Invalid attributes producing extra null characters during DTD validation #127
Description
Use the catalog here to reproduce this issue: #104 (comment)
test.xml
<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE concept PUBLIC "-//OASIS//DTD DITA Concept//EN" "concept.dtd">
<concept id="foo">
<title>foo</title>
<conbody>
<note type="note" verbose="yes">
<p>The verbose attribute is invalid, and it causes wstx to produce a
null character when writing the XML.</p>
</note>
</conbody>
</concept>WstxValidatorTest.java
import com.ctc.wstx.stax.WstxInputFactory;
import com.ctc.wstx.stax.WstxOutputFactory;
import java.io.ByteArrayOutputStream;
import java.io.File;
import java.nio.file.Paths;
import javax.xml.catalog.CatalogFeatures;
import javax.xml.catalog.CatalogManager;
import javax.xml.stream.XMLInputFactory;
public class WstxValidatorTest {
public static void main(String[] args) throws Exception {
var catalog =
CatalogManager.catalogResolver(
CatalogFeatures.defaults(), Paths.get("path/to/catalog.xml").toUri());
var factory = new WstxInputFactory();
factory.setProperty(XMLInputFactory.IS_VALIDATING, true);
factory.setProperty(XMLInputFactory.RESOLVER, catalog);
var streamReader = factory.createXMLStreamReader(new File("path/to/test.xml"));
streamReader.setValidationProblemHandler(p -> System.err.println(p.getMessage()));
var reader = factory.createXMLEventReader(streamReader);
var buffer = new ByteArrayOutputStream();
var writer = new WstxOutputFactory().createXMLEventWriter(buffer);
while (reader.hasNext()) {
var event = reader.nextEvent();
if (event.isStartElement()) {
var attrs = event.asStartElement().getAttributes();
while (attrs.hasNext()) {
var attr = attrs.next();
System.out.println(
attr.getName()
+ " = '"
+ attr.getValue()
+ "' ( "
+ hex(attr.getValue().getBytes())
+ ")");
}
}
writer.add(event);
}
var xmlResult = new String(buffer.toByteArray(), "UTF-8");
System.out.println(xmlResult);
}
static String hex(byte[] bytes) {
var buffer = new StringBuilder();
for (var i : bytes) {
buffer.append(String.format("0x%02x ", i));
}
return buffer.toString();
}
}Output:
...
Element <note> has no attribute "verbose"
type = 'note' ( 0x6e 0x6f 0x74 0x65 )
verbose = 'yes ' ( 0x79 0x65 0x73 0x00 0x00 0x00 0x00 )
class = '- topic/note ' ( 0x2d 0x20 0x74 0x6f 0x70 0x69 0x63 0x2f 0x6e 0x6f 0x74 0x65 0x20 )
Exception in thread "main" com.ctc.wstx.exc.WstxIOException: Invalid null character in text to output
at com.ctc.wstx.sw.BaseNsStreamWriter.doWriteAttr(BaseNsStreamWriter.java:531)
at com.ctc.wstx.sw.SimpleNsStreamWriter.writeAttribute(SimpleNsStreamWriter.java:90)
at org.codehaus.stax2.ri.Stax2EventWriterImpl.add(Stax2EventWriterImpl.java:61)
at org.codehaus.stax2.ri.Stax2EventWriterImpl.add(Stax2EventWriterImpl.java:108)
at WstxValidatorTest.main(WstxValidatorTest.java:46)
Caused by: java.io.IOException: Invalid null character in text to output
at com.ctc.wstx.api.InvalidCharHandler$FailingHandler.convertInvalidChar(InvalidCharHandler.java:52)
at com.ctc.wstx.sw.XmlWriter.handleInvalidChar(XmlWriter.java:628)
at com.ctc.wstx.sw.BufferingXmlWriter.writeAttrValue(BufferingXmlWriter.java:1082)
at com.ctc.wstx.sw.BufferingXmlWriter.writeAttribute(BufferingXmlWriter.java:925)
at com.ctc.wstx.sw.BaseNsStreamWriter.doWriteAttr(BaseNsStreamWriter.java:528)
... 4 more
Notice the output for the verbose attribute. The attribute value is being padded with extra null characters.