Package org.apache.nutch.crawl

Class LinkDbReader

java.lang.Object

org.apache.hadoop.conf.Configured

org.apache.nutch.util.AbstractChecker

org.apache.nutch.crawl.LinkDbReader

All Implemented Interfaces:

Closeable, AutoCloseable, Configurable, Tool

public class LinkDbReader
extends AbstractChecker
implements Closeable

Read utility for the LinkDb.

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
static class	LinkDbReader.LinkDBDumpMapper

Field Summary

Fields inherited from class org.apache.nutch.util.AbstractChecker

keepClientCnxOpen, stdin, tcpPort, usage

Constructor Summary

Constructors

Constructor	Description
LinkDbReader()
LinkDbReader(Configuration conf, Path directory)

Method Summary

Modifier and Type	Method	Description
void	close()
String[]	getAnchors(Text url)
Inlinks	getInlinks(Text url)
void	init(Path directory)
static void	main(String[] args)
void	openReaders()
protected int	process(String line, StringBuilder output)
void	processDumpJob(String linkdb, String output, String regex)
int	run(String[] args)

Methods inherited from class org.apache.nutch.util.AbstractChecker

getProtocolOutput, parseArgs, processSingle, processStdin, processTCP, run

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

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

openReaders

public void openReaders()
                 throws IOException

Throws:

IOException

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 AutoCloseable

Specified by:

close in interface Closeable

Throws:

IOException

processDumpJob

public void processDumpJob(String linkdb,
                           String output,
                           String regex)
                    throws IOException,
                           InterruptedException,
                           ClassNotFoundException

Throws:

IOException

InterruptedException

ClassNotFoundException

process

protected int process(String line,
                      StringBuilder output)
               throws Exception

Specified by:

process in class AbstractChecker

Throws:

Exception

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