public PatternConcatenationFilterFactory(final IndexSettings indexSettings, final Environment environment, final String name,
            final Settings settings) {
        super(indexSettings, name, settings);

        final String pattern1Str = settings.get("pattern1");
        final String pattern2Str = settings.get("pattern2", ".*");

        if (logger.isDebugEnabled()) {

    /** Parameters for the extraction process */
    private final Map<String, String> params;

    /** Container for accessing crawler components */
    private final CrawlerContainer crawlerContainer;

    /** MIME type of the content */
    private String mimeType;

    /** Filename of the content */
    private String filename;

    /** Cache file size threshold in bytes */

            assertEquals("file4", new String(InputStreamUtil.getBytes(responseData.getResponseBody())));
            assertEquals(5, responseData.getContentLength());
        }

        try {
            smbClient.doGet(baseUrl);
            fail();
        } catch (final ChildUrlsException e) {
            String[] urls = e.getChildUrlList().stream().map(r -> r.getUrl()).sorted().toArray(String[]::new);

public class KuromojiPartOfSpeechFilterFactory extends AbstractTokenFilterFactory {

    private final Set<String> stopTags = new HashSet<>();

    public KuromojiPartOfSpeechFilterFactory(IndexSettings indexSettings, Environment env, String name, Settings settings) {
        super(indexSettings, name, settings);
        List<String> wordList = Analysis.parseWordList(env, settings, "stoptags", s -> s);
        if (wordList != null) {

     * @return the detected content type
     */
    String getContentType(InputStream is, String filename);

    /**
     * Determines the content type of the given input stream using the provided parameters.
     * @param is the input stream to analyze
     * @param params the parameters containing additional information like filename
     * @return the detected content type
     */
    String getContentType(InputStream is, Map<String, String> params);

        // Default constructor
    }

    /**
     * Queue index name.
     */
    protected String queueIndex = ".crawler.queue";

    /**
     * Data index name.
     */
    protected String dataIndex = ".crawler.data";

    /**
     * Filter index name.
     */
    protected String filterIndex = ".crawler.filter";

    /**
     * Number of shards for the queue index.
     */

    protected volatile Map<String, Queue<UrlQueueImpl<Long>>> urlQueueMap = new HashMap<>();

    /** Map of session IDs to access result maps for storing crawling results. */
    protected volatile Map<String, Map<String, AccessResultImpl<Long>>> sessionMap = new HashMap<>();

    /** Map of session IDs to include URL patterns for filtering URLs. */
    protected volatile Map<String, List<Pattern>> includeUrlPatternMap = new HashMap<>();

     * Normalizes the given text.
     * @param text The text to normalize
     * @param field The field name
     * @param langs The language
     * @return The normalized text
     */
    String normalize(String text, String field, String... langs);

    /**
     * Retrieves the location (URL) of the sitemap.
     *
     * @return the location of the sitemap as a String.
     */
    String getLoc();

    /**
     * Retrieves the last modification date of the sitemap.
     *
     * @return A string representing the last modification date.
     */
    String getLastmod();

     */
    public ExtractException(final String message, final Throwable cause) {
        super(message, cause);
    }

    /**
     * Constructs a new ExtractException with the specified detail message.
     *
     * @param message the detail message. The detail message is saved for later retrieval by the {@link #getMessage()} method.
     */
    public ExtractException(final String message) {
        super(message);
    }