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

  <mime-type type="application/vnd.ms-excel.sheet.binary.macroenabled.12">
    <_comment>Microsoft Excel 2007 Binary Spreadsheet</_comment>
    <glob pattern="*.xlsb"/>
    <sub-class-of type="application/x-tika-ooxml"/>
  </mime-type>

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

        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 java.util.Map;

import org.apache.poi.hssf.usermodel.HSSFWorkbook;
import org.codelibs.fess.crawler.entity.ExtractData;
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"));

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

    }

    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);

        final AtomicBoolean streamClosed = new AtomicBoolean(false);

        try (final InputStream originalStream = ResourceUtil.getResourceAsStream("extractor/msoffice/test.xls")) {
            final InputStream trackableStream = createTrackableInputStream(originalStream, streamClosed);
            final ExtractData result = extractor.getText(trackableStream, null);

            assertNotNull(result);

- JUnit 4.x
- DBFlute UTFlute (PlainTestCase)
- Apache POI (for MS Office tests)
- Apache Commons Compress (for archive tests)

### Test Resources:
- `extractor/msoffice/test.doc`
- `extractor/msoffice/test.xls`
- `extractor/msoffice/test.ppt`
- `extractor/test.txt`
- `extractor/zip/test.zip`

## Key Improvements Tested

### 1. Resource Management
- ✅ Try-with-resources usage in MS Office extractors