Directive directive = new Directive("MyBot");

        directive.addAllow("/public/");
        directive.addAllow("/images/");

        String[] allows = directive.getAllows();
        assertEquals(2, allows.length);
        assertEquals("/public/", allows[0]);
        assertEquals("/images/", allows[1]);
    }

    public void test_directiveAddAllowNoDuplicates() {

### 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)

#### Archives and Compressed Files
- ZIP, TAR, GZ archives
- LHA compression format
- Nested archive extraction

    }

    /**
     * Gets the path to image files directory.
     *
     * @param names the path components to append to the images directory
     * @return the Path object pointing to the images directory
     */
    public static Path getImagePath(final String... names) {
        return getPath(StringUtil.EMPTY, "images", names);
    }

    /**
     * Gets the path to CSS files directory.

/**
 * HTML tag-based thumbnail generator that creates thumbnails from image content
 * referenced in HTML documents. This generator extracts images from HTML content
 * and processes them to create thumbnail images based on configured dimensions
 * and format settings.
 *
 * <p>The generator validates image MIME types, processes image data through
 * ImageIO operations, and applies scaling and cropping to generate thumbnails

        }
        return false;
    }

    /**
     * Gets the image filename for a document based on its document map.
     *
     * @param docMap the document data map
     * @return the generated image filename
     */
    protected String getImageFilename(final Map<String, Object> docMap) {

                && checkFileType(uploadedFileName, fessConfig.getSupportedUploadedMediaExtentionsAsArray())) {
            uploadFile = new File(getServletContext().getRealPath("/images/" + fileName));
        } else if (checkFileType(fileName, fessConfig.getSupportedUploadedCssExtentionsAsArray())
                && checkFileType(uploadedFileName, fessConfig.getSupportedUploadedCssExtentionsAsArray())) {

- **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/
├── fess-crawler/              # Core framework
├── fess-crawler-lasta/        # LastaFlute DI integration

        }
        return switch (mimeType) {
        case "image/gif" -> ".gif";
        case "image/tiff" -> ".tiff";
        case "image/svg+xml" -> ".svg";
        case "image/jpeg" -> ".jpg";
        case "image/png" -> ".png";
        case "image/bmp", "image/x-windows-bmp", "image/x-ms-bmp" -> ".bmp";
        case "image/vnd.adobe.photoshop", "image/photoshop", "application/x-photoshop", "application/photoshop" -> ".psd";

        // But exclude images and admin section
        urlFilter.addExclude(".*\\.(jpg|png|gif)$");
        urlFilter.addExclude(".*/admin/.*");

        assertTrue(urlFilter.match("https://example.com/page.html"));
        assertTrue(urlFilter.match("https://example.com/document.pdf"));
        assertFalse(urlFilter.match("https://example.com/image.jpg"));

import jakarta.servlet.ServletContext;

/**
 * Job class for generating thumbnails for documents in the search engine.
 * This job executes the ThumbnailGenerator process as a separate JVM process
 * to create thumbnail images for supported document types.
 */
public class GenerateThumbnailJob extends ExecJob {
    /** Logger for this class. */
    static final Logger logger = LogManager.getLogger(GenerateThumbnailJob.class);