*
 * @author bowez
 * @author shinsuke
 *
 */
public class RobotsTxtHelper {

    /** Pattern for parsing user-agent records. */
    protected static final Pattern USER_AGENT_RECORD =
            Pattern.compile("^user-agent:\\s*([^\\t\\n\\x0B\\f\\r]+)\\s*$", Pattern.CASE_INSENSITIVE);

    /** Pattern for parsing disallow records. */

 * It uses SAX parser for XML sitemaps and XML sitemap indexes,
 * and handles potential exceptions during parsing.
 * The class also includes inner classes for handling XML sitemap and sitemap index parsing.
 */
public class SitemapsHelper {
    private static final Logger logger = LogManager.getLogger(SitemapsHelper.class);

    /** The size of the preload buffer for checking file format. */

                responseData.addMetaData(SMB_CREATE_TIME, new Date(file.createTime()));
                try {
                    if (logger.isDebugEnabled()) {
                        logger.debug("Parsing SmbFile Owner: {}", filePath);
                    }
                    final SID ownerUser = file.getOwnerUser();
                    if (ownerUser != null) {

                responseData.addMetaData(SMB_CREATE_TIME, new Date(file.createTime()));
                try {
                    if (logger.isDebugEnabled()) {
                        logger.debug("Parsing SmbFile Owner: {}", filePath);
                    }
                    final SID ownerUser = file.getOwnerUser();
                    if (ownerUser != null) {

            }
        } catch (final MessagingException e) {
            if (logger.isDebugEnabled()) {
                logger.debug("Exception in parsing BodyPart.", e);
            }
        }
    }

    /**
     * Gets the received date from a message by parsing the received headers.
     *
     * @param message the message to get the received date from
     * @return the received date or null if not found

 * passed to a {@link ChildUrlsException} to be processed by the crawler.
 * </p>
 *
 * <p>
 * The class also handles potential {@link IOException}s that may occur during
 * the parsing of the response body.
 * </p>
 */
public class SitemapsResponseProcessor implements ResponseProcessor {
    /** The crawler container for component lookup. */
    @Resource
    protected CrawlerContainer crawlerContainer;

     *
     * @param accessResultData the data containing the XML content to be parsed
     * @return a map containing the parsed data from the XML content
     * @throws CrawlerSystemException if an error occurs while parsing the XML content
     */
    public static Map<String, Object> getDataMap(final AccessResultData<?> accessResultData) {
        // create input source

import org.codelibs.fess.suggest.entity.SuggestItem;
import org.codelibs.fess.suggest.index.contents.querylog.QueryLog;
import org.codelibs.fess.suggest.normalizer.Normalizer;

/**
 * Interface for parsing content and creating suggest items.
 */
public interface ContentsParser {
    /**
     * Parses the given search words and creates a SuggestItem.
     *
     * @param words the array of search words

 * <p>It also handles the exclusion of search words based on certain criteria and manages the
 * maximum length of analyzed content.</p>
 *
 * <p>Methods in this class may throw SuggesterException in case of failures during the parsing process.</p>
 *
 * <p>Usage example:</p>
 * <pre>
 * {@code
 * DefaultContentsParser parser = new DefaultContentsParser();

         * @throws InvalidResponseException If the response is invalid
         * @throws NoSuchAlgorithmException If the algorithm is not available
         * @throws XmlParserException If XML parsing fails
         * @throws IOException If an I/O error occurs
         * @throws ServerException If a server error occurs
         */
        private StatObjectResponse getStatObject()