}

    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);

Shinsuke Sugaya <******@****.***> 1444529815 +0900

Shinsuke Sugaya <******@****.***> 1444529815 +0900

/- - - - - - - - - - - - - - - - - - - -
playsql
  |-data
     |-common
     |  |-xls
     |     |-10-master.xls
     |     |-defaultValueMap.dataprop
     |-ut
        |-xls
           |-20-member.xls  
           |-30-product.xls  
           |-defaultValueMap.dataprop
- - - - - - - - - -/

The format of a xls file is like this:
/- - - - - - - - - - - - - - - - - - - -
|MEMBER_ID|MEMBER_NAME|BIRTHDATE |

application/access             mdf              # Microsoft Access
#application/excel              xls              # Microsoft Excel
application/vnd.ms-excel       xls              # Microsoft Excel
application/font-tdpfr         pfr              # TrueDoc Portable Font Resource
application/futuresplash       spl              # Macromedia Flash
application/hep                hep              # Hummingbird Host Explorer Profiles

        byte[] buffer = new byte[100];
        int len = cmd.writeParametersWireFormat(buffer, 0);
        assertTrue(len >= 2);
        // writeInt2 writes in little-endian format (LSB first)
        assertEquals(0xAB, buffer[0] & 0xFF);
        assertEquals(0x12, buffer[1] & 0xFF);
        // Check that the path is written after the referral level
        // The path should be written starting at index 2

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 {

    /**
     * Creates a new MsExcelExtractor instance.
     */
    public MsExcelExtractor() {

            assertEquals("application/pdf", mimeMap.getMimeType("pdf"));
            assertEquals("application/msword", mimeMap.getMimeType("doc"));
            assertEquals("application/vnd.ms-excel", mimeMap.getMimeType("xls"));
            assertEquals("text/html", mimeMap.getMimeType("html"));
            assertEquals("text/html", mimeMap.getMimeType("htm"));
            assertEquals("image/jpeg", mimeMap.getMimeType("jpg"));

        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"));
    }

application/access             mdf              # Microsoft Access
#application/excel              xls              # Microsoft Excel
application/vnd.ms-excel       xls              # Microsoft Excel
application/font-tdpfr         pfr              # TrueDoc Portable Font Resource
application/futuresplash       spl              # Macromedia Flash
application/hep                hep              # Hummingbird Host Explorer Profiles