}

    public void test_getHtml_utf8() {
        final InputStream in = ResourceUtil.getResourceAsStream("extractor/test_utf8.html");
        final ExtractData data = htmlExtractor.getText(in, null);
        final String content = data.getContent();
        CloseableUtil.closeQuietly(in);
        logger.info(content);
        assertTrue(content.contains("テスト"));

 */
public class MsPublisherExtractor extends AbstractExtractor {

    /*
     * (non-Javadoc)
     *
     * @see org.codelibs.fess.crawler.extractor.Extractor#getText(java.io.InputStream,
     * 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.");
        }

        this.queryFreq = queryFreq;
        timestamp = ZonedDateTime.now();
        emptySource = createEmptyMap();
        id = SuggestUtil.createSuggestTextId(this.text);
    }

    public String getText() {
        return text;
    }

    public String[][] getReadings() {
        return readings;
    }

    public String[] getTags() {
        return tags;
    }

        final String content = msExcelExtractor.getText(in, null).getContent();
        CloseableUtil.closeQuietly(in);
        logger.info(content);
        assertTrue(content.contains("テスト"));
    }

    public void test_getText_null() {
        try {
            msExcelExtractor.getText(null, null);
            fail();
        } catch (final CrawlerSystemException e) {

        final String content = msPowerPointExtractor.getText(in, null).getContent();
        CloseableUtil.closeQuietly(in);
        logger.info(content);
        assertTrue(content.contains("テスト"));
    }

    public void test_getText_null() {
        try {
            msPowerPointExtractor.getText(null, null);
            fail();
        } catch (final CrawlerSystemException e) {

        final String content = textExtractor.getText(in, null).getContent();
        CloseableUtil.closeQuietly(in);
        logger.info(content);
        assertTrue(content.contains("テスト"));
    }

    public void test_getText_null() {
        try {
            textExtractor.getText(null, null);
            fail();
        } catch (final CrawlerSystemException e) {

= vendor/github.com/chai2010/gettext-go licensed under: =

Copyright 2013 ChaiShushan <chaishushan{AT}gmail.com>. All rights reserved.

Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are
met:

   * Redistributions of source code must retain the above copyright
notice, this list of conditions and the following disclaimer.

            tarExtractor.setMaxContentSize(100);
            tarExtractor.getText(in, null);
            fail();
        } catch (MaxLengthExceededException e) {
            // pass
        }
        tarExtractor.setMaxContentSize(-1);
    }

    public void test_getText_null() {
        try {
            tarExtractor.getText(null, null);
            fail();
        } catch (final CrawlerSystemException e) {

        final String content = pdfExtractorForPdfPassword.getText(in, params).getContent();
        CloseableUtil.closeQuietly(in);
        logger.info(content);
        assertTrue(content.contains("テスト"));
    }

    public void test_getText_null() {
        try {
            pdfExtractor.getText(null, null);
            fail();
        } catch (final CrawlerSystemException e) {

    protected boolean isDaemonThread = false;

    /*
     * (non-Javadoc)
     *
     * @see org.codelibs.fess.crawler.extractor.Extractor#getText(java.io.InputStream,
     * 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.");
        }