throw exception;
        }
    }

    /**
     * Calculates the limit document number based on total, percentage, and number.
     * @param total The total number of documents.
     * @param limitPercentage The limit percentage.
     * @param limitNumber The limit number.
     * @return The calculated limit document number.
     */

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

    /** Maximum content size for extraction. -1 means no limit. */
    protected long maxContentSize = -1;

    /**
     * Creates a new LhaExtractor instance.
     */
    public LhaExtractor() {
        super();
    }

    /**

                return Collections.emptyList();
            }

            List<String> readings = new ArrayList<>();
            int limit = Math.min(langs.length, getMaxReadingNum());

            for (int i = 0; i < limit; i++) {
                readings.add(text.toUpperCase() + "_" + langs[i]);
            }

            return readings;
        }
    }

```java
// Configure memory usage
crawler.crawlerContext.setMaxAccessCount(10000);     // Limit crawled URLs
crawler.crawlerContext.setMaxDepth(5);               // Limit crawl depth

// Use streaming for large files
container.singleton("fileTransformer", FileTransformer.class, transformer -> {
    transformer.setMaxContentSize(10 * 1024 * 1024); // 10MB limit
});
```

## Troubleshooting

### Common Issues

     * This method delegates to {@link FileInputStream#mark(int)}.
     *
     * @param readlimit the maximum limit of bytes that can be read before the mark position becomes invalid
     */
    @Override
    public synchronized void mark(final int readlimit) {
        fileInputStream.mark(readlimit);
    }

    /**

        accessResult.init(responseData, resultData);
        return accessResult;
    }

    /**
     * Checks if the access count is within the allowed limit.
     *
     * @param crawlerContext the crawler context
     * @return true if access count is within limit, false otherwise
     */
    protected boolean checkAccessCount(final CrawlerContext crawlerContext) {
        if (crawlerContext.getMaxAccessCount() > 0) {

     */
    @Override
    public int hashCode() {
        return inputStream.hashCode();
    }

    /**
     * Marks the current position in this input stream.
     *
     * @param readlimit the maximum limit of bytes that can be read before the mark position becomes invalid
     */
    @Override
    public synchronized void mark(final int readlimit) {
        inputStream.mark(readlimit);
    }

    /**

    /** The maximum depth for crawling. A value of -1 indicates no depth check. */
    protected int maxDepth = -1;

    /** The maximum number of URLs to access. A value of 0 indicates no limit. */
    protected long maxAccessCount = 0;

    /**
     * Returns the session ID.
     * @return The session ID.
     */
    public String getSessionId() {
        return sessionId;
    }

    /** The access timeout in seconds. Default is null (no timeout). */
    protected Integer accessTimeout = null; // seconds

    /** The maximum content length in bytes. Default is null (no limit). */
    protected Long maxContentLength = null;

    /**
     * Constructs a new AbstractCrawlerClient.
     */
    public AbstractCrawlerClient() {
        // NOP
    }

    /**

        "stopwords": "_english_"
      },
      "content_length_filter": {
        "type": "length",
        "max": 30
      },
      "limit_token_count_filter": {
        "type": "limit",
        "max_token_count": 10000
      },
      "stemmer_en_filter": {
        "type": "stemmer",
        "name": "possessive_english"
      },
      "arabic_stop": {
        "type":       "stop",