/**
 * {@link HtmlXpathExtractor} is an implementation of the {@link org.codelibs.fess.crawler.extractor.Extractor} interface.
 * It uses XPath expressions to extract text content from HTML documents.
 * <p>
 * This class provides methods to configure the XPath expressions, parser features, and properties.
 * It also includes caching mechanism for XPathAPI instances to improve performance.
 * </p>
 * <p>

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.service.UrlFilterService;

import jakarta.annotation.Resource;

/**
 * Implementation of the {@link UrlFilterService} interface.
 * This class provides methods for managing URL filtering rules,
 * including adding include and exclude URL patterns, deleting patterns,
 * and retrieving lists of compiled URL patterns. It utilizes a

import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.interval.IntervalController;

/**
 * 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.

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

/**
 * RobotsTxtException is an exception class that represents an error related to robots.txt processing during web crawling.
 * It extends CrawlerSystemException and provides constructors to create instances with a message and/or a cause.
 *
 */
public class RobotsTxtException extends CrawlerSystemException {

    private static final long serialVersionUID = 1L;

    /**

 * It also provides a method to retrieve the extracted data as a String from an AccessResultData object.
 *
 * <p>
 * The class handles character encoding issues by attempting to use the specified charset.
 * If the specified charset is invalid, it falls back to UTF-8.
 * </p>
 *
 * <p>

/**
 * An exception that indicates multiple crawling access exceptions occurred.
 * This exception holds an array of Throwable objects representing the individual causes.
 * It extends CrawlingAccessException and provides methods to print the stack traces of all causes.
 *
 */
public class MultipleCrawlingAccessException extends CrawlingAccessException {

    private static final long serialVersionUID = 1L;

    /**

import org.codelibs.fess.crawler.util.AccessResultCallback;

import jakarta.annotation.Resource;

/**
 * Implementation of the {@link DataService} interface for managing access result data.
 * This class provides methods to store, retrieve, update, and delete access results,
 * as well as to iterate over them. It uses a {@link MemoryDataHelper} to store the data in memory.
 *
 * <p>

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

/**
 * Exception thrown during sitemaps processing in the crawler.
 * This exception extends {@link org.codelibs.fess.crawler.exception.CrawlerSystemException}
 * and provides constructors for wrapping other exceptions or creating a new exception with a message.
 */
public class SitemapsException extends CrawlerSystemException {
    private static final long serialVersionUID = 1L;

    /**

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

/**
 * Configuration class for OpenSearch crawler settings.
 * This class provides configuration for index names, shards, and replicas
 * for the queue, data, and filter indices used by the crawler.
 */
public class OpenSearchCrawlerConfig {
    /**
     * Constructs a new OpenSearchCrawlerConfig.