htmlparser-cvs — syncmail email notification of CVS commits

[Htmlparser-cvs] htmlparser/src/org/htmlparser/util ChainedException.java,1.30,1.31 CommandLine.java,1.29,1.30 DefaultParserFeedback.java,1.17,1.18 FeedbackManager.java,1.31,1.32 Generate.java,1.32,1.33 IteratorImpl.java,1.18,1.19 LinkProcessor.java,1.16,1.17 NodeIterator.java,1.18,1.19 NodeList.java,1.31,1.32 ParserException.java,1.16,1.17 ParserFeedback.java,1.17,1.18 ParserUtils.java,1.19,1.20 PeekingIterator.java,1.6,1.7 SimpleNodeIterator.java,1.20,1.21 Translate.java,1.26,1.27 package.html,1.6,1.7

[<der...@us...>]

Update of /cvsroot/htmlparser/htmlparser/src/org/htmlparser/util
In directory sc8-pr-cvs1:/tmp/cvs-serv7401/htmlparser/src/org/htmlparser/util

Modified Files:
	ChainedException.java CommandLine.java 
	DefaultParserFeedback.java FeedbackManager.java Generate.java 
	IteratorImpl.java LinkProcessor.java NodeIterator.java 
	NodeList.java ParserException.java ParserFeedback.java 
	ParserUtils.java PeekingIterator.java SimpleNodeIterator.java 
	Translate.java package.html 
Log Message:
Update version headers to 1.4-20030622 and update changelog.



Index: ChainedException.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/util/ChainedException.java,v
retrieving revision 1.30
retrieving revision 1.31
diff -C2 -d -r1.30 -r1.31
*** ChainedException.java	1 Jun 2003 20:50:17 -0000	1.30
--- ChainedException.java	22 Jun 2003 21:37:47 -0000	1.31
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030601 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030622 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //

Index: CommandLine.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/util/CommandLine.java,v
retrieving revision 1.29
retrieving revision 1.30
diff -C2 -d -r1.29 -r1.30
*** CommandLine.java	1 Jun 2003 20:50:17 -0000	1.29
--- CommandLine.java	22 Jun 2003 21:37:47 -0000	1.30
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030601 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030622 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //

Index: DefaultParserFeedback.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/util/DefaultParserFeedback.java,v
retrieving revision 1.17
retrieving revision 1.18
diff -C2 -d -r1.17 -r1.18
*** DefaultParserFeedback.java	1 Jun 2003 20:50:17 -0000	1.17
--- DefaultParserFeedback.java	22 Jun 2003 21:37:47 -0000	1.18
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030601 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030622 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //

Index: FeedbackManager.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/util/FeedbackManager.java,v
retrieving revision 1.31
retrieving revision 1.32
diff -C2 -d -r1.31 -r1.32
*** FeedbackManager.java	1 Jun 2003 20:50:17 -0000	1.31
--- FeedbackManager.java	22 Jun 2003 21:37:47 -0000	1.32
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030601 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030622 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //

Index: Generate.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/util/Generate.java,v
retrieving revision 1.32
retrieving revision 1.33
diff -C2 -d -r1.32 -r1.33
*** Generate.java	1 Jun 2003 20:50:18 -0000	1.32
--- Generate.java	22 Jun 2003 21:37:47 -0000	1.33
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030601 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030622 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //

Index: IteratorImpl.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/util/IteratorImpl.java,v
retrieving revision 1.18
retrieving revision 1.19
diff -C2 -d -r1.18 -r1.19
*** IteratorImpl.java	1 Jun 2003 20:50:18 -0000	1.18
--- IteratorImpl.java	22 Jun 2003 21:37:47 -0000	1.19
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030601 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030622 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //

Index: LinkProcessor.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/util/LinkProcessor.java,v
retrieving revision 1.16
retrieving revision 1.17
diff -C2 -d -r1.16 -r1.17
*** LinkProcessor.java	1 Jun 2003 20:50:18 -0000	1.16
--- LinkProcessor.java	22 Jun 2003 21:37:47 -0000	1.17
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030601 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030622 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //

Index: NodeIterator.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/util/NodeIterator.java,v
retrieving revision 1.18
retrieving revision 1.19
diff -C2 -d -r1.18 -r1.19
*** NodeIterator.java	1 Jun 2003 20:50:18 -0000	1.18
--- NodeIterator.java	22 Jun 2003 21:37:47 -0000	1.19
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030601 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030622 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //

Index: NodeList.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/util/NodeList.java,v
retrieving revision 1.31
retrieving revision 1.32
diff -C2 -d -r1.31 -r1.32
*** NodeList.java	13 Jun 2003 20:27:04 -0000	1.31
--- NodeList.java	22 Jun 2003 21:37:47 -0000	1.32
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030601 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030622 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //

Index: ParserException.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/util/ParserException.java,v
retrieving revision 1.16
retrieving revision 1.17
diff -C2 -d -r1.16 -r1.17
*** ParserException.java	1 Jun 2003 20:50:18 -0000	1.16
--- ParserException.java	22 Jun 2003 21:37:47 -0000	1.17
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030601 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030622 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //

Index: ParserFeedback.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/util/ParserFeedback.java,v
retrieving revision 1.17
retrieving revision 1.18
diff -C2 -d -r1.17 -r1.18
*** ParserFeedback.java	1 Jun 2003 20:50:18 -0000	1.17
--- ParserFeedback.java	22 Jun 2003 21:37:47 -0000	1.18
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030601 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030622 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //

Index: ParserUtils.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/util/ParserUtils.java,v
retrieving revision 1.19
retrieving revision 1.20
diff -C2 -d -r1.19 -r1.20
*** ParserUtils.java	1 Jun 2003 20:50:18 -0000	1.19
--- ParserUtils.java	22 Jun 2003 21:37:48 -0000	1.20
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030601 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030622 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //

Index: PeekingIterator.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/util/PeekingIterator.java,v
retrieving revision 1.6
retrieving revision 1.7
diff -C2 -d -r1.6 -r1.7
*** PeekingIterator.java	1 Jun 2003 20:50:18 -0000	1.6
--- PeekingIterator.java	22 Jun 2003 21:37:48 -0000	1.7
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030601 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030622 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //

Index: SimpleNodeIterator.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/util/SimpleNodeIterator.java,v
retrieving revision 1.20
retrieving revision 1.21
diff -C2 -d -r1.20 -r1.21
*** SimpleNodeIterator.java	1 Jun 2003 20:50:18 -0000	1.20
--- SimpleNodeIterator.java	22 Jun 2003 21:37:48 -0000	1.21
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030601 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  // 
--- 1,3 ----
! // HTMLParser Library v1_4_20030622 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  // 

Index: Translate.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/util/Translate.java,v
retrieving revision 1.26
retrieving revision 1.27
diff -C2 -d -r1.26 -r1.27
*** Translate.java	19 Jun 2003 17:24:30 -0000	1.26
--- Translate.java	22 Jun 2003 21:37:48 -0000	1.27
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030601 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030622 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //

Index: package.html
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/util/package.html,v
retrieving revision 1.6
retrieving revision 1.7
diff -C2 -d -r1.6 -r1.7
*** package.html	1 Jun 2003 20:50:18 -0000	1.6
--- package.html	22 Jun 2003 21:37:49 -0000	1.7
***************
*** 6,10 ****
    @(#)package.html	1.60 98/01/27
  
!  HTMLParser Library v1_4_20030601 - A java-based parser for HTML
   Copyright (C) Dec 31, 2000 Somik Raha
  
--- 6,10 ----
    @(#)package.html	1.60 98/01/27
  
!  HTMLParser Library v1_4_20030622 - A java-based parser for HTML
   Copyright (C) Dec 31, 2000 Somik Raha
  

[Htmlparser-cvs] htmlparser/src/org/htmlparser/tests/visitorsTests AllTests.java,1.25,1.26

[<der...@us...>]

Update of /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/visitorsTests
In directory sc8-pr-cvs1:/tmp/cvs-serv7401/htmlparser/src/org/htmlparser/tests/visitorsTests

Modified Files:
	AllTests.java 
Log Message:
Update version headers to 1.4-20030622 and update changelog.



Index: AllTests.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/visitorsTests/AllTests.java,v
retrieving revision 1.25
retrieving revision 1.26
diff -C2 -d -r1.25 -r1.26
*** AllTests.java	1 Jun 2003 20:50:17 -0000	1.25
--- AllTests.java	22 Jun 2003 21:37:47 -0000	1.26
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030601 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030622 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //

[Htmlparser-cvs] htmlparser/src/org/htmlparser/tests DecodingNodeTest.java,1.1,1.2

[<jke...@us...>]

Update of /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests
In directory sc8-pr-cvs1:/tmp/cvs-serv16674/src/org/htmlparser/tests

Modified Files:
	DecodingNodeTest.java 
Log Message:
added support for StringNode Decoration

Index: DecodingNodeTest.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/DecodingNodeTest.java,v
retrieving revision 1.1
retrieving revision 1.2
diff -C2 -d -r1.1 -r1.2
*** DecodingNodeTest.java	17 Jun 2003 03:26:20 -0000	1.1
--- DecodingNodeTest.java	19 Jun 2003 17:24:30 -0000	1.2
***************
*** 18,22 ****
  		
  		while (nodes.hasMoreNodes()) 
! 			decodedContent.append(nodes.nextNode().toHtml());			
  
  		return decodedContent.toString();
--- 18,22 ----
  		
  		while (nodes.hasMoreNodes()) 
! 			decodedContent.append(nodes.nextNode().toPlainTextString());			
  
  		return decodedContent.toString();
***************
*** 25,32 ****
  	public void testAmpersand() throws Exception {
  		String ENCODED_WORKSHOP_TITLE =
! 			"<H1>The Testing &amp; Refactoring Workshop</H1>";
  			
  		String DECODED_WORKSHOP_TITLE =
! 			"<H1>The Testing & Refactoring Workshop</H1>";
  
  		assertEquals(
--- 25,32 ----
  	public void testAmpersand() throws Exception {
  		String ENCODED_WORKSHOP_TITLE =
! 			"The Testing &amp; Refactoring Workshop";
  			
  		String DECODED_WORKSHOP_TITLE =
! 			"The Testing & Refactoring Workshop";
  
  		assertEquals(

[Htmlparser-cvs] htmlparser/src/org/htmlparser/parserHelper StringParser.java,1.26,1.27

[<jke...@us...>]

Update of /cvsroot/htmlparser/htmlparser/src/org/htmlparser/parserHelper
In directory sc8-pr-cvs1:/tmp/cvs-serv16674/src/org/htmlparser/parserHelper

Modified Files:
	StringParser.java 
Log Message:
added support for StringNode Decoration

Index: StringParser.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/parserHelper/StringParser.java,v
retrieving revision 1.26
retrieving revision 1.27
diff -C2 -d -r1.26 -r1.27
*** StringParser.java	17 Jun 2003 03:26:19 -0000	1.26
--- StringParser.java	19 Jun 2003 17:24:30 -0000	1.27
***************
*** 29,33 ****
  package org.htmlparser.parserHelper;
  
! import org.htmlparser.AbstractNode;
  import org.htmlparser.NodeReader;
  import org.htmlparser.Parser;
--- 29,33 ----
  package org.htmlparser.parserHelper;
  
! import org.htmlparser.Node;
  import org.htmlparser.NodeReader;
  import org.htmlparser.Parser;
***************
*** 74,78 ****
       * encountering quotes.
  	 */		
! 	public AbstractNode find(NodeReader reader,String input,int position, boolean balance_quotes)
  	{
  		StringBuffer textBuffer = new StringBuffer();
--- 74,78 ----
       * encountering quotes.
  	 */		
! 	public Node find(NodeReader reader,String input,int position, boolean balance_quotes)
  	{
  		StringBuffer textBuffer = new StringBuffer();
***************
*** 139,144 ****
  			}
  		}
! 		return new StringNode(textBuffer, textBegin, textEnd,
! 				  				reader.getParser().shouldDecodeNodes());
  	}
  }
--- 139,144 ----
  			}
  		}
! 		return StringNode.createStringNode(textBuffer, textBegin, textEnd,
! 				  						    reader.getParser().shouldDecodeNodes());
  	}
  }

[Htmlparser-cvs] htmlparser/src/org/htmlparser/util Translate.java,1.25,1.26

[<jke...@us...>]

Update of /cvsroot/htmlparser/htmlparser/src/org/htmlparser/util
In directory sc8-pr-cvs1:/tmp/cvs-serv16674/src/org/htmlparser/util

Modified Files:
	Translate.java 
Log Message:
added support for StringNode Decoration

Index: Translate.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/util/Translate.java,v
retrieving revision 1.25
retrieving revision 1.26
diff -C2 -d -r1.25 -r1.26
*** Translate.java	1 Jun 2003 20:50:18 -0000	1.25
--- Translate.java	19 Jun 2003 17:24:30 -0000	1.26
***************
*** 470,473 ****
--- 470,477 ----
          return (ret);
      }
+     
+     public static String decode (StringBuffer stringBuffer) {
+     	return decode(stringBuffer.toString());
+     }
  
      /**

[Htmlparser-cvs] htmlparser/src/org/htmlparser DecodingNode.java,NONE,1.1 Node.java,1.25,1.26 StringNode.java,1.21,1.22 AbstractNode.java,1.1,1.2

[<jke...@us...>]

Update of /cvsroot/htmlparser/htmlparser/src/org/htmlparser
In directory sc8-pr-cvs1:/tmp/cvs-serv16674/src/org/htmlparser

Modified Files:
	Node.java StringNode.java AbstractNode.java 
Added Files:
	DecodingNode.java 
Log Message:
added support for StringNode Decoration

--- NEW FILE: DecodingNode.java ---
package org.htmlparser;

import org.htmlparser.tags.CompositeTag;
import org.htmlparser.util.NodeList;
import org.htmlparser.util.Translate;
import org.htmlparser.visitors.NodeVisitor;


public class DecodingNode implements Node {
	private Node delegate; 

	protected DecodingNode(Node node) {
		delegate = node;
	}

	public String toPlainTextString() {
		return Translate.decode(delegate.toPlainTextString());
	}
	
	public void accept(NodeVisitor visitor) {
		delegate.accept(visitor);
	}

	public void collectInto(NodeList collectionList, Class nodeType) {
		delegate.collectInto(collectionList, nodeType);
	}

	public void collectInto(NodeList collectionList, String filter) {
		delegate.collectInto(collectionList, filter);
	}

	public int elementBegin() {
		return delegate.elementBegin();
	}

	public int elementEnd() {
		return delegate.elementEnd();
	}

	public CompositeTag getParent() {
		return delegate.getParent();
	}

	public String getText() {
		return delegate.getText();
	}

	public void setParent(CompositeTag tag) {
		delegate.setParent(tag);
	}

	public void setText(String text) {
		delegate.setText(text);
	}

	public String toHtml() {
		return delegate.toHtml();
	}

	public String toHTML() {
		return delegate.toHTML();
	}

}

Index: Node.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/Node.java,v
retrieving revision 1.25
retrieving revision 1.26
diff -C2 -d -r1.25 -r1.26
*** Node.java	17 Jun 2003 03:26:19 -0000	1.25
--- Node.java	19 Jun 2003 17:24:30 -0000	1.26
***************
*** 113,116 ****
  	 */
  	public abstract void setParent(CompositeTag tag);
! 		
! }
\ No newline at end of file
--- 113,126 ----
  	 */
  	public abstract void setParent(CompositeTag tag);
! 	
! 	/**
! 	 * Returns the text of the string line
! 	 */
! 	public String getText();		
! 	
! 	/**
! 	 * Sets the string contents of the node.
! 	 * @param The new text for the node.
! 	 */
! 	public void setText(String text);		
! }

Index: StringNode.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/StringNode.java,v
retrieving revision 1.21
retrieving revision 1.22
diff -C2 -d -r1.21 -r1.22
*** StringNode.java	17 Jun 2003 03:26:19 -0000	1.21
--- StringNode.java	19 Jun 2003 17:24:30 -0000	1.22
***************
*** 31,35 ****
  
  import org.htmlparser.util.NodeList;
- import org.htmlparser.util.Translate;
  import org.htmlparser.visitors.NodeVisitor;
  
--- 31,34 ----
***************
*** 39,47 ****
  public class StringNode extends AbstractNode
  {
- 	/**
- 	 * boolean to tell whether decoding of this node should happen or not. 
- 	 */	
- 	private boolean shouldDecode = false;;
- 	
  	public static final String STRING_FILTER="-string";
  	
--- 38,41 ----
***************
*** 63,78 ****
  		
  	}
! 	
! 	public StringNode(StringBuffer textBuffer, int textBegin, int textEnd,
! 						boolean shouldDecode) {
! 		this(textBuffer, textBegin, textEnd);
! 		this.shouldDecode = shouldDecode;					
  	}
  
  	/**
  	 * Returns the text of the string line
  	 */
! 	public String getText()
! 	{
  		return textBuffer.toString();
  	}
--- 57,73 ----
  		
  	}
! 
! 	public static Node createStringNode(
! 		StringBuffer textBuffer, int textBegin, int textEnd, boolean shouldDecode) {
! 		if (shouldDecode)
! 			return new DecodingNode(new StringNode(textBuffer, textBegin, textEnd));								  	
! 		return new StringNode(textBuffer, textBegin, textEnd);
  	}
+ 	
  
  	/**
  	 * Returns the text of the string line
  	 */
! 	public String getText() {
  		return textBuffer.toString();
  	}
***************
*** 87,102 ****
  	
  	public String toPlainTextString() {
! 		return nodeContents();
  	}
  	
  	public String toHtml() {
! 		return nodeContents();
! 	}
! 
! 	private String nodeContents() {
! 		String result = textBuffer.toString();
! 		if (shouldDecode)
! 			result = Translate.decode(result);
! 		return result;
  	}
  	
--- 82,90 ----
  	
  	public String toPlainTextString() {
! 		return textBuffer.toString();
  	}
  	
  	public String toHtml() {
! 		return textBuffer.toString();
  	}
  	
***************
*** 104,107 ****
--- 92,96 ----
  		return "Text = "+getText()+"; begins at : "+elementBegin()+"; ends at : "+elementEnd();
  	}
+ 	
  	public void collectInto(NodeList collectionList, String filter) {
  		if (filter==STRING_FILTER) collectionList.add(this);
***************
*** 111,114 ****
  		visitor.visitStringNode(this);
  	}
- 
  }
--- 100,102 ----

Index: AbstractNode.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/AbstractNode.java,v
retrieving revision 1.1
retrieving revision 1.2
diff -C2 -d -r1.1 -r1.2
*** AbstractNode.java	13 Jun 2003 20:27:04 -0000	1.1
--- AbstractNode.java	19 Jun 2003 17:24:30 -0000	1.2
***************
*** 190,193 ****
--- 190,208 ----
  		parent = tag;
  	}
+ 	
+ 	/**
+ 	 * Returns the text of the string line
+ 	 */
+ 	public String getText() {
+ 		return null;
+ 	}
+ 	
+ 	/**
+ 	 * Sets the string contents of the node.
+ 	 * @param The new text for the node.
+ 	 */
+ 	public void setText(String text) {
+ 
+ 	}
  
  }

[Htmlparser-cvs] htmlparser/src/org/htmlparser/tests DecodingNodeTest.java,NONE,1.1 AllTests.java,1.39,1.40

[<jke...@us...>]

Update of /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests
In directory sc8-pr-cvs1:/tmp/cvs-serv18761/src/org/htmlparser/tests

Modified Files:
	AllTests.java 
Added Files:
	DecodingNodeTest.java 
Log Message:
add setting for parser to perform the Translate.decode() on all StringNodes. This will later be refactored to a Decorator implementation.

--- NEW FILE: DecodingNodeTest.java ---
package org.htmlparser.tests;

import org.htmlparser.util.NodeIterator;
import org.htmlparser.util.ParserException;

public class DecodingNodeTest extends ParserTestCase {

	public DecodingNodeTest(String name) {
		super(name);
	}

	private String parseToObtainDecodedResult(String STRING_TO_DECODE)
		throws ParserException {
		StringBuffer decodedContent = new StringBuffer();
		createParser(STRING_TO_DECODE);
		parser.setNodeDecoding(true);  // tell parser to decode StringNodes
		NodeIterator nodes = parser.elements();
		
		while (nodes.hasMoreNodes()) 
			decodedContent.append(nodes.nextNode().toHtml());			

		return decodedContent.toString();
	}

	public void testAmpersand() throws Exception {
		String ENCODED_WORKSHOP_TITLE =
			"<H1>The Testing &amp; Refactoring Workshop</H1>";
			
		String DECODED_WORKSHOP_TITLE =
			"<H1>The Testing & Refactoring Workshop</H1>";

		assertEquals(
			"ampersand in string",
			DECODED_WORKSHOP_TITLE,
			parseToObtainDecodedResult(ENCODED_WORKSHOP_TITLE));
	}

	public void testNumericReference() throws Exception {
		String ENCODED_DIVISION_SIGN =
			"&#247; is the division sign.";
			
		String DECODED_DIVISION_SIGN =
			"÷ is the division sign.";
			
		assertEquals(
			"numeric reference for division sign",
			DECODED_DIVISION_SIGN,
			parseToObtainDecodedResult(ENCODED_DIVISION_SIGN));
	}
	
	
	public void testReferencesInString () throws Exception {
		String ENCODED_REFERENCE_IN_STRING =
			"Thus, the character entity reference &divide; is a more convenient" +
			" form than &#247; for obtaining the division sign (÷)";
		
		String DECODED_REFERENCE_IN_STRING =
			"Thus, the character entity reference ÷ is a more convenient" +
			" form than ÷ for obtaining the division sign (÷)";
		
		assertEquals (
			"character references within a string",
			DECODED_REFERENCE_IN_STRING,
			parseToObtainDecodedResult(ENCODED_REFERENCE_IN_STRING));
	}

	public void testBogusCharacterEntityReference() throws Exception {
		
		String ENCODED_BOGUS_CHARACTER_ENTITY = 
			"The character entity reference &divode; is bogus";
			
		String DECODED_BOGUS_CHARACTER_ENTITY =
			"The character entity reference &divode; is bogus";
		
		assertEquals (
			"bogus character entity reference",
			DECODED_BOGUS_CHARACTER_ENTITY,
			parseToObtainDecodedResult(ENCODED_BOGUS_CHARACTER_ENTITY));
	}
	
	

}

Index: AllTests.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/AllTests.java,v
retrieving revision 1.39
retrieving revision 1.40
diff -C2 -d -r1.39 -r1.40
*** AllTests.java	1 Jun 2003 20:50:14 -0000	1.39
--- AllTests.java	17 Jun 2003 03:26:20 -0000	1.40
***************
*** 104,107 ****
--- 104,108 ----
  		TestSuite basic = new TestSuite("Basic Tests");
  		basic.addTestSuite(ParserTest.class);
+ 		basic.addTestSuite(DecodingNodeTest.class);
          suite.addTest(basic);
  		suite.addTest(org.htmlparser.tests.scannersTests.AllTests.suite());

[Htmlparser-cvs] htmlparser/src/org/htmlparser/parserHelper StringParser.java,1.25,1.26

[<jke...@us...>]

Update of /cvsroot/htmlparser/htmlparser/src/org/htmlparser/parserHelper
In directory sc8-pr-cvs1:/tmp/cvs-serv18761/src/org/htmlparser/parserHelper

Modified Files:
	StringParser.java 
Log Message:
add setting for parser to perform the Translate.decode() on all StringNodes. This will later be refactored to a Decorator implementation.

Index: StringParser.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/parserHelper/StringParser.java,v
retrieving revision 1.25
retrieving revision 1.26
diff -C2 -d -r1.25 -r1.26
*** StringParser.java	13 Jun 2003 20:27:04 -0000	1.25
--- StringParser.java	17 Jun 2003 03:26:19 -0000	1.26
***************
*** 139,143 ****
  			}
  		}
! 		return new StringNode(textBuffer,textBegin,textEnd);
  	}
  }
--- 139,144 ----
  			}
  		}
! 		return new StringNode(textBuffer, textBegin, textEnd,
! 				  				reader.getParser().shouldDecodeNodes());
  	}
  }

[Htmlparser-cvs] htmlparser/src/org/htmlparser Node.java,1.24,1.25 Parser.java,1.44,1.45 StringNode.java,1.20,1.21

[<jke...@us...>]

Update of /cvsroot/htmlparser/htmlparser/src/org/htmlparser
In directory sc8-pr-cvs1:/tmp/cvs-serv18761/src/org/htmlparser

Modified Files:
	Node.java Parser.java StringNode.java 
Log Message:
add setting for parser to perform the Translate.decode() on all StringNodes. This will later be refactored to a Decorator implementation.

Index: Node.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/Node.java,v
retrieving revision 1.24
retrieving revision 1.25
diff -C2 -d -r1.24 -r1.25
*** Node.java	13 Jun 2003 20:27:04 -0000	1.24
--- Node.java	17 Jun 2003 03:26:19 -0000	1.25
***************
*** 113,115 ****
--- 113,116 ----
  	 */
  	public abstract void setParent(CompositeTag tag);
+ 		
  }

Index: Parser.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/Parser.java,v
retrieving revision 1.44
retrieving revision 1.45
diff -C2 -d -r1.44 -r1.45
*** Parser.java	13 Jun 2003 20:27:04 -0000	1.44
--- Parser.java	17 Jun 2003 03:26:19 -0000	1.45
***************
*** 183,186 ****
--- 183,193 ----
  
  	/**
+ 	 * Flag to tell the parser to decode nodes while parsing.  
+ 	 * Decoding occurs via the method, org.htmlparser.util.Translate.decode()
+ 	 */
+ 	private boolean shouldDecodeNodes = false;
+ 
+ 
+ 	/**
  	 * Feedback object.
  	 */
***************
*** 1208,1211 ****
--- 1215,1229 ----
  	public static String getLineSeparator() {
  		return lineSeparator;
+ 	}
+ 
+ 	/**
+ 	 * Tells the parser to decode nodes using org.htmlparser.util.Translate.decode()
+ 	 */
+ 	public void setNodeDecoding(boolean shouldDecodeNodes) {
+ 			this.shouldDecodeNodes = shouldDecodeNodes;
+ 		}
+ 
+ 	public boolean shouldDecodeNodes() {
+ 		return shouldDecodeNodes;
  	}
  }

Index: StringNode.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/StringNode.java,v
retrieving revision 1.20
retrieving revision 1.21
diff -C2 -d -r1.20 -r1.21
*** StringNode.java	13 Jun 2003 20:27:04 -0000	1.20
--- StringNode.java	17 Jun 2003 03:26:19 -0000	1.21
***************
*** 31,34 ****
--- 31,35 ----
  
  import org.htmlparser.util.NodeList;
+ import org.htmlparser.util.Translate;
  import org.htmlparser.visitors.NodeVisitor;
  
***************
*** 38,42 ****
--- 39,49 ----
  public class StringNode extends AbstractNode
  {
+ 	/**
+ 	 * boolean to tell whether decoding of this node should happen or not. 
+ 	 */	
+ 	private boolean shouldDecode = false;;
+ 	
  	public static final String STRING_FILTER="-string";
+ 	
  	/**
  	 * The text of the string.
***************
*** 57,60 ****
--- 64,72 ----
  	}
  	
+ 	public StringNode(StringBuffer textBuffer, int textBegin, int textEnd,
+ 						boolean shouldDecode) {
+ 		this(textBuffer, textBegin, textEnd);
+ 		this.shouldDecode = shouldDecode;					
+ 	}
  
  	/**
***************
*** 73,82 ****
  		textBuffer = new StringBuffer (text);
  	}
  	public String toPlainTextString() {
! 		return textBuffer.toString();
  	}
  	public String toHtml() {
! 		return textBuffer.toString();
  	}
  	public String toString() {
  		return "Text = "+getText()+"; begins at : "+elementBegin()+"; ends at : "+elementEnd();
--- 85,104 ----
  		textBuffer = new StringBuffer (text);
  	}
+ 	
  	public String toPlainTextString() {
! 		return nodeContents();
  	}
+ 	
  	public String toHtml() {
! 		return nodeContents();
  	}
+ 
+ 	private String nodeContents() {
+ 		String result = textBuffer.toString();
+ 		if (shouldDecode)
+ 			result = Translate.decode(result);
+ 		return result;
+ 	}
+ 	
  	public String toString() {
  		return "Text = "+getText()+"; begins at : "+elementBegin()+"; ends at : "+elementEnd();

[Htmlparser-cvs] htmlparser/src/org/htmlparser/tests/temporaryFailures AttributeParserTest.java,NONE,1.1 TagParserTest.java,NONE,1.1

[<so...@us...>]

Update of /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/temporaryFailures
In directory sc8-pr-cvs1:/tmp/cvs-serv7764/src/org/htmlparser/tests/temporaryFailures

Added Files:
	AttributeParserTest.java TagParserTest.java 
Log Message:
added temporaryFailures package

--- NEW FILE: AttributeParserTest.java ---
// HTMLParser Library v1_4_20030601 - A java-based parser for HTML
// Copyright (C) Dec 31, 2000 Somik Raha
//
// This library is free software; you can redistribute it and/or
// modify it under the terms of the GNU Lesser General Public
// License as published by the Free Software Foundation; either
// version 2.1 of the License, or (at your option) any later version.
//
// This library is distributed in the hope that it will be useful,
// but WITHOUT ANY WARRANTY; without even the implied warranty of
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
// Lesser General Public License for more details.
// 
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
// Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
//
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
// 
// Postal Address : 
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
// 2583 Cedar Street, Berkeley, 
// CA 94708, USA
// Website : http://www.industriallogic.com

// ---- IMPORTANT: This class has failing tests ----
// Original Location: org.htmlparser.tests.parserHelperTests;
// Pls rememeber to add test back to org.htmlparser.tests.parserHelperTests.AllTests.suite()
// and delete these comments when you're done.
// ----   NEEDS FIXING                          ----

package org.htmlparser.tests.temporaryFailures;

import java.util.Hashtable;

import org.htmlparser.Parser;
import org.htmlparser.parserHelper.AttributeParser;
import org.htmlparser.tags.Tag;
import org.htmlparser.tags.data.TagData;
import org.htmlparser.tests.ParserTestCase;

public class AttributeParserTest extends ParserTestCase {
	private AttributeParser parser;
	private Tag tag;
	private Hashtable table;
	
	public AttributeParserTest(String name) {
		super(name);
	}

	protected void setUp() {
		parser = new AttributeParser();
	}
	
	public void getParameterTableFor(String tagContents) {
		tag = new Tag(new TagData(0,0,tagContents,""));
		table = parser.parseAttributes(tag);
		
	}
	
	public void testParseParameters() {
		getParameterTableFor("a b = \"c\"");
		assertEquals("Value","c",table.get("B"));
	}

	public void testParseTokenValues() {
		getParameterTableFor("a b = \"'\"");
		assertEquals("Value","'",table.get("B"));
	}
        
	public void testParseEmptyValues() {
		getParameterTableFor("a b = \"\"");
		assertEquals("Value","",table.get("B"));		
	}

	public void testParseMissingEqual() {
		getParameterTableFor("a b\"c\"");
		assertEquals("ValueB","",table.get("B"));
                
	}
        
    public void testTwoParams(){
		getParameterTableFor("PARAM NAME=\"Param1\" VALUE=\"Somik\">\n");
		assertEquals("Param1","Param1",table.get("NAME"));
		assertEquals("Somik","Somik",table.get("VALUE"));                
    }

    public void testPlainParams(){
        getParameterTableFor("PARAM NAME=Param1 VALUE=Somik");
        assertEquals("Param1","Param1",table.get("NAME"));
        assertEquals("Somik","Somik",table.get("VALUE"));                
    }
    
    public void testValueMissing() {
        getParameterTableFor("INPUT type=\"checkbox\" name=\"Authorize\" value=\"Y\" checked");
        assertEquals("Name of Tag","INPUT",table.get(Tag.TAGNAME));
        assertEquals("Type","checkbox",table.get("TYPE"));                
        assertEquals("Name","Authorize",table.get("NAME"));
        assertEquals("Value","Y",table.get("VALUE"));
        assertEquals("Checked","",table.get("CHECKED"));
    }

    /**
     * This is a simulation of a bug reported by Dhaval Udani - wherein 
     * a space before the end of the tag causes a problem - there is a key
     * in the table with just a space in it and an empty value
     */
    public void testIncorrectSpaceKeyBug() {
        getParameterTableFor("TEXTAREA name=\"Remarks\" ");
		// There should only be two keys..
		assertEquals("There should only be two keys",2,table.size());
		// The first key is name
		String key1 = "NAME";
		String value1 = (String)table.get(key1);
		assertEquals("Expected value 1", "Remarks",value1);
		String key2 = Tag.TAGNAME;
		assertEquals("Expected Value 2","TEXTAREA",table.get(key2));
    }

    public void testNullTag(){
        getParameterTableFor("INPUT type=");
        assertEquals("Name of Tag","INPUT",table.get(Tag.TAGNAME));
        assertEquals("Type","",table.get("TYPE"));                
    }
    
    public void testAttributeWithSpuriousEqualTo() {
    	getParameterTableFor(
			"a class=rlbA href=/news/866201.asp?0sl=-32"
		);
		assertStringEquals(
			"href",
			"/news/866201.asp?0sl=-32",
			(String)table.get("HREF")
		);
    }
    
    public void testQuestionMarksInAttributes() {
		getParameterTableFor(
			"a href=\"mailto:sa...@ne...?subject=Site Comments\""
    	);
		assertStringEquals(
			"href",
			"mailto:sa...@ne...?subject=Site Comments",
			(String)table.get("HREF")
		);
		assertStringEquals(
			"tag name",
			"A",
			(String)table.get(Tag.TAGNAME)
		);
    }

    /**
     * Believe it or not Moi (vincent_aumont) wants htmlparser to parse a text file
     * containing something that looks nearly like a tag:
     * <pre>
     * "                        basic_string&lt;char, string_char_traits&lt;char&gt;, &lt;&gt;&gt;::basic_string()"
     * </pre>
     * This was throwing a null pointer exception when the empty &lt;&gt; was encountered.
     * Bug #725420 NPE in StringBean.visitTag
     **/
    public void testEmptyTag () {
		getParameterTableFor("");
		assertNotNull ("No Tag.TAGNAME",table.get(Tag.TAGNAME));
    }

    /**
     * Test attributes when they contain scriptlets.
     * Submitted by Cory Seefurth
     * See also feature request #725376 Handle script in attributes.
     * Only perform this test if it's version 1.4 or higher.
     */
    public void testJspWithinAttributes() {
        Parser parser;
        
        parser = new Parser ();
        if (1.4 <= Parser.getVersionNumber ())
        {
            getParameterTableFor(
                "a href=\"<%=Application(\"sURL\")%>/literature/index.htm"
            );
            assertStringEquals(
                "href",
                "<%=Application(\"sURL\")%>/literature/index.htm",
                (String)table.get("HREF")
            );
        }
    }
    
    /**
     * Test Script in attributes.
     * See feature request #725376 Handle script in attributes.
     * Only perform this test if it's version 1.4 or higher.
     */
    public void testScriptedTag () {
        Parser parser;
        
        parser = new Parser ();
        if (1.4 <= Parser.getVersionNumber ())
        {
            getParameterTableFor("body onLoad=defaultStatus=''");
            String name = (String)table.get(Tag.TAGNAME);
            assertNotNull ("No Tag.TAGNAME", name);
            assertStringEquals("tag name parsed incorrectly", "BODY", name);
            String value = (String)table.get ("ONLOAD");
            assertStringEquals ("parameter parsed incorrectly", "defaultStatus=''", value);
        }
    }
}

--- NEW FILE: TagParserTest.java ---
// HTMLParser Library v1_4_20030601 - A java-based parser for HTML
// Copyright (C) Dec 31, 2000 Somik Raha
//
// This library is free software; you can redistribute it and/or
// modify it under the terms of the GNU Lesser General Public
// License as published by the Free Software Foundation; either
// version 2.1 of the License, or (at your option) any later version.
//
// This library is distributed in the hope that it will be useful,
// but WITHOUT ANY WARRANTY; without even the implied warranty of
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
// Lesser General Public License for more details.
// 
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
// Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
//
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
// 
// Postal Address : 
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic, Inc.
// 2583 Cedar Street, Berkeley, 
// CA 94708, USA
// Website : http://www.industriallogic.com

// ---- IMPORTANT: This class has failing tests ----
// Original Location: org.htmlparser.tests.parserHelperTests;
// Pls rememeber to add test back to org.htmlparser.tests.parserHelperTests.AllTests.suite()
// and delete these comments when you're done.
// ----   NEEDS FIXING                          ----

package org.htmlparser.tests.temporaryFailures;
import java.util.HashMap;
import java.util.Map;

import org.htmlparser.Node;
import org.htmlparser.Parser;
import org.htmlparser.tags.LinkTag;
import org.htmlparser.tags.Tag;
import org.htmlparser.tests.ParserTestCase;
import org.htmlparser.util.ParserException;

public class TagParserTest extends ParserTestCase {
	private static final String TEST_HTML = "<!DOCTYPE HTML PUBLIC \"-//W3C//DTD HTML 4.0 Transitional//EN\">" +
		"<!-- Server: sf-web2 -->" +
		"<html lang=\"en\">" +
		"  <head><link rel=\"stylesheet\" type=\"text/css\" href=\"http://sourceforge.net/cssdef.php\">" +
		"	<meta http-equiv=\"Content-Type\" content=\"text/html; charset=iso-8859-1\">" +
		"    <TITLE>SourceForge.net: Modify: 711073 - HTMLTagParser not threadsafe as a static variable in Tag</TITLE>" +
		"	<SCRIPT language=\"JavaScript\" type=\"text/javascript\">" +
		"	<!--" +
		"	function help_window(helpurl) {" +
		"		HelpWin = window.open( 'http://sourceforge.net' + helpurl,'HelpWindow','scrollbars=yes,resizable=yes,toolbar=no,height=400,width=400');" +
		"	}" +
		"	// -->" +
		"	</SCRIPT>" +
		"		<link rel=\"SHORTCUT ICON\" href=\"/images/favicon.ico\">" +
		"<!-- This is temp javascript for the jump button. If we could actually have a jump script on the server side that would be ideal -->" +
		"<script language=\"JavaScript\" type=\"text/javascript\">" +
		"<!--" +
		"	function jump(targ,selObj,restore){ //v3.0" +
		"	if (selObj.options[selObj.selectedIndex].value) " +
		"		eval(targ+\".location='\"+selObj.options[selObj.selectedIndex].value+\"'\");" +
		"	if (restore) selObj.selectedIndex=0;" +
		"	}" +
		"	//-->" +
		"</script>" +
		"<a href=\"http://normallink.com/sometext.html\">" +
		"<style type=\"text/css\">" +
		"<!--" +
		"A:link { text-decoration:none }" +
		"A:visited { text-decoration:none }" +
		"A:active { text-decoration:none }" +
		"A:hover { text-decoration:underline; color:#0066FF; }" +
		"-->" +
		"</style>" +
		"</head>" +
		"<body bgcolor=\"#FFFFFF\" text=\"#000000\" leftmargin=\"0\" topmargin=\"0\" marginwidth=\"0\" marginheight=\"0\" link=\"#003399\" vlink=\"#003399\" alink=\"#003399\">";
	private Map results;
	private int testProgress;
	
	public TagParserTest(String name) {
		super(name);
	}
	
	public void testTagWithQuotes() throws Exception {
		String testHtml = 
		"<img src=\"http://g-images.amazon.com/images/G/01/merchants/logos/marshall-fields-logo-20.gif\" width=87 height=20 border=0 alt=\"Marshall Field's\">";
		
		createParser(testHtml);
		parseAndAssertNodeCount(1);
		assertType("should be Tag",Tag.class,node[0]);
		Tag tag = (Tag)node[0];
		assertStringEquals("alt","Marshall Field's",tag.getAttribute("ALT"));
		assertStringEquals(
			"html",
			"<IMG BORDER=\"0\" ALT=\"Marshall Field's\" WIDTH=\"87\" SRC=\"http://g-images.amazon.com/images/G/01/merchants/logos/marshall-fields-logo-20.gif\" HEIGHT=\"20\">",
			tag.toHtml()
		);
	}
	
	public void testEmptyTag() throws Exception {
		createParser("<custom/>");
		parseAndAssertNodeCount(1);
		assertType("should be Tag",Tag.class,node[0]);
		Tag tag = (Tag)node[0];
		assertStringEquals("tag name","CUSTOM",tag.getTagName());
		assertTrue("empty tag",tag.isEmptyXmlTag());
		assertStringEquals(
			"html",
			"<CUSTOM/>",
			tag.toHtml()
		);
	}
	
	public void testTagWithCloseTagSymbolInAttribute() throws ParserException {
		createParser("<tag att=\"a>b\">");
		parseAndAssertNodeCount(1);
		assertType("should be Tag",Tag.class,node[0]);
		Tag tag = (Tag)node[0];
		assertStringEquals("attribute","a>b",tag.getAttribute("att"));
	}
	
	public void testTagWithOpenTagSymbolInAttribute() throws ParserException {
		createParser("<tag att=\"a<b\">");
		parseAndAssertNodeCount(1);
		assertType("should be Tag",Tag.class,node[0]);
		Tag tag = (Tag)node[0];
		assertStringEquals("attribute","a<b",tag.getAttribute("att"));
	}

	public void testTagWithSingleQuote() throws ParserException {
		createParser("<tag att=\'a<b\'>");
		parseAndAssertNodeCount(1);
		assertType("should be Tag",Tag.class,node[0]);
		Tag tag = (Tag)node[0];
		assertStringEquals("html","<TAG ATT=\"a<b\">",tag.toHtml());
		assertStringEquals("attribute","a<b",tag.getAttribute("att"));
    }

    /**
     * The following multi line test cases are from
     * bug #725749 Parser does not handle < and > in multi-line attributes
     * submitted by Joe Robins (zorblak)
     */

    public void testMultiLine1 () throws ParserException
    {
        createParser("<meta name=\"foo\" content=\"foo<bar>\">");
        parseAndAssertNodeCount (1);
        assertType ("should be Tag", Tag.class, node[0]);
        Tag tag = (Tag)node[0];
        String html = tag.toHtml ();
        assertStringEquals ("html","<META CONTENT=\"foo<bar>\" NAME=\"foo\">", html);
        String attribute1 = tag.getAttribute ("NAME");
        assertStringEquals ("attribute 1","foo", attribute1);
        String attribute2 = tag.getAttribute ("CONTENT");
        assertStringEquals ("attribute 2","foo<bar>", attribute2);
    }

    public void testMultiLine2 () throws ParserException
    {
        createParser("<meta name=\"foo\" content=\"foo<bar\">");
        parseAndAssertNodeCount (1);
        assertType ("should be Tag", Tag.class, node[0]);
        Tag tag = (Tag)node[0];
        String html = tag.toHtml ();
        assertStringEquals ("html","<META CONTENT=\"foo<bar\" NAME=\"foo\">", html);
        String attribute1 = tag.getAttribute ("NAME");
        assertStringEquals ("attribute 1","foo", attribute1);
        String attribute2 = tag.getAttribute ("CONTENT");
        assertStringEquals ("attribute 2","foo<bar", attribute2);
    }

    public void testMultiLine3 () throws ParserException
    {
        createParser("<meta name=\"foo\" content=\"foobar>\">");
        parseAndAssertNodeCount (1);
        assertType ("should be Tag", Tag.class, node[0]);
        Tag tag = (Tag)node[0];
        String html = tag.toHtml ();
        assertStringEquals ("html","<META CONTENT=\"foobar>\" NAME=\"foo\">", html);
        String attribute1 = tag.getAttribute ("NAME");
        assertStringEquals ("attribute 1","foo", attribute1);
        String attribute2 = tag.getAttribute ("CONTENT");
        assertStringEquals ("attribute 2","foobar>", attribute2);
    }

    public void testMultiLine4 () throws ParserException
    {
        createParser("<meta name=\"foo\" content=\"foo\nbar>\">");
        parseAndAssertNodeCount (1);
        assertType ("should be Tag", Tag.class, node[0]);
        Tag tag = (Tag)node[0];
        String html = tag.toHtml ();
        assertStringEquals ("html","<META CONTENT=\"foo\r\nbar>\" NAME=\"foo\">", html);
        String attribute1 = tag.getAttribute ("NAME");
        assertStringEquals ("attribute 1","foo", attribute1);
        String attribute2 = tag.getAttribute ("CONTENT");
        assertStringEquals ("attribute 2","foo\r\nbar>", attribute2);
    }

    /**
     * Test multiline tag like attribute.
     * See feature request #725749 Handle < and > in multi-line attributes.
     * Only perform this test if it's version 1.4 or higher.
     */
    public void testMultiLine5 () throws ParserException
    {
        // <meta name="foo" content="<foo>
        // bar">
        createParser("<meta name=\"foo\" content=\"<foo>\nbar\">");
        if (1.4 <= Parser.getVersionNumber ())
        {
            parseAndAssertNodeCount (1);
            assertType ("should be Tag", Tag.class, node[0]);
            Tag tag = (Tag)node[0];
            String html = tag.toHtml ();
            assertStringEquals ("html","<META CONTENT=\"<foo>\r\nbar\" NAME=\"foo\">", html);
            String attribute1 = tag.getAttribute ("NAME");
            assertStringEquals ("attribute 1","foo", attribute1);
            String attribute2 = tag.getAttribute ("CONTENT");
            assertStringEquals ("attribute 2","<foo>\r\nbar", attribute2);
        }
    }

    /**
     * Test multiline broken tag like attribute.
     * See feature request #725749 Handle < and > in multi-line attributes.
     * Only perform this test if it's version 1.4 or higher.
     */
    public void testMultiLine6 () throws ParserException
    {
        // <meta name="foo" content="foo>
        // bar">
        createParser("<meta name=\"foo\" content=\"foo>\nbar\">");
        if (1.4 <= Parser.getVersionNumber ())
        {
            parseAndAssertNodeCount (1);
            assertType ("should be Tag", Tag.class, node[0]);
            Tag tag = (Tag)node[0];
            String html = tag.toHtml ();
            assertStringEquals ("html","<META CONTENT=\"foo>\r\nbar\" NAME=\"foo\">", html);
            String attribute1 = tag.getAttribute ("NAME");
            assertStringEquals ("attribute 1","foo", attribute1);
            String attribute2 = tag.getAttribute ("CONTENT");
            assertStringEquals ("attribute 2","foo>\r\nbar", attribute2);
        }
    }
	
    /**
     * Test multiline split tag like attribute.
     * See feature request #725749 Handle < and > in multi-line attributes.
     * Only perform this test if it's version 1.4 or higher.
     */
    public void testMultiLine7 () throws ParserException
    {
        // <meta name="foo" content="<foo
        // bar">
        createParser("<meta name=\"foo\" content=\"<foo\nbar\"");
        if (1.4 <= Parser.getVersionNumber ())
        {
            parseAndAssertNodeCount (1);
            assertType ("should be Tag", Tag.class, node[0]);
            Tag tag = (Tag)node[0];
            String html = tag.toHtml ();
            assertStringEquals ("html","<META CONTENT=\"<foo\r\nbar\" NAME=\"foo\">", html);
            String attribute1 = tag.getAttribute ("NAME");
            assertStringEquals ("attribute 1","foo", attribute1);
            String attribute2 = tag.getAttribute ("CONTENT");
            assertStringEquals ("attribute 2","<foo\r\nbar", attribute2);
        }
    }

    /**
     * End of multi line test cases.
     */

    /**
     * Test multiple threads running against the parser.
     * See feature request #736144 Handle multi-threaded operation.
     * Only perform this test if it's version 1.4 or higher.
     */
	public void testThreadSafety() throws Exception
    {
        createParser("<html></html>");
        if (1.4 <= Parser.getVersionNumber ())
        {
            String testHtml1 = "<a HREF=\"/cgi-bin/view_search?query_text=postdate>20020701&txt_clr=White&bg_clr=Red&url=http://localhost/Testing/Report1.html\">20020702 Report 1</A>" +
                                TEST_HTML;

            String testHtml2 = "<a href=\"http://normallink.com/sometext.html\">" +
                                TEST_HTML;
            ParsingThread parsingThread [] = 
                new ParsingThread[100];
            results = new HashMap();
            testProgress = 0;
            for (int i=0;i<parsingThread.length;i++) {
                if (i<parsingThread.length/2) 
                    parsingThread[i] = 
                        new ParsingThread(i,testHtml1,parsingThread.length);
                    else
                        parsingThread[i] = 
                            new ParsingThread(i,testHtml2,parsingThread.length);

                Thread thread = new Thread(parsingThread[i]);					
                thread.start();
            }

            int completionValue = computeCompletionValue(parsingThread.length);

            do {
                try {
                    Thread.sleep(50);
                }
                catch (InterruptedException e) {
                }
            }	
            while (testProgress!=completionValue);
            for (int i=0;i<parsingThread.length;i++) {
                if (!parsingThread[i].passed()) {
                    assertNotNull("Thread "+i+" link 1",parsingThread[i].getLink1());
                    assertNotNull("Thread "+i+" link 2",parsingThread[i].getLink2());
                    if (i<parsingThread.length/2) {
                        assertStringEquals(
                            "Thread "+i+", link 1:",
                            "/cgi-bin/view_search?query_text=postdate>20020701&txt_clr=White&bg_clr=Red&url=http://localhost/Testing/Report1.html",
                            parsingThread[i].getLink1().getLink()
                        );
                        assertStringEquals(
                            "Thread "+i+", link 2:",
                            "http://normallink.com/sometext.html",
                            parsingThread[i].getLink2().getLink()
                        );
                    } else {
                        assertStringEquals(
                            "Thread "+i+", link 1:",
                            "http://normallink.com/sometext.html",
                            parsingThread[i].getLink1().getLink()
                        );
                        assertNotNull("Thread "+i+" link 2",parsingThread[i].getLink2());
                        assertStringEquals(
                            "Thread "+i+", link 2:",
                            "/cgi-bin/view_search?query_text=postdate>20020701&txt_clr=White&bg_clr=Red&url=http://localhost/Testing/Report1.html",
                            parsingThread[i].getLink2().getLink()
                        );
                    }				
                }
            }
		}

	}

	private int computeCompletionValue(int numThreads) {
		return numThreads * (numThreads - 1) / 2;
	}
	
	class ParsingThread implements Runnable {
		Parser parser;
		int id;
		LinkTag link1, link2;
		boolean result;
		int max;
		
		ParsingThread(int id, String testHtml, int max) {
			this.id = id;
			this.max = max;
			this.parser = 
				Parser.createParser(testHtml);
			parser.registerScanners();
		}
		
		public void run() {
			try {
				result = false;
				Node linkTag [] = parser.extractAllNodesThatAre(LinkTag.class);
				link1 = (LinkTag)linkTag[0];
				link2 = (LinkTag)linkTag[1];
				if (id<max/2) {
					if (link1.getLink().equals("/cgi-bin/view_search?query_text=postdate>20020701&txt_clr=White&bg_clr=Red&url=http://localhost/Testing/Report1.html") &&
						link2.getLink().equals("http://normallink.com/sometext.html"))
						result = true;
				} else {
					if (link1.getLink().equals("http://normallink.com/sometext.html") &&
						link2.getLink().equals("http://normallink.com/sometext.html"))
						result = true;
				}
			}
			catch (ParserException e) {
				System.err.println("Parser Exception");
				e.printStackTrace();
			}
			finally {
				testProgress += id;
			}
		}
		
		public LinkTag getLink1() {
			return link1;
		}
		
		public LinkTag getLink2() {
			return link2;
		}
		
		public boolean passed() {
			return result;
		}
	}	
}

[Htmlparser-cvs] htmlparser/src/org/htmlparser/tests/parserHelperTests AllTests.java,1.17,1.18 AttributeParserTest.java,1.32,NONE TagParserTest.java,1.31,NONE

[<so...@us...>]

Update of /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/parserHelperTests
In directory sc8-pr-cvs1:/tmp/cvs-serv7764/src/org/htmlparser/tests/parserHelperTests

Modified Files:
	AllTests.java 
Removed Files:
	AttributeParserTest.java TagParserTest.java 
Log Message:
added temporaryFailures package

Index: AllTests.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/parserHelperTests/AllTests.java,v
retrieving revision 1.17
retrieving revision 1.18
diff -C2 -d -r1.17 -r1.18
*** AllTests.java	1 Jun 2003 20:50:14 -0000	1.17
--- AllTests.java	17 Jun 2003 01:52:25 -0000	1.18
***************
*** 28,32 ****
  
  package org.htmlparser.tests.parserHelperTests;
! import junit.framework.TestSuite;
  
  public class AllTests extends junit.framework.TestCase 
--- 28,32 ----
  
  package org.htmlparser.tests.parserHelperTests;
! import junit.framework.*;
  
  public class AllTests extends junit.framework.TestCase 
***************
*** 39,48 ****
        public static TestSuite suite() {
          TestSuite suite = new TestSuite("Parser Helper Tests");
! 
!         suite.addTestSuite(AttributeParserTest.class);
          suite.addTestSuite(CompositeTagScannerHelperTest.class);
          suite.addTestSuite(RemarkNodeParserTest.class);
          suite.addTestSuite(StringParserTest.class);
!         suite.addTestSuite(TagParserTest.class);
  
          return suite;
--- 39,49 ----
        public static TestSuite suite() {
          TestSuite suite = new TestSuite("Parser Helper Tests");
! 		// To-do: Test below should be enabled after it passes
! //      suite.addTestSuite(AttributeParserTest.class);
          suite.addTestSuite(CompositeTagScannerHelperTest.class);
          suite.addTestSuite(RemarkNodeParserTest.class);
          suite.addTestSuite(StringParserTest.class);
! 		// To-do: Test below should be enabled after it passes
! //      suite.addTestSuite(TagParserTest.class);
  
          return suite;

--- AttributeParserTest.java DELETED ---

--- TagParserTest.java DELETED ---

[Htmlparser-cvs] htmlparser/src/org/htmlparser/tests/temporaryFailures - New directory

[<so...@us...>]

Update of /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/temporaryFailures
In directory sc8-pr-cvs1:/tmp/cvs-serv7744/src/org/htmlparser/tests/temporaryFailures

Log Message:
Directory /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/temporaryFailures added to the repository

[Htmlparser-cvs] htmlparser/src/org/htmlparser/tags Tag.java,1.31,1.32

[<so...@us...>]

Update of /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tags
In directory sc8-pr-cvs1:/tmp/cvs-serv6437/src/org/htmlparser/tags

Modified Files:
	Tag.java 
Log Message:
new AttributeParser created every time attributes are to be parsed. 
Done to achieve thread-safety.

Index: Tag.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tags/Tag.java,v
retrieving revision 1.31
retrieving revision 1.32
diff -C2 -d -r1.31 -r1.32
*** Tag.java	13 Jun 2003 20:27:05 -0000	1.31
--- Tag.java	17 Jun 2003 01:38:23 -0000	1.32
***************
*** 67,71 ****
  	private final static String EMPTY_STRING="";
  	
! 	private static AttributeParser paramParser = new AttributeParser();
  	private static TagParser tagParser;
  	/**
--- 67,71 ----
  	private final static String EMPTY_STRING="";
  	
! 	private AttributeParser attributeParser;
  	private static TagParser tagParser;
  	/**
***************
*** 181,185 ****
  	 */
  	private Hashtable parseAttributes(){
! 	 	return paramParser.parseAttributes(this);
  	}
  
--- 181,186 ----
  	 */
  	private Hashtable parseAttributes(){
! 	 	attributeParser = new AttributeParser();
! 	 	return attributeParser.parseAttributes(this);
  	}
  

[Htmlparser-cvs] htmlparser/src/org/htmlparser/parserHelper AttributeParser.java,1.25,1.26

[<so...@us...>]

Update of /cvsroot/htmlparser/htmlparser/src/org/htmlparser/parserHelper
In directory sc8-pr-cvs1:/tmp/cvs-serv6124/src/org/htmlparser/parserHelper

Modified Files:
	AttributeParser.java 
Log Message:
refactored AttributeParser to be more readable

Index: AttributeParser.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/parserHelper/AttributeParser.java,v
retrieving revision 1.25
retrieving revision 1.26
diff -C2 -d -r1.25 -r1.26
*** AttributeParser.java	1 Jun 2003 20:50:10 -0000	1.25
--- AttributeParser.java	17 Jun 2003 01:35:04 -0000	1.26
***************
*** 44,55 ****
   */
  public class AttributeParser {
!     private final String delima = " \t\r\n\f=\"'>";
!     private final String delimb = " \t\r\n\f\"'>";
!     private final char doubleQuote = '\"';
!     private final char singleQuote = '\'';
      private String delim;
  
  
  
  	/**
  	* Method to break the tag into pieces.
--- 44,68 ----
   */
  public class AttributeParser {
!     private final String DELIMETERS = " \t\r\n\f=\"'>";
!     private final String DELIMETERS_WITHOUT_EQUALS = " \t\r\n\f\"'>";
!     private final char DOUBLE_QUOTE = '\"';
!     private final char SINGLE_QUOTE = '\'';
      private String delim;
  
  
  
+ 	private Hashtable attributeTable;
+ 	private String element;
+ 	private String name;
+ 	private String value;
+ 	private String part;
+ 	private String empty;
+ 	private boolean equal;
+ 	private StringTokenizer tokenizer;
+ 	private boolean doubleQuote;
+ 	private boolean singleQuote;
+ 	private boolean ready;
+ 	private String currentToken;
+ 	private String tokenAccumulator;
  	/**
  	* Method to break the tag into pieces.
***************
*** 91,149 ****
  	*
  	*/
!    public Hashtable parseAttributes(Tag tag){
!         Hashtable h = new Hashtable();
!         String element,name,value,nextPart=null;
!         String empty=null;
          name=null;
          value=null;
          element=null;
!         boolean waitingForEqual=false;
!         delim=delima;
!         StringTokenizer tokenizer = new StringTokenizer(tag.getText(),delim,true);
          while (true) {
!             nextPart=getNextPart(tokenizer,delim);
!             delim=delima;
!             if (element==null && nextPart != null && !nextPart.equals("=")){
!                 element = nextPart;
!                 putDataIntoTable(h,element,null,true);
              }
              else {
!                 if (nextPart != null && (0 < nextPart.length ())) {
!                     if (name == null) {
!                         if (!nextPart.substring(0,1).equals(" ")) {
!                             name = nextPart;
!                             waitingForEqual=true;
!                         }
!                     }
!                     else {
!                         if (waitingForEqual){
!                             if (nextPart.equals("=")) {
!                                 waitingForEqual=false;
!                                 delim=delimb;
!                             }
!                             else {
!                                  putDataIntoTable(h,name,"",false);
!                                  name=nextPart;
!                                  value=null;
!                             }
!                         }
!                         if (!waitingForEqual && !nextPart.equals("=")) {
!                             value=nextPart;
!                             putDataIntoTable(h,name,value,false);
!                             name=null;
!                             value=null;
!                         }
!                     }
                  }
                  else {
!                     if (name != null) {
!                       if (name.equals("/")) {
!                         putDataIntoTable(h,Tag.EMPTYTAG,"",false);
!                       } else {
!                         putDataIntoTable(h,name,"",false);
!                       }
!                       name=null;
!                       value=null;
!                     }
                      break;
                  }
--- 104,130 ----
  	*
  	*/
!    public Hashtable parseAttributes(Tag tag) {
! 		attributeTable = new Hashtable();
! 		part = null;
! 		empty = null;
          name=null;
          value=null;
          element=null;
! 		equal = false;
!         delim=DELIMETERS;
! 		tokenizer = new StringTokenizer(tag.getText(),delim,true);
          while (true) {
!             part=getNextPartUsing(delim);
!             delim=DELIMETERS;
!             if (element==null && part != null && !part.equals("=")){
!                 element = part;
!                 putDataIntoTable(attributeTable,element,null,true);
              }
              else {
!                 if (isValid(part)) {
!                     process(part);
                  }
                  else {
!                    	processInvalidPart();
                      break;
                  }
***************
*** 151,207 ****
          }
          if (null == element) // handle no tag contents
!             putDataIntoTable(h,"",null,true);
!         return h;
      }
  
!     private String getNextPart(StringTokenizer tokenizer,String deli){
!         String tokenAccumulator=null;
!         boolean isDoubleQuote=false;
!         boolean isSingleQuote=false;
!         boolean isDataReady=false;
!         String currentToken;
!         while (isDataReady == false && tokenizer.hasMoreTokens()) {
!             currentToken = tokenizer.nextToken(deli);
!             //
!             // First let's combine tokens that are inside "" or ''
!             //
!             if (isDoubleQuote || isSingleQuote) {
!                 if (isDoubleQuote && currentToken.charAt(0)==doubleQuote){
!                     isDoubleQuote= false;
!                     isDataReady=true;
!                 } else if (isSingleQuote && currentToken.charAt(0)==singleQuote) {
!                     isSingleQuote=false;
!                     isDataReady=true;
!                 }else {
!                     tokenAccumulator += currentToken;
!                     continue;
!                 }
!             } else if (currentToken.charAt(0)==doubleQuote){
!                 isDoubleQuote= true;
!                 tokenAccumulator = "";
!                 continue;
!             } else if (currentToken.charAt(0)==singleQuote){
!                 isSingleQuote=true;
!                 tokenAccumulator="";
!                 continue;
!             } else tokenAccumulator = currentToken;
  
!             if (tokenAccumulator.equals(currentToken)) {
  
!                 if (delim.indexOf(tokenAccumulator)>=0) {
!                     if (tokenAccumulator.equals("=")){
!                         isDataReady=true;
!                     }
!                 }
!                 else {
  
!                     isDataReady=true;
!                 }
!             }
!             else isDataReady=true;
  
          }
          return tokenAccumulator;
      }
  
  
--- 132,243 ----
          }
          if (null == element) // handle no tag contents
!             putDataIntoTable(attributeTable,"",null,true);
!         return attributeTable;
      }
  
! 	private void processInvalidPart() {
! 		 if (name != null) {
! 		      if (name.equals("/")) {
! 		        putDataIntoTable(attributeTable,Tag.EMPTYTAG,"",false);
! 		      } else {
! 		        putDataIntoTable(attributeTable,name,"",false);
! 		      }
! 		      name=null;
! 		      value=null;
! 		    }
! 	}
  
! 	private boolean isValid(String part) {
! 		return part != null && (0 < part.length ());
! 	}
  
! 	private void process(String part) {
! 		if (name == null) {
! 		    if (!part.substring(0,1).equals(" ")) {
! 		        name = part;
! 		        equal=true;
! 		    }
! 		}
! 		else {
! 		    if (equal){
! 		        if (part.equals("=")) {
! 		            equal=false;
! 		            delim=DELIMETERS_WITHOUT_EQUALS;
! 		        }
! 		        else {
! 		             putDataIntoTable(attributeTable,name,"",false);
! 		             name=part;
! 		             value=null;
! 		        }
! 		    }
! 		    if (!equal && !part.equals("=")) {
! 		        value=part;
! 		        putDataIntoTable(attributeTable,name,value,false);
! 		        name=null;
! 		        value=null;
! 		    }
! 		}
! 	}
  
!     private String getNextPartUsing(String delimiter) {
! 		tokenAccumulator = null;
! 		doubleQuote = false;
! 		singleQuote = false;
! 		ready = false;
!         while (ready == false && tokenizer.hasMoreTokens()) {
!             currentToken = tokenizer.nextToken(delimiter);
  
+             if (doubleQuote || singleQuote) {
+                 combineTokensInsideSingleOrDoubleQuotes();
+             } else if (isCurrentTokenDoubleQuote()){
+                 doubleQuote= true;
+                 tokenAccumulator = "";
+             } else if (isCurrentTokenSingleQuote()){
+                 singleQuote=true;
+                 tokenAccumulator="";
+             } else {
+             	tokenAccumulator = currentToken;
+                 ready = isReadyWithNextPart(currentToken);
+             }
          }
          return tokenAccumulator;
      }
+ 
+ 	private boolean isReadyWithNextPart(String currentToken) {
+ 		boolean ready = false;
+ 		if (isDelimeter(currentToken)) {
+ 		    if (currentToken.equals("=")){
+ 		        ready=true;
+ 		    }
+ 		}
+ 		else {
+ 		    ready=true;
+ 		}
+ 		return ready;
+ 	}
+ 
+ 	private boolean isDelimeter(String token) {
+ 		return delim.indexOf(tokenAccumulator)>=0;
+ 	}
+ 	
+ 	private boolean isCurrentTokenSingleQuote() {
+ 		return currentToken.charAt(0)==SINGLE_QUOTE;
+ 	}
+ 
+ 	private boolean isCurrentTokenDoubleQuote() {
+ 		return currentToken.charAt(0)==DOUBLE_QUOTE;
+ 	}
+ 
+ 	private void combineTokensInsideSingleOrDoubleQuotes() {
+ 		if (doubleQuote && currentToken.charAt(0)==DOUBLE_QUOTE){
+ 		    doubleQuote= false;
+ 		    ready=true;
+ 		} else if (singleQuote && currentToken.charAt(0)==SINGLE_QUOTE) {
+ 		    singleQuote=false;
+ 		    ready=true;
+ 		}else {
+ 		    tokenAccumulator += currentToken;
+ 		}
+ 	}
  
  

[Htmlparser-cvs] htmlparser/src/org/htmlparser/parserHelper ScriptScannerHelper.java,1.1,1.2

[<so...@us...>]

Update of /cvsroot/htmlparser/htmlparser/src/org/htmlparser/parserHelper
In directory sc8-pr-cvs1:/tmp/cvs-serv5788/src/org/htmlparser/parserHelper

Modified Files:
	ScriptScannerHelper.java 
Log Message:
added header

Index: ScriptScannerHelper.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/parserHelper/ScriptScannerHelper.java,v
retrieving revision 1.1
retrieving revision 1.2
diff -C2 -d -r1.1 -r1.2
*** ScriptScannerHelper.java	17 Jun 2003 01:32:06 -0000	1.1
--- ScriptScannerHelper.java	17 Jun 2003 01:33:01 -0000	1.2
***************
*** 1,2 ****
--- 1,29 ----
+ //HTMLParser Library v1_4_20030601 - A java-based parser for HTML
+ //Copyright (C) Dec 31, 2000 Somik Raha
+ //
+ //This library is free software; you can redistribute it and/or
+ //modify it under the terms of the GNU Lesser General Public
+ //License as published by the Free Software Foundation; either
+ //version 2.1 of the License, or (at your option) any later version.
+ //
+ //This library is distributed in the hope that it will be useful,
+ //but WITHOUT ANY WARRANTY; without even the implied warranty of
+ //MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ //Lesser General Public License for more details.
+ // 
+ //You should have received a copy of the GNU Lesser General Public
+ //License along with this library; if not, write to the Free Software
+ //Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ //
+ //For any questions or suggestions, you can write to me at :
+ //Email :so...@in...
+ // 
+ //Postal Address : 
+ //Somik Raha
+ //Extreme Programmer & Coach
+ //Industrial Logic, Inc.
+ //2583 Cedar Street, Berkeley, 
+ //CA 94708, USA
+ //Website : http://www.industriallogic.com
  package org.htmlparser.parserHelper;
  

[Htmlparser-cvs] htmlparser/src/org/htmlparser/parserHelper ScriptScannerHelper.java,NONE,1.1

[<so...@us...>]

Update of /cvsroot/htmlparser/htmlparser/src/org/htmlparser/parserHelper
In directory sc8-pr-cvs1:/tmp/cvs-serv5705/src/org/htmlparser/parserHelper

Added Files:
	ScriptScannerHelper.java 
Log Message:
created ScriptScannerHelper to allow thread safety in ScriptScanner

--- NEW FILE: ScriptScannerHelper.java ---
package org.htmlparser.parserHelper;

import org.htmlparser.*;
import org.htmlparser.scanners.*;
import org.htmlparser.tags.*;
import org.htmlparser.tags.data.*;
import org.htmlparser.util.*;



public class ScriptScannerHelper {

	private int endTagLoc;
	private Tag endTag;
	private Tag startTag;
	private int startingPos;
	private boolean sameLine;
	private boolean endTagFound;
	private NodeReader reader;
	private StringBuffer scriptContents;
	private ScriptScanner scriptScanner;
	private Tag tag;
	private String url;
	private String currLine;
	
	public ScriptScannerHelper(Tag tag, String url, NodeReader nodeReader, String currLine, ScriptScanner scriptScanner) {
		this.reader = nodeReader;
		this.scriptScanner = scriptScanner;
		this.tag = tag;
		this.url = url;
		this.currLine = currLine;
	}

	public Tag scan() throws ParserException {
		int startLine = reader.getLastLineNumber();
		startTag = tag;
		extractScriptTagFrom(currLine);
		if (isScriptEndTagNotFound()) {
			createScriptEndTag(tag, currLine);
		}
		return createScriptTagUsing(url, currLine, startLine);
	}
	
	private Tag createScriptTagUsing(String url, String currLine, int startLine) {
		return scriptScanner.createTag(
			new TagData(
				startTag.elementBegin(),
				endTag.elementEnd(),
				startLine,
				reader.getLastLineNumber(),
				startTag.getText(),
				currLine,
				url,
				false
			), new CompositeTagData(
				startTag,endTag,createChildrenNodeList()
			)
		);
	}

	private NodeList createChildrenNodeList() {
		NodeList childrenNodeList = new NodeList();
		childrenNodeList.add(
			new StringNode(
				scriptContents,
				startTag.elementEnd(),
				endTag.elementBegin()-1
			)
		);
		return childrenNodeList;
	}

	private void createScriptEndTag(Tag tag, String currLine) {
		// If end tag doesn't exist, create one
		String endTagName = tag.getTagName();
		int endTagBegin = reader.getLastReadPosition()+1 ;
		int endTagEnd = endTagBegin + endTagName.length() + 2; 
		endTag = new EndTag(
			new TagData(
				endTagBegin,
				endTagEnd,
				endTagName,
				currLine
			)
		);
	}

	private boolean isScriptEndTagNotFound() {
		return endTag == null;
	}

	private void extractScriptTagFrom(String currLine) throws ParserException {
		String line = null;
		scriptContents = new StringBuffer();
		endTagFound = false;
		
		endTag = null;
		line = currLine;
		sameLine = true;
		startingPos = startTag.elementEnd();
		do {
			doExtractionOfScriptContentsFrom(line);
			if (!endTagFound) {
				line = reader.getNextLine();
				startingPos = 0;
			}
			if (sameLine) 
				sameLine = false;
		}
		while (line!=null && !endTagFound);
	}

	private void doExtractionOfScriptContentsFrom(String line) throws ParserException {
		endTagLoc = line.toUpperCase().indexOf(scriptScanner.getEndTag(),startingPos);
		findStartingAndEndingLocations(line);
		
		if (endTagLoc!=-1) {
			extractEndTagFrom(line);
		} else {
			continueParsing(line);
		}
	}

	private void continueParsing(String line) {
		if (sameLine) 
			scriptContents.append(
				line.substring(
					startTag.elementEnd()+1
				)
			);
		else {
			scriptContents.append(Parser.getLineSeparator());
			scriptContents.append(line);
		}
	}

	private void extractEndTagFrom(String line) throws ParserException {
		endTagFound = true;
		endTag = (EndTag)EndTag.find(line,endTagLoc);
		if (sameLine) 
			scriptContents.append(
				getCodeBetweenStartAndEndTags(
					line,
					startTag,
					endTagLoc)
			);
		else {
			scriptContents.append(Parser.getLineSeparator());
			scriptContents.append(line.substring(0,endTagLoc));
		}
		
		reader.setPosInLine(endTag.elementEnd());
	}

	private void findStartingAndEndingLocations(String line) {
		while (endTagLoc>0 && isThisEndTagLocationFalseMatch(line, endTagLoc)) {
			startingPos = endTagLoc+scriptScanner.getEndTag().length();
			endTagLoc = line.toUpperCase().indexOf(scriptScanner.getEndTag(), startingPos); 	
		}
	}

	public String getCodeBetweenStartAndEndTags(
		String line,
		Tag startTag,
		int endTagLoc) throws ParserException {
		try {
			
			return line.substring(
				startTag.elementEnd()+1,
				endTagLoc
			);
		}
		catch (Exception e) {
			StringBuffer msg = new StringBuffer("Error in getCodeBetweenStartAndEndTags():\n");
			msg.append("substring starts at: "+(startTag.elementEnd()+1)).append("\n");
			msg.append("substring ends at: "+(endTagLoc));
			throw new ParserException(msg.toString(),e);
		}
	}

	private boolean isThisEndTagLocationFalseMatch(String line, int endTagLoc) {
		if (endTagLoc+scriptScanner.getEndTag().length() > line.length()-1) return false;
		char charAfterSuspectedEndTag = 
			line.charAt(endTagLoc+scriptScanner.getEndTag().length()); 
		return charAfterSuspectedEndTag=='"' || charAfterSuspectedEndTag=='\'';
	}
}

[Htmlparser-cvs] htmlparser/src/org/htmlparser/scanners ScriptScanner.java,1.27,1.28

[<so...@us...>]

Update of /cvsroot/htmlparser/htmlparser/src/org/htmlparser/scanners
In directory sc8-pr-cvs1:/tmp/cvs-serv5705/src/org/htmlparser/scanners

Modified Files:
	ScriptScanner.java 
Log Message:
created ScriptScannerHelper to allow thread safety in ScriptScanner

Index: ScriptScanner.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/scanners/ScriptScanner.java,v
retrieving revision 1.27
retrieving revision 1.28
diff -C2 -d -r1.27 -r1.28
*** ScriptScanner.java	17 Jun 2003 00:43:56 -0000	1.27
--- ScriptScanner.java	17 Jun 2003 01:32:06 -0000	1.28
***************
*** 32,35 ****
--- 32,36 ----
  /////////////////////////
  import org.htmlparser.*;
+ import org.htmlparser.parserHelper.*;
  import org.htmlparser.tags.*;
  import org.htmlparser.tags.data.*;
***************
*** 43,55 ****
  	private static final String MATCH_NAME [] = {"SCRIPT"};
  	private static final String ENDERS [] = {"BODY", "HTML"};
! 	private int endTagLoc;
! 	private Tag endTag;
! 	private Tag startTag;
! 	private int startingPos;
! 	private boolean sameLine;
! 	private boolean endTagFound;
! 	private NodeReader reader;
  	
! 	private StringBuffer scriptContents;
  	public ScriptScanner() {
  		super("",MATCH_NAME,ENDERS);
--- 44,50 ----
  	private static final String MATCH_NAME [] = {"SCRIPT"};
  	private static final String ENDERS [] = {"BODY", "HTML"};
! 
  	
! 
  	public ScriptScanner() {
  		super("",MATCH_NAME,ENDERS);
***************
*** 77,88 ****
  		throws ParserException {
  		try {
! 			this.reader = nodeReader;
! 			int startLine = reader.getLastLineNumber();
! 			startTag = tag;
! 			extractScriptTagFrom(currLine);
! 			if (isScriptEndTagNotFound()) {
! 				createScriptEndTag(tag, currLine);
! 			}
! 			return createScriptTagUsing(url, currLine, startLine);
  			
  		}
--- 72,78 ----
  		throws ParserException {
  		try {
! 			ScriptScannerHelper helper = 
! 				new ScriptScannerHelper(tag,url,nodeReader,currLine, this);
! 			return helper.scan();
  			
  		}
***************
*** 92,231 ****
  	}
  
- 	private Tag createScriptTagUsing(String url, String currLine, int startLine) {
- 		return createTag(
- 			new TagData(
- 				startTag.elementBegin(),
- 				endTag.elementEnd(),
- 				startLine,
- 				reader.getLastLineNumber(),
- 				startTag.getText(),
- 				currLine,
- 				url,
- 				false
- 			), new CompositeTagData(
- 				startTag,endTag,createChildrenNodeList()
- 			)
- 		);
- 	}
- 
- 	private NodeList createChildrenNodeList() {
- 		NodeList childrenNodeList = new NodeList();
- 		childrenNodeList.add(
- 			new StringNode(
- 				scriptContents,
- 				startTag.elementEnd(),
- 				endTag.elementBegin()-1
- 			)
- 		);
- 		return childrenNodeList;
- 	}
- 
- 	private void createScriptEndTag(Tag tag, String currLine) {
- 		// If end tag doesn't exist, create one
- 		String endTagName = tag.getTagName();
- 		int endTagBegin = reader.getLastReadPosition()+1 ;
- 		int endTagEnd = endTagBegin + endTagName.length() + 2; 
- 		endTag = new EndTag(
- 			new TagData(
- 				endTagBegin,
- 				endTagEnd,
- 				endTagName,
- 				currLine
- 			)
- 		);
- 	}
- 
- 	private boolean isScriptEndTagNotFound() {
- 		return endTag == null;
- 	}
- 
- 	private void extractScriptTagFrom(String currLine) throws ParserException {
- 		String line = null;
- 		scriptContents = new StringBuffer();
- 		endTagFound = false;
- 		
- 		endTag = null;
- 		line = currLine;
- 		sameLine = true;
- 		startingPos = startTag.elementEnd();
- 		do {
- 			doExtractionOfScriptContentsFrom(line);
- 			if (!endTagFound) {
- 				line = reader.getNextLine();
- 				startingPos = 0;
- 			}
- 			if (sameLine) 
- 				sameLine = false;
- 		}
- 		while (line!=null && !endTagFound);
- 	}
- 
- 	private void doExtractionOfScriptContentsFrom(String line) throws ParserException {
- 		endTagLoc = line.toUpperCase().indexOf(getEndTag(),startingPos);
- 		findStartingAndEndingLocations(line);
- 		
- 		if (endTagLoc!=-1) {
- 			extractEndTagFrom(line);
- 		} else {
- 			continueParsing(line);
- 		}
- 	}
- 
- 	private void continueParsing(String line) {
- 		if (sameLine) 
- 			scriptContents.append(
- 				line.substring(
- 					startTag.elementEnd()+1
- 				)
- 			);
- 		else {
- 			scriptContents.append(Parser.getLineSeparator());
- 			scriptContents.append(line);
- 		}
- 	}
- 
- 	private void extractEndTagFrom(String line) throws ParserException {
- 		endTagFound = true;
- 		endTag = (EndTag)EndTag.find(line,endTagLoc);
- 		if (sameLine) 
- 			scriptContents.append(
- 				getCodeBetweenStartAndEndTags(
- 					line,
- 					startTag,
- 					endTagLoc)
- 			);
- 		else {
- 			scriptContents.append(Parser.getLineSeparator());
- 			scriptContents.append(line.substring(0,endTagLoc));
- 		}
- 		
- 		reader.setPosInLine(endTag.elementEnd());
- 	}
- 
- 	private void findStartingAndEndingLocations(String line) {
- 		while (endTagLoc>0 && isThisEndTagLocationFalseMatch(line, endTagLoc)) {
- 			startingPos = endTagLoc+getEndTag().length();
- 			endTagLoc = line.toUpperCase().indexOf(getEndTag(), startingPos); 	
- 		}
- 	}
- 
- 	public String getCodeBetweenStartAndEndTags(
- 		String line,
- 		Tag startTag,
- 		int endTagLoc) throws ParserException {
- 		try {
- 			
- 			return line.substring(
- 				startTag.elementEnd()+1,
- 				endTagLoc
- 			);
- 		}
- 		catch (Exception e) {
- 			StringBuffer msg = new StringBuffer("Error in getCodeBetweenStartAndEndTags():\n");
- 			msg.append("substring starts at: "+(startTag.elementEnd()+1)).append("\n");
- 			msg.append("substring ends at: "+(endTagLoc));
- 			throw new ParserException(msg.toString(),e);
- 		}
- 	}
  
  	/**
--- 82,85 ----
***************
*** 238,247 ****
  	}
  	
! 	private boolean isThisEndTagLocationFalseMatch(String line, int endTagLoc) {
! 		if (endTagLoc+getEndTag().length() > line.length()-1) return false;
! 		char charAfterSuspectedEndTag = 
! 			line.charAt(endTagLoc+getEndTag().length()); 
! 		return charAfterSuspectedEndTag=='"' || charAfterSuspectedEndTag=='\'';
! 	}
  
  }
--- 92,96 ----
  	}
  	
! 
  
  }

[Htmlparser-cvs] htmlparser/src/org/htmlparser/scanners ScriptScanner.java,1.26,1.27

[<so...@us...>]

Update of /cvsroot/htmlparser/htmlparser/src/org/htmlparser/scanners
In directory sc8-pr-cvs1:/tmp/cvs-serv1059/src/org/htmlparser/scanners

Modified Files:
	ScriptScanner.java 
Log Message:
updated scriptscanner header

Index: ScriptScanner.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/scanners/ScriptScanner.java,v
retrieving revision 1.26
retrieving revision 1.27
diff -C2 -d -r1.26 -r1.27
*** ScriptScanner.java	17 Jun 2003 00:43:09 -0000	1.26
--- ScriptScanner.java	17 Jun 2003 00:43:56 -0000	1.27
***************
*** 1,3 ****
! // HTMLParser Library v1_3_20030518 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030601 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //

[Htmlparser-cvs] htmlparser/src/org/htmlparser/scanners ScriptScanner.java,1.25,1.26

[<so...@us...>]

Update of /cvsroot/htmlparser/htmlparser/src/org/htmlparser/scanners
In directory sc8-pr-cvs1:/tmp/cvs-serv935/src/org/htmlparser/scanners

Modified Files:
	ScriptScanner.java 
Log Message:
fixed ScriptScanner failing tests..

Index: ScriptScanner.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/scanners/ScriptScanner.java,v
retrieving revision 1.25
retrieving revision 1.26
diff -C2 -d -r1.25 -r1.26
*** ScriptScanner.java	1 Jun 2003 20:50:12 -0000	1.25
--- ScriptScanner.java	17 Jun 2003 00:43:09 -0000	1.26
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030601 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_3_20030518 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
***************
*** 28,59 ****
  
  package org.htmlparser.scanners;
! 
! import org.htmlparser.tags.ScriptTag;
! import org.htmlparser.tags.Tag;
! import org.htmlparser.tags.data.CompositeTagData;
! import org.htmlparser.tags.data.TagData;
! 
  /**
   * The HTMLScriptScanner identifies javascript code
   */
  public class ScriptScanner extends CompositeTagScanner {
  	private static final String MATCH_NAME [] = {"SCRIPT"};
  	private static final String ENDERS [] = {"BODY", "HTML"};
  	public ScriptScanner() {
! 		this("");
  	}
  
  	public ScriptScanner(String filter) {
! 		this(filter,MATCH_NAME,ENDERS);
! 	}
! 
! 	public ScriptScanner(String filter, String[] nameOfTagToMatch, String[] enders) {
! 		this(filter,nameOfTagToMatch,enders, new String[0], true, true);
  	}
  
! 	public ScriptScanner(String filter, String[] nameOfTagToMatch, String[] enders, String[] endtagenders, boolean allowSelfChildren, boolean balance_quotes) {
! 		super(filter,nameOfTagToMatch,enders, new String[0], allowSelfChildren, balance_quotes);
  	}
! 
  	public String [] getID() {
  		return MATCH_NAME;
--- 28,67 ----
  
  package org.htmlparser.scanners;
! /////////////////////////
! // HTML Parser Imports //
! /////////////////////////
! import org.htmlparser.*;
! import org.htmlparser.tags.*;
! import org.htmlparser.tags.data.*;
! import org.htmlparser.util.*;
  /**
   * The HTMLScriptScanner identifies javascript code
   */
+ 
  public class ScriptScanner extends CompositeTagScanner {
+ 	private static final String SCRIPT_END_TAG = "</SCRIPT>";
  	private static final String MATCH_NAME [] = {"SCRIPT"};
  	private static final String ENDERS [] = {"BODY", "HTML"};
+ 	private int endTagLoc;
+ 	private Tag endTag;
+ 	private Tag startTag;
+ 	private int startingPos;
+ 	private boolean sameLine;
+ 	private boolean endTagFound;
+ 	private NodeReader reader;
+ 	
+ 	private StringBuffer scriptContents;
  	public ScriptScanner() {
! 		super("",MATCH_NAME,ENDERS);
  	}
  
  	public ScriptScanner(String filter) {
! 		super(filter,MATCH_NAME,ENDERS);
  	}
  
! 	public ScriptScanner(String filter, String[] nameOfTagToMatch) {
! 		super(filter,nameOfTagToMatch,ENDERS);
  	}
! 	
  	public String [] getID() {
  		return MATCH_NAME;
***************
*** 65,67 ****
--- 73,247 ----
  		return new ScriptTag(tagData,compositeTagData);
  	}
+ 
+ 	public Tag scan(Tag tag, String url, NodeReader nodeReader, String currLine)
+ 		throws ParserException {
+ 		try {
+ 			this.reader = nodeReader;
+ 			int startLine = reader.getLastLineNumber();
+ 			startTag = tag;
+ 			extractScriptTagFrom(currLine);
+ 			if (isScriptEndTagNotFound()) {
+ 				createScriptEndTag(tag, currLine);
+ 			}
+ 			return createScriptTagUsing(url, currLine, startLine);
+ 			
+ 		}
+ 		catch (Exception e) {
+ 			throw new ParserException("Error in ScriptScanner: ",e);
+ 		}
+ 	}
+ 
+ 	private Tag createScriptTagUsing(String url, String currLine, int startLine) {
+ 		return createTag(
+ 			new TagData(
+ 				startTag.elementBegin(),
+ 				endTag.elementEnd(),
+ 				startLine,
+ 				reader.getLastLineNumber(),
+ 				startTag.getText(),
+ 				currLine,
+ 				url,
+ 				false
+ 			), new CompositeTagData(
+ 				startTag,endTag,createChildrenNodeList()
+ 			)
+ 		);
+ 	}
+ 
+ 	private NodeList createChildrenNodeList() {
+ 		NodeList childrenNodeList = new NodeList();
+ 		childrenNodeList.add(
+ 			new StringNode(
+ 				scriptContents,
+ 				startTag.elementEnd(),
+ 				endTag.elementBegin()-1
+ 			)
+ 		);
+ 		return childrenNodeList;
+ 	}
+ 
+ 	private void createScriptEndTag(Tag tag, String currLine) {
+ 		// If end tag doesn't exist, create one
+ 		String endTagName = tag.getTagName();
+ 		int endTagBegin = reader.getLastReadPosition()+1 ;
+ 		int endTagEnd = endTagBegin + endTagName.length() + 2; 
+ 		endTag = new EndTag(
+ 			new TagData(
+ 				endTagBegin,
+ 				endTagEnd,
+ 				endTagName,
+ 				currLine
+ 			)
+ 		);
+ 	}
+ 
+ 	private boolean isScriptEndTagNotFound() {
+ 		return endTag == null;
+ 	}
+ 
+ 	private void extractScriptTagFrom(String currLine) throws ParserException {
+ 		String line = null;
+ 		scriptContents = new StringBuffer();
+ 		endTagFound = false;
+ 		
+ 		endTag = null;
+ 		line = currLine;
+ 		sameLine = true;
+ 		startingPos = startTag.elementEnd();
+ 		do {
+ 			doExtractionOfScriptContentsFrom(line);
+ 			if (!endTagFound) {
+ 				line = reader.getNextLine();
+ 				startingPos = 0;
+ 			}
+ 			if (sameLine) 
+ 				sameLine = false;
+ 		}
+ 		while (line!=null && !endTagFound);
+ 	}
+ 
+ 	private void doExtractionOfScriptContentsFrom(String line) throws ParserException {
+ 		endTagLoc = line.toUpperCase().indexOf(getEndTag(),startingPos);
+ 		findStartingAndEndingLocations(line);
+ 		
+ 		if (endTagLoc!=-1) {
+ 			extractEndTagFrom(line);
+ 		} else {
+ 			continueParsing(line);
+ 		}
+ 	}
+ 
+ 	private void continueParsing(String line) {
+ 		if (sameLine) 
+ 			scriptContents.append(
+ 				line.substring(
+ 					startTag.elementEnd()+1
+ 				)
+ 			);
+ 		else {
+ 			scriptContents.append(Parser.getLineSeparator());
+ 			scriptContents.append(line);
+ 		}
+ 	}
+ 
+ 	private void extractEndTagFrom(String line) throws ParserException {
+ 		endTagFound = true;
+ 		endTag = (EndTag)EndTag.find(line,endTagLoc);
+ 		if (sameLine) 
+ 			scriptContents.append(
+ 				getCodeBetweenStartAndEndTags(
+ 					line,
+ 					startTag,
+ 					endTagLoc)
+ 			);
+ 		else {
+ 			scriptContents.append(Parser.getLineSeparator());
+ 			scriptContents.append(line.substring(0,endTagLoc));
+ 		}
+ 		
+ 		reader.setPosInLine(endTag.elementEnd());
+ 	}
+ 
+ 	private void findStartingAndEndingLocations(String line) {
+ 		while (endTagLoc>0 && isThisEndTagLocationFalseMatch(line, endTagLoc)) {
+ 			startingPos = endTagLoc+getEndTag().length();
+ 			endTagLoc = line.toUpperCase().indexOf(getEndTag(), startingPos); 	
+ 		}
+ 	}
+ 
+ 	public String getCodeBetweenStartAndEndTags(
+ 		String line,
+ 		Tag startTag,
+ 		int endTagLoc) throws ParserException {
+ 		try {
+ 			
+ 			return line.substring(
+ 				startTag.elementEnd()+1,
+ 				endTagLoc
+ 			);
+ 		}
+ 		catch (Exception e) {
+ 			StringBuffer msg = new StringBuffer("Error in getCodeBetweenStartAndEndTags():\n");
+ 			msg.append("substring starts at: "+(startTag.elementEnd()+1)).append("\n");
+ 			msg.append("substring ends at: "+(endTagLoc));
+ 			throw new ParserException(msg.toString(),e);
+ 		}
+ 	}
+ 
+ 	/**
+ 	 * Gets the end tag that the scanner uses to stop scanning. Subclasses of
+ 	 * <code>ScriptScanner</code> you should override this method.
+ 	 * @return String containing the end tag to search for, i.e. &lt;/SCRIPT&gt;
+ 	 */ 
+ 	public String getEndTag() {
+ 		return SCRIPT_END_TAG;
+ 	}
+ 	
+ 	private boolean isThisEndTagLocationFalseMatch(String line, int endTagLoc) {
+ 		if (endTagLoc+getEndTag().length() > line.length()-1) return false;
+ 		char charAfterSuspectedEndTag = 
+ 			line.charAt(endTagLoc+getEndTag().length()); 
+ 		return charAfterSuspectedEndTag=='"' || charAfterSuspectedEndTag=='\'';
+ 	}
+ 
  }

[Htmlparser-cvs] htmlparser/src/org/htmlparser/tests/scannersTests ScriptScannerTest.java,1.27,1.28

[<so...@us...>]

Update of /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/scannersTests
In directory sc8-pr-cvs1:/tmp/cvs-serv935/src/org/htmlparser/tests/scannersTests

Modified Files:
	ScriptScannerTest.java 
Log Message:
fixed ScriptScanner failing tests..

Index: ScriptScannerTest.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/scannersTests/ScriptScannerTest.java,v
retrieving revision 1.27
retrieving revision 1.28
diff -C2 -d -r1.27 -r1.28
*** ScriptScannerTest.java	1 Jun 2003 20:50:16 -0000	1.27
--- ScriptScannerTest.java	17 Jun 2003 00:43:08 -0000	1.28
***************
*** 117,121 ****
  		
  		StringBuffer sb2 = new StringBuffer();
! 		sb2.append("if(navigator.appName.indexOf(\"Netscape\") != -1)\r\n"); 
  		sb2.append(" document.write ('xxx');\r\n"); 
  		sb2.append("else\r\n"); 
--- 117,121 ----
  		
  		StringBuffer sb2 = new StringBuffer();
! 		sb2.append("\r\nif(navigator.appName.indexOf(\"Netscape\") != -1)\r\n"); 
  		sb2.append(" document.write ('xxx');\r\n"); 
  		sb2.append("else\r\n"); 
***************
*** 172,176 ****
  		ScriptTag scriptTag = (ScriptTag)node[0];
  		String scriptCode = scriptTag.getScriptCode();	  
! 		String expectedCode = "<!--\r\n"+
  						  "  function validateForm()\r\n"+
  						  "  {\r\n"+
--- 172,176 ----
  		ScriptTag scriptTag = (ScriptTag)node[0];
  		String scriptCode = scriptTag.getScriptCode();	  
! 		String expectedCode = "\r\n<!--\r\n"+
  						  "  function validateForm()\r\n"+
  						  "  {\r\n"+
***************
*** 180,184 ****
  						  "     return true;\r\n"+
  						  "  }\r\n"+
! 						  "// -->";
  		assertStringEquals("Expected Code",expectedCode,scriptCode);
  	}
--- 180,184 ----
  						  "     return true;\r\n"+
  						  "  }\r\n"+
! 						  "// -->\r\n";
  		assertStringEquals("Expected Code",expectedCode,scriptCode);
  	}
***************
*** 561,565 ****
  	
  	public void testScanScriptWithTagsInComment() throws ParserException {
! 		String javascript = "// This is javascript with <li> tag in the comment\n";
  		createParser("<script>\n"+ javascript + "\n</script>");
  		parser.registerScanners();
--- 561,565 ----
  	
  	public void testScanScriptWithTagsInComment() throws ParserException {
! 		String javascript = "// This is javascript with <li> tag in the comment";
  		createParser("<script>\n"+ javascript + "\n</script>");
  		parser.registerScanners();
***************
*** 568,572 ****
  		ScriptTag scriptTag = (ScriptTag)node[0];
  		String scriptCode = scriptTag.getScriptCode();
! 		assertStringEquals("Expected Code",javascript,scriptCode);
  	}
  	
--- 568,578 ----
  		ScriptTag scriptTag = (ScriptTag)node[0];
  		String scriptCode = scriptTag.getScriptCode();
! 		String expectedCode = 
! 			wrapLineSeperatorAround(javascript);
! 		assertStringEquals("Expected Code",expectedCode,scriptCode);
! 	}
! 
! 	private String wrapLineSeperatorAround(String javascript) {
! 		return Parser.getLineSeparator()+javascript+Parser.getLineSeparator();
  	}
  	
***************
*** 576,579 ****
--- 582,586 ----
  			"that spans multiple lines;";
  		createParser("<script>\n"+ javascript + "\n</script>");
+ 		Parser.setLineSeparator("\n");
  		parser.registerScanners();
  		parseAndAssertNodeCount(1);
***************
*** 581,585 ****
  		ScriptTag scriptTag = (ScriptTag)node[0];
  		String scriptCode = scriptTag.getScriptCode();
! 		assertStringEquals("Expected Code",javascript,scriptCode);
  	}
  	
--- 588,595 ----
  		ScriptTag scriptTag = (ScriptTag)node[0];
  		String scriptCode = scriptTag.getScriptCode();
! 		
! 		String expectedCode =
! 			wrapLineSeperatorAround(javascript);
! 		assertStringEquals("Expected Code",expectedCode,scriptCode);
  	}
  	
***************
*** 593,597 ****
  		ScriptTag scriptTag = (ScriptTag)node[0];
  		String scriptCode = scriptTag.getScriptCode();
! 		assertStringEquals("Expected Code",javascript,scriptCode);
  	}
  	
--- 603,609 ----
  		ScriptTag scriptTag = (ScriptTag)node[0];
  		String scriptCode = scriptTag.getScriptCode();
! 		String expectedCode = 
! 			wrapLineSeperatorAround(javascript);
! 		assertStringEquals("Expected Code",expectedCode,scriptCode);
  	}
  	

[Htmlparser-cvs] htmlparser/src/org/htmlparser/tests/parserHelperTests AttributeParserTest.java,1.31,1.32

[<so...@us...>]

Update of /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/parserHelperTests
In directory sc8-pr-cvs1:/tmp/cvs-serv935/src/org/htmlparser/tests/parserHelperTests

Modified Files:
	AttributeParserTest.java 
Log Message:
fixed ScriptScanner failing tests..

Index: AttributeParserTest.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/parserHelperTests/AttributeParserTest.java,v
retrieving revision 1.31
retrieving revision 1.32
diff -C2 -d -r1.31 -r1.32
*** AttributeParserTest.java	1 Jun 2003 20:50:14 -0000	1.31
--- AttributeParserTest.java	17 Jun 2003 00:43:09 -0000	1.32
***************
*** 168,173 ****
       * Only perform this test if it's version 1.4 or higher.
       */
!     public void testJspWithinAttributes()
!     {
          Parser parser;
          
--- 168,172 ----
       * Only perform this test if it's version 1.4 or higher.
       */
!     public void testJspWithinAttributes() {
          Parser parser;
          
***************
*** 191,196 ****
       * Only perform this test if it's version 1.4 or higher.
       */
!     public void testScriptedTag ()
!     {
          Parser parser;
          
--- 190,194 ----
       * Only perform this test if it's version 1.4 or higher.
       */
!     public void testScriptedTag () {
          Parser parser;
          

[Htmlparser-cvs] htmlparser/src/org/htmlparser/parserapplications LinkExtractor.java,1.33,1.34 Robot.java,1.37,1.38

[<jke...@us...>]

Update of /cvsroot/htmlparser/htmlparser/src/org/htmlparser/parserapplications
In directory sc8-pr-cvs1:/tmp/cvs-serv17851/src/org/htmlparser/parserapplications

Modified Files:
	LinkExtractor.java Robot.java 
Log Message:
Renamed Node to AbstractNode, extracted the new interface, Node, and moved line separator code from AbstractNode to Parser.

Index: LinkExtractor.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/parserapplications/LinkExtractor.java,v
retrieving revision 1.33
retrieving revision 1.34
diff -C2 -d -r1.33 -r1.34
*** LinkExtractor.java	1 Jun 2003 20:50:11 -0000	1.33
--- LinkExtractor.java	13 Jun 2003 20:27:04 -0000	1.34
***************
*** 30,34 ****
  package org.htmlparser.parserapplications;
  
- 
  import org.htmlparser.Node;
  import org.htmlparser.Parser;
--- 30,33 ----

Index: Robot.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/parserapplications/Robot.java,v
retrieving revision 1.37
retrieving revision 1.38
diff -C2 -d -r1.37 -r1.38
*** Robot.java	1 Jun 2003 20:50:11 -0000	1.37
--- Robot.java	13 Jun 2003 20:27:04 -0000	1.38
***************
*** 28,31 ****
--- 28,32 ----
  
  package org.htmlparser.parserapplications;
+ 
  import org.htmlparser.Node;
  import org.htmlparser.Parser;

[Htmlparser-cvs] htmlparser/src/org/htmlparser/scanners TagScanner.java,1.26,1.27

[<jke...@us...>]

Update of /cvsroot/htmlparser/htmlparser/src/org/htmlparser/scanners
In directory sc8-pr-cvs1:/tmp/cvs-serv17851/src/org/htmlparser/scanners

Modified Files:
	TagScanner.java 
Log Message:
Renamed Node to AbstractNode, extracted the new interface, Node, and moved line separator code from AbstractNode to Parser.

Index: TagScanner.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/scanners/TagScanner.java,v
retrieving revision 1.26
retrieving revision 1.27
diff -C2 -d -r1.26 -r1.27
*** TagScanner.java	1 Jun 2003 20:50:12 -0000	1.26
--- TagScanner.java	13 Jun 2003 20:27:05 -0000	1.27
***************
*** 35,38 ****
--- 35,39 ----
  import java.util.Map;
  
+ import org.htmlparser.AbstractNode;
  import org.htmlparser.Node;
  import org.htmlparser.NodeReader;
***************
*** 264,268 ****
  	 * Insert an EndTag in the currentLine, just before the occurence of the provided tag
  	 */
! 	public String insertEndTagBeforeNode(Node node, String currentLine) {
  		String newLine = currentLine.substring(0,node.elementBegin());
  		newLine += "</A>";
--- 265,269 ----
  	 * Insert an EndTag in the currentLine, just before the occurence of the provided tag
  	 */
! 	public String insertEndTagBeforeNode(AbstractNode node, String currentLine) {
  		String newLine = currentLine.substring(0,node.elementBegin());
  		newLine += "</A>";

[Htmlparser-cvs] htmlparser/src/org/htmlparser/tags OptionTag.java,1.19,1.20 EndTag.java,1.19,1.20 Tag.java,1.30,1.31 CompositeTag.java,1.42,1.43

[<jke...@us...>]

Update of /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tags
In directory sc8-pr-cvs1:/tmp/cvs-serv17851/src/org/htmlparser/tags

Modified Files:
	OptionTag.java EndTag.java Tag.java CompositeTag.java 
Log Message:
Renamed Node to AbstractNode, extracted the new interface, Node, and moved line separator code from AbstractNode to Parser.

Index: OptionTag.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tags/OptionTag.java,v
retrieving revision 1.19
retrieving revision 1.20
diff -C2 -d -r1.19 -r1.20
*** OptionTag.java	1 Jun 2003 20:50:13 -0000	1.19
--- OptionTag.java	13 Jun 2003 20:27:05 -0000	1.20
***************
*** 31,35 ****
  import org.htmlparser.tags.data.CompositeTagData;
  import org.htmlparser.tags.data.TagData;
- import org.htmlparser.util.ParserUtils;
  
  public class OptionTag extends CompositeTag
--- 31,34 ----

Index: EndTag.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tags/EndTag.java,v
retrieving revision 1.19
retrieving revision 1.20
diff -C2 -d -r1.19 -r1.20
*** EndTag.java	1 Jun 2003 20:50:13 -0000	1.19
--- EndTag.java	13 Jun 2003 20:27:05 -0000	1.20
***************
*** 29,33 ****
  package org.htmlparser.tags;
  
! import org.htmlparser.Node;
  import org.htmlparser.tags.data.TagData;
  import org.htmlparser.visitors.NodeVisitor;
--- 29,33 ----
  package org.htmlparser.tags;
  
! import org.htmlparser.AbstractNode;
  import org.htmlparser.tags.data.TagData;
  import org.htmlparser.visitors.NodeVisitor;
***************
*** 58,62 ****
  	 * @param position Position to start parsing from
  	 */
! 	public static Node find(String input,int position)
  	{
  		int state = ENDTAG_BEFORE_PARSING_STATE;
--- 58,62 ----
  	 * @param position Position to start parsing from
  	 */
! 	public static AbstractNode find(String input,int position)
  	{
  		int state = ENDTAG_BEFORE_PARSING_STATE;

Index: Tag.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tags/Tag.java,v
retrieving revision 1.30
retrieving revision 1.31
diff -C2 -d -r1.30 -r1.31
*** Tag.java	1 Jun 2003 20:50:13 -0000	1.30
--- Tag.java	13 Jun 2003 20:27:05 -0000	1.31
***************
*** 34,38 ****
  import java.util.Map;
  
! import org.htmlparser.Node;
  import org.htmlparser.NodeReader;
  import org.htmlparser.parserHelper.AttributeParser;
--- 34,38 ----
  import java.util.Map;
  
! import org.htmlparser.AbstractNode;
  import org.htmlparser.NodeReader;
  import org.htmlparser.parserHelper.AttributeParser;
***************
*** 50,54 ****
   * @author Kaarle Kaila 23.10.2001
   */
! public class Tag extends Node
  {
  	public static final String TYPE = "TAG";
--- 50,54 ----
   * @author Kaarle Kaila 23.10.2001
   */
! public class Tag extends AbstractNode
  {
  	public static final String TYPE = "TAG";
***************
*** 291,300 ****
  	 * @param reader The NodeReader that is to be used for reading the url
  	 */
! 	public Node scan(Map scanners,String url,NodeReader reader) throws ParserException
  	{
  		if (tagContents.length()==0) return this;
  		try {
  			boolean found=false;
! 			Node retVal=null;
  			// Find the first word in the scanners
  			String firstWord = extractWord(tagContents.toString());
--- 291,300 ----
  	 * @param reader The NodeReader that is to be used for reading the url
  	 */
! 	public AbstractNode scan(Map scanners,String url,NodeReader reader) throws ParserException
  	{
  		if (tagContents.length()==0) return this;
  		try {
  			boolean found=false;
! 			AbstractNode retVal=null;
  			// Find the first word in the scanners
  			String firstWord = extractWord(tagContents.toString());

Index: CompositeTag.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tags/CompositeTag.java,v
retrieving revision 1.42
retrieving revision 1.43
diff -C2 -d -r1.42 -r1.43
*** CompositeTag.java	1 Jun 2003 20:50:13 -0000	1.42
--- CompositeTag.java	13 Jun 2003 20:27:05 -0000	1.43
***************
*** 30,34 ****
  
  import org.htmlparser.*;
! import org.htmlparser.Node;
  import org.htmlparser.tags.data.CompositeTagData;
  import org.htmlparser.tags.data.TagData;
--- 30,34 ----
  
  import org.htmlparser.*;
! import org.htmlparser.AbstractNode;
  import org.htmlparser.tags.data.CompositeTagData;
  import org.htmlparser.tags.data.TagData;
***************
*** 93,97 ****
  				if (prevNode.elementEnd()>node.elementBegin()) {
  					// Its a new line
! 					sb.append(lineSeparator);					
  				}
  			}
--- 93,97 ----
  				if (prevNode.elementEnd()>node.elementBegin()) {
  					// Its a new line
! 					sb.append(Parser.getLineSeparator());					
  				}
  			}
***************
*** 100,104 ****
  		}
  		if (prevNode.elementEnd()>endTag.elementBegin()) {
! 			sb.append(lineSeparator);
  		}
  	}
--- 100,104 ----
  		}
  		if (prevNode.elementEnd()>endTag.elementBegin()) {
! 			sb.append(Parser.getLineSeparator());
  		}
  	}
***************
*** 269,273 ****
  		StringBuffer buff = new StringBuffer();
  		for (SimpleNodeIterator e = children();e.hasMoreNodes();) {
! 			Node node = (Node)e.nextNode();
  			buff.append(node.toHtml());
  		}
--- 269,273 ----
  		StringBuffer buff = new StringBuffer();
  		for (SimpleNodeIterator e = children();e.hasMoreNodes();) {
! 			AbstractNode node = (AbstractNode)e.nextNode();
  			buff.append(node.toHtml());
  		}

[Htmlparser-cvs] htmlparser/src/org/htmlparser/tests ParserTest.java,1.30,1.31 ParserTestCase.java,1.14,1.15

[<jke...@us...>]

Update of /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests
In directory sc8-pr-cvs1:/tmp/cvs-serv17851/src/org/htmlparser/tests

Modified Files:
	ParserTest.java ParserTestCase.java 
Log Message:
Renamed Node to AbstractNode, extracted the new interface, Node, and moved line separator code from AbstractNode to Parser.

Index: ParserTest.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/ParserTest.java,v
retrieving revision 1.30
retrieving revision 1.31
diff -C2 -d -r1.30 -r1.31
*** ParserTest.java	1 Jun 2003 20:50:14 -0000	1.30
--- ParserTest.java	13 Jun 2003 20:27:04 -0000	1.31
***************
*** 37,40 ****
--- 37,41 ----
  import java.util.Map;
  
+ import org.htmlparser.AbstractNode;
  import org.htmlparser.Node;
  import org.htmlparser.Parser;
***************
*** 90,94 ****
  		parser.getReader().mark(5000);
  
! 		Node [] node = new Node[500];
  		int i = 0;
  		for (NodeIterator e = parser.elements();e.hasMoreNodes();)
--- 91,95 ----
  		parser.getReader().mark(5000);
  
! 		Node [] node = new AbstractNode[500];
  		int i = 0;
  		for (NodeIterator e = parser.elements();e.hasMoreNodes();)
***************
*** 341,345 ****
              out.close ();
              parser = new Parser (file.getAbsolutePath ());
!             nodes = new Node[30];
              i = 0;
              for (enumeration = parser.elements (); enumeration.hasMoreNodes ();)
--- 342,346 ----
              out.close ();
              parser = new Parser (file.getAbsolutePath ());
!             nodes = new AbstractNode[30];
              i = 0;
              for (enumeration = parser.elements (); enumeration.hasMoreNodes ();)
***************
*** 417,421 ****
  		parser = new Parser(url);
          i = 0;
!         nodes = new Node[30];
  		for (NodeIterator e = parser.elements(); e.hasMoreNodes();)
  			nodes[i++] = e.nextNode();
--- 418,422 ----
  		parser = new Parser(url);
          i = 0;
!         nodes = new AbstractNode[30];
  		for (NodeIterator e = parser.elements(); e.hasMoreNodes();)
  			nodes[i++] = e.nextNode();
***************
*** 551,555 ****
  		
  		parser = new Parser(url);
! 		Node node [] = new Node[30];
  		int i = 0;
  		for (NodeIterator e = parser.elements();e.hasMoreNodes();) {
--- 552,556 ----
  		
  		parser = new Parser(url);
! 		Node node [] = new AbstractNode[30];
  		int i = 0;
  		for (NodeIterator e = parser.elements();e.hasMoreNodes();) {

Index: ParserTestCase.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/ParserTestCase.java,v
retrieving revision 1.14
retrieving revision 1.15
diff -C2 -d -r1.14 -r1.15
*** ParserTestCase.java	24 May 2003 02:05:50 -0000	1.14
--- ParserTestCase.java	13 Jun 2003 20:27:04 -0000	1.15
***************
*** 7,10 ****
--- 7,11 ----
  import junit.framework.TestCase;
  
+ import org.htmlparser.AbstractNode;
  import org.htmlparser.Node;
  import org.htmlparser.NodeReader;
***************
*** 41,45 ****
  		reader =  new NodeReader(new BufferedReader(sr),5000);
  		parser = new Parser(reader,new DefaultParserFeedback());
! 		node = new Node[40];
  	}
  
--- 42,46 ----
  		reader =  new NodeReader(new BufferedReader(sr),5000);
  		parser = new Parser(reader,new DefaultParserFeedback());
! 		node = new AbstractNode[40];
  	}
  
***************
*** 49,53 ****
  		reader =  new NodeReader(new BufferedReader(sr),5000);
  		parser = new Parser(reader,new DefaultParserFeedback());
! 		node = new Node[numNodes];
  	}
  
--- 50,54 ----
  		reader =  new NodeReader(new BufferedReader(sr),5000);
  		parser = new Parser(reader,new DefaultParserFeedback());
! 		node = new AbstractNode[numNodes];
  	}
  
***************
*** 57,61 ****
  		reader =  new NodeReader(new BufferedReader(sr),url);
  		parser = new Parser(reader,new DefaultParserFeedback());
! 		node = new Node[40];
  	}
  
--- 58,62 ----
  		reader =  new NodeReader(new BufferedReader(sr),url);
  		parser = new Parser(reader,new DefaultParserFeedback());
! 		node = new AbstractNode[40];
  	}
  
***************
*** 65,69 ****
  		reader =  new NodeReader(new BufferedReader(sr),url);
  		parser = new Parser(reader,new DefaultParserFeedback());
! 		node = new Node[numNodes];
  	}
  	
--- 66,70 ----
  		reader =  new NodeReader(new BufferedReader(sr),url);
  		parser = new Parser(reader,new DefaultParserFeedback());
! 		node = new AbstractNode[numNodes];
  	}