import java.io.Closeable;
import java.util.Map;

/**
 * Interface for reading documents and extracting their contents into a map.
 * Implementations of this interface should provide the logic for reading
 * documents and converting them into a key-value structure.
 *
 * <p>This interface extends {@link java.io.Closeable}, so implementations

/**
 * 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 {

    /**

import java.util.Map;

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

/**
 * The Extractor interface defines methods for extracting text data from an input stream.
 * Implementations of this interface should provide the logic for extracting text and
 * optionally override the default weight value.
 */
public interface Extractor {

    /**
     * Extracts text data from the given input stream.
     *

import org.codelibs.fess.crawler.exception.MaxLengthExceededException;
import org.codelibs.fess.crawler.exception.MultipleCrawlingAccessException;

/**
 * A fault-tolerant wrapper for CrawlerClient that implements retry logic for failed requests.
 * This client will attempt to execute requests multiple times before giving up, with configurable
 * retry counts and intervals between attempts.
 *

 * {@link CrawlerContainer}. It also provides a convenient method for
 * registering the extractor with the {@link ExtractorFactory}.
 * </p>
 *
 * <p>
 * Subclasses should implement the actual extraction logic in their own
 * methods, leveraging the helper methods provided by this abstract class.
 * </p>
 *
 */
public abstract class AbstractExtractor implements Extractor {

    /** The crawler container. */
    @Resource

 * {@code ruleId} and {@code responseProcessor}.
 * </p>
 *
 * <p>
 * Subclasses should extend this class and implement the abstract methods
 * defined in the {@link Rule} interface to provide specific rule logic.
 * </p>
 *
 */
public abstract class AbstractRule implements Rule {

    private static final long serialVersionUID = 1L;

    /** The rule ID. */
    protected String ruleId;

/**
 * An abstract base class for implementing {@link IntervalController}.
 * Provides a common structure for handling delays at different stages of the crawling process.
 * It encapsulates the delay logic and exception handling, allowing subclasses to focus on
 * defining the specific delay behavior for each stage.
 *
 * <p>
 * This class defines the contract for delaying the crawling process at various points, such as:
 * </p>

```java
public class CustomExtractor extends AbstractExtractor {
    @Override
    public ExtractData getText(final InputStream inputStream, final Map<String, String> params) {
        // Custom extraction logic
        ExtractData extractData = new ExtractData();
        // ... implementation
        return extractData;
    }
}

// Register custom extractor

        responseData3.setHttpStatusCode(500);
        assertFalse(rule.match(responseData3));
    }

    /**
     * Test ConfigurableRule with multiple conditions (AND logic)
     */
    public void test_configurableRule_multipleConditions() {
        ConfigurableRule rule = new ConfigurableRule();
        rule.setRuleId("multiRule");

        final Settings settings = Settings.builder().putList("http.hosts", hosts).build();
        return new HttpClient(settings, null);
    }

    /**
     * Executes an OpenSearch operation with retry logic.
     *
     * @param <T> The response type.
     * @param func The function to execute.
     * @return The response from the operation.
     */