assertContentType("application/msword", "extractor/msoffice/test.doc", "hoge.doc");
        assertContentType("application/vnd.ms-excel", "test/text1.txt", "hoge.xls");
        assertContentType("application/vnd.ms-excel", "extractor/msoffice/test.xls", "hoge.xls");
        assertContentType("application/vnd.ms-powerpoint", "test/text1.txt", "hoge.ppt");

            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>

        }
        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 Excel", extractData.getValues("extended-properties:Application")[0]);
        assertEquals("sugaya", extractData.getValues("meta:last-author")[0]);
        assertEquals("太郎", extractData.getValues("dc:creator")[0]);

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

						<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>

- **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/

labels.facet_contentLength_1mto5m=1MB - 5MB
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_contentLength_1mto5m=1MB - 5MB
labels.facet_contentLength_5m=5MB -  
labels.facet_filetype_title=Tipo di file
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 Foglio di calcolo
labels.facet_filetype_odp=ODF Presentazione
labels.facet_filetype_pdf=PDF

- **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)