spfactory.setFeature(Constants.FEATURE_EXTERNAL_PARAMETER_ENTITIES, false);
            // create a sax parser
            final SAXParser parser = spfactory.newSAXParser();
            try {
                parser.setProperty(XMLConstants.ACCESS_EXTERNAL_DTD, StringUtil.EMPTY);
                parser.setProperty(XMLConstants.ACCESS_EXTERNAL_SCHEMA, StringUtil.EMPTY);
            } catch (final Exception e) {

        // Default constructor
    }

    /**
     * Parses a robots.txt file from the given input stream using UTF-8 encoding.
     * @param stream the input stream to parse
     * @return the parsed RobotsTxt object, or null if disabled
     */
    public RobotsTxt parse(final InputStream stream) {
        return parse(stream, Constants.UTF_8);
    }

    /**

     * @param normalizer the normalizer to use for normalizing values
     * @return a list of suggest items parsed from the query log
     */
    List<SuggestItem> parseQueryLog(QueryLog queryLog, String[] fields, String[] tagFieldNames, String roleFieldName,
            ReadingConverter readingConverter, Normalizer normalizer);

    /**
     * Parses a document and extracts suggest items based on the provided fields and converters.
     *

import jakarta.annotation.Resource;

/**
 * A response processor implementation that handles sitemaps.
 * It parses the response body as a SitemapSet, extracts URLs from the sitemaps,
 * and adds them as child URLs to be crawled.
 *
 * <p>
 * This class uses a {@link SitemapsHelper} to parse the sitemap XML or text.
 * It then iterates through the sitemaps in the SitemapSet, extracts the URL

        final DOMParser parser = getDomParser();
        try (final Reader reader = new StringReader(content)) {
            parser.parse(new InputSource(reader));
        } catch (final Exception e) {
            logger.warn("Failed to parse the content.", e);
            return new ExtractData(extractString(content));
        }

        final Document document = parser.getDocument();
        try {

            SynonymMap.Builder parser = null;

            if ("wordnet".equalsIgnoreCase(settings.get("format"))) {
                parser = new WordnetSynonymParser(true, expand, analyzer);
                ((WordnetSynonymParser) parser).parse(rulesReader);
            } else {
                parser = new SolrSynonymParser(true, expand, analyzer);
                ((SolrSynonymParser) parser).parse(rulesReader);
            }

    /** Map of regex patterns to passwords for static password configuration. */
    protected Map<Pattern, String> passwordMap = new HashMap<>();

    /** Cache for parsed password configurations from extraction parameters. */
    private final Map<String, List<Pair<Pattern, String>>> configPasswordMap = new ConcurrentHashMap<>();

    /**
     * Creates a new PasswordBasedExtractor instance.

        try {
            sitemapsHelper.parse(in);
            fail();
        } catch (final CrawlingAccessException e) {
            // NOP
        }
    }

    public void test_parseXmlSitemaps_invalid2() {
        final byte[] bytes = "test".getBytes();
        final InputStream in = new ByteArrayInputStream(bytes);

        try {
            sitemapsHelper.parse(in);
            fail();

/**
 * 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;

    /**

     * when making decisions, they may crawl pages marked "hourly" less
     * frequently than that, and they may crawl pages marked "yearly" more
     * frequently than that. Crawlers may periodically crawl pages marked
     * "never" so that they can handle unexpected changes to those pages.
     */
    private String changefreq;

    /**