org.apache.nutch.net.urlnormalizer.slash

Class SlashURLNormalizer

java.lang.Object

org.apache.nutch.net.urlnormalizer.slash.SlashURLNormalizer

All Implemented Interfaces:

Configurable, URLNormalizer

public class SlashURLNormalizer
extends java.lang.Object
implements URLNormalizer

Author:

markus@openindex.io

Field Summary

Fields inherited from interface org.apache.nutch.net.URLNormalizer

X_POINT_ID

Constructor Summary

Constructors

Constructor and Description
SlashURLNormalizer()
SlashURLNormalizer(java.lang.String slashesFile)

Method Summary

Modifier and Type	Method and Description
Configuration	getConf()
java.lang.String	normalize(java.lang.String url, CrawlDatum crawlDatum, java.lang.String scope)
java.lang.String	normalize(java.lang.String url, java.lang.String scope)
void	setConf(Configuration conf)

Methods inherited from class java.lang.Object

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

Constructor Detail

SlashURLNormalizer

public SlashURLNormalizer()

SlashURLNormalizer

public SlashURLNormalizer(java.lang.String slashesFile)

Method Detail

getConf

public Configuration getConf()

Specified by:

getConf in interface Configurable

setConf

public void setConf(Configuration conf)

Specified by:

setConf in interface Configurable

normalize

public java.lang.String normalize(java.lang.String url,
                                  java.lang.String scope)
                           throws java.net.MalformedURLException

Specified by:

normalize in interface URLNormalizer

Throws:

java.net.MalformedURLException

normalize

public java.lang.String normalize(java.lang.String url,
                                  CrawlDatum crawlDatum,
                                  java.lang.String scope)
                           throws java.net.MalformedURLException

Throws:

java.net.MalformedURLException