Tidy (oct22) failed to parse comments

Hello,
   I'm using tidy as a HTML parser for my program. There are some cases that tidy will make mistakes on comment contains a lot of '-'(although this is not good according to HTML4.0 ).  You could find the case in http://cn.yahoo.com/  I've made a fix for this problem.

       Best Regards
       Yudong Yang
       

in lexer.c
and function GetToken(Lexer *lexer, uint mode)


            case LEX_COMMENT:  /* seen <!-- so look for --> */

                /* look for 1st - */
                if (c != '-')
                {
                    if (comments > 2 && c == '>')
                        ReportWarning(lexer, null, null, BAD_COMMENT);

                    comments = -1;
                    continue;
                }

                /* now look for 2nd - */

                c = ReadChar(lexer->in);

                if (c == EndOfStream)
                {
                    ReportWarning(lexer, null, null, BAD_COMMENT);
                    UngetChar(c, lexer->in);
                    continue;
                }

                AddCharToLexer(lexer, c);

                if (c != '-')
                {
                    comments = 0;
                    continue;
                }

    for(;;)  // skip all ------ like strings
    {
     c = ReadChar(lexer->in);
     if(c != '-') 
     {
                     UngetChar(c, lexer->in);
      break;
     }
                    AddCharToLexer(lexer, c);  // just add the -
    }

                lexer->state = LEX_ENDCOMMENT;
                continue;

            case LEX_ENDCOMMENT:  /* seen <!-- .... -- */
    {
     int spc=0;
     for (;;)  // first skip the possiable HTML 4.0 enabled white spaces
     {
      map = MAP(c);
      
      if((map & white) == 0)
       break;
      
      comments = 0;
      c = ReadChar(lexer->in);
      AddCharToLexer(lexer, c);
      spc ++;
     }
     if (c == '>')
     {
      lexer->lexsize -= 3+spc;
      lexer->txtend = lexer->lexsize;
      lexer->lexbuf[lexer->lexsize] = '\0';
      lexer->state = LEX_CONTENT;
      lexer->waswhite = no;
      return lexer->token = CommentToken(lexer);
     }
     else {  // not end of comment
      
       /*
       SGML comment syntax is truly daft!!!
       
         A comment declaration consists of `<!' followed by zero or
         more comments followed by `>'. Each comment starts with
         `--' and includes all text up to and including the next
         occurrence of `--'. In a comment declaration, white space
         is allowed after each comment, but not before the first
         comment.  The entire comment declaration is ignored.
         
        <!-- another -- -- comment -->
        <!-- --->  is bad, so is <!-- foo ----- bar -->
      */
      
      /* set error position just before offending chararcter */
      lexer->lines = lexer->in->curline;
      lexer->columns = lexer->in->curcol - 1;
      ReportWarning(lexer, null, null, BAD_COMMENT);
      
      /* treat the chars as part of the comment*/
      lexer->state = LEX_COMMENT;  /* comment */
      UngetChar(c, lexer->in);
      lexer->lexsize--;   
      lexer->lexbuf[lexer->lexsize] = '\0';       
      continue;
     }
    }