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

/**
 * Extracts text content from Microsoft PowerPoint documents.
 */
public class MsPowerPointExtractor extends AbstractExtractor {

    /**
     * Creates a new MsPowerPointExtractor instance.
     */
    public MsPowerPointExtractor() {
        super();

        assertEquals("こめんと", extractData.getValues("w:Comments")[0]);
        assertEquals("たぐ|さぶたいとる", String.join("|", extractData.getValues("dc:subject")));
        assertEquals("Microsoft Office Word", extractData.getValues("extended-properties:Application")[0]);
        assertEquals("sugaya", extractData.getValues("meta:last-author")[0]);
        assertEquals("太郎", extractData.getValues("dc:creator")[0]);

    <!-- Use DefaultDetector / org.apache.tika.parser.microsoft.POIFSContainerDetector for more reliable detection of OLE2 documents -->
    <alias type="application/vnd.ms-word"/>
    <_comment>Microsoft Word Document</_comment>
    <tika:link>http://en.wikipedia.org/wiki/.doc</tika:link>
    <tika:uti>com.microsoft.word.doc</tika:uti>
    <magic priority="50">
      <match value="Microsoft\ Word\ 6.0\ Document" type="string" offset="2080"/>

- **FTP**: FTP server crawling with authentication
- **SMB/CIFS**: Windows network shares
- **Storage**: Cloud storage systems (MinIO, S3-compatible)

### Content Formats

#### Office Documents
- Microsoft Office (Word, Excel, PowerPoint)
- OpenOffice/LibreOffice documents
- RTF, WordPerfect

#### PDFs and Images
- PDF documents (text and metadata extraction)
- Images (JPEG, PNG, GIF, TIFF, BMP)

			<artifactId>tika-parser-mail-module</artifactId>
			<version>${tika.version}</version>
		</dependency>
		<dependency>
			<groupId>org.apache.tika</groupId>
			<artifactId>tika-parser-microsoft-module</artifactId>
			<version>${tika.version}</version>
		</dependency>
		<dependency>
			<groupId>org.apache.tika</groupId>
			<artifactId>tika-parser-miscoffice-module</artifactId>

				"image/vnd.fastbidsheet",
				"image/vnd.fpx",
				"image/vnd.fst",
				"image/vnd.fujixerox.edmics-mmr",
				"image/vnd.fujixerox.edmics-rlc",
				"image/vnd.globalgraphics.pgb",
				"image/vnd.microsoft.icon",
				"image/vnd.mix",
				"image/vnd.ms-modi",
				"image/vnd.net-fpx",
				"image/vnd.radiance",
				"image/vnd.sealed.png",
				"image/vnd.sealedmedia.softseal.gif",