org.apache.nutch.protocol
Class Content

java.lang.Object
  org.apache.nutch.protocol.Content

All Implemented Interfaces:

org.apache.hadoop.io.Writable

public final class Content
extends Object
implements org.apache.hadoop.io.Writable

Field Summary

static String

DIR_NAME

Constructor Summary

Content()

Content(String url, String base, byte[] content, String contentType, Metadata metadata, org.apache.hadoop.conf.Configuration conf)

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

Method Summary

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[] args)
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()
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,
               org.apache.hadoop.conf.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 org.apache.hadoop.io.Writable

Throws:

IOException

write

public final void write(DataOutput out)
                 throws IOException

Specified by:

write in interface org.apache.hadoop.io.Writable

Throws:

IOException

read

public static Content read(DataInput in)
                    throws IOException

Throws:

IOException

getUrl

public String getUrl()

The url fetched.

getBaseUrl

public String getBaseUrl()

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

getContent

public byte[] getContent()

The binary content retrieved.

setContent

public void setContent(byte[] content)

getContentType

public String getContentType()

The media type of the retrieved content.

See Also:

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

setContentType

public void setContentType(String contentType)

getMetadata

public Metadata getMetadata()

Other protocol-specific data.

setMetadata

public void setMetadata(Metadata metadata)

Other protocol-specific data.

equals

public boolean equals(Object o)

Overrides:

equals in class Object

toString

public String toString()

Overrides:

toString in class Object

main

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

Throws:

Exception