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

    }

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

        // Spreadsheet Formats
        extensionMap.put("ods", "tsv");
        extensionMap.put("ots", "tsv");
        extensionMap.put("sxc", "tsv");
        extensionMap.put("xls", "tsv");
        extensionMap.put("xlsx", "tsv");
        extensionMap.put("csv", "tsv");
        extensionMap.put("tsv", "tsv");
        // Presentation Formats
        extensionMap.put("odp", "pdf");
        extensionMap.put("otp", "pdf");

    }

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

        msExcelExtractor = container.getComponent("msExcelExtractor");
    }

    public void test_getText() {
        final InputStream in = ResourceUtil.getResourceAsStream("extractor/msoffice/test.xls");
        final String content = msExcelExtractor.getText(in, null).getContent();
        CloseableUtil.closeQuietly(in);
        logger.info(content);
        assertTrue(content.contains("テスト"));
    }

import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.exception.ExtractException;

/**
 * Gets a text from .xls file.
 *
 * @author shinsuke
 *
 */
public class MsExcelExtractor extends AbstractExtractor {
    /*
     * (non-Javadoc)
     *
     * @see

    <_comment>Office Open XML Workbook</_comment>
    <glob pattern="*.xlsx"/>
    <sub-class-of type="application/x-tika-ooxml"/>
  </mime-type>

  <mime-type type="application/vnd.openxmlformats-officedocument.spreadsheetml.template">
    <_comment>Office Open XML Workbook Template</_comment>
    <glob pattern="*.xltx"/>
    <sub-class-of type="application/x-tika-ooxml"/>
  </mime-type>

    // public ResponseData call() throws Exception {
    // String[] urls =
    // new String[] {
    // "http://.../",
    // "http://.../test.pdf",
    // "http://.../test.doc",
    // "http://.../test.xls",
    // "http://.../test.ppt",
    // "http://.../test.txt", };
    // for (String url : urls) {
    // ResponseData responseData = httpClient.doGet(url);
    // // assertEquals(200, responseData.getHttpStatusCode());