* 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>
 * <ul>
 *   <li>Before processing a URL ({@link #delayBeforeProcessing()})</li>

package org.codelibs.fess.crawler.rule;

import java.io.Serializable;

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

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

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

/**
 * The ResponseProcessor interface defines a contract for processing response data.
 * Implementations of this interface are responsible for handling the response data
 * obtained during a crawling process.
 */
public interface ResponseProcessor {

    /**

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

/**
 * LogType defines the different types of log messages that can be generated during the crawling process.
 * Each enum constant represents a specific event or state in the crawler's execution.
 */
public enum LogType {

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

/**
 * The {@code IntervalController} interface defines methods for controlling
 * the delay intervals in a web crawler. It includes constants representing
 * different types of processing states and a method to introduce a delay
 * based on the type of processing.
 * <p>

 */
package org.codelibs.fess.crawler.extractor;

import java.io.InputStream;
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 {

# EditorConfig helps developers define and maintain consistent
# coding styles between different editors and IDEs
# editorconfig.org

root = true

[*]

indent_style = space
indent_size = 4


end_of_line = lf
charset = utf-8
trim_trailing_whitespace = true
insert_final_newline = true

# Markdown files sometimes need trailing whitespaces.
[*.md]
trim_trailing_whitespace = false

[*.{yml,yaml}]
indent_size = 2

 * represents a valid sitemap. It uses a SitemapsHelper to validate the response body as an InputStream.
 * The rule checks if the URL matches the defined regex pattern and then validates the content as a sitemap.
 * If any exception occurs during the sitemap validation, it logs the error and returns false.
 *
 */
public class SitemapsRule extends RegexRule {
    /**

import org.codelibs.fess.crawler.entity.AccessResultData;
import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.crawler.entity.ResultData;

/**
 * The Transformer interface defines methods for transforming response data
 * and retrieving data from access results.
 */
public interface Transformer {

    /**
     * Transforms the given ResponseData into a ResultData.
     *

 * 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 {

    private static final long serialVersionUID = 1L;

    /** The rule ID. */