = childUrlList.stream().filter(d -> StringUtil.isNotBlank(d.getUrl())
                && urlSet.add(d.getUrl() + "\n" + d.getMetaData()) && crawlerContext.urlFilter.match(d.getUrl())).map(d -> {
                    final UrlQueue<?> uq = crawlerContainer.getComponent("urlQueue");
                    uq.setCreateTime(SystemUtil.currentTimeMillis());
                    uq.setDepth(depth);