throws CIFSException {
        byte[] decompressed = decompress(compressedData, offset, length, algorithm);
        if (outputBuffer.length - outputOffset < decompressed.length) {
            throw new CIFSException("Output buffer too small");
        }
        System.arraycopy(decompressed, 0, outputBuffer, outputOffset, decompressed.length);
        return decompressed.length;
    }

    @Override

    }

    /**
     * Decompresses GZIP-compressed data.
     *
     * @param compressed The GZIP-compressed data to decompress
     * @return Decompressed data
     * @throws IORuntimeException if decompression fails
     */
    protected byte[] gzipDecompress(final byte[] compressed) {
        try (final ByteArrayInputStream bis = new ByteArrayInputStream(compressed);

import org.xml.sax.helpers.DefaultHandler;

/**
 * Helper class for parsing and validating sitemaps.
 * It supports XML sitemaps, XML sitemap indexes, and text sitemaps,
 * and can handle GZIP compressed sitemaps.
 * The class provides methods to check if an input stream is a valid sitemap,
 * and to parse an input stream into a {@link SitemapSet} object.
 * It uses SAX parser for XML sitemaps and XML sitemap indexes,

    /** Directory attribute */
    int ATTR_DIRECTORY = 0x10;
    /** Archive attribute */
    int ATTR_ARCHIVE = 0x20;

    // extended file attribute encoding(others same as above)
    /** Compressed file attribute */
    int ATTR_COMPRESSED = 0x800;
    /** Normal file attribute */
    int ATTR_NORMAL = 0x080;
    /** Temporary file attribute */
    int ATTR_TEMPORARY = 0x100;

        recordNameField.set(nameQueryResponse, mockRecordName);

        // Prepare a byte array with valid NetBIOS name format
        byte[] src = new byte[100];
        int srcIndex = 0;

        // Start with compressed name pointer (0xC0) to use questionName
        src[srcIndex] = (byte) 0xC0;
        src[srcIndex + 1] = 0x0C; // Pointer offset
        // recordType (2 bytes)
        src[srcIndex + 2] = 0x00;

        } catch (final Exception e) {
            throw new CrawlingAccessException("Failed to parse " + url, e);
        }
    }

    /**
     * Decodes a similar document hash from its compressed and encoded form.
     * Reverses the encoding process applied by encodeSimilarDocHash.
     *
     * @param hash the encoded hash string to decode

    /**
     * Files is marked to be archived
     */
    int ATTR_ARCHIVE = 0x20;

    // extended file attribute encoding(others same as above)
    /**
     * File is compressed.
     */
    int ATTR_COMPRESSED = 0x800;
    /**
     * File is a normal file.
     */
    int ATTR_NORMAL = 0x080;
    /**
     * File is temporary.
     */
    int ATTR_TEMPORARY = 0x100;

- RTF, WordPerfect

#### PDFs and Images
- PDF documents (text and metadata extraction)
- Images (JPEG, PNG, GIF, TIFF, BMP)
- Image metadata (EXIF, IPTC, XMP)

#### Archives and Compressed Files
- ZIP, TAR, GZ archives
- LHA compression format
- Nested archive extraction

#### Web and Markup
- HTML, XHTML with XPath support
- XML documents
- JSON and structured data