fullWidthHalfWidth = Transliterator.getInstance("Fullwidth-Halfwidth");
        anyLower = Transliterator.getInstance("Any-Lower");
    }

    @Override
    public void init() throws IOException {
        // nothing
    }

    @Override
    public List<String> convert(final String text, final String field, final String... lang) {
        final List<String> list = new ArrayList<>();

                throw new IllegalArgumentException("Could not load " + suffixWordsFile.getAbsolutePath(), e);
            }
        } else {
            suffixWords = new CharArraySet(0, false);
        }
    }

    @Override
    public TokenStream create(final TokenStream tokenStream) {
        return new NumberConcatenationFilter(tokenStream, suffixWords);
    }

 *
 */
public class HtmlExtractorTest extends PlainTestCase {
    private static final Logger logger = LogManager.getLogger(HtmlExtractorTest.class);

    public HtmlExtractor htmlExtractor;

    @Override
    protected void setUp() throws Exception {
        super.setUp();
        StandardCrawlerContainer container = new StandardCrawlerContainer().singleton("htmlExtractor", HtmlExtractor.class);

            endOffset++;
            posInc = 0;
        }
        return queue.size() > qSize;
    }

    @Override
    public void end() throws IOException {
        super.end();
        offsetAttr.setOffset(finalOffset, finalOffset);
    }

    @Override
    public void reset() throws IOException {
        super.reset();
        block.setLength(0);
        prevToken = null;

 *
 */
public class MsExcelExtractorTest extends PlainTestCase {
    private static final Logger logger = LogManager.getLogger(MsExcelExtractorTest.class);

    public MsExcelExtractor msExcelExtractor;

    @Override
    protected void setUp() throws Exception {
        super.setUp();
        StandardCrawlerContainer container = new StandardCrawlerContainer().singleton("msExcelExtractor", MsExcelExtractor.class);

public class MsPowerPointExtractorTest extends PlainTestCase {
    private static final Logger logger = LogManager.getLogger(MsPowerPointExtractorTest.class);

    public MsPowerPointExtractor msPowerPointExtractor;

    @Override
    protected void setUp() throws Exception {
        super.setUp();
        StandardCrawlerContainer container = new StandardCrawlerContainer().singleton("msPowerPointExtractor", MsPowerPointExtractor.class);

     * @param in The input stream (not used).
     * @param params The parameters, expected to contain ExtractData.RESOURCE_NAME_KEY.
     * @return An ExtractData object containing the filename as content.
     */
    @Override
    public ExtractData getText(final InputStream in, final Map<String, String> params) {
        if (in == null) {
            throw new CrawlerSystemException("The inputstream is null.");
        }

        super();
    }

    /**
     * Extracts text from the Visio input stream.
     * @param in The input stream.
     * @param params The parameters.
     * @return The extracted data.
     */
    @Override
    public ExtractData getText(final InputStream in, final Map<String, String> params) {
        if (in == null) {
            throw new CrawlerSystemException("The inputstream is null.");
        }
        try {

    /**
     * Constructs a new {@link NormalizerChain}.
     */
    public NormalizerChain() {
        // nothing
    }

    List<Normalizer> normalizers = new ArrayList<>();

    @Override
    public String normalize(final String text, final String field, final String... langs) {
        String tmp = text;
        for (final Normalizer normalizer : normalizers) {

        this.stopWords =
                Analysis.parseWords(env, settings, "stopwords", JapaneseAnalyzer.getDefaultStopSet(), NAMED_STOP_WORDS, ignoreCase);
    }

    @Override
    public TokenStream create(TokenStream tokenStream) {
        if (removeTrailing) {
            return new StopFilter(tokenStream, stopWords);
        } else {