/**
 * <p>
 * {@link ESSourceReader} reads documents from Elasticsearch using the scroll API.
 * It implements the {@link DocumentReader} interface to provide a way to iterate over documents
 * in a large index without loading all of them into memory at once.
 * </p>
 *
 * <p>
 * The reader supports limiting the number of documents read based on a percentage of the total documents

            this.reader = reader;
        }

        /**
         * Executes the text processing operation on the provided reader.
         *
         * This method reads characters from the reader and processes them according to the following rules:
         * - ISO control characters and space characters are treated as spaces.

        // Test user boost
        item.setUserBoost(2.0f);
        assertEquals(2.0f, item.getUserBoost(), 0.001f);

        // Test readings
        String[][] newReadings = { { "read1", "read2" }, { "read3" } };
        item.setReadings(newReadings);
        assertArrayEquals(newReadings, item.getReadings());

        // Test fields
        String[] fields = { "field1", "field2" };

     */
    public void setOutputEncoding(final String outputEncoding) {
        this.outputEncoding = outputEncoding;
    }

    /**
     * Sets whether to read content as text if extraction fails.
     * @param readAsTextIfFailed If true, read a content as a text when an extraction fails.
     */
    public void setReadAsTextIfFailed(final boolean readAsTextIfFailed) {
        this.readAsTextIfFailed = readAsTextIfFailed;

            if (minioClient == null) {
                throw new IOException("Access is not ready.");
            }
            try {
                final GetObjectArgs args = GetObjectArgs.builder().bucket(bucketName).object(objectName).build();
                return minioClient.getObject(args);

        final BufferedInputStream bis = new BufferedInputStream(in);
        bis.mark(preloadSize);

        final byte[] bytes = new byte[preloadSize];
        try {
            if (bis.read(bytes) == -1) {
                return false;
            }

            final String preloadDate = new String(bytes, Constants.UTF_8);

            try {
                QueryLog queryLog = queryLogReader.read();
                while (queryLog != null) {
                    if (Thread.currentThread().isInterrupted()) {
                        break;
                    }
                    queryLogs.add(queryLog);
                    queryLog = queryLogReader.read();

 *       to extract child URLs.</li>
 *   <li><b>defaultEncoding:</b> The default character encoding to use if none is
 *       specified in the HTML content.</li>
 *   <li><b>preloadSizeForCharset:</b> The number of bytes to read from the input
 *       stream to determine the character set encoding.</li>
 *   <li><b>invalidUrlPattern:</b> A regular expression pattern used to identify
 *       invalid URLs.</li>
 * </ul>
 *
 * <p>

         * @return true if terminated, false otherwise.
         */
        public boolean isTeminated() {
            return teminated;
        }
    }

    /**
     * Thread to read and buffer output from an input stream.
     */
    protected static class InputStreamThread extends Thread {

        private BufferedReader br;

        private final List<String> list = new LinkedList<>();

    client.setMaxConnectionsPerRoute(20);   // Per-host connections
    client.setConnectionTimeout(30000);     // Connection timeout
    client.setSocketTimeout(60000);         // Read timeout
});
```

### Memory Management

```java
// Configure memory usage
crawler.crawlerContext.setMaxAccessCount(10000);     // Limit crawled URLs