Patch surrogate handling for attributes (based on apache/xalan-j#4 (comment) fix) and for text

Author: epilogic-ch

src/org/apache/xml/serializer/ToHTMLStream.java

@@ -1455,22 +1455,23 @@ else if ((ch < m_maxCharacter) && (m_maxCharacter == 0xFFFF)
                     {
                     writer.write(ch);  // no escaping in this case
                     }
-                    else
                     */
-                    String outputStringForChar = m_charInfo.getOutputStringForChar(ch);
-                    if (null != outputStringForChar)
-                    {
-                        writer.write(outputStringForChar);
-                    }
-                    else if (escapingNotNeeded(ch))
-                    {
-                        writer.write(ch); // no escaping in this case
-                    }
-                    else
-                    {
-                        writer.write("&#");
-                        writer.write(Integer.toString(ch));
-                        writer.write(';');
+                    else {
+                        String outputStringForChar = m_charInfo.getOutputStringForChar(ch);
+                        if (null != outputStringForChar)
+                        {
+                            writer.write(outputStringForChar);
+                        }
+                        else if (escapingNotNeeded(ch))
+                        {
+                            writer.write(ch); // no escaping in this case
+                        }
+                        else
+                        {
+                            writer.write("&#");
+                            writer.write(Integer.toString(ch));
+                            writer.write(';');
+                        }
                     }
                 }
                 cleanStart = i + 1;

src/org/apache/xml/serializer/ToStream.java

@@ -1600,6 +1600,14 @@ else if (m_encodingInfo.isInEncoding(ch)) {
                         // just leave it get added on to the clean characters
 
                     }
+                    else if (Encodings.isHighUTF16Surrogate(ch)) {
+                        writeOutCleanChars(chars, i, lastDirtyCharProcessed);
+                        writeUTF16Surrogate(ch, chars, i, end);
+                        // two input characters processed
+                        // this increments by one and the for()
+                        // loop i elf increments by another one.
+                        lastDirtyCharProcessed = ++i;
+                    }
                     else {
                         // This is a fallback plan, we should never get here
                         // but if the character wasn't previously handled