import org.codelibs.fess.crawler.service.UrlFilterService;

import jakarta.annotation.Resource;

/**
 * Implementation of the {@link UrlFilter} interface.
 * This class provides functionality to filter URLs based on include and exclude patterns.
 * It uses a {@link UrlFilterService} to manage the URL filtering rules.
 * The class supports caching of include and exclude patterns for scenarios where a session ID is not available.

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

/**
 * The UrlQueue interface represents a queue of URLs to be processed by a web crawler.
 * It provides methods to get and set various properties of a URL queue entry.
 *
 * @param <IDTYPE> the type of the identifier for the URL queue entry
 */
public interface UrlQueue<IDTYPE> {

 *   <li>writeTimeout - Write timeout in milliseconds (default: 10000)</li>
 *   <li>readTimeout - Read timeout in milliseconds (default: 10000)</li>
 * </ul>
 *
 * <p>The client supports URLs in the format: {@code storage://bucket-name/object-path}
 *
 * <p>Features:
 * <ul>
 *   <li>Automatic initialization of MinIO client</li>
 *   <li>Support for HEAD and GET operations</li>

    /** Map of session IDs to include URL patterns for filtering URLs. */
    protected volatile Map<String, List<Pattern>> includeUrlPatternMap = new HashMap<>();

    /** Map of session IDs to exclude URL patterns for filtering URLs. */
    protected volatile Map<String, List<Pattern>> excludeUrlPatternMap = new HashMap<>();

    /**

                            }
                        }
                    } catch (final Exception e) {
                        logger.warn(e.getLocalizedMessage());
                    }
                    buf.reset();
                } else {
                    buf.write(b);
                }
            }
        }));
    }

    /** The charset used for encoding and decoding. */

    private CrawlerPooledObjectFactory<TestComponent> factory;
    private StandardCrawlerContainer container;

    @Override
    protected void setUp() throws Exception {
        super.setUp();

        // Reset counters before each test
        TestComponent.resetCounter();
        SingletonTestComponent.resetInstanceCount();

        // Initialize container with test components

 *
 * <p>This class is final and cannot be instantiated.</p>
 *
 * <p>The following parameters are managed:</p>
 * <ul>
 *   <li>{@link UrlQueue} - The queue of URLs to be crawled.</li>
 *   <li>{@link CrawlerContext} - The context of the current crawling process.</li>
 *   <li>{@link UrlQueueService} - The service for managing the URL queue.</li>

/**
 * Handler for the "storage" protocol, allowing access to objects stored in a MinIO-compatible storage service.
 * This handler extends {@link URLStreamHandler} to provide a way to open connections to storage objects
 * using URLs with the "storage" protocol.
 *
 * <p>
 * The URL format is expected to be: {@code storage://bucketName/objectName}.
 * The bucket name and object name are extracted from the URL.
 * </p>
 *
 * <p>

        public int getProcessCount() {
            return processCount;
        }

        public ResponseData getLastProcessedData() {
            return lastProcessedData;
        }

        public void reset() {
            processCount = 0;
            lastProcessedData = null;
        }
    }

    private StandardCrawlerContainer container;
    private TestRuleManager ruleManager;

     * @return the response data
     * @throws CrawlingAccessException if unable to access the URI
     * @throws ChildUrlsException if the URI represents a directory with child URLs
     */
    protected ResponseData getResponseData(final String uri, final boolean includeContent) {
        final ResponseData responseData = new ResponseData();
        try {