Package org.apache.nutch.protocol

Class Content

java.lang.Object

org.apache.nutch.protocol.Content

All Implemented Interfaces:

Writable

public final class Content
extends Object
implements Writable

Field Summary

Fields

Modifier and Type	Field	Description
static String	DIR_NAME

Constructor Summary

Constructors

Constructor	Description
Content()
Content(String url, String base, byte[] content, String contentType, Metadata metadata, Configuration conf)
Content(String url, String base, byte[] content, String contentType, Metadata metadata, MimeUtil mimeTypes)

Method Summary

Modifier and Type	Method	Description
boolean	equals(Object o)
String	getBaseUrl()	The base url for relative links contained in the content.
byte[]	getContent()	The binary content retrieved.
String	getContentType()	The media type of the retrieved content.
Metadata	getMetadata()	Other protocol-specific data.
String	getUrl()	The url fetched.
static void	main(String[] argv)
static Content	read(DataInput in)
void	readFields(DataInput in)
void	setContent(byte[] content)
void	setContentType(String contentType)
void	setMetadata(Metadata metadata)	Other protocol-specific data.
String	toString()
String	toString(String charset)
String	toString(Charset charset)
void	write(DataOutput out)

Methods inherited from class java.lang.Object

clone, finalize, getClass, hashCode, notify, notifyAll, wait, wait, wait

Field Detail

DIR_NAME

public static final String DIR_NAME

See Also:

Constant Field Values

Constructor Detail

Content

public Content()

Content

public Content(String url,
               String base,
               byte[] content,
               String contentType,
               Metadata metadata,
               Configuration conf)

Content

public Content(String url,
               String base,
               byte[] content,
               String contentType,
               Metadata metadata,
               MimeUtil mimeTypes)

Method Detail

readFields

public final void readFields(DataInput in)
                      throws IOException

Specified by:

readFields in interface Writable

Throws:

IOException

write

public final void write(DataOutput out)
                 throws IOException

Specified by:

write in interface Writable

Throws:

IOException

read

public static Content read(DataInput in)
                    throws IOException

Throws:

IOException

getUrl

public String getUrl()

The url fetched.

Returns:

the fetched url

getBaseUrl

public String getBaseUrl()

The base url for relative links contained in the content. Maybe be different from url if the request redirected.

Returns:

the base url

getContent

public byte[] getContent()

The binary content retrieved.

Returns:

content as a byte[]

setContent

public void setContent(byte[] content)

getContentType

public String getContentType()

The media type of the retrieved content.

Returns:

content type

See Also:

http://www.iana.org/assignments/media-types/

setContentType

public void setContentType(String contentType)

getMetadata

public Metadata getMetadata()

Other protocol-specific data.

Returns:

additional Metadata

setMetadata

public void setMetadata(Metadata metadata)

Other protocol-specific data.

Parameters:

metadata - a populated Metadata object to set

equals

public boolean equals(Object o)

Overrides:

equals in class Object

toString

public String toString()

Overrides:

toString in class Object

toString

public String toString(String charset)

toString

public String toString(Charset charset)

main

public static void main(String[] argv)
                 throws Exception

Throws:

Exception