[Htmlparser-cvs] htmlparser/src/org/htmlparser/lexer Lexer.java,1.22,1.23

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

Update of /cvsroot/htmlparser/htmlparser/src/org/htmlparser/lexer
In directory sc8-pr-cvs1:/tmp/cvs-serv31101/lexer

Modified Files:
	Lexer.java 
Log Message:
Fix bug #789439 Japanese page causes OutOfMemory Exception
Modified the lexer to skip over JIS escape sequences.



Index: Lexer.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/lexer/Lexer.java,v
retrieving revision 1.22
retrieving revision 1.23
diff -C2 -d -r1.22 -r1.23
*** Lexer.java	8 Dec 2003 01:31:51 -0000	1.22
--- Lexer.java	31 Dec 2003 14:40:49 -0000	1.23
***************
*** 312,315 ****
--- 312,359 ----
  
      /**
+      * Advance the cursor through a JIS escape sequence.
+      * @param cursor A cursor positioned within the escape sequence.
+      */
+     protected void scanJIS (Cursor cursor)
+         throws
+             ParserException
+     {
+         boolean done;
+         char ch;
+         int state;
+ 
+         done = false;
+         state = 0;
+         while (!done)
+         {
+             ch = mPage.getCharacter (cursor);
+             if (0 == ch)
+                 done = true;
+             else
+                 switch (state)
+                 {
+                     case 0:
+                         if (0x1b == ch) // escape
+                             state = 1;
+                         break;
+                     case 1:
+                         if ('(' == ch)
+                             state = 2;
+                         else
+                             state = 0;
+                         break;
+                     case 2:
+                         if ('J' == ch)
+                             done = true;
+                         else
+                             state = 0;
+                         break;
+                     default:
+                         throw new IllegalStateException ("how the fuck did we get in state " + state);
+                 }
+         }
+     }
+ 
+     /**
       * Parse a string node.
       * Scan characters until "</", "<%", "<!" or < followed by a
***************
*** 325,331 ****
          boolean done;
          char ch;
-         int length;
-         int begin;
-         int end;
          char quote;
          Node ret;
--- 369,372 ----
***************
*** 338,341 ****
--- 379,403 ----
              if (0 == ch)
                  done = true;
+             else if (0x1b == ch) // escape
+             {
+                 ch = mPage.getCharacter (cursor);
+                 if (0 == ch)
+                     done = true;
+                 else if ('$' == ch)
+                 {
+                     ch = mPage.getCharacter (cursor);
+                     if (0 == ch)
+                         done = true;
+                     else if ('B' == ch)
+                         scanJIS (cursor);
+                     else
+                     {
+                         cursor.retreat ();
+                         cursor.retreat ();
+                     }
+                 }
+                 else
+                     cursor.retreat ();
+             }
              else if (quotesmart && (0 == quote) && (('\'' == ch) || ('"' == ch)))
                  quote = ch; // enter quoted state