[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 ----
  	}
  	
! 
  
  }