/** Max Buffer Size */
    protected static final int MAX_BUF_SIZE = 10 * 1024 * 1024; // 10m

    /**
     * Validates that a given path is safe and does not attempt path traversal attacks.
     * <p>
     * This method checks if the resolved absolute path starts with the allowed base directory,
     * preventing access to files outside the intended directory through path traversal

        });
    }

    /**
     * Handles user login with the provided credentials.
     *
     * @param form the login form containing username and password
     * @return the HTML response after login attempt
     */
    @Execute
    public HtmlResponse login(final LoginForm form) {
        validate(form, messages -> {}, () -> asIndexPage(form));
        verifyToken(() -> asIndexPage(form));

                    logger.debug("Token expired: expiryTime={}, currentTime={}", tokenExpiryTime, currentTime);
                }
                return false;
            }
            // Attempt to refresh token using MSAL4J silent authentication
            try {
                final EntraIdAuthenticator authenticator = ComponentUtil.getComponent(EntraIdAuthenticator.class);

        final Path safePath = baseDir.resolve("subdir/file.txt");

        assertTrue("Safe path should be allowed", FileUtil.isPathSafe(safePath, baseDir));
    }

    /**
     * Test isPathSafe with path traversal attempt
     *
     * @throws Exception
     */
    @Test
    public void testIsPathSafe_PathTraversalAttempt() throws Exception {
        final Path baseDir = tempFolder.getRoot().toPath();

 * </p>
 * <ul>
 *   <li>Normalizing text content</li>
 *   <li>Handling resource names and content types</li>
 *   <li>Retrying extraction without resource name or content type if the initial attempt fails</li>
 *   <li>Extracting text from metadata if the main content extraction fails</li>
 *   <li>Reading content as plain text if all other methods fail</li>
 *   <li>Applying post-extraction filters</li>

                    if (errorCount > maxErrorCount) {
                        throw e;
                    }
                    errorCount++;
                    logger.warn("Failed to access AccessResult data. Retrying... (attempt={}/{})", errorCount, maxErrorCount, e);
                } finally {
                    if (systemHelper.isForceStop()) {
                        finishCrawling = true;
                        if (logger.isDebugEnabled()) {

        String objectName = (String) getField(conn, "objectName");
        assertEquals("/path//to//object.txt", objectName);
    }

    /**
     * Test that getInputStream() attempts to connect if not connected.
     */
    public void test_getInputStream_autoConnect() throws Exception {
        URL url = new URL("gcs://mybucket/object.txt");
        Handler handler = new Handler();

        String objectName = (String) getField(conn, "objectName");
        assertEquals("/path//to//object.txt", objectName);
    }

    /**
     * Test that getInputStream() attempts to connect if not connected.
     */
    public void test_getInputStream_autoConnect() throws Exception {
        URL url = new URL("storage://mybucket/object.txt");
        Handler handler = new Handler();

    /**
     * Creates a new instance of CrawlerClientFactory.
     */
    public CrawlerClientFactory() {
        // NOP
    }

    /**
     * Initializes the CrawlerClientFactory.
     * Attempts to register itself with a "crawlerClientCreator" component if available.
     */
    @PostConstruct
    public void init() {
        try {

 */
public class IndexingHelper {
    /** Logger for this class */
    private static final Logger logger = LogManager.getLogger(IndexingHelper.class);

    /** Maximum number of retry attempts for failed operations */
    protected int maxRetryCount = 5;

    /** Default number of rows to process in a single batch */
    protected int defaultRowSize = 100;

    /**