}
    }

    /**
     * Gets the mail properties used for email processing.
     *
     * @return the mail properties
     */
    public Properties getMailProperties() {
        return mailProperties;
    }

    /**
     * Sets the mail properties used for email processing.
     *
     * @param mailProperties the mail properties to set
     */

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

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

/**
 * The RuleManager interface provides methods to manage rules for processing response data.
 * It allows adding, retrieving, and removing rules, as well as checking for their existence.
 */
public interface RuleManager {

    /**
     * Retrieves the rule associated with the given response data.

 *
 * <p>
 * A Sitemap file provides search engines with a list of URLs available for crawling.
 * This class encapsulates the essential attributes of a Sitemap entry, allowing for efficient management
 * and processing of Sitemap data.
 * </p>
 *
 * <p>
 * The {@code loc} attribute specifies the URL of the Sitemap, while the {@code lastmod} attribute

            } catch (final Exception e) {
                if (logger.isDebugEnabled()) {
                    logger.debug("Exception on SID processing.", e);
                }
            }
        }
    }

    /**
     * Preprocesses the URI before processing the request.
     *
     * @param uri the URI to preprocess
     * @return the preprocessed URI

 * <p>
 * The {@link ContentWriter} functional interface is used to abstract the process of writing content to a writer.
 * </p>
 *
 * <p>
 * The class uses temporary files for processing large input streams and ensures that these files are deleted after
 * processing.
 * </p>
 *
 */
public class TikaExtractor extends PasswordBasedExtractor {

    private static final Logger logger = LogManager.getLogger(TikaExtractor.class);

import jakarta.annotation.Resource;

/**
 * The {@code CrawlerThread} class represents a thread that executes the crawling process.
 * It is responsible for fetching URLs from the queue, accessing the content,
 * processing the response, and extracting child URLs.
 *
 * <p>
 * This class implements the {@link Runnable} interface, allowing it to be executed in a separate thread.

    /**
     * Initializes the access result with response data and result data.
     *
     * @param responseData The response data from the crawl operation.
     * @param resultData The result data from content processing.
     */
    @Override
    public void init(final ResponseData responseData, final ResultData resultData) {

        setCreateTime(System.currentTimeMillis());
        if (responseData != null) {

 *
 * <p>The factory maintains a map of regular expression patterns to crawler clients,
 * allowing for URL-based client selection. Clients can be added with specific patterns
 * and optionally at specific positions in the processing order.</p>
 *
 * <p>This factory is typically initialized through dependency injection and can be
 * configured with initialization parameters that are passed to all registered clients.</p>
 *
 * <p>Features:</p>

                throw new ExtractException(e);
            }
        }

        return encoding;
    }

    /**
     * Extracts text content from the given content by removing tags and processing attributes.
     * @param content The content to extract from.
     * @return The extracted text.
     */
    protected String extractString(final String content) {

 *
 * <p>
 * The main purpose of this class is to simplify the extraction process by providing a fluent interface
 * for configuring the extraction parameters and handling the underlying complexities of content processing,
 * such as MIME type detection, extractor selection, and content length validation.
 * </p>
 *
 * <p>
 * Example usage:
 * </p>
 *
 * <pre>
 * {@code