org.apache.manifoldcf.crawler.connectors.webcrawler
Class LinkParseState

java.lang.Object
  extended by org.apache.manifoldcf.crawler.connectors.webcrawler.BasicParseState
      extended by org.apache.manifoldcf.crawler.connectors.webcrawler.ScriptParseState
          extended by org.apache.manifoldcf.crawler.connectors.webcrawler.MetaParseState
              extended by org.apache.manifoldcf.crawler.connectors.webcrawler.LinkParseState
Direct Known Subclasses:
FormParseState

public class LinkParseState
extends MetaParseState

This class recognizes and interprets all links


Field Summary
protected  IHTMLHandler handler
           
 
Fields inherited from class org.apache.manifoldcf.crawler.connectors.webcrawler.ScriptParseState
scriptParseState, SCRIPTPARSESTATE_INSCRIPT, SCRIPTPARSESTATE_NORMAL
 
Fields inherited from class org.apache.manifoldcf.crawler.connectors.webcrawler.BasicParseState
BASICPARSESTATE_IN_ATTR_LOOKING_FOR_VALUE, BASICPARSESTATE_IN_ATTR_NAME, BASICPARSESTATE_IN_ATTR_VALUE, BASICPARSESTATE_IN_COMMENT, BASICPARSESTATE_IN_DOUBLE_QUOTES_ATTR_VALUE, BASICPARSESTATE_IN_END_TAG_NAME, BASICPARSESTATE_IN_SINGLE_QUOTES_ATTR_VALUE, BASICPARSESTATE_IN_TAG_NAME, BASICPARSESTATE_IN_TAG_SAW_SLASH, BASICPARSESTATE_IN_UNQUOTED_ATTR_VALUE, BASICPARSESTATE_NORMAL, BASICPARSESTATE_SAWCOMMENTDASH, BASICPARSESTATE_SAWDASH, BASICPARSESTATE_SAWEXCLAMATION, BASICPARSESTATE_SAWLEFTBRACKET, BASICPARSESTATE_SAWSECONDCOMMENTDASH, currentAttrMap, currentAttrName, currentAttrNameBuffer, currentState, currentTagName, currentTagNameBuffer, currentValueBuffer, mapLookup
 
Constructor Summary
LinkParseState(IHTMLHandler handler)
           
 
Method Summary
protected  void noteNonscriptTag(java.lang.String tagName, java.util.Map attributes)
           
 
Methods inherited from class org.apache.manifoldcf.crawler.connectors.webcrawler.ScriptParseState
noteEndTag, noteNonscriptEndTag, noteTag
 
Methods inherited from class org.apache.manifoldcf.crawler.connectors.webcrawler.BasicParseState
dealWithCharacter, finishUp, htmlAttributeDecode, isHTMLWhitespace, mapChunk
 
Methods inherited from class java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait
 

Field Detail

handler

protected IHTMLHandler handler
Constructor Detail

LinkParseState

public LinkParseState(IHTMLHandler handler)
Method Detail

noteNonscriptTag

protected void noteNonscriptTag(java.lang.String tagName,
                                java.util.Map attributes)
                         throws org.apache.manifoldcf.core.interfaces.ManifoldCFException
Overrides:
noteNonscriptTag in class MetaParseState
Throws:
org.apache.manifoldcf.core.interfaces.ManifoldCFException