Test demonstrates that characters outside of normal ascii range can be used as element content.
<!DOCTYPE doc [ <!ELEMENT doc (#PCDATA)> ]> <doc>เจมส์</doc>
| Expected result | Actual result for org.apache.crimson.parser.XMLReaderImpl |
|---|---|
<?xml version="1.0" encoding="UTF-8"?>
<ConformanceResults>
<startDocument/>
<startElement>
<namespaceURI/>
<localName>doc</localName>
<qualifiedName>doc</qualifiedName>
<attributes/>
</startElement>
<char>เ</char>
<char>จ</char>
<char>ม</char>
<char>ส</char>
<char>์</char>
<endElement>
<namespaceURI/>
<localName>doc</localName>
<qualifiedName>doc</qualifiedName>
</endElement>
<endDocument/>
</ConformanceResults>
| <?xml version="1.0" encoding="UTF-8"?>
<ConformanceResults>
<startDocument/>
<startElement>
<namespaceURI/>
<localName>doc</localName>
<qualifiedName>doc</qualifiedName>
<attributes/>
</startElement>
<char>เ</char>
<char>จ</char>
<char>ม</char>
<char>ส</char>
<char>์</char>
<endElement>
<namespaceURI/>
<localName>doc</localName>
<qualifiedName>doc</qualifiedName>
</endElement>
<endDocument/>
</ConformanceResults>
|