- 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

				}
			}
		}
		return false, false, nil
	}
	return false, false, erErr
}

const (
	xMinIOHealing = ReservedMetadataPrefix + "healing"
	xMinIODataMov = ReservedMetadataPrefix + "data-mov"
)

// SetHealing marks object (version) as being healed.
// Note: this is to be used only from healObject
func (fi *FileInfo) SetHealing() {
	if fi.Metadata == nil {
		fi.Metadata = make(map[string]string)

X13, X14, X15, X16, X17, X10, X11) SHA512ROUND1(79, X11, X12, X13, X14, X15, X16, X17, X10) MOV (0*8)(X20), X5 MOV (1*8)(X20), X6 MOV (2*8)(X20), X7 MOV (3*8)(X20), X8 ADD X5, X10 // H0 = a + H0 ADD X6, X11 // H1 = b + H1 ADD X7, X12 // H2 = c + H2 ADD X8, X13 // H3 = d + H3 MOV X10, (0*8)(X20) MOV X11, (1*8)(X20) MOV X12, (2*8)(X20) MOV X13, (3*8)(X20) MOV (4*8)(X20), X5 MOV (5*8)(X20), X6 MOV (6*8)(X20), X7 MOV (7*8)(X20), X8 ADD X5, X14 // H4 = e + H4 ADD X6, X15 // H5 = f + H5 ADD X7, X16 // H6 =...

Instead, the compiler operates on a kind of semi-abstract instruction set,
and instruction selection occurs partly after code generation.
The assembler works on the semi-abstract form, so
when you see an instruction like <code>MOV</code>
what the toolchain actually generates for that operation might
not be a move instruction at all, perhaps a clear or load.
Or it might correspond exactly to the machine instruction with that name.

				"video/vnd.nokia.videovoip",
				"video/vnd.objectvideo",
				"video/vnd.sealed.mpeg1",
				"video/vnd.sealed.mpeg4",
				"video/vnd.sealed.swf",
				"video/vnd.sealedmedia.softseal.mov",
				"video/vnd.vivo",
				"video/x-f4v",
				"video/x-flc",
				"video/x-fli",
				"video/x-flv",
				"video/x-jng",
				"video/x-m4v",
				"video/x-mng",
				"video/x-ms-asf",

	VPERMPD $216, Y7, Y7 // c4e3fd01ffd8
	// Check that LEAL is permitted to use overflowing offset.
	LEAL 2400959708(BP)(R10*1), BP // 428dac15dcbc1b8f
	LEAL 3395469782(AX)(R10*1), AX // 428d8410d6c162ca
	// Make sure MOV CR/DR continues to work after changing its movtabs.
	MOVQ CR0, AX // 0f20c0
	MOVQ CR0, DX // 0f20c2
	MOVQ CR4, DI // 0f20e7
	MOVQ AX, CR0 // 0f22c0
	MOVQ DX, CR0 // 0f22c2
	MOVQ DI, CR4 // 0f22e7

	VMOVQ	$0x8040201008040202, $0x7040201008040201, V20         // VMOVQ	$-9205322385119247870, $8088500183983456769, V20

// mov(to/from sp)
	MOVD	$0x1002(RSP), R1              // MOVD	$4098(RSP), R1              // e107409121080091
	MOVD	$0x1708(RSP), RSP             // MOVD	$5896(RSP), RSP             // ff074091ff231c91

// https://www.iana.org/domains/root/db/moto.html
moto

// motorcycles : XYZ.COM LLC
// https://www.iana.org/domains/root/db/motorcycles.html
motorcycles

// mov : Charleston Road Registry Inc.
// https://www.iana.org/domains/root/db/mov.html
mov

// movie : Binky Moon, LLC
// https://www.iana.org/domains/root/db/movie.html
movie

// msd : MSD Registry Holdings, Inc.

moscow
moseushi.hokkaido.jp
mosjoen.no
mosjøen.no
moskenes.no
moss.no
mosvik.no
motegi.tochigi.jp
moto
motobu.okinawa.jp
motorcycles
motosu.gifu.jp
motoyama.kochi.jp
mov
movie
movimiento.bo
moåreke.no
mp
mp.br
mq
mr
mr.no
mragowo.pl
mrap.accesspoint.s3-global.amazonaws.com
ms
ms.gov.br
ms.it
ms.kr
ms.leg.br
ms.us

      <!-- Common starting Atoms of fixed size -->
      <match value="\x00\x00\x00\x08wide" type="string" offset="0"/>
    </magic>
    <glob pattern="*.qt"/>
    <glob pattern="*.mov"/>
    <sub-class-of type="application/quicktime" />
  </mime-type>

  <mime-type type="video/raw"/>
  <mime-type type="video/rtp-enc-aescm128"/>
  <mime-type type="video/rtx"/>