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;

/**

- **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)

        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]);