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

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
                  extended by org.apache.manifoldcf.crawler.connectors.webcrawler.FormParseState

public class FormParseState
extends LinkParseState

This class interprets the tag stream generated by the BasicParseState class, and keeps track of the form tags.


Field Summary
protected  int formParseState
           
protected static int FORMPARSESTATE_IN_FORM
           
protected static int FORMPARSESTATE_IN_SELECT
           
protected static int FORMPARSESTATE_IN_TEXTAREA
           
protected static int FORMPARSESTATE_NORMAL
           
protected  java.lang.String selectMultiple
           
protected  java.lang.String selectName
           
 
Fields inherited from class org.apache.manifoldcf.crawler.connectors.webcrawler.LinkParseState
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
FormParseState(IHTMLHandler handler)
           
 
Method Summary
protected  void noteNonscriptEndTag(java.lang.String tagName)
           
protected  void noteNonscriptTag(java.lang.String tagName, java.util.Map attributes)
           
 
Methods inherited from class org.apache.manifoldcf.crawler.connectors.webcrawler.ScriptParseState
noteEndTag, 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

FORMPARSESTATE_NORMAL

protected static final int FORMPARSESTATE_NORMAL
See Also:
Constant Field Values

FORMPARSESTATE_IN_FORM

protected static final int FORMPARSESTATE_IN_FORM
See Also:
Constant Field Values

FORMPARSESTATE_IN_SELECT

protected static final int FORMPARSESTATE_IN_SELECT
See Also:
Constant Field Values

FORMPARSESTATE_IN_TEXTAREA

protected static final int FORMPARSESTATE_IN_TEXTAREA
See Also:
Constant Field Values

formParseState

protected int formParseState

selectName

protected java.lang.String selectName

selectMultiple

protected java.lang.String selectMultiple
Constructor Detail

FormParseState

public FormParseState(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 LinkParseState
Throws:
org.apache.manifoldcf.core.interfaces.ManifoldCFException

noteNonscriptEndTag

protected void noteNonscriptEndTag(java.lang.String tagName)
                            throws org.apache.manifoldcf.core.interfaces.ManifoldCFException
Overrides:
noteNonscriptEndTag in class ScriptParseState
Throws:
org.apache.manifoldcf.core.interfaces.ManifoldCFException