import org.apache.tika.metadata.TIFF;
import org.apache.tika.metadata.TikaCoreProperties;
import org.apache.tika.metadata.TikaMimeKeys;

/**
 * Represents extracted data from a crawled resource, including content and metadata.
 */
public class ExtractData
        implements TikaCoreProperties, CreativeCommons, Geographic, HttpHeaders, Message, ClimateForcast, TIFF, TikaMimeKeys, Serializable {

#### Office Documents
- Microsoft Office (Word, Excel, PowerPoint)
- OpenOffice/LibreOffice documents
- 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

    <glob pattern="*.crw"/>
  </mime-type>

  <mime-type type="image/x-canon-cr2">
    <_comment>Canon raw image, version 2, TIFF-based</_comment>
    <!-- basically tiff header with 'CR' at offset 8; major version is at offset 9, minor at 10/.
     priority must be higher than tiff -->
    <magic priority="60">
      <!-- MM.* = Big endian (M=Motorola) and 0x002a in big endian    -->