private static final Logger logger = LogManager.getLogger(ESSourceReader.class);

    /** Queue of documents. */
    protected final Queue<Map<String, Object>> queue = new ConcurrentLinkedQueue<>();
    /** Flag indicating if reading is finished. */
    protected final AtomicBoolean isFinished = new AtomicBoolean(false);
    /** Random number generator. */
    protected final Random random = new Random();

    /** OpenSearch client. */

    /** The OpenSearch client. */
    protected final Client client;
    /** The suggest settings. */
    protected final SuggestSettings suggestSettings;
    /** The reading converter. */
    protected final ReadingConverter readingConverter;
    /** The contents reading converter. */
    protected final ReadingConverter contentsReadingConverter;
    /** The normalizer. */
    protected final Normalizer normalizer;
    /** The analyzer. */

 *   <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>
 *   <li>Handling Tika exceptions, including zip bomb exceptions</li>
 * </ul>
 *
 * <p>

            }
        }

        /**
         * Gets an input stream to read from the storage object.
         *
         * @return An input stream for reading the object content
         * @throws IOException If the object cannot be accessed
         */
        @Override
        public InputStream getInputStream() throws IOException {
            if (minioClient == null) {

     */
    public void test_name_whitespace() {
        // Leading whitespace
        testTransformer.setName("  leadingSpaces");
        assertEquals("  leadingSpaces", testTransformer.getName());

        // Trailing whitespace
        testTransformer.setName("trailingSpaces  ");
        assertEquals("trailingSpaces  ", testTransformer.getName());

        // Both leading and trailing
        testTransformer.setName("  bothSpaces  ");

import org.apache.logging.log4j.Logger;
import org.codelibs.core.lang.StringUtil;

/**
 * Utility class for text normalization and processing.
 *
 * This class provides methods to normalize text by reading characters from a provided Reader
 * and processing them according to specific rules. The main functionality is encapsulated
 * within the nested {@link TextNormalizeContext} class.
 *

     *
     * @return the response body as an InputStream, or null if no response body is available
     * @throws IORuntimeException if an I/O error occurs while reading the response body file
     */
    public InputStream getResponseBody() {
        if (responseBodyBytes != null) {
            return new ByteArrayInputStream(responseBodyBytes);
        }

        private final int maxLineBuffer;

        /**
         * Constructs a new InputStreamThread.
         * @param is The InputStream to read from.
         * @param charset The charset to use for reading.
         * @param maxOutputLineBuffer The maximum number of lines to buffer.
         */
        public InputStreamThread(final InputStream is, final String charset, final int maxOutputLineBuffer) {
            try {

     *
     * @param inputStream the input stream to read from
     * @return the detected character set name, or null if not found
     * @throws CrawlingAccessException if an error occurs while reading the content
     */
    protected String loadCharset(final InputStream inputStream) {
        BufferedInputStream bis = null;
        String encoding = null;
        try {