[Htmlparser-cvs] htmlparser/src/org/htmlparser/lexer/nodes RemarkNode.java,1.16,1.17 StringNode.java,1.17,1.18

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

Update of /cvsroot/htmlparser/htmlparser/src/org/htmlparser/lexer/nodes
In directory sc8-pr-cvs1.sourceforge.net:/tmp/cvs-serv25994/lexer/nodes

Modified Files:
	RemarkNode.java StringNode.java 
Log Message:
Fix bug #900128 RemarkNode.setText() does not set Text
Add override setText() to StringNode and RemarkNode.
Add unit tests to excercise the new code.
Remove remaining XX_FILTER constants.



Index: RemarkNode.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/lexer/nodes/RemarkNode.java,v
retrieving revision 1.16
retrieving revision 1.17
diff -C2 -d -r1.16 -r1.17
*** RemarkNode.java	2 Jan 2004 16:24:53 -0000	1.16
--- RemarkNode.java	29 Feb 2004 12:52:20 -0000	1.17
***************
*** 38,56 ****
  public class RemarkNode extends AbstractNode
  {
!     public final static String REMARK_NODE_FILTER="-r";
  
      /**
!      * Constructor takes in the text string, beginning and ending posns.
!      * @param page The page this string is on.
!      * @param start The beginning position of the string.
!      * @param end The ending positiong of the string.
       */
      public RemarkNode (Page page, int start, int end)
      {
          super (page, start, end);
      }
  
      /**
       * Returns the text contents of the comment tag.
       */
      public String getText()
--- 38,72 ----
  public class RemarkNode extends AbstractNode
  {
!     /**
!      * The contents of the remark node, or override text.
!      */
!     protected String mText;
  
      /**
!      * Constructor takes in the text string.
!      * @param text The string node text. For correct generation of HTML, this
!      * should not contain representations of tags (unless they are balanced).
!      */
!     public RemarkNode (String text)
!     {
!         super (null, 0, 0);
!         setText (text);
!     }
! 
!     /**
!      * Constructor takes in the page and beginning and ending posns.
!      * @param page The page this remark is on.
!      * @param start The beginning position of the remark.
!      * @param end The ending positiong of the remark.
       */
      public RemarkNode (Page page, int start, int end)
      {
          super (page, start, end);
+         mText = null;
      }
  
      /**
       * Returns the text contents of the comment tag.
+      * @return The contents of the text inside the comment delimiters.
       */
      public String getText()
***************
*** 60,73 ****
          String ret;
  
!         start = getStartPosition () + 4;
!         end = getEndPosition () - 3;
!         if (start >= end)
!             ret = "";
          else
!             ret = mPage.getText (start, end);
  
          return (ret);
      }
  
      public String toPlainTextString()
      {
--- 76,108 ----
          String ret;
  
!         if (null == mText)
!         {
!             start = getStartPosition () + 4; // <!--
!             end = getEndPosition () - 3; // -->
!             if (start >= end)
!                 ret = "";
!             else
!                 ret = mPage.getText (start, end);
!         }
          else
!             ret = mText;
  
          return (ret);
      }
  
+     /**
+      * Sets the string contents of the node.
+      * If the text has the remark delimiters (&lt;!-- --&gt;), these are stripped off.
+      * @param text The new text for the node.
+      */
+     public void setText (String text)
+     {
+         mText = text;
+         if (text.startsWith ("<!--") && text.endsWith ("-->"))
+             mText = text.substring (4, text.length () - 3);
+         nodeBegin = 0;
+         nodeEnd = mText.length ();
+     }
+ 
      public String toPlainTextString()
      {
***************
*** 77,85 ****
      public String toHtml()
      {
!         return (mPage.getText (getStartPosition (), getEndPosition ()));
      }
  
      /**
       * Print the contents of the remark tag.
       */
      public String toString()
--- 112,138 ----
      public String toHtml()
      {
!         StringBuffer buffer;
!         String ret;
!         
!         if (null == mText)
!             ret = mPage.getText (getStartPosition (), getEndPosition ());
!         else
!         {
!             buffer = new StringBuffer (mText.length () + 7);
!             buffer.append ("<!--");
!             buffer.append (mText);
!             buffer.append ("-->");
!             ret = buffer.toString ();
!         }
! 
!         return (ret);
      }
  
      /**
       * Print the contents of the remark tag.
+      * This is suitable for display in a debugger or output to a printout.
+      * Control characters are replaced by their equivalent escape
+      * sequence and contents is truncated to 80 characters.
+      * @return A string representation of the remark node.
       */
      public String toString()
***************
*** 95,110 ****
          endpos = getEndPosition ();
          ret = new StringBuffer (endpos - startpos + 20);
!         start = new Cursor (getPage (), startpos);
!         end = new Cursor (getPage (), endpos);
!         ret.append ("Rem (");
!         ret.append (start);
!         ret.append (",");
!         ret.append (end);
!         ret.append ("): ");
!         while (start.getPosition () < endpos)
          {
!             try
              {
!                 c = mPage.getCharacter (start);
                  switch (c)
                  {
--- 148,203 ----
          endpos = getEndPosition ();
          ret = new StringBuffer (endpos - startpos + 20);
!         if (null == mText)
          {
!             start = new Cursor (getPage (), startpos);
!             end = new Cursor (getPage (), endpos);
!             ret.append ("Rem (");
!             ret.append (start);
!             ret.append (",");
!             ret.append (end);
!             ret.append ("): ");
!             start.setPosition (startpos + 4); // <!--
!             endpos -= 3; // -->
!             while (start.getPosition () < endpos)
              {
!                 try
!                 {
!                     c = mPage.getCharacter (start);
!                     switch (c)
!                     {
!                         case '\t':
!                             ret.append ("\\t");
!                             break;
!                         case '\n':
!                             ret.append ("\\n");
!                             break;
!                         case '\r':
!                             ret.append ("\\r");
!                             break;
!                         default:
!                             ret.append (c);
!                     }
!                 }
!                 catch (ParserException pe)
!                 {
!                     // not really expected, but we're only doing toString, so ignore
!                 }
!                 if (77 <= ret.length ())
!                 {
!                     ret.append ("...");
!                     break;
!                 }
!             }
!         }
!         else
!         {
!             ret.append ("Rem (");
!             ret.append (startpos);
!             ret.append (",");
!             ret.append (endpos);
!             ret.append ("): ");
!             while (startpos < endpos)
!             {
!                 c = mText.charAt (startpos);
                  switch (c)
                  {
***************
*** 121,133 ****
                          ret.append (c);
                  }
!             }
!             catch (ParserException pe)
!             {
!                 // not really expected, but we'return only doing toString, so ignore
!             }
!             if (77 <= ret.length ())
!             {
!                 ret.append ("...");
!                 break;
              }
          }
--- 214,223 ----
                          ret.append (c);
                  }
!                 if (77 <= ret.length ())
!                 {
!                     ret.append ("...");
!                     break;
!                 }
!                 startpos++;
              }
          }

Index: StringNode.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/lexer/nodes/StringNode.java,v
retrieving revision 1.17
retrieving revision 1.18
diff -C2 -d -r1.17 -r1.18
*** StringNode.java	2 Jan 2004 16:24:53 -0000	1.17
--- StringNode.java	29 Feb 2004 12:52:20 -0000	1.18
***************
*** 38,45 ****
  public class StringNode extends AbstractNode
  {
!     public static final String STRING_FILTER = "-string";
  
      /**
!      * Constructor takes in the text string, beginning and ending posns.
       * @param page The page this string is on.
       * @param start The beginning position of the string.
--- 38,59 ----
  public class StringNode extends AbstractNode
  {
!     /**
!      * The contents of the string node, or override text.
!      */
!     protected String mText;
  
      /**
!      * Constructor takes in the text string.
!      * @param text The string node text. For correct generation of HTML, this
!      * should not contain representations of tags (unless they are balanced).
!      */
!     public StringNode (String text)
!     {
!         super (null, 0, 0);
!         setText (text);
!     }
! 
!     /**
!      * Constructor takes in the page and beginning and ending posns.
       * @param page The page this string is on.
       * @param start The beginning position of the string.
***************
*** 49,52 ****
--- 63,67 ----
      {
          super (page, start, end);
+         mText = null;
      }
  
***************
*** 65,81 ****
      public void setText (String text)
      {
!         mPage = new Page (text);
          nodeBegin = 0;
!         nodeEnd = text.length ();
!         // TODO: this really needs work
!         try
!         {
!             Cursor cursor = new Cursor (mPage, nodeBegin);
!             for (int i = nodeBegin; i < nodeEnd; i++)
!                 mPage.getCharacter (cursor);
!         }
!         catch (ParserException pe)
!         {
!         }
      }
  
--- 80,86 ----
      public void setText (String text)
      {
!         mText = text;
          nodeBegin = 0;
!         nodeEnd = mText.length ();
      }
  
***************
*** 87,91 ****
      public String toHtml ()
      {
!         return (mPage.getText (getStartPosition (), getEndPosition ()));
      }
  
--- 92,102 ----
      public String toHtml ()
      {
!         String ret;
!         
!         ret = mText;
!         if (null == ret)
!             ret = mPage.getText (getStartPosition (), getEndPosition ());
! 
!         return (ret);
      }
  
***************
*** 109,124 ****
          endpos = getEndPosition ();
          ret = new StringBuffer (endpos - startpos + 20);
!         start = new Cursor (getPage (), startpos);
!         end = new Cursor (getPage (), endpos);
!         ret.append ("Txt (");
!         ret.append (start);
!         ret.append (",");
!         ret.append (end);
!         ret.append ("): ");
!         while (start.getPosition () < endpos)
          {
!             try
              {
!                 c = mPage.getCharacter (start);
                  switch (c)
                  {
--- 120,173 ----
          endpos = getEndPosition ();
          ret = new StringBuffer (endpos - startpos + 20);
!         if (null == mText)
          {
!             start = new Cursor (getPage (), startpos);
!             end = new Cursor (getPage (), endpos);
!             ret.append ("Txt (");
!             ret.append (start);
!             ret.append (",");
!             ret.append (end);
!             ret.append ("): ");
!             while (start.getPosition () < endpos)
              {
!                 try
!                 {
!                     c = mPage.getCharacter (start);
!                     switch (c)
!                     {
!                         case '\t':
!                             ret.append ("\\t");
!                             break;
!                         case '\n':
!                             ret.append ("\\n");
!                             break;
!                         case '\r':
!                             ret.append ("\\r");
!                             break;
!                         default:
!                             ret.append (c);
!                     }
!                 }
!                 catch (ParserException pe)
!                 {
!                     // not really expected, but we're only doing toString, so ignore
!                 }
!                 if (77 <= ret.length ())
!                 {
!                     ret.append ("...");
!                     break;
!                 }
!             }
!         }
!         else
!         {
!             ret.append ("Txt (");
!             ret.append (startpos);
!             ret.append (",");
!             ret.append (endpos);
!             ret.append ("): ");
!             while (startpos < endpos)
!             {
!                 c = mText.charAt (startpos);
                  switch (c)
                  {
***************
*** 135,147 ****
                          ret.append (c);
                  }
!             }
!             catch (ParserException pe)
!             {
!                 // not really expected, but we'return only doing toString, so ignore
!             }
!             if (77 <= ret.length ())
!             {
!                 ret.append ("...");
!                 break;
              }
          }
--- 184,193 ----
                          ret.append (c);
                  }
!                 if (77 <= ret.length ())
!                 {
!                     ret.append ("...");
!                     break;
!                 }
!                 startpos++;
              }
          }