}

    public void test_getText_mswordx() {
        InputStream in = ResourceUtil.getResourceAsStream("extractor/msoffice/test.docx");
        Map<String, String> params = new HashMap<String, String>();
        params.put("resourceName", "test.docx");
        ExtractData extractData = jodExtractor.getText(in, params);
        String content = extractData.getContent();
        CloseableUtil.closeQuietly(in);

        assertContentType("application/vnd.openxmlformats-officedocument.wordprocessingml.document", "test/text1.txt", "hoge.docx");
        assertContentType("application/vnd.openxmlformats-officedocument.wordprocessingml.document", "extractor/msoffice/test.docx",
                "hoge.docx");
        assertContentType("application/vnd.openxmlformats-officedocument.spreadsheetml.sheet", "test/text1.txt", "hoge.xlsx");

        extensionMap.put("odt", "txt");
        extensionMap.put("ott", "txt");
        extensionMap.put("sxw", "txt");
        extensionMap.put("rtf", "txt");
        extensionMap.put("doc", "txt");
        extensionMap.put("docx", "txt");
        extensionMap.put("wpd", "txt");
        extensionMap.put("txt", "txt");
        extensionMap.put("html", "txt");
        // Spreadsheet Formats
        extensionMap.put("ods", "tsv");

        assertEquals("application/msword", extractData.getValues("Content-Type")[0]);
    }

    public void test_getTika_mswordx() {
        final InputStream in = ResourceUtil.getResourceAsStream("extractor/msoffice/test.docx");
        final ExtractData extractData = tikaExtractor.getText(in, null);
        final String content = extractData.getContent();
        CloseableUtil.closeQuietly(in);
        logger.info(content);

    <glob pattern="*.wbmp"/>
  </mime-type>

  <mime-type type="image/vnd.zbrush.dcx">
    <acronym>DCX</acronym>
    <_comment>ZSoft Multi-Page Paintbrush</_comment>
    <alias type="image/x-dcx"/>
    <magic priority="50">
      <match value="0xB168DE3A" type="string" offset="0"/>
    </magic>
    <glob pattern="*.dcx"/>
  </mime-type>

  <mime-type type="image/vnd.zbrush.pcx">

            final List<Map<String, Object>> docs = new ArrayList<>(docPerReq);
            try (final DocumentReader documentReader = reader.get()) {
                Map<String, Object> doc = documentReader.read();
                while (doc != null) {
                    if (Thread.currentThread().isInterrupted()) {
                        break;
                    }
                    docs.add(doc);

        final String value = "<?xml version=\"1.0\"?>\n"//
                + "<doc>\n"//
                + "<field name=\"title\">タイトル</field>\n"//
                + "<field name=\"body\">第一章 第一節 ほげほげふがふが LINK 第2章 第2節</field>\n"//
                + "<field name=\"list\"><list><item>リスト1</item><item>リスト2</item><item>リスト3</item></list></field>\n"//
                + "</doc>";

        private final Node doc;

        public DefaultNamespaceContext(final Node doc) {
            this.doc = doc;
        }

        @Override
        public String getNamespaceURI(final String prefix) {
            return getNamespaceForPrefix(prefix, doc);
        }

        final String value = "<?xml version=\"1.0\"?>\n"//
                + "<doc>\n"//
                + "<field name=\"title\">タイトル</field>\n"//
                + "<field name=\"body\">第一章 第一節 ほげほげふがふが LINK 第2章 第2節</field>\n"//
                + "<field name=\"list\"><list><item>リスト1</item><item>リスト2</item><item>リスト3</item></list></field>\n"//
                + "</doc>";

            final PDDocument doc = document;
            final Set<Exception> exceptionSet = new HashSet<>();
            final Thread task = new Thread(() -> {
                try {
                    stripper.writeText(doc, writer);
                    extractEmbeddedDocuments(doc, writer);
                    extractAnnotations(doc, writer);
                } catch (final Exception e) {