<postConstruct name="addCondition">
			<arg>"mimetype"</arg>
			<arg>"application/vnd.ms-excel"</arg>
		</postConstruct>
		<postConstruct name="addCondition">
			<arg>"mimetype"</arg>
			<arg>"application/vnd.ms-excel.sheet.2"</arg>
		</postConstruct>
		<postConstruct name="addCondition">
			<arg>"mimetype"</arg>
			<arg>"application/vnd.ms-excel.sheet.3"</arg>
		</postConstruct>
		<postConstruct name="addCondition">

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

    /**
     * Extracts text from the Excel input stream.
     * @param in The input stream.
     * @param params The parameters.
     * @return The extracted data.
     */
    @Override

application/vnd.ms-excel=excel\n\
application/vnd.ms-excel.sheet.2=excel\n\
application/vnd.ms-excel.sheet.3=excel\n\
application/vnd.ms-excel.sheet.4=excel\n\
application/vnd.ms-excel.workspace.3=excel\n\
application/vnd.ms-excel.workspace.4=excel\n\
application/vnd.openxmlformats-officedocument.spreadsheetml.sheet=excel\n\
application/vnd.ms-powerpoint=powerpoint\n\

            extractor.getText(invalidStream, null);
            fail("Expected exception for invalid Excel document");
        } catch (final ExtractException e) {
            // ExtractException with improved message
            assertTrue("Error message should contain context about Excel document or extraction",
                    e.getMessage().contains("Excel") || e.getMessage().contains("extract"));
        } catch (final RuntimeException e) {

						<option value="word" <c:if test="${as.filetype.contains('word')}">selected</c:if>><la:message
								key="labels.advance_search_filetype_word"
							/></option>
						<option value="excel" <c:if test="${as.filetype.contains('excel')}">selected</c:if>><la:message
								key="labels.advance_search_filetype_excel"
							/></option>

     * application/vnd.ms-excel=excel<br>
     * application/vnd.ms-excel.sheet.2=excel<br>
     * application/vnd.ms-excel.sheet.3=excel<br>
     * application/vnd.ms-excel.sheet.4=excel<br>
     * application/vnd.ms-excel.workspace.3=excel<br>
     * application/vnd.ms-excel.workspace.4=excel<br>
     * application/vnd.openxmlformats-officedocument.spreadsheetml.sheet=excel<br>

				"application/vnd.ms-artgalry",
				"application/vnd.ms-asf",
				"application/vnd.ms-cab-compressed",
				"application/vnd.ms-excel",
				"application/vnd.ms-excel.addin.macroenabled.12",
				"application/vnd.ms-excel.sheet.macroenabled.12",
				"application/vnd.ms-excel.sheet.binary.macroenabled.12",
				"application/vnd.ms-fontobject",
				"application/vnd.ms-htmlhelp",
				"application/vnd.ms-ims",

labels.facet_contentLength_1mto5m=1MB - 5MB
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

- **File**: Local/network file systems
- **FTP**: With authentication
- **SMB/CIFS**: Windows shares (SMB1/SMB2+)
- **Storage**: MinIO/S3-compatible

### Content Formats

Office (Word, Excel, PowerPoint), PDF, Archives (ZIP, TAR, GZ), HTML, XML, JSON, Media (audio/video metadata), Images (EXIF/IPTC/XMP)

---

## Architecture

### Module Structure

```
fess-crawler-parent/

  <mime-type type="application/vnd.ms-excel">
    <!-- Use DefaultDetector / org.apache.tika.parser.microsoft.POIFSContainerDetector for more reliable detection of OLE2 documents -->
    <alias type="application/msexcel" />
    <_comment>Microsoft Excel Spreadsheet</_comment>
    <magic priority="50">
      <match value="Microsoft\ Excel\ 5.0\ Worksheet" type="string" offset="2080"/>