This project has retired. For details please refer to its Attic page.

org.apache.lenya.search.crawler
Class HTMLHandler

java.lang.Object
  javax.swing.text.html.HTMLEditorKit.ParserCallback
      org.apache.lenya.search.crawler.HTMLHandler

All Implemented Interfaces:

ContentHandler

public final class HTMLHandler
extends javax.swing.text.html.HTMLEditorKit.ParserCallback
implements ContentHandler

DOCUMENT ME!

Field Summary

Fields inherited from class javax.swing.text.html.HTMLEditorKit.ParserCallback

IMPLIED

Constructor Summary

HTMLHandler()
Constructor - initializes variables

Method Summary

java.lang.String	getAuthor() Parse Content. [24] 320:1
java.lang.String	getCategories() Return categories (from META tags)
java.lang.String	getContents() Return contents
java.lang.String	getDescription() Return description (from META tags)
java.lang.String	getHREF() Return META HREF
java.lang.String	getKeywords() Return keywords (from META tags)
java.util.List	getLinks() Return links
long	getPublished() Return published date (from META tag)
boolean	getRobotFollow() Return boolean true if links are to be followed
boolean	getRobotIndex() Return boolean true if this is to be indexed
java.lang.String	getTitle() Return page title
void	handleAnchor(javax.swing.text.MutableAttributeSet attribs) Handle Anchor tags
void	handleEndTag(javax.swing.text.html.HTML.Tag tag, int pos) Closing tag
void	handleMeta(javax.swing.text.MutableAttributeSet attribs) Handle META tags
void	handleSimpleTag(javax.swing.text.html.HTML.Tag tag, javax.swing.text.MutableAttributeSet attribs, int pos) Handle standalone tags
void	handleStartTag(javax.swing.text.html.HTML.Tag tag, javax.swing.text.MutableAttributeSet attribs, int pos) Opening tag
void	handleText(char[] text, int pos) Handle page text
void	parse(java.io.InputStream in) Parse Content.

Methods inherited from class javax.swing.text.html.HTMLEditorKit.ParserCallback

flush, handleComment, handleEndOfLineString, handleError

Methods inherited from class java.lang.Object

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

Constructor Detail

HTMLHandler

public HTMLHandler()

Constructor - initializes variables

Method Detail

getAuthor

public java.lang.String getAuthor()

Parse Content. [24] 320:1

Specified by:

getAuthor in interface ContentHandler

Returns:

DOCUMENT ME!

getCategories

public java.lang.String getCategories()

Return categories (from META tags)

Specified by:

getCategories in interface ContentHandler

Returns:

DOCUMENT ME!

getContents

public java.lang.String getContents()

Return contents

Specified by:

getContents in interface ContentHandler

Returns:

DOCUMENT ME!

getDescription

public java.lang.String getDescription()

Return description (from META tags)

Specified by:

getDescription in interface ContentHandler

Returns:

DOCUMENT ME!

getHREF

public java.lang.String getHREF()

Return META HREF

Specified by:

getHREF in interface ContentHandler

Returns:

DOCUMENT ME!

getKeywords

public java.lang.String getKeywords()

Return keywords (from META tags)

Specified by:

getKeywords in interface ContentHandler

Returns:

DOCUMENT ME!

getLinks

public java.util.List getLinks()

Return links

Specified by:

getLinks in interface ContentHandler

Returns:

DOCUMENT ME!

getPublished

public long getPublished()

Return published date (from META tag)

Specified by:

getPublished in interface ContentHandler

Returns:

DOCUMENT ME!

getRobotFollow

public boolean getRobotFollow()

Return boolean true if links are to be followed

Specified by:

getRobotFollow in interface ContentHandler

Returns:

DOCUMENT ME!

getRobotIndex

public boolean getRobotIndex()

Return boolean true if this is to be indexed

Specified by:

getRobotIndex in interface ContentHandler

Returns:

DOCUMENT ME!

getTitle

public java.lang.String getTitle()

Return page title

Specified by:

getTitle in interface ContentHandler

Returns:

DOCUMENT ME!

handleAnchor

public void handleAnchor(javax.swing.text.MutableAttributeSet attribs)

Handle Anchor tags

Parameters:

attribs - DOCUMENT ME!

handleEndTag

public void handleEndTag(javax.swing.text.html.HTML.Tag tag,
                         int pos)

Closing tag

Overrides:

handleEndTag in class javax.swing.text.html.HTMLEditorKit.ParserCallback

Parameters:

tag - DOCUMENT ME!

pos - DOCUMENT ME!

handleMeta

public void handleMeta(javax.swing.text.MutableAttributeSet attribs)

Handle META tags

Parameters:

attribs - DOCUMENT ME!

handleSimpleTag

public void handleSimpleTag(javax.swing.text.html.HTML.Tag tag,
                            javax.swing.text.MutableAttributeSet attribs,
                            int pos)

Handle standalone tags

Overrides:

handleSimpleTag in class javax.swing.text.html.HTMLEditorKit.ParserCallback

Parameters:

tag - DOCUMENT ME!

attribs - DOCUMENT ME!

pos - DOCUMENT ME!

handleStartTag

public void handleStartTag(javax.swing.text.html.HTML.Tag tag,
                           javax.swing.text.MutableAttributeSet attribs,
                           int pos)

Opening tag

Overrides:

handleStartTag in class javax.swing.text.html.HTMLEditorKit.ParserCallback

Parameters:

tag - DOCUMENT ME!

attribs - DOCUMENT ME!

pos - DOCUMENT ME!

handleText

public void handleText(char[] text,
                       int pos)

Handle page text

Overrides:

handleText in class javax.swing.text.html.HTMLEditorKit.ParserCallback

Parameters:

text - DOCUMENT ME!

pos - DOCUMENT ME!

parse

public void parse(java.io.InputStream in)

Parse Content.

Specified by:

parse in interface ContentHandler

Parameters:

in - DOCUMENT ME!