import org.codelibs.fess.crawler.processor.ResponseProcessor;

/**
 * The Rule interface defines the contract for implementing rules that can be applied to
 * response data in a web crawler. Implementations of this interface should provide logic
 * to determine if a given response data matches the rule, retrieve the rule's identifier,
 * and obtain the associated response processor.
 */
public interface Rule extends Serializable {

        includeFilter.processUrl("http://example.com/");

        assertEquals(1, includeFilter.cachedIncludeSet.size());
        assertEquals(0, includeFilter.cachedExcludeSet.size());
        assertEquals("http://example.com/.*", includeFilter.cachedIncludeSet.toArray()[0]);

        includeFilter.processUrl("https://test.com");

    /**
     * Artifact type name for a JAR file that can be placed either on the annotation processor class path
     * or module path. The path (classes or modules) is chosen by the plugin, possibly using heuristic rules.
     */
    String PROCESSOR = "processor";

    /**
     * Artifact type name for a JAR file to unconditionally place on the annotation processor class path.
     * If the JAR is modular, its module information are ignored.
     */

        connect(con -> {
            final RequestProcessor processor = new RequestProcessor(encoding, threshold);
            processor.accept(con);
            try (final CurlResponse res = processor.getResponse()) {
                actionListener.accept(res);
            } catch (final IOException e) {
                exceptionListener.accept(e);

      assertTrue("I received an event when I wasn't ready!", ready);
      eventsReceived.add(event);
    }
  }

  public void testEventOrderingIsPredictable() {
    EventProcessor processor = new EventProcessor();
    bus.register(processor);

    EventRecorder recorder = new EventRecorder();
    bus.register(recorder);

    bus.post(FIRST);

    assertEquals(
        "EventRecorder expected events in order",

     * @return The query class name.
     */
    protected abstract String getQueryClassName();

    /**
     * Registers this query command with the query processor.
     * Associates this command with its query class name in the processor.
     */
    public void register() {
        ComponentUtil.getQueryProcessor().add(getQueryClassName(), this);
    }

    /**
     * Gets the query field configuration.

import org.codelibs.fess.crawler.exception.ChildUrlsException;
import org.codelibs.fess.crawler.helper.SitemapsHelper;
import org.codelibs.fess.crawler.processor.ResponseProcessor;

import jakarta.annotation.Resource;

/**
 * A response processor implementation that handles sitemaps.
 * It parses the response body as a SitemapSet, extracts URLs from the sitemaps,
 * and adds them as child URLs to be crawled.
 *
 * <p>

    }

    /**
     * Test processUrl method with various URL patterns
     */
    public void test_processUrl_basic() {
        String sessionId = "test-session-012";
        urlFilter.init(sessionId);

        // Process URL should handle different URL formats
        urlFilter.processUrl("https://example.com/");
        urlFilter.processUrl("http://test.com/path/to/page");

		<property name="ruleId">"sitemapsRule"</property>
		<property name="responseProcessor">
			<component
				class="org.codelibs.fess.crawler.processor.impl.SitemapsResponseProcessor">
			</component>
		</property>
		<postConstruct name="addRule">
			<arg>"url"</arg>
			<arg>".*sitemap.*"</arg>
		</postConstruct>
	</component>

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

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

/**
 * NullResponseProcessor is a class that implements the ResponseProcessor interface.