labels.facet_filetype_3g2=3g2ビデオ
labels.facet_filetype_avi=AVIビデオ
labels.facet_filetype_flv=FLVビデオ
labels.facet_filetype_mpeg=MPEGビデオ
labels.facet_filetype_mp4=MP4ビデオ
labels.facet_filetype_ogv=OGVビデオ
labels.facet_filetype_qt=QuickTimeビデオ
labels.facet_filetype_m4v=M4Vビデオ
labels.facet_filetype_ogg=OGGオーディオ
labels.facet_filetype_wav=WAVオーディオ
labels.facet_filetype_webp=WebPオーディオ
labels.facet_filetype_aif=AIFオーディオ

- 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

   *
   * @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());

   *
   * @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");

    /** The key of the message: MPGA Audio */
    public static final String LABELS_facet_filetype_mpga = "{labels.facet_filetype_mpga}";

    /** The key of the message: MP4A Audio */
    public static final String LABELS_facet_filetype_mp4a = "{labels.facet_filetype_mp4a}";

    /** The key of the message: OGA Audio */

o.default.fn.modal=ut,Ct._jQueryInterface};var St=["background","cite","href","itemtype","longdesc","poster","src","xlink:href"],Nt=/^(?:(?:https?|mailto|ftp|tel|file|sms):|[^#&/:?]*(?:[#/?]|$))/i,Dt=/^data:(?:image\/(?:bmp|gif|jpeg|jpg|png|tiff|webp)|video\/(?:mpeg|mp4|ogg|webm)|audio\/(?:mp3|oga|ogg|opus));base64,[\d+/a-z]+=*$/i;function At(t,e,n){if(0===t.length)return t;if(n&&"function"==typeof n)return n(t);for(var i=(new window.DOMParser).parseFromString(t,"text/html"),o=Object.keys(e),a=[].slice.call(i.body...

image, video and audio types.\n *\n * Shoutout to Angular https://github.com/angular/angular/blob/12.2.x/packages/core/src/sanitization/url_sanitizer.ts\n */\nconst DATA_URL_PATTERN = /^data:(?:image\\/(?:bmp|gif|jpeg|jpg|png|tiff|webp)|video\\/(?:mpeg|mp4|ogg|webm)|audio\\/(?:mp3|oga|ogg|opus));base64,[\\d+/a-z]+=*$/i\n\nfunction allowedAttribute(attr, allowedAttributeList) {\n  const attrName = attr.nodeName.toLowerCase()\n\n  if (allowedAttributeList.indexOf(attrName) !== -1) {\n    if (uriAttrs.indexOf(attrName)...