org.apache.nutch.crawl
Class LinkDbReader

java.lang.Object
  org.apache.hadoop.conf.Configured
      org.apache.nutch.crawl.LinkDbReader

All Implemented Interfaces:

Closeable, Configurable, Tool

public class LinkDbReader
extends Configured
implements Tool, Closeable

.

Field Summary

static org.slf4j.Logger

LOG

Constructor Summary

LinkDbReader()

LinkDbReader(Configuration conf, Path directory)

Method Summary

void	close()
String[]	getAnchors(Text url)
Inlinks	getInlinks(Text url)
void	init(Path directory)
static void	main(String[] args)
void	processDumpJob(String linkdb, String output)
int	run(String[] args)

Methods inherited from class org.apache.hadoop.conf.Configured

getConf, setConf

Methods inherited from class java.lang.Object

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

Methods inherited from interface org.apache.hadoop.conf.Configurable

getConf, setConf

Field Detail

LOG

public static final org.slf4j.Logger LOG

Constructor Detail

LinkDbReader

public LinkDbReader()

LinkDbReader

public LinkDbReader(Configuration conf,
                    Path directory)
             throws Exception

Throws:

Exception

Method Detail

init

public void init(Path directory)
          throws Exception

Throws:

Exception

getAnchors

public String[] getAnchors(Text url)
                    throws IOException

Throws:

IOException

getInlinks

public Inlinks getInlinks(Text url)
                   throws IOException

Throws:

IOException

close

public void close()
           throws IOException

Specified by:

close in interface Closeable

Throws:

IOException

processDumpJob

public void processDumpJob(String linkdb,
                           String output)
                    throws IOException

Throws:

IOException

main

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

Throws:

Exception

run

public int run(String[] args)
        throws Exception

Specified by:

run in interface Tool

Throws:

Exception