# Patterns to exclude for file search processing.
crawler.document.file.default.exclude.search.patterns=

# cache

# Whether document cache is enabled.
crawler.document.cache.enabled=true
# Maximum size (bytes) for document cache.
crawler.document.cache.max.size=2621440
# Supported MIME types for document cache.
crawler.document.cache.supported.mimetypes=text/html

     */
    boolean generate(String thumbnailId, File outputFile);

    /**
     * Checks if this generator can handle the given document.
     * @param docMap The document map containing metadata.
     * @return True if this generator can handle the document, false otherwise.
     */
    boolean isTarget(Map<String, Object> docMap);

    /**
     * Checks if this thumbnail generator is available for use.

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

 * This transformer handles document transformation and content extraction using
 * the standard Fess file transformation process with support for various content types.
 *
 * <p>It extends AbstractFessFileTransformer to provide file-specific transformation
 * capabilities while using the appropriate extractor for each document type.</p>
 */

        assertTrue(entry2.isComplete());
        assertTrue(entry1.hasChild("document.txt"));
        assertFalse(entry1.hasChild("subfolder"));
        assertTrue(entry2.hasChild("subfolder"));
        assertFalse(entry2.hasChild("document.txt"));

        // Test individual change notification
        directoryLeaseManager.handleDirectoryChange(dir1, "document.txt", DirectoryChangeNotifier.DirectoryChangeType.FILE_REMOVED);

            var client_id = Date.now()
            document.querySelector("#ws-id").textContent = client_id;
            var ws = new WebSocket(`ws://localhost:8000/ws/${client_id}`);
            ws.onmessage = function(event) {
                var messages = document.getElementById('messages')
                var message = document.createElement('li')
                var content = document.createTextNode(event.data)

                final String id = crawlingInfoHelper.generateId(dataMap);

                if (logger.isDebugEnabled()) {
                    logger.debug("Searching indexed document: {}", id);
                }
                final Map<String, Object> document = indexingHelper.getDocument(searchEngineClient, id,
                        new String[] { fessConfig.getIndexFieldId(), fessConfig.getIndexFieldLastModified(),

    }

    /**
     * Deletes document-related suggest words.
     *
     * @return JSON response indicating success or failure
     */
    // DELETE /api/admin/suggest/document
    @Execute
    public JsonResponse<ApiResult> delete$document() {
        if (!suggestHelper.deleteDocumentWords()) {

     *
     * @param builder
     *            {@link DocumentBuilder}; must not be {@literal null}.
     * @param is
     *            Input stream; must not be {@literal null}.
     * @return {@link Document}
     */
    public static Document parse(final DocumentBuilder builder, final InputStream is) {
        assertArgumentNotNull("builder", builder);
        assertArgumentNotNull("is", is);

        try {

import org.lastaflute.web.util.LaRequestUtil;

import jakarta.servlet.http.HttpServletRequest;

/**
 * Utility class for document data manipulation and type conversion.
 * This class provides static methods for extracting typed values from document maps,
 * URL encoding, and other document-related operations. It's designed as a final
 * utility class with only static methods.
 *
 */
public final class DocumentUtil {