final AtomicBoolean streamClosed = new AtomicBoolean(false);

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

- 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
- ✅ Proper closure of POI objects

		<property name="name">"msofficeThumbnailGenerator"</property>
		<property name="commandList">
			["${path}/generate-thumbnail",
			"msoffice",
			"${url}",
			"${outputFile}"]
		</property>
		<property name="generatorList">
			["${path}/generate-thumbnail"]
		</property>
		<postConstruct name="addCondition">
			<arg>"mimetype"</arg>

  <mime-type type="application/x-tika-msoffice-embedded">
    <sub-class-of type="application/x-tika-msoffice"/>
  </mime-type>
  <mime-type type="application/x-tika-msoffice-embedded;format=ole10_native">
    <sub-class-of type="application/x-tika-msoffice-embedded"/>
    <_comment>OLE10 Native Embedded Document</_comment>
  </mime-type>
  <mime-type type="application/x-tika-msoffice-embedded;format=comp_obj">

				"application/x-tar",
				"application/x-tex",
				"application/x-tex-tfm",
				"application/x-texinfo",
				"application/x-tika-msoffice",
				"application/x-tika-msoffice-embedded",
				"application/x-tika-msoffice-embedded;format=ole10_native",
				"application/x-tika-msoffice-embedded;format=comp_obj",
				"application/x-tika-msworks-spreadsheet",
				"application/x-tika-ooxml",
				"application/x-tika-ooxml-protected",

import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.exception.ExtractException;
import org.codelibs.fess.crawler.extractor.Extractor;
import org.jodconverter.core.office.OfficeException;
import org.jodconverter.core.office.OfficeManager;
import org.jodconverter.local.LocalConverter;

import jakarta.annotation.PostConstruct;
import jakarta.annotation.PreDestroy;

/**

system](https://fess.codelibs.org/15.3/admin/fileconfig-guide.html), or [Data Store](https://fess.codelibs.org/15.3/admin/dataconfig-guide.html) (such as a CSV or database). Many file formats are supported including (but not limited to): Microsoft Office, PDF, and zip.

*[Fess Site Search](https://github.com/codelibs/fess-site-search)* is a free alternative to [Google Site Search](https://enterprise.google.com/search/products/gss.html). For more details, see the [FSS JS Generator document...

/admin/fileconfig-guide.html) oder [Datenspeicher](https://fess.codelibs.org/15.3/admin/dataconfig-guide.html) (wie CSV oder Datenbank) durchsuchen kann. Viele Dateiformate werden unterstützt, einschließlich (aber nicht beschränkt auf): Microsoft Office, PDF und zip.

*[Fess Site Search](https://github.com/codelibs/fess-site-search)* ist eine kostenlose Alternative zur [Google Site Search](https://enterprise.google.com/search/products/gss.html). Weitere Details finden Sie in der [Dokumentation...

*[Fess 网站搜索](https://github.com/codelibs/fess-site-search)* 是 [Google 网站搜索](https://enterprise.google.com/search/products/gss.html)的免费替代品。更多详情请参阅 [FSS JS 生成器文档](https://fss-generator.codelibs.org/docs/manual)。

## 官网

    echo "convert"
  else
    echo ""
  fi
}

if [[ x"$HOME" = "x/root" ]] || [[ x"$HOME" = "x/var/root" ]] ; then
  HOME=/var/lib/fess
fi

if [[ x"${cmd_type}" = "xmsoffice" ]] ; then
  im_cmd=$(get_imagemagick_cmd)
  if [[ -z "${im_cmd}" ]] ; then
    echo "ImageMagick (convert or magick) does not exist."
    exit 1
  fi
  check_command pdftoppm
  check_command unoconv