assertContentType("application/vnd.ms-powerpoint", "extractor/msoffice/test.ppt", "h&oge.ppt");
        assertContentType("application/vnd.ms-powerpoint", "extractor/msoffice/test.ppt", "h?oge.ppt");
        assertContentType("application/vnd.ms-powerpoint", "extractor/msoffice/test.ppt", "******@****.***");
        assertContentType("application/vnd.ms-powerpoint", "extractor/msoffice/test.ppt", "h:oge.ppt");

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

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

    /**
     * Extracts text from the PowerPoint input stream.
     * @param in The input stream.

        extractorFactory.addExtractor("application/msword", tikaExtractor);
        extractorFactory.addExtractor("application/vnd.ms-excel", tikaExtractor);
        extractorFactory.addExtractor("application/vnd.ms-powerpoint", tikaExtractor);
        extractorFactory.addExtractor("application/vnd.visio", tikaExtractor);
        extractorFactory.addExtractor("application/pdf", pdfExtractor);

						<option value="excel" <c:if test="${as.filetype.contains('excel')}">selected</c:if>><la:message
								key="labels.advance_search_filetype_excel"
							/></option>
						<option value="powerpoint" <c:if test="${as.filetype.contains('powerpoint')}">selected</c:if>><la:message
								key="labels.advance_search_filetype_powerpoint"
							/></option>
					</select>
				</div>
			</div>
			<div class="mb-3 row">

        assertEquals("1", extractData.getValues("meta:word-count")[0]);
        assertEquals("たぐ|さぶたいとる", String.join("|", extractData.getValues("dc:subject")));
        assertEquals("Microsoft PowerPoint", extractData.getValues("extended-properties:Application")[0]);
        assertEquals("sugaya", extractData.getValues("meta:last-author")[0]);
        assertEquals("太郎", extractData.getValues("dc:creator")[0]);

application/lotus-123          wks              # Lotus 123
application/mac-binhex40       hqx              # Macintosh binhexed archives
application/mspowerpoint       ppt              # Microsoft Powerpoint
application/msword             doc              # Microsoft Word
application/octet-stream       bin exe ani      # Binary File
application/oda                oda
application/pagemaker          pm5 pt5 pm       # PageMaker

						<option value="excel" <c:if test="${as.filetype.contains('excel')}">selected</c:if>><la:message
								key="labels.advance_search_filetype_excel"
							/></option>
						<option value="powerpoint" <c:if test="${as.filetype.contains('powerpoint')}">selected</c:if>><la:message
								key="labels.advance_search_filetype_powerpoint"
							/></option>
					</select>
				</div>
			</div>
			<div class="mb-3 row">

labels.facet_contentLength_5m=5MB -  
labels.facet_filetype_title=File Type
labels.facet_filetype_html=HTML
labels.facet_filetype_word=MS Word
labels.facet_filetype_excel=MS Excel
labels.facet_filetype_powerpoint=MS PowerPoint
labels.facet_filetype_odt=ODF Word
labels.facet_filetype_ods=ODF Spreadsheet
labels.facet_filetype_odp=ODF Presentation
labels.facet_filetype_pdf=PDF
labels.facet_filetype_fb2=FictionBook

labels.facet_contentLength_5m=5MB -  
labels.facet_filetype_title=檔案類型
labels.facet_filetype_html=HTML
labels.facet_filetype_word=MS Word
labels.facet_filetype_excel=MS Excel
labels.facet_filetype_powerpoint=MS PowerPoint
labels.facet_filetype_odt=ODF Word
labels.facet_filetype_ods=ODF Spreadsheet
labels.facet_filetype_odp=ODF Presentation
labels.facet_filetype_pdf=PDF
labels.facet_filetype_fb2=FictionBook

- **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)
- Image metadata (EXIF, IPTC, XMP)