LhaExtractor lhaExtractor = container.getComponent("lhaExtractor");
        PasswordBasedExtractor pdfExtractor = container.getComponent("pdfExtractor");
        extractorFactory.addExtractor("application/msword", tikaExtractor);
        extractorFactory.addExtractor("application/vnd.ms-excel", tikaExtractor);
        extractorFactory.addExtractor("application/vnd.ms-powerpoint", tikaExtractor);

        assertContentType("text/html", "html/test1.html", "hoge.htm");
        assertContentType("text/html", "html/test1.shtml", "hoge.shtml");

        assertContentType("application/msword", "test/text1.txt", "hoge.doc");
        assertContentType("application/msword", "extractor/msoffice/test.doc", "hoge.doc");
        assertContentType("application/vnd.ms-excel", "test/text1.txt", "hoge.xls");

# cache
crawler.document.cache.enabled=true
crawler.document.cache.max.size=2621440
crawler.document.cache.supported.mimetypes=text/html

        assertEquals("ぶんるい", extractData.getValues("cp:category")[0]);
        assertEquals("1", extractData.getValues("meta:page-count")[0]);
        assertEquals("application/msword", extractData.getValues("Content-Type")[0]);
    }

    public void test_getTika_mswordx() {
        final InputStream in = ResourceUtil.getResourceAsStream("extractor/msoffice/test.docx");

    /** The key of the configuration. e.g. 1m */
    String INDEX_INDICES_TIMEOUT = "index.indices.timeout";

    /** The key of the configuration. e.g. text/html=html<br>
     * application/msword=word<br>
     * application/vnd.openxmlformats-officedocument.wordprocessingml.document=word<br>
     * application/vnd.ms-excel=excel<br>
     * application/vnd.ms-excel.sheet.2=excel<br>