--- old/src/share/classes/javax/swing/text/html/parser/Parser.java 2012-06-25 12:36:29.585203607 +0400 +++ new/src/share/classes/javax/swing/text/html/parser/Parser.java 2012-06-25 12:36:26.231494278 +0400 @@ -1,5 +1,5 @@ /* - * Copyright (c) 1998, 2010, Oracle and/or its affiliates. All rights reserved. + * Copyright (c) 1998, 2012, Oracle and/or its affiliates. All rights reserved. * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. * * This code is free software; you can redistribute it and/or modify it @@ -80,6 +80,9 @@ public class Parser implements DTDConstants { + //Maximum codepoint value within BMP + private final int MAX_BMP_BOUND = 65535; + private char text[] = new char[1024]; private int textpos = 0; private TagElement last; @@ -952,8 +955,22 @@ ch = readCh(); break; } - char data[] = {mapNumericReference((char) n)}; - return data; + //Check if n codepoint is within BMP; convert into surrogate + //pair otherwise + try { + char data[]; + if (n <= MAX_BMP_BOUND) { + data = Character.toChars(mapNumericReference((char) n)); + } else { + data = Character.toChars(n); + } + + return data; + } + catch(IllegalArgumentException ex) { + error(ex.toString()); + return new char[0]; + } } addString('#'); if (!parseIdentifier(false)) { --- /dev/null 2012-06-25 12:36:40.000000000 +0400 +++ new/test/javax/swing/text/html/parser/Parser/6836089/Test6836089.java 2012-06-25 12:36:36.536470434 +0400 @@ -0,0 +1,23 @@ +/* + * @test + * @bug 6836089 + * @summary Tests correct parsing of characters inside Base Multilingual Plane + * @author Vladislav Karnaukhov + */ + +import javax.swing.*; +import javax.swing.text.html.*; + +public class Test6836089 { + + public static void main(String[] args) { + JTextPane htmlPane = new JTextPane(); + htmlPane.setEditorKit(new HTMLEditorKit()); + + //if the output is �, the test failed + htmlPane.setText("𠀀"); + System.out.println("\ud840\udc00".codePointAt(0)); + + System.out.println(htmlPane.getText()); + } +}