import java.io.IOException;
import java.io.InputStream;
import java.util.Map;

import org.apache.poi.hslf.usermodel.HSLFShape;
import org.apache.poi.hslf.usermodel.HSLFSlideShow;
import org.apache.poi.hslf.usermodel.HSLFTextParagraph;
import org.apache.poi.sl.extractor.SlideShowExtractor;
import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.exception.ExtractException;

        validateInputStream(in);
        try (final HSSFWorkbook workbook = new HSSFWorkbook(in);
                final org.apache.poi.hssf.extractor.ExcelExtractor excelExtractor =
                        new org.apache.poi.hssf.extractor.ExcelExtractor(workbook)) {
            return new ExtractData(excelExtractor.getText());
        } catch (final IOException e) {

			<version>${jhighlight.version}</version>
		</dependency>
		<dependency>
			<groupId>org.apache.poi</groupId>
			<artifactId>poi</artifactId>
			<version>${poi.version}</version>
		</dependency>
		<dependency>
			<groupId>org.apache.poi</groupId>
			<artifactId>poi-ooxml</artifactId>
			<version>${poi.version}</version>
			<exclusions>
				<exclusion>
					<groupId>stax</groupId>

        } catch (final RuntimeException e) {
            // POI may throw IllegalArgumentException or other RuntimeExceptions
            // for invalid data, which is also acceptable
            assertNotNull("Exception message should not be null", e.getMessage());
        }
    }

    /**
     * Test that MsExcelExtractor throws appropriate exception for invalid data.
     * POI may throw various exceptions depending on the type of invalid data.

     */
    @Override
    public ExtractData getText(final InputStream in, final Map<String, String> params) {
        validateInputStream(in);
        try (final org.apache.poi.hwpf.extractor.WordExtractor wordExtractor = new org.apache.poi.hwpf.extractor.WordExtractor(in)) {
            return new ExtractData(wordExtractor.getText());
        } catch (final IOException e) {

 * governing permissions and limitations under the License.
 */
package org.codelibs.fess.crawler.extractor.impl;

import java.io.IOException;
import java.io.InputStream;
import java.util.Map;

import org.apache.poi.hdgf.extractor.VisioTextExtractor;
import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.exception.ExtractException;

/**

```bash
mvn test -Dtest=MsWordExtractorTest,ExtractorResourceManagementTest
```

## Test Requirements

### Dependencies:
- 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`

				<include name="dataformat/commons-compress-*" />
				<include name="dataformat/commons-math3-*" />
				<include name="dataformat/curvesapi-*" />
				<include name="dataformat/orangesignal-csv-*" />
				<include name="dataformat/poi-*" />
				<include name="dataformat/SparseBitSet-*" />
				<include name="dataformat/stax-api-*" />
				<include name="dataformat/xmlbeans-*" />
				<include name="minhash/guava-*" />

 * governing permissions and limitations under the License.
 */
package org.codelibs.fess.crawler.extractor.impl;

import java.io.IOException;
import java.io.InputStream;
import java.util.Map;

import org.apache.poi.hpbf.extractor.PublisherTextExtractor;
import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.exception.ExtractException;

/**

- **License**: Apache 2.0
- **DI**: LastaFlute DI
- **Repo**: https://github.com/codelibs/fess-crawler

### Tech Stack

- **HTTP**: Apache HttpComponents 4.5+
- **Extraction**: Apache Tika 3.0+, POI 5.3+, PDFBox 3.0+
- **Testing**: JUnit 4, UTFlute, Mockito 5.7.0
- **Storage**: In-memory (default), OpenSearch (optional)

### Protocols

- **HTTP/HTTPS**: Full crawling, cookies, auth, robots.txt