ADDITIONAL SYSTEM INFORMATION :
Property settings:
    file.encoding = UTF-8
    file.separator = /
    java.class.path =
    java.class.version = 69.0
    java.home = /home/user/.sdkman/candidates/java/25.0.1-tem
    java.io.tmpdir = /tmp
    java.library.path = /usr/java/packages/lib
        /usr/lib64
        /lib64
        /lib
        /usr/lib
    java.runtime.name = OpenJDK Runtime Environment
    java.runtime.version = 25.0.1+8-LTS
    java.specification.name = Java Platform API Specification
    java.specification.vendor = Oracle Corporation
    java.specification.version = 25
    java.vendor = Eclipse Adoptium
    java.vendor.url = https://adoptium.net/
    java.vendor.url.bug = https://github.com/adoptium/adoptium-support/issues
    java.vendor.version = Temurin-25.0.1+8
    java.version = 25.0.1
    java.version.date = 2025-10-21
    java.vm.compressedOopsMode = Zero based
    java.vm.info = mixed mode, sharing
    java.vm.name = OpenJDK 64-Bit Server VM
    java.vm.specification.name = Java Virtual Machine Specification
    java.vm.specification.vendor = Oracle Corporation
    java.vm.specification.version = 25
    java.vm.vendor = Eclipse Adoptium
    java.vm.version = 25.0.1+8-LTS
    jdk.debug = release
    line.separator = \n
    native.encoding = UTF-8
    os.arch = amd64
    os.name = Linux
    os.version = 6.8.0-90-generic
    path.separator = :
    stderr.encoding = UTF-8
    stdin.encoding = UTF-8
    stdout.encoding = UTF-8
    sun.arch.data.model = 64
    sun.boot.library.path = /home/user/.sdkman/candidates/java/25.0.1-tem/lib
    sun.cpu.endian = little
    sun.io.unicode.encoding = UnicodeLittle
    sun.java.launcher = SUN_STANDARD
    sun.jnu.encoding = UTF-8
    sun.management.compiler = HotSpot 64-Bit Tiered Compilers
    user.country = US
    user.dir = /home/user
    user.home = /home/user
    user.language = en
    user.name = user

openjdk version "25.0.1" 2025-10-21 LTS
OpenJDK Runtime Environment Temurin-25.0.1+8 (build 25.0.1+8-LTS)
OpenJDK 64-Bit Server VM Temurin-25.0.1+8 (build 25.0.1+8-LTS, mixed mode, sharing)


A DESCRIPTION OF THE PROBLEM :
When an emoji with a variation selector (e.g., 🐧 = U+1F427 + U+FE0F) is placed inside a CDATA section, JDK XML Transformer incorrectly splits the emoji from its variation selector during transformation.

This violates the Unicode in XML specification (W3C TR #20, Section 4.3), which states that "For a variation selector to have an effect it must immediately follow its base character."

STEPS TO FOLLOW TO REPRODUCE THE PROBLEM :
When transforming XML with emoji containing variation selectors (like 🐧), the JDK's XML Transformer splits the emoji into multiple CDATA sections, separating the base character from its variation selector.

Input:
```xml
<div><![CDATA[🐧]]></div>
```

---------- BEGIN SOURCE ----------
import javax.xml.parsers.DocumentBuilder;
import javax.xml.parsers.DocumentBuilderFactory;
import javax.xml.transform.Transformer;
import javax.xml.transform.TransformerFactory;
import javax.xml.transform.dom.DOMSource;
import javax.xml.transform.stream.StreamResult;
import org.w3c.dom.Document;
import java.io.StringWriter;

public class EmojiVariationSelectorBug {
    public static void main(String[] args) throws Exception {
        String input = "<div><![CDATA[🐧]]></div>";
        
        System.out.println("Input XML:");
        System.out.println(input);
        System.out.println();
        
        DocumentBuilderFactory dbFactory = DocumentBuilderFactory.newInstance();
        DocumentBuilder dBuilder = dbFactory.newDocumentBuilder();
        
        Document document = dBuilder.parse(new java.io.ByteArrayInputStream(input.getBytes("UTF-8")));
        
        DOMSource domSource = new DOMSource(document);
        StringWriter writer = new StringWriter();
        StreamResult result = new StreamResult(writer);
        
        TransformerFactory tf = TransformerFactory.newInstance();
        Transformer transformer = tf.newTransformer();
        transformer.transform(domSource, result);
        
        String output = writer.toString();
        
        System.out.println("Output XML:");
        System.out.println(output);
        System.out.println();
        
        String expected = "<div><![CDATA[🐧]]></div>";
        boolean isCorrect = output.contains("<![CDATA[🐧]]>");
        
        if (isCorrect) {
            System.out.println("✓ TEST PASSED");
        } else {
            System.out.println("✗ TEST FAILED: Emoji with variation selector is split across CDATA sections");
            System.out.println();
            System.out.println("The transformer incorrectly splits the emoji from its variation selector,");
            System.out.println("violating Unicode in XML spec (W3C TR #20, Section 4.3).");
            
            System.exit(1);
        }
    }
}
---------- END SOURCE ----------

FREQUENCY :
ALWAYS