}
        return new Extractor() {
            @Override
            public ExtractData getText(final InputStream in, final Map<String, String> params) {
                for (final Extractor extractor : extractors) {
                    try {
                        return extractor.getText(in, params);
                    } catch (final UnsupportedExtractException e) {

public class KanjiNumberFilterFactory extends AbstractTokenFilterFactory {

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

    @Override
    public TokenStream create(final TokenStream tokenStream) {

    PROCESS_CHILD_URLS_BY_EXCEPTION,
    /** Indicates processing a child URL due to an exception. */
    PROCESS_CHILD_URL_BY_EXCEPTION,
    /** Indicates an access exception during crawling. */
    CRAWLING_ACCESS_EXCEPTION,
    /** Indicates a general exception during crawling. */
    CRAWLING_EXCEPTION,
    /** Indicates no URL is available in the queue. */
    NO_URL_IN_QUEUE,
    /** Indicates the start of a crawler thread. */

     * java.util.Map)
     */
    @Override
    public ExtractData getText(final InputStream in, final Map<String, String> params) {
        if (in == null) {
            throw new CrawlerSystemException("The inputstream is null.");
        }

        final String password = getPassword(params);
        try (PDDocument document = Loader.loadPDF(new RandomAccessReadBuffer(in), password)) {

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

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

        final List<String> tagList = Analysis.parseWordList(environment, settings, "tags", s -> s);

     * @param id       the ID of the suggestion to delete
     * @return a result object containing the outcome of the delete operation
     */
    SuggestWriterResult delete(Client client, SuggestSettings settings, String index, String id);

    /**
     * Deletes documents from the specified index based on the given query.
     *
     * @param client the OpenSearch client to use for the operation

        @Override
        public void init(String sessionId) {
        }

        @Override
        public void addInclude(String urlPattern) {
        }

        @Override
        public void addExclude(String urlPattern) {
        }

        @Override
        public boolean match(String url) {
            return true;
        }

        @Override

public class DisableGraphFilterFactory extends AbstractTokenFilterFactory {

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

    @Override
    public TokenStream create(final TokenStream tokenStream) {

public class DefaultContentsParserTest extends TestCase {
    DefaultContentsParser defaultContentsParser = new DefaultContentsParser();
    String[] supportedFields = new String[] { "content", "title" };
    String[] tagFieldNames = new String[] { "label", "virtual_host" };
    String roleFieldName = "role";

    public void test_parseQueryLog() throws Exception {

        QueryLog queryLog = new QueryLog("content:検索エンジン", null);

        assertEquals("123 abc", normalizeText(" 123\nabc\n123 ", 100, -1, -1, true));
        assertEquals("123# !$", normalizeText(" 123#123!$123  ", 100, -1, -1, true));
    }

    public static String normalizeText(final String str, final int initialCapacity, final int maxAlphanumTermSize,
            final int maxSymbolTermSize, final boolean removeDuplication) {
        if (str == null) {
            return StringUtil.EMPTY;
        }