Java EE (Java Enterprise Edition) General Discussion

Hi everyone,

I have a simple XML with one UTF-8 character É like this:

<?xml version="1.0" encoding="UTF-8"?>
<x10> <x69 x67='Tax_ID' x68='É'/> </x10>

The transform is an identity transform:

<?xml version="1.0" encoding="UTF-8"?>
<xsl:stylesheet version="1.0" xmlns:xsl="http://www.w3.org/1999/XSL/Transform">
  <xsl:output method="xml" indent="yes" encoding="UTF-8"/>
  
<xsl:template match="@*|node()">
   <xsl:copy>
      <xsl:apply-templates select="@*|node()"/>
   </xsl:copy>
</xsl:template>

</xsl:stylesheet>

But after transform, the output changed from

Before tansform: <?xml version="1.0" encoding="UTF-8"?><x10> <x69 x67="Tax_ID" x68="É"/> </x10>

to

After transform: <?xml version="1.0" encoding="UTF-8"?><x10> <x69 x67="Tax_ID" x68="É"/> </x10>

The character is not correctly encoded.

Here is my testing code, the xml lib is xalan:

public class TransformTest
{
  private static String ENC = "UTF-8";
  private static String xml = "<?xml version=\"1.0\" encoding=\"UTF-8\"?>" + 
                                       "<x10> <x69 x67=\"Tax_ID\" x68=\"É\"/> </x10>";
  private static String xslt = "<?xml version=\"1.0\" encoding=\"UTF-8\"?>" +
                               "<xsl:stylesheet version=\"1.0\" xmlns:xsl=\"http://www.w3.org/1999/XSL/Transform\">" +
                               "<xsl:output method=\"xml\" indent=\"yes\" encoding=\"UTF-8\"/>" +
                               "<xsl:template match=\"@*|node()\">" +
                               "<xsl:copy>" +
                               "<xsl:apply-templates select=\"@*|node()\"/>" +
                               "</xsl:copy>" +
                               "</xsl:template>" +
                               "</xsl:stylesheet>";
  private static TransformerFactory factory = TransformerFactory.newInstance();
  private static StreamSource xslSource = null;
  private static StreamSource xmlSource = null;
  
  public TransformTest()
  {
  }
  
  /**
   * @param args
   */
  public static void main( String[] args )
  {
    System.out.println( "Before tansform: " + xml );
    
    try
    {
      xslSource = new StreamSource( new InputStreamReader( new ByteArrayInputStream( xslt.getBytes(ENC)), ENC ));
      xmlSource = new StreamSource( new InputStreamReader( new ByteArrayInputStream( xml.getBytes(ENC)), ENC ) );
      
      Templates templates = factory.newTemplates( xslSource );
      
      Transformer transformer = templates.newTransformer();
      
      ByteArrayOutputStream bao = new ByteArrayOutputStream();
      
      StreamResult result = new StreamResult ( new OutputStreamWriter (bao, ENC));
      
      transformer.transform( xmlSource, result );
      
      System.out.println("After transform: " + bao.toString());
      
    }
    catch(Exception ex)
    {
      ex.printStackTrace();
    }
  }

}

Any helps are appreciated!

Thanks,

Mian