/**
 * 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
 * should also handle resource cleanup when the {@link #close()} method is called.</p>
 */
public interface DocumentReader extends Closeable {

     *  a number of objects each time it is called.  This could be optimized
     *  to keep the same objects around, but then thread-safety issues would arise.
     *
     *  @param contextNode The node to start searching from.
     *  @param expression A valid XPath string.
     *  @return An XPathEvaluationResult, which can be used to obtain a string, number, nodelist, etc, should never be null.
     *

    /**
     * Adds a rule to the specified index.
     *
     * @param index the position at which the rule should be added
     * @param rule the rule to be added
     */
    /**
     * Adds a rule to the specified index.
     *
     * @param index the position at which the rule should be added
     * @param rule the rule to be added
     */
    void addRule(int index, Rule rule);

    /**

 * {@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 {

 * and provides getter and setter methods for common properties such as
 * {@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 {

 * governing permissions and limitations under the License.
 */
package org.codelibs.fess.suggest.normalizer;

/**
 * An interface for normalizing text.
 * Implementations of this interface should provide a method to normalize
 * a given text based on the specified field and optional language parameters.
 */
public interface Normalizer {
    /**
     * Normalizes the given text.

    /**
     * Identifies the time that the corresponding Sitemap file was modified. It
     * does not correspond to the time that any of the pages listed in that
     * Sitemap were changed. The value for the lastmod tag should be in W3C
     * Datetime format.
     *
     * By providing the last modification timestamp, you enable search engine
     * crawlers to retrieve only a subset of the Sitemaps in the index i.e. a

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 {

    /**

 *     String name = header.getName();
 *     String value = header.getValue();
 *     boolean isValid = header.isValid();
 * </pre>
 *
 * <p>Note: The name should not be blank and the value should not be null for the header to be considered valid.</p>
 *
 * @see java.io.Serializable
 */
public class RequestHeader implements Serializable {

    private static final long serialVersionUID = 1L;

     */
    protected abstract void delayForWaitingNewUrl();

    /**
     * Checks if exceptions during the delay process should be ignored.
     * @return true if exceptions should be ignored, false otherwise.
     */
    public boolean isIgnoreException() {
        return ignoreException;
    }

    /**
     * Sets whether to ignore exceptions.