src/com/sun/org/apache/xml/internal/serializer/ToHTMLStream.java

@@ -1,8 +1,7 @@
 /*
- * reserved comment block
- * DO NOT REMOVE OR ALTER!
+ * Copyright (c) 2014, 2018, Oracle and/or its affiliates. All rights reserved.
  */
 /*
  * Copyright 2001-2004 The Apache Software Foundation.
  *
  * Licensed under the Apache License, Version 2.0 (the "License");

@@ -41,10 +40,11 @@
  *
  * This class is not a public API, it is public
  * because it is used from another package.
  *
  * @xsl.usage internal
+ * @LastModified: Sept 2018
  */
 public final class ToHTMLStream extends ToStream
 {
 
     /** This flag is set while receiving events from the DTD */

@@ -1019,11 +1019,11 @@
     protected void processAttribute(
         java.io.Writer writer,
         String name,
         String value,
         ElemDesc elemDesc)
-        throws IOException
+        throws IOException, SAXException
     {
         writer.write(' ');
 
         if (   ((value.length() == 0) || value.equalsIgnoreCase(name))
             && elemDesc != null

@@ -1343,11 +1343,11 @@
      *
      * @throws org.xml.sax.SAXException
      */
     public void writeAttrString(
         final java.io.Writer writer, String string, String encoding)
-        throws IOException
+        throws IOException, SAXException
     {
         final int end = string.length();
         if (end > m_attrBuff.length)
         {
             m_attrBuff = new char[end * 2 + 1];

@@ -1395,17 +1395,20 @@
                 {
                     i = pos - 1;
                 }
                 else
                 {
-                    if (Encodings.isHighUTF16Surrogate(ch))
+                    if (Encodings.isHighUTF16Surrogate(ch) ||
+                            Encodings.isLowUTF16Surrogate(ch))
                     {
-
-                            writeUTF16Surrogate(ch, chars, i, end);
-                            i++; // two input characters processed
-                                 // this increments by one and the for()
-                                 // loop itself increments by another one.
+                        if (writeUTF16Surrogate(ch, chars, i, end) >= 0) {
+                            // move the index if the low surrogate is consumed
+                            // as writeUTF16Surrogate has written the pair
+                            if (Encodings.isHighUTF16Surrogate(ch)) {
+                                i++;
+                            }
+                        }
                     }
 
                     // The next is kind of a hack to keep from escaping in the case
                     // of Shift_JIS and the like.