[Htmlparser-cvs] htmlparser/src/org/htmlparser/scanners LinkScanner.java,1.38,1.39 TagScanner.java,1.21,1.22

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

Update of /cvsroot/htmlparser/htmlparser/src/org/htmlparser/scanners
In directory sc8-pr-cvs1:/tmp/cvs-serv30035/org/htmlparser/scanners

Modified Files:
	LinkScanner.java TagScanner.java 
Log Message:
Fix tab handling on the suggestion of oyoaha (philippe blanc).
Rewrite some string handling methods to remove gross inefficiencies.



Index: LinkScanner.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/scanners/LinkScanner.java,v
retrieving revision 1.38
retrieving revision 1.39
diff -C2 -d -r1.38 -r1.39
*** LinkScanner.java	12 May 2003 01:37:45 -0000	1.38
--- LinkScanner.java	17 May 2003 12:12:49 -0000	1.39
***************
*** 118,140 ****
  	 * scan has begun, and hence allows us to write scanners that can work with dirty html
  	 */
! 	public boolean evaluate(String s,TagScanner previousOpenScanner)
! 	{
! 		// Eat up leading blanks
! 		s = absorbLeadingBlanks(s);		
! 		boolean retVal;
! 		char ch = s.charAt(0);
! 		
! 		if (s.length()<5) retVal = false; else
! 		if ((ch=='a' || ch=='A') && (s.charAt(1)==' ' || s.charAt(1)=='\n' || s.charAt(1)=='\r')) retVal = true; else retVal = false;
  
! 		if (retVal)
! 		{
! 			if (s.toUpperCase().indexOf("HREF")==-1)
! 				retVal=false;
! 		} 
  
- 		return retVal;
- 	
- 	}
      /**
       * Extract the link from the given string. The URL of the actual html page is also 
--- 118,142 ----
  	 * scan has begun, and hence allows us to write scanners that can work with dirty html
  	 */
!     public boolean evaluate (String s, TagScanner previousOpenScanner)
!     {
!         char ch;
!         boolean ret;
!         
!         // eat up leading blanks
!         s = absorbLeadingBlanks (s);
!         if (5 > s.length ())
!             ret = false;
!         else
!         {
!             ch = s.charAt (0);
!             if ((ch=='a' || ch=='A') && Character.isWhitespace (s.charAt (1)))
!                 ret = -1 != s.toUpperCase().indexOf ("HREF");
!             else
!                 ret = false;
!         }
  
!         return (ret);
!     }
  
      /**
       * Extract the link from the given string. The URL of the actual html page is also 

Index: TagScanner.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/scanners/TagScanner.java,v
retrieving revision 1.21
retrieving revision 1.22
diff -C2 -d -r1.21 -r1.22
*** TagScanner.java	12 May 2003 01:37:45 -0000	1.21
--- TagScanner.java	17 May 2003 12:12:49 -0000	1.22
***************
*** 103,119 ****
  	
  	/**
! 	 * Insert the method's description here.
! 	 * Creation date: (6/18/2001 2:15:02 AM)
! 	 * @return java.lang.String
  	 */
! 	public static String absorbLeadingBlanks(String s) 
! 	{
! 	  String temp = new String(s);
! 	  while (temp.length()!=0 && temp.charAt(0)==' ')
! 	  {
! 	    temp = temp.substring(1,temp.length());
! 	  }
! 	  return temp;
! 	}
  
    /**
--- 103,129 ----
  	
  	/**
! 	 * Remove whitespace from the front of the given string.
!      * @param s The string to trim.
! 	 * @return Either the same string or a string with whitespace chopped off.
  	 */
!     public static String absorbLeadingBlanks (String s) 
!     {
!         int length;
!         int i;
!         String ret;
! 
!         i = 0;
!         length = s.length ();
!         while (i < length && Character.isWhitespace (s.charAt (i)))
!             i++;
!         if (0 == i)
!             ret = s;
!         else if (length == i)
!             ret = "";
!         else
!             ret = s.substring (i);
! 
!         return (ret);
!     }
  
    /**