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");

        final AtomicBoolean streamClosed = new AtomicBoolean(false);

        try (final InputStream originalStream = ResourceUtil.getResourceAsStream("extractor/msoffice/test.doc")) {
            final InputStream trackableStream = createTrackableInputStream(originalStream, streamClosed);
            final ExtractData result = extractor.getText(trackableStream, null);

        logger.info(content);
        assertTrue(content.contains("テスト"));
    }

    public void test_getTika_msword() {
        final InputStream in = ResourceUtil.getResourceAsStream("extractor/msoffice/test.doc");
        final ExtractData extractData = tikaExtractor.getText(in, null);
        final String content = extractData.getContent();
        CloseableUtil.closeQuietly(in);
        logger.info(content);

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;

/**

labels.user_pager=Pager
labels.pager=Pager
labels.user_street=Street
labels.street=Street
labels.user_postalCode=Postal Code
labels.postalCode=Postal Code
labels.user_physicalDeliveryOfficeName=Office
labels.physicalDeliveryOfficeName=Office
labels.user_destinationIndicator=Destination Indicator
labels.destinationIndicator=Destination Indicator
labels.user_internationaliSDNNumber=International ISDN Number

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

labels.user_pager=Pager
labels.pager=Pager
labels.user_street=Street
labels.street=Street
labels.user_postalCode=Postal Code
labels.postalCode=Postal Code
labels.user_physicalDeliveryOfficeName=Office
labels.physicalDeliveryOfficeName=Office
labels.user_destinationIndicator=Destination Indicator
labels.destinationIndicator=Destination Indicator
labels.user_internationaliSDNNumber=International ISDN Number

- **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/