SAX, incor. data for XML element, XML 1.1 doc (1.0 ok) in JRE 6 (JRE 5 ok)

Question

Hello,
for some reason, the test case below fails when driven with Java 6. Looks like, when long string data is stored in a XML element, DocumentHandler's characters() method will be provided with incorrect data.
With XML 1.0, parsing works fine in all my tests, Apache Xerces, JRE 5, JRE 6.
With XML 1.1., parsing works fine with Apache Xerces, JRE5 but not with JRE6.
I've checked it with latest JRE 6 update 4.
Anyone else xperiencing such problems with XML1.1 parsing when using JAXP bundled with Java 6?
I've tried to file a bug at bugdatabase, but for some reason I got no response for my issue - so I'm trying the forum now ;-)
Thanx for comments
Merten
import java.io.StringReader;
import javax.xml.parsers.SAXParser;
import javax.xml.parsers.SAXParserFactory;
import org.xml.sax.Attributes;
import org.xml.sax.InputSource;
import org.xml.sax.SAXException;
import org.xml.sax.helpers.DefaultHandler;
import junit.framework.TestCase;
import junit.framework.TestResult;
import junit.framework.TestSuite;
/** snippet to demonstrate problem in SAXParser */
public class ProblemWithSAXParser extends TestCase
public static void main(String[] args)
TestResult result=junit.textui.TestRunner.run(suite());
System.exit(result.wasSuccessful() ? 0 : 1);
private static junit.framework.Test suite()
final TestSuite ts=new TestSuite();
ts.addTestSuite(ProblemWithSAXParser.class);
return (ts);
/** small DocumentHandler, just waiting for one and only XML element <c></c> */
class MySAXDocumentHandler extends DefaultHandler
boolean listening=false;
public void startElement(final String uri, final String localName, final String qName, final Attributes attributes)
throws SAXException
System.out.println("startElement uri " + uri + " localName " + localName + " qName " + qName);
if("c".equals(qName))
listening=true;
public void endElement(final String uri, final String localName, final String qName) throws SAXException
System.out.println("endElement uri " + uri + " localName " + localName + " qName " + qName);
if("c".equals(qName))
listening=false;
public void characters(final char ch[], final int start, final int length) throws SAXException
if(listening)
final String str=new String(ch, start, length);
System.out.println("<c> element, start==" + start + " length==" + length + " ch.length==" + ch.length + " ch=="
+ str);
sb.append(str);
private final StringBuffer sb=new StringBuffer();
/** return what I got for XML element <c></c> */
public String toString()
return (sb.toString());
/** test an XML document with an element <c>, use XML 1.0 and XML 1.1 and some (more)
* content in the XML element */
public void testWithSunAndApache() throws Exception
// test XML element content for <c> element
final StringBuffer plain_str=new StringBuffer("");
for(int i=0; i < 500; i++)
plain_str.append("0123456789 This is some text ").append(i).append(". ");
final String xml_orig=plain_str.toString();
// SAX parsers, one Sun, one (original) Apache Xerces
// accept that Apache Xerces is not in path ...
final String prop_name="javax.xml.parsers.SAXParserFactory";
final String prop_val_sun="com.sun.org.apache.xerces.internal.jaxp.SAXParserFactoryImpl";
final String prop_val_apache="org.apache.xerces.jaxp.SAXParserFactoryImpl";
System.setProperty(prop_name, prop_val_sun);
final SAXParser sax_sun=SAXParserFactory.newInstance().newSAXParser();
System.out.println("SaxParser Sun= " + sax_sun);
assertTrue(("" + sax_sun).indexOf("com.sun.") >= 0);
System.setProperty(prop_name, prop_val_apache);
SAXParser sax_apache;
try
sax_apache=SAXParserFactory.newInstance().newSAXParser();
catch(final Throwable t)
System.err.println("no Apache Xerces in path? " + t);
sax_apache=null;
System.out.println("SaxParser Apache= " + sax_apache);
assertTrue(sax_apache==null || ("" + sax_apache).startsWith("org.apache."));
// i==0: XML 1.0, i==1: XML 1.1
for(int i=0; i <= 1; i++)
assert i == 0 || i == 1;
final String xml_version=(i == 0 ? "1.0" : "1.1");
final StringBuffer sb=new StringBuffer("<?xml version=\"" + xml_version + "\" encoding=\"UTF-8\"?><c>");
sb.append(xml_orig);
sb.append("</c>");
final String xml=sb.toString();
// parse it!
final StringReader string_reader_sun, string_reader_apache;
string_reader_sun=new StringReader(xml);
final InputSource input_source_sun=new InputSource(string_reader_sun);
string_reader_apache=new StringReader(xml);
final InputSource input_source_apache=new InputSource(string_reader_apache);
final MySAXDocumentHandler my_handler_sun, my_handler_apache;
my_handler_sun=new MySAXDocumentHandler();
my_handler_apache=new MySAXDocumentHandler();
sax_sun.parse(input_source_sun, my_handler_sun);
if(sax_apache!=null)
sax_apache.parse(input_source_apache, my_handler_apache);
final String xml_sun=my_handler_sun.toString();
final String xml_apache=my_handler_apache.toString();
assertNotNull(xml_sun);
assertNotNull(xml_apache);
System.out.println("xml version " + xml_version);
System.out.println("xml " + xml);
System.out.println("xml_orig " + xml_orig);
System.out.println("xml_sun " + xml_sun);
System.out.println("xml_apache " + xml_apache);
// test the data returned from DocumentHandler
if(sax_apache!=null)
assertEquals(xml_orig, xml_apache);
assertEquals(xml_orig.length(), xml_sun.length()); // length seems to be okay
assertEquals(xml_orig, xml_sun); // content seems to be not okay for XML 1.1
}

Answer 1

thanx, DrClap, haven't seen the "code" button for some reason, code is attached again
The output of my test is like this for JRE6 (truncated)
xml_sun 456789 This is is some text 0. 0123456789 This is some text 1.
xml_apache 0123456789 This is some text 0. 0123456789 This is some text 1.
Notice, xml_sun not only starts wrong ("0123" missing) - for some reason, the text there is not "This is some text" but "This is is some text" - very interesting in a way. I guess there's an issue with repeated text chunks ...
So, the data in my XML element is kind of changed, the length of the string is okay but the characters are "misplaced" or so :-) I thought about a problem with StringBuffer first, but the StringBuffer works fine for Apache ... so I really think there's an issue with JRE 6's parser for XML 1.1
Merten
import java.io.StringReader;
import javax.xml.parsers.SAXParser;
import javax.xml.parsers.SAXParserFactory;
import org.xml.sax.Attributes;
import org.xml.sax.InputSource;
import org.xml.sax.SAXException;
import org.xml.sax.helpers.DefaultHandler;
import junit.framework.TestCase;
import junit.framework.TestResult;
import junit.framework.TestSuite;
/** snippet to demonstrate problem in SAXParser */
public class ProblemWithSAXParser extends TestCase
public static void main(String[] args)
  TestResult result=junit.textui.TestRunner.run(suite());
  System.exit(result.wasSuccessful() ? 0 : 1);
private static junit.framework.Test suite()
  final TestSuite ts=new TestSuite();
  ts.addTestSuite(ProblemWithSAXParser.class);
  return (ts);
/** small DocumentHandler, just waiting for one and only XML element <c></c> */
class MySAXDocumentHandler extends DefaultHandler
  boolean listening=false;
  public void startElement(final String uri, final String localName, final String qName, final Attributes attributes)
    throws SAXException
   System.out.println("startElement uri " + uri + " localName " + localName + " qName " + qName);
   if("c".equals(qName))
    listening=true;
  public void endElement(final String uri, final String localName, final String qName) throws SAXException
   System.out.println("endElement uri " + uri + " localName " + localName + " qName " + qName);
   if("c".equals(qName))
    listening=false;
  public void characters(final char ch[], final int start, final int length) throws SAXException
   if(listening)
    final String str=new String(ch, start, length);
    System.out.println("<c> element, start==" + start + " length==" + length + " ch.length==" + ch.length + " ch=="
      + str);
    sb.append(str);
  private final StringBuffer sb=new StringBuffer();
  /** return what I got for XML element <c></c> */
  public String toString()
   return (sb.toString());
/** test an XML document with an element <c>, use XML 1.0 and XML 1.1 and some (more)
  * content in the XML element */
public void testWithSunAndApache() throws Exception
  // test XML element content for <c> element
  final StringBuffer plain_str=new StringBuffer("");
  for(int i=0; i < 500; i++)
   plain_str.append("0123456789 This is some text ").append(i).append(". ");
  final String xml_orig=plain_str.toString();
  // SAX parsers, one Sun, one (original) Apache Xerces
  // accept that Apache Xerces is not in path ...
  final String prop_name="javax.xml.parsers.SAXParserFactory";
  final String prop_val_sun="com.sun.org.apache.xerces.internal.jaxp.SAXParserFactoryImpl";
  final String prop_val_apache="org.apache.xerces.jaxp.SAXParserFactoryImpl";
  System.setProperty(prop_name, prop_val_sun);
  final SAXParser sax_sun=SAXParserFactory.newInstance().newSAXParser();
  System.out.println("SaxParser Sun= " + sax_sun);
  assertTrue(("" + sax_sun).indexOf("com.sun.") >= 0);
  System.setProperty(prop_name, prop_val_apache);
  SAXParser sax_apache;
  try
   sax_apache=SAXParserFactory.newInstance().newSAXParser();
  catch(final Throwable t)
   System.err.println("no Apache Xerces in path? " + t);
   sax_apache=null;
  System.out.println("SaxParser Apache= " + sax_apache);
  assertTrue(sax_apache==null || ("" + sax_apache).startsWith("org.apache."));
  // i==0: XML 1.0, i==1: XML 1.1
  for(int i=0; i <= 1; i++)
   assert i == 0 || i == 1;
   final String xml_version=(i == 0 ? "1.0" : "1.1");
   final StringBuffer sb=new StringBuffer("<?xml version=\"" + xml_version + "\" encoding=\"UTF-8\"?><c>");
   sb.append(xml_orig);
   sb.append("</c>");
   final String xml=sb.toString();
   // parse it!
   final StringReader string_reader_sun, string_reader_apache;
   string_reader_sun=new StringReader(xml);
   final InputSource input_source_sun=new InputSource(string_reader_sun);
   string_reader_apache=new StringReader(xml);
   final InputSource input_source_apache=new InputSource(string_reader_apache);
   final MySAXDocumentHandler my_handler_sun, my_handler_apache;
   my_handler_sun=new MySAXDocumentHandler();
   my_handler_apache=new MySAXDocumentHandler();
   sax_sun.parse(input_source_sun, my_handler_sun);
   if(sax_apache!=null)
    sax_apache.parse(input_source_apache, my_handler_apache);
   final String xml_sun=my_handler_sun.toString();
   final String xml_apache=my_handler_apache.toString();
   assertNotNull(xml_sun);
   assertNotNull(xml_apache);
   System.out.println("xml version " + xml_version);
   System.out.println("xml        " + xml);
   System.out.println("xml_orig   " + xml_orig);
   System.out.println("xml_sun    " + xml_sun);
   System.out.println("xml_apache " + xml_apache);
   // test the data returned from DocumentHandler
   if(sax_apache!=null)
    assertEquals(xml_orig, xml_apache);
   assertEquals(xml_orig.length(), xml_sun.length()); // length seems to be okay
   assertEquals(xml_orig, xml_sun); // content seems to be not okay for XML 1.1
}