8349699: XSL transform fails with certain UTF-8 characters on 1024 byte boundaries

Author: JoeWang-Java

Diff for: src/java.xml/share/classes/com/sun/org/apache/xml/internal/serializer/ToStream.java

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2006, 2022, Oracle and/or its affiliates. All rights reserved.
+ * Copyright (c) 2006, 2025, Oracle and/or its affiliates. All rights reserved.
  */
 /*
  * Licensed to the Apache Software Foundation (ASF) under one or more
@@ -55,7 +55,7 @@
  * serializers (xml, html, text ...) that write output to a stream.
  *
  * @xsl.usage internal
- * @LastModified: Mar 2022
+ * @LastModified: Feb 2025
  */
 abstract public class ToStream extends SerializerBase {
 
@@ -955,7 +955,7 @@ protected int writeUTF16Surrogate(char c, char ch[], int i, int end)
         throws IOException, SAXException
     {
         int status = -1;
-        if (i + 1 >= end)
+        if (i + 1 >= end && m_highSurrogate == 0)
         {
             m_highSurrogate = c;
             return status;

Diff for: test/jaxp/javax/xml/jaxp/unittest/transform/JDK8207760.java

@@ -41,10 +41,10 @@
 
 /*
  * @test
+ * @bug 8207760 8349699
+ * @summary Verifies that a surrogate pair at the edge of a buffer is properly handled
  * @library /javax/xml/jaxp/libs /javax/xml/jaxp/unittest
  * @run testng/othervm transform.JDK8207760
- * @summary Verifies that a surrogate pair at the edge of a buffer is properly handled
- * @bug 8207760
  */
 public class JDK8207760 {
     final String xsl8207760 =
@@ -101,6 +101,33 @@ public Object[][] getDataBug8207760_cdata() {
         };
     }
 
+    /*
+     * @bug 8349699
+     * Verifies that a surrogate pair at the edge of a buffer is properly handled
+     * when serializing into a Character section.
+     */
+    @Test
+    public final void testBug8349699() throws Exception {
+        String xs = "x".repeat(1017);
+        String expected = xs + "\uD835\uDF03\uD835\uDF00\uD835\uDF00\uD835\uDF00\uD835\uDF00";
+        String xml = "<?xml version=\"1.0\" ?><a>{1017x}\uD835\uDF03\uD835\uDF00\uD835\uDF00<b>\uD835\uDF00</b>\uD835\uDF00</a> "
+                .replace("{1017x}", xs);
+        String xsl = """
+                <?xml version="1.0" encoding="UTF-8"?>
+                <xsl:stylesheet version="1.0" xmlns:xsl="http://www.w3.org/1999/XSL/Transform">
+                  <xsl:output encoding="UTF-8" method="text" />
+                  <xsl:template match="/"><xsl:apply-templates select="node()" /></xsl:template>
+                </xsl:stylesheet>
+                """;
+
+        Transformer t = createTransformerFromInputstream(
+                new ByteArrayInputStream(xsl.getBytes(StandardCharsets.UTF_8)));
+        //t.setOutputProperty(OutputKeys.ENCODING, StandardCharsets.UTF_8.name());
+        StringWriter sw = new StringWriter();
+        t.transform(new StreamSource(new StringReader(xml)), new StreamResult(sw));
+        Assert.assertEquals(sw.toString(), expected);
+    }
+
     /*
      * @bug 8207760
      * Verifies that a surrogate pair at the edge of a buffer is properly handled