- Nested archive extraction

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

#### Media Files
- Audio formats (MP3, WAV, FLAC)
- Video formats (MP4, AVI, MOV)
- Metadata extraction from media files

## Architecture

### Multi-Module Structure

```
fess-crawler-parent/
├── fess-crawler/              # Core crawler framework

				"application/mediaservercontrol+xml",
				"application/mikey",
				"application/moss-keys",
				"application/moss-signature",
				"application/mosskey-data",
				"application/mosskey-request",
				"application/mp4",
				"application/mpeg4-generic",
				"application/mpeg4-iod",
				"application/mpeg4-iod-xmt",
				"application/msword",
				"application/msword2",
				"application/msword5",
				"application/mxf",

   *
   * @since 28.1
   */
  public static final MediaType JP2K = createConstant(IMAGE_TYPE, "jp2");

  /* audio types */
  public static final MediaType MP4_AUDIO = createConstant(AUDIO_TYPE, "mp4");
  public static final MediaType MPEG_AUDIO = createConstant(AUDIO_TYPE, "mpeg");
  public static final MediaType OGG_AUDIO = createConstant(AUDIO_TYPE, "ogg");

                        + "      <video:description>Sample video description</video:description>\n"
                        + "      <video:content_loc>http://www.example.com/video123.mp4</video:content_loc>\n"
                        + "      <video:duration>600</video:duration>\n" + "    </video:video>\n" + "  </url>\n" + "</urlset>";
        final InputStream in = new ByteArrayInputStream(xml.getBytes());

application/x-rar-compressed=rar\n\
video/3gp=3gp\n\
video/3g2=3g2\n\
video/x-msvideo=avi\n\
video/x-flv=flv\n\
video/mpeg=mpeg\n\
video/mp4=mp4\n\
video/ogv=ogv\n\
video/quicktime=qt\n\
video/x-m4v=m4v\n\
audio/x-aif=aif\n\
audio/midi=midi\n\
audio/mpga=mpga\n\
audio/mp4=mp4a\n\
audio/ogg=oga\n\
audio/x-wav=wav\n\
image/webp=webp\n\
image/bmp=bmp\n\
image/x-icon=ico\n\
image/x-icon=ico\n\

   *
   * @since 28.1
   */
  public static final MediaType JP2K = createConstant(IMAGE_TYPE, "jp2");

  /* audio types */
  public static final MediaType MP4_AUDIO = createConstant(AUDIO_TYPE, "mp4");
  public static final MediaType MPEG_AUDIO = createConstant(AUDIO_TYPE, "mpeg");
  public static final MediaType OGG_AUDIO = createConstant(AUDIO_TYPE, "ogg");

labels.facet_filetype_3gp=3gp Video
labels.facet_filetype_3g2=3g2 Video
labels.facet_filetype_avi=AVI Video
labels.facet_filetype_flv=FLV Video
labels.facet_filetype_mpeg=MPEG Video
labels.facet_filetype_mp4=MP4 Video
labels.facet_filetype_ogv=OGV Video
labels.facet_filetype_qt=QuickTime Video
labels.facet_filetype_m4v=M4V Video
labels.facet_filetype_ogg=OGG Audio
labels.facet_filetype_wav=WAV Audio

labels.facet_filetype_rar=RAR存檔
labels.facet_filetype_3gp=3gp視訊
labels.facet_filetype_3g2=3g2視訊
labels.facet_filetype_avi=AVI視訊
labels.facet_filetype_flv=FLV視訊
labels.facet_filetype_mpeg=MPEG視訊
labels.facet_filetype_mp4=MP4視訊
labels.facet_filetype_ogv=OGV視訊
labels.facet_filetype_qt=QuickTime視訊
labels.facet_filetype_m4v=M4V視訊
labels.facet_filetype_ogg=OGG音訊
labels.facet_filetype_wav=WAV音訊
labels.facet_filetype_webp=WebP音訊

     * video/x-msvideo=avi<br>
     * video/x-flv=flv<br>
     * video/mpeg=mpeg<br>
     * video/mp4=mp4<br>
     * video/ogv=ogv<br>
     * video/quicktime=qt<br>
     * video/x-m4v=m4v<br>
     * audio/x-aif=aif<br>
     * audio/midi=midi<br>
     * audio/mpga=mpga<br>
     * audio/mp4=mp4a<br>
     * audio/ogg=oga<br>
     * audio/x-wav=wav<br>
     * image/webp=webp<br>
     * image/bmp=bmp<br>

labels.facet_filetype_3gp=3gp-video
labels.facet_filetype_3g2=3g2-video
labels.facet_filetype_avi=AVI-video
labels.facet_filetype_flv=FLV-video
labels.facet_filetype_mpeg=MPEG-video
labels.facet_filetype_mp4=MP4-video
labels.facet_filetype_ogv=OGV-video
labels.facet_filetype_qt=QuickTime-video
labels.facet_filetype_m4v=M4V-video
labels.facet_filetype_ogg=OGG-audio
labels.facet_filetype_wav=WAV-audio